TY - JOUR TI - High-frequency intraday trading for battery storages AU - Schaurecker, David AU - Wozabal, David AU - Löhndorf, Nils AU - Staake, Thorsten PY - 2026 SP - 1-15 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/117799 LA - eng AB - Maximizing revenue for grid-scale battery energy storage systems in continuous intraday electricity markets requires strategies that are able to seize trading opportunities as soon as new information arrives. This paper introduces and evaluates a computationally efficient, high-frequency implementation of the rolling intrinsic trading strategy for battery energy storage systems on the intraday market for power. By combining the established rolling intrinsic logic with a full limit order book representation and a fast dynamic programming approximation, our method explicitly considers the continuously updated list of buy and sell offers, market rules, a linear approximation of degradation, and other technical parameters at a millisecond resolution. The standard rolling intrinsic strategy is adapted for continuous intraday electricity markets and solved using a dynamic programming approximation that is two to three orders of magnitude faster than an exact mixed-integer linear programming solution. A detailed backtest over a full year of German order book data demonstrates that the proposed dynamic programming formulation does not reduce trading profits and enables the policy to react to every relevant order book update, enabling realistic rapid backtesting. Our results show the significant revenue potential of high-frequency trading: our policy earns 58 % more than when re-optimizing only once every hour and 14 % more than when re-optimizing once per minute, highlighting that profits critically depend on trading speed. Furthermore, we leverage the speed of our algorithm to train a parametric extension of the rolling intrinsic, increasing yearly revenue by 8.4% out of sample. KW - Electricity trading KW - Asset-backed trading KW - Short-term power markets KW - Dynamic programming KW - Limit order book ER - TY - JOUR TI - High-frequency intraday trading for battery storages AU - Schaurecker, David AU - Wozabal, David AU - Löhndorf, Nils AU - Staake, Thorsten PY - 2026 JO - Applied energy VL - 425 IS - 128550 SP - 1-15 PB - Elsevier CY - Amsterdam [u.a.] SN - 1872-9118 DO - 10.1016/j.apenergy.2026.128550 UR - https://fis.uni-bamberg.de/handle/uniba/117290 LA - eng AB - Maximizing revenue for grid-scale battery energy storage systems in continuous intraday electricity markets requires strategies that are able to seize trading opportunities as soon as new information arrives. This paper introduces and evaluates a computationally efficient, high-frequency implementation of the rolling intrinsic trading strategy for battery energy storage systems on the intraday market for power. By combining the established rolling intrinsic logic with a full limit order book representation and a fast dynamic programming approximation, our method explicitly considers the continuously updated list of buy and sell offers, market rules, a linear approximation of degradation, and other technical parameters at a millisecond resolution. The standard rolling intrinsic strategy is adapted for continuous intraday electricity markets and solved using a dynamic programming approximation that is two to three orders of magnitude faster than an exact mixed-integer linear programming solution. A detailed backtest over a full year of German order book data demonstrates that the proposed dynamic programming formulation does not reduce trading profits and enables the policy to react to every relevant order book update, enabling realistic rapid backtesting. Our results show the significant revenue potential of high-frequency trading: our policy earns 58 % more than when re-optimizing only once every hour and 14 % more than when re-optimizing once per minute, highlighting that profits critically depend on trading speed. Furthermore, we leverage the speed of our algorithm to train a parametric extension of the rolling intrinsic, increasing yearly revenue by 8.4% out of sample. KW - Electricity trading KW - Asset-backed trading KW - Short-term power markets KW - Dynamic programming KW - Limit order book ER - TY - CPAPER TI - HEAPO : An Open Dataset for Heat Pump Optimization with Smart Electricity Meter Data and On-Site Inspection Protocols AU - Brudermueller, Tobias AU - Fleisch, Elgar AU - González Vayá, Marina AU - Staake, Thorsten Robert PY - 2026 SP - 699-711 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/116869 LA - eng AB - Heat pumps are essential for decarbonizing residential heating but consume substantial electrical energy, impacting operational costs and grid demand. Many systems run inefciently due to planning faws, operational faults, or misconfgurations. While optimizing performance requires skilled professionals, labor shortages hinder large-scale interventions. However, digital tools and improved data availability create new service opportunities for energy efciency, predictive maintenance, and demand-side management. To support research and practical solutions, we present an open-source dataset of electricity consumption from 1,408 households with heat pumps and smart electricity meters in the canton of Zurich, Switzerland, recorded at 15-minute and daily resolutions between 2018-11-03 and 2024-03-21. The dataset includes household metadata, weather data from 8 stations, and ground truth data from 410 feld visit protocols collected by energy consultants during system optimizations. Additionally, the dataset includes a Python-based data loader to facilitate seamless data processing and exploration. KW - heat pump KW - optimization KW - smart electricity meter KW - open energy data ER - TY - CPAPER TI - Research Method Classification with Deep Transfer Learning for Semi-Automatic Meta-Analysis of Information Systems Papers AU - Anisienia, Anna AU - Mueller, Roland M. AU - Kupfer, Anna AU - Staake, Thorsten Robert PY - 2026 SP - 6099-6108 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/114495 LA - eng AB - This paper presents an artifact that uses deep transfer learning methods for the multi-label classification of research methods for an Information Systems corpus. The artifact can support researchers with frequently performed yet time-consuming classification and structure-seeking tasks that are often part of literature analyses. We use a corpus of 5,388 papers from AIS journals and conferences, of which 1,766 have been manually labelled with up to five research methods. The unlabelled papers are used for finetuning the language model, whereas the labelled data are used for training and testing. Our approach outperforms state of the art research method classification that deploy SVM. We show that deep transfer learning models can lead to a better recognition of research methods than shallower word embedding approaches like word2vec or GloVe. The results illustrate the potential of establishing semiautomated methods for meta-analysis. KW - - ER - TY - JOUR TI - Electric vehicle charging strategies in residential communities : Permissible penetration levels and emissions AU - Mehta, Prakhar AU - Tiefenbeck, Verena AU - Staake, Thorsten PY - 2026 SP - 1-18 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/113193 LA - eng AB - This study investigates the impact of three electric vehicle (EV) charging strategies on distribution transformer overloading and charging emissions. Real-world GPS-tracked mobility profiles are used to simulate EV charging, and power balance simulations quantify transformer overloading for combinations of seven residential community sizes, four driver groups and five EV penetration levels. High spatio-temporal resolution emissions intensity data inform EV charging emissions estimates. Findings indicate that while all three charging strategies allow 20% EV penetration, greater penetration depends on community size and the charging strategy. The results further illustrate how grid operators can update transformer sizing conventions to accommodate 100% EV penetration. In the absence of local photovoltaic generation, charging slowly overnight minimizes transformer overloading but maximizes emissions, insinuating trade-offs. However, even with current levels of local PV generation, charging during sunshine hours may, on average, already emit and overload the least, mitigating trade-off concerns between distribution grids and the environment. KW - Electric vehicle (EV) KW - Charging demand KW - Charging strategies KW - Grid impact KW - GHG emissions KW - Transformer overloading ER - TY - JOUR TI - Validating Explainer Methods : A Functionally Grounded Approach for Numerical Forecasting AU - Haag, Felix AU - Hopf, Konstantin AU - Staake, Thorsten PY - 2026 SP - 819-836 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/113131 LA - eng AB - Forecasting systems have a long tradition in providing outputs accompanied by explanations. While the vast majority of such explanations relies on inherently interpretable linear statistical models, research has put forth eXplainable Artificial Intelligence (XAI) methods to improve the comprehensibility of nonlinear machine learning models. As explanations related to forecasts constitute important building blocks in forecasting systems, the validation of explainer methods is an essential part of system selection, parameterization, and adoption. Current research on explainer method assessment focuses on metrics for classification rather than numerical forecasting and predominantly assesses explanation quality within time-consuming, costly, and subjective studies involving humans. Given that the functional validation of explanations is of core interest to research on forecasting, our paper makes three contributions: First, we establish an approach for functionally grounded validations of explainer methods for numerical forecasting. Second, we propose computational rules for the metrics consistency, stability, and faithfulness. Third, we demonstrate our approach for the forecasting case of electricity demand estimation for energy benchmarks and compare a linear statistical approach with the state-of-the-art XAI methods SHapley Additive exPlanations (SHAP), Local Interpretable Model-agnostic Explanations (LIME), and Explainable Boosting Machine (EBM). Our work allows research and practice to validate and compare the quality of explainer methods on a functionally grounded level. KW - explainable artificial intelligence KW - explainer method validation KW - explanation quality KW - interpretable machine learning KW - numerical forecasting ER - TY - JOUR TI - Do dynamic electricity tariffs change the gains of residential PV-battery systems? : A simulation-based evaluation using data from 448 households AU - Lorenz, Christian AU - Bayer, Daniel R. AU - Pruckner, Marco AU - Staake, Thorsten AU - Hopf, Konstantin PY - 2026 SP - 1-18 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/113020 LA - eng AB - Residential battery energy storage systems (BESS) and dynamic electricity tariffs are important building blocks for grid integration of renewable electricity. While various BESS operation strategies have been studied, a systematic comparison under dynamic tariffs (real-time pricing) is missing. Using rule-based and linear optimization approaches grounded on 5 years of data from 448 households, we estimate upper and lower bounds of net gains from using fixed and dynamic pricing. For a 10 kWh BESS, dynamic tariffs at a similar price level as fixed tariffs yield 12.7 % higher net gains, even under a price-agnostic self-consumption maximization strategy. We find that a perfect day-ahead forecast increases net profits by 6 % compared to naïve forecasts (e.g., previous day / week). Compared to a simple rule-based approach, operating BESS with linear optimization over a full-year of perfect information generates additional net profits of 14 %. With day-ahead forecasting, BESS above 15 kWh are best operated by maximizing self-consumption. Our findings offer practical guidance for homeowners considering investments and demonstrate benefits of switching tariffs. They also support policymakers in designing subsidies and regulations for private BESS and dynamic tariff adoption. For utility companies, the results help advance tariff schemes to redistribute market risks and realize grid flexibilities. KW - Residential battery energy storage systems (BESS) KW - Dynamic electricity tariffs KW - Forecasting KW - Simulation KW - BESS operation ER - TY - CPAPER TI - Fostering active student engagement in flipped classroom teaching with social normative feedback AU - May, Maximilian AU - Hopf, Konstantin AU - Haag, Felix AU - Staake, Thorsten AU - Wortmann, Felix PY - 2026 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/112514 LA - eng AB - Abstract. Digital learning platforms have reshaped traditional education by enabling more flexible access to learning materials. Building on this foundation, the flipped classroom model facilitates independent knowledge acquisition while offering interactive support for knowledge application. However, students often struggle with timely completion of graded assignments and underutilize voluntary assignments, which impacts learning outcomes. This study examines the potential of social normative feedback in addressing these challenges. We conduct a randomized controlled trial (N = 140) in a Bachelor’s course, providing students with social normative feedback on correct assignment completion. Our findings indicate that the intervention reduced late submissions of graded assignments by 8.4 percentage points (18.5 %), which correlates with higher performance. However, the intervention did not yield significant effects on engagement with voluntary assignments, leaving room for future research. This study contributes to digital interventions in education, offering insights into how behavioral interventions can optimize student participation in flipped classrooms. KW - Flipped Classroom, KW - Social Normative Feedback KW - Self Regulated Learning KW - Digital Interventions ER - TY - JOUR TI - Electric vehicle charging strategies in residential communities : Permissible penetration levels and emissions AU - Mehta, Prakhar AU - Tiefenbeck, Verena AU - Staake, Thorsten PY - 2026 JO - Energy reports VL - 15 IS - 108978 SP - 1-18 PB - Elsevier CY - Amsterdam [u.a.] SN - 2352-4847 DO - 10.1016/j.egyr.2025.108978 UR - https://fis.uni-bamberg.de/handle/uniba/112830 LA - eng AB - This study investigates the impact of three electric vehicle (EV) charging strategies on distribution transformer overloading and charging emissions. Real-world GPS-tracked mobility profiles are used to simulate EV charging, and power balance simulations quantify transformer overloading for combinations of seven residential community sizes, four driver groups and five EV penetration levels. High spatio-temporal resolution emissions intensity data inform EV charging emissions estimates. Findings indicate that while all three charging strategies allow 20% EV penetration, greater penetration depends on community size and the charging strategy. The results further illustrate how grid operators can update transformer sizing conventions to accommodate 100% EV penetration. In the absence of local photovoltaic generation, charging slowly overnight minimizes transformer overloading but maximizes emissions, insinuating trade-offs. However, even with current levels of local PV generation, charging during sunshine hours may, on average, already emit and overload the least, mitigating trade-off concerns between distribution grids and the environment. KW - Electric vehicle (EV) KW - Charging demand KW - Charging strategies KW - Grid impact KW - GHG emissions KW - Transformer overloading ER - TY - JOUR TI - Validating Explainer Methods : A Functionally Grounded Approach for Numerical Forecasting AU - Haag, Felix AU - Hopf, Konstantin AU - Staake, Thorsten PY - 2026 JO - Journal of Forecasting VL - 45 IS - 2 SP - 819-836 PB - Wiley Interscience CY - New York, NY SN - 0277-6693 DO - 10.1002/for.70060 UR - https://fis.uni-bamberg.de/handle/uniba/112074 LA - eng AB - Forecasting systems have a long tradition in providing outputs accompanied by explanations. While the vast majority of such explanations relies on inherently interpretable linear statistical models, research has put forth eXplainable Artificial Intelligence (XAI) methods to improve the comprehensibility of nonlinear machine learning models. As explanations related to forecasts constitute important building blocks in forecasting systems, the validation of explainer methods is an essential part of system selection, parameterization, and adoption. Current research on explainer method assessment focuses on metrics for classification rather than numerical forecasting and predominantly assesses explanation quality within time-consuming, costly, and subjective studies involving humans. Given that the functional validation of explanations is of core interest to research on forecasting, our paper makes three contributions: First, we establish an approach for functionally grounded validations of explainer methods for numerical forecasting. Second, we propose computational rules for the metrics consistency, stability, and faithfulness. Third, we demonstrate our approach for the forecasting case of electricity demand estimation for energy benchmarks and compare a linear statistical approach with the state-of-the-art XAI methods SHapley Additive exPlanations (SHAP), Local Interpretable Model-agnostic Explanations (LIME), and Explainable Boosting Machine (EBM). Our work allows research and practice to validate and compare the quality of explainer methods on a functionally grounded level. KW - explainable artificial intelligence KW - explainer method validation KW - explanation quality KW - interpretable machine learning KW - numerical forecasting ER - TY - JOUR TI - Do dynamic electricity tariffs change the gains of residential PV-battery systems? : A simulation-based evaluation using data from 448 households AU - Lorenz, Christian AU - Bayer, Daniel R. AU - Pruckner, Marco AU - Staake, Thorsten AU - Hopf, Konstantin PY - 2026 JO - Energy Policy VL - 209 IS - Part A, 114952 SP - 1-18 PB - Elsevier Science CY - Amsterdam [u.a.] SN - 1873-6777 DO - 10.1016/j.enpol.2025.114952 UR - https://fis.uni-bamberg.de/handle/uniba/112075 LA - eng AB - Residential battery energy storage systems (BESS) and dynamic electricity tariffs are important building blocks for grid integration of renewable electricity. While various BESS operation strategies have been studied, a systematic comparison under dynamic tariffs (real-time pricing) is missing. Using rule-based and linear optimization approaches grounded on 5 years of data from 448 households, we estimate upper and lower bounds of net gains from using fixed and dynamic pricing. For a 10 kWh BESS, dynamic tariffs at a similar price level as fixed tariffs yield 12.7 % higher net gains, even under a price-agnostic self-consumption maximization strategy. We find that a perfect day-ahead forecast increases net profits by 6 % compared to naïve forecasts (e.g., previous day / week). Compared to a simple rule-based approach, operating BESS with linear optimization over a full-year of perfect information generates additional net profits of 14 %. With day-ahead forecasting, BESS above 15 kWh are best operated by maximizing self-consumption. Our findings offer practical guidance for homeowners considering investments and demonstrate benefits of switching tariffs. They also support policymakers in designing subsidies and regulations for private BESS and dynamic tariff adoption. For utility companies, the results help advance tariff schemes to redistribute market risks and realize grid flexibilities. KW - Residential battery energy storage systems (BESS) KW - Dynamic electricity tariffs KW - Forecasting KW - Simulation KW - BESS operation ER - TY - GEN TI - An assessment of the electrical energy and power deficit during dark doldrums in a renewable-heavy power grid : the example of Germany AU - Achtnicht, Lukas AU - Hopf, Konstantin AU - Staake, Thorsten PY - 2025 SP - 26 PB - Elsevier CY - Amsterdam SN - 1556-5068 DO - 10.2139/ssrn.5491407 UR - https://fis.uni-bamberg.de/handle/uniba/117090 LA - eng ER - TY - CPAPER TI - HEAPO : An Open Dataset for Heat Pump Optimization with Smart Electricity Meter Data and On-Site Inspection Protocols AU - Brudermueller, Tobias AU - Fleisch, Elgar AU - González Vayá, Marina AU - Staake, Thorsten Robert PY - 2025 T2 - Proceedings of the 16th ACM International Conference on Future and Sustainable Energy Systems SP - 699-711 PB - Association for Computing Machinery CY - New York SN - 979-8-4007-1125-1 DO - 10.1145/3679240.3734637 UR - https://fis.uni-bamberg.de/handle/uniba/116736 LA - eng AB - Heat pumps are essential for decarbonizing residential heating but consume substantial electrical energy, impacting operational costs and grid demand. Many systems run inefciently due to planning faws, operational faults, or misconfgurations. While optimizing performance requires skilled professionals, labor shortages hinder large-scale interventions. However, digital tools and improved data availability create new service opportunities for energy efciency, predictive maintenance, and demand-side management. To support research and practical solutions, we present an open-source dataset of electricity consumption from 1,408 households with heat pumps and smart electricity meters in the canton of Zurich, Switzerland, recorded at 15-minute and daily resolutions between 2018-11-03 and 2024-03-21. The dataset includes household metadata, weather data from 8 stations, and ground truth data from 410 feld visit protocols collected by energy consultants during system optimizations. Additionally, the dataset includes a Python-based data loader to facilitate seamless data processing and exploration. KW - heat pump KW - optimization KW - smart electricity meter KW - open energy data ER - TY - JOUR TI - DAIAD : Open Water Monitoring AU - Athanasiou, S. AU - Staake, Thorsten Robert AU - Stiefmeier, Thomas AU - Sartorius, C. AU - Tompkins, J. AU - Lytras, E. PY - 2025 SP - 1044-1049 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/109448 LA - eng AB - DAIAD is an FP7 research project addressing the challenge of improving the management of water resources through real-time knowledge of water consumption in order to improve societal awareness, induce sustainable changes in consumer behavior, and explore new water demand management strategies. In this paper we present the motivation of our work, our vision and objectives, along with an early architectural overview of the planned DAIAD system. KW - Real time water monitoring KW - Big Data KW - Interventions KW - Water Demand Management ER - TY - JOUR TI - Estimation of energy efficiency of heat pumps in residential buildings using real operation data AU - Brudermueller, Tobias AU - Potthoff, Ugne AU - Fleisch, Elgar AU - Wortmann, Felix AU - Staake, Thorsten Robert PY - 2025 SP - 1-15 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/110865 LA - eng AB - As heat pumps become more prevalent in residential buildings, effective performance monitoring is essential. Design flaws, incorrect settings, and faults can escalate energy consumption and costs, leading to discrepancies in user expectations and hindering the widespread adoption of this technology crucial for the heating transition.However, field studies using large data sets to offer insights into real-world performance and methods for identifying lowperforming systems in practical, scalable applications are lacking. In the largest field study to date, we analyze sensor data from 1023 heat pumps across Central Europe monitored over two years. Based on existing approaches for controlled laboratory conditions, we derive methods to evaluate and classify real-world performance using operational data. Applying these methods, we find that 17% of air-source and 2% of ground-source heat pumps do not meet existing efficiency standards. Additionally, around 10% of systems are oversized, while approximately 1% are undersized. This underscores the need for standardized post-installation performance evaluation procedures and digital tools to provide actionable feedback for users and installers to enhance operational efficiency and guide future installations. KW - - ER - TY - CPAPER TI - Fostering active student engagement in flipped classroom teaching with social normative feedback AU - May, Maximilian AU - Hopf, Konstantin AU - Haag, Felix AU - Staake, Thorsten AU - Wortmann, Felix PY - 2025 T2 - Wirtschaftsinformatik 2025 Proceedings PB - AISel UR - https://fis.uni-bamberg.de/handle/uniba/112880 LA - eng AB - Abstract. Digital learning platforms have reshaped traditional education by enabling more flexible access to learning materials. Building on this foundation, the flipped classroom model facilitates independent knowledge acquisition while offering interactive support for knowledge application. However, students often struggle with timely completion of graded assignments and underutilize voluntary assignments, which impacts learning outcomes. This study examines the potential of social normative feedback in addressing these challenges. We conduct a randomized controlled trial (N = 140) in a Bachelor’s course, providing students with social normative feedback on correct assignment completion. Our findings indicate that the intervention reduced late submissions of graded assignments by 8.4 percentage points (18.5 %), which correlates with higher performance. However, the intervention did not yield significant effects on engagement with voluntary assignments, leaving room for future research. This study contributes to digital interventions in education, offering insights into how behavioral interventions can optimize student participation in flipped classrooms. KW - Flipped Classroom, KW - Social Normative Feedback KW - Self Regulated Learning KW - Digital Interventions ER - TY - CHAP TI - A feedback component that leverages counterfactual explanations for smart learning support AU - Günther, Sebastian A. AU - Haag, Felix AU - Hopf, Konstantin AU - Handschuh, Philipp AU - Klose, Maria AU - Staake, Thorsten PY - 2025 SP - 285-291 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/112236 LA - eng AB - The growing prevalence of digital learning in higher education is accompanied by challenges regarding students’ self-regulated learning. While there is a plethora of behavioral interventions that aim at supporting students’ self-regulated learning, they often do not consider the heterogeneity of students in their intervention design. This paper presents a novel feedback intervention that leverages the potential of machine learning and counterfactual explanations for providing personalized feedback to support students’ learning. Ultimately, this approach could automatically adapt to different courses and thereby empower scalable and effective feedback. KW - Learning analytics KW - Explainable artificial intelligence KW - Counterfactual explanations KW - Feedback intervention KW - Experiment KW - Self-regulated learning ER - TY - JOUR TI - The effect of digital rewards on the motivation of children to perform everyday health behavior AU - Graichen, Joanna AU - Stingl, Carlo AU - Dangis, Glenda AU - Pakarinen, Anni AU - Rosio, Riitta AU - Salanterä, Sanna AU - Terho, Kirsi AU - Günther, Sebastian A. AU - Siloaho, Antti AU - Staake, Thorsten PY - 2025 SP - 1-9 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/112134 LA - eng AB - Information technology can serve as a powerful tool for promoting children's learning. In this context, digital, symbolic rewards are frequently employed to enhance task performance. However, it has been observed that once rewards are removed, intrinsic motivation to perform a task may decrease below baseline levels, a phenomenon referred to as motivation crowding. There is a lack of consensus among researchers under which circumstances motivation crowding happens among children. Here, a field experiment with three distinct groups tests the presence or absence of motivation crowding. This paper reports the findings from the cluster randomized field study that investigated a digital health intervention guiding and rewarding children to engage in everyday health behaviors. Behavioral data from 254 children between the ages of three and six was collected over a five-week period. The results provide empirical evidence that digital rewards successfully helped children adapt everyday health behaviors and refute motivation crowding among children in the context of digital rewards. The findings are important for advancing the use of motivation crowding theory in children, for providing insights into children's behavior, and helping researchers develop digital motivational cues for children. At the same time, the digital intervention outlined in the paper embodies an effective and scalable measure for engaging children in health prevention behavior. KW - Motivation crowding KW - Digital rewards KW - Child health KW - Behavioral field experiment ER - TY - JOUR TI - The effect of digital rewards on the motivation of children to perform everyday health behavior AU - Graichen, Joanna AU - Stingl, Carlo AU - Dangis, Glenda AU - Pakarinen, Anni AU - Rosio, Riitta AU - Salanterä, Sanna AU - Terho, Kirsi AU - Günther, Sebastian A. AU - Siloaho, Antti AU - Staake, Thorsten Robert PY - 2025 JO - Computers in Human Behavior Reports VL - 20 IS - 100879 SP - 1-9 PB - Elsevier BV CY - Amsterdam SN - 2451-9588 DO - 10.1016/j.chbr.2025.100879 UR - https://fis.uni-bamberg.de/handle/uniba/111809 LA - eng AB - Information technology can serve as a powerful tool for promoting children's learning. In this context, digital, symbolic rewards are frequently employed to enhance task performance. However, it has been observed that once rewards are removed, intrinsic motivation to perform a task may decrease below baseline levels, a phenomenon referred to as motivation crowding. There is a lack of consensus among researchers under which circumstances motivation crowding happens among children. Here, a field experiment with three distinct groups tests the presence or absence of motivation crowding. This paper reports the findings from the cluster randomized field study that investigated a digital health intervention guiding and rewarding children to engage in everyday health behaviors. Behavioral data from 254 children between the ages of three and six was collected over a five-week period. The results provide empirical evidence that digital rewards successfully helped children adapt everyday health behaviors and refute motivation crowding among children in the context of digital rewards. The findings are important for advancing the use of motivation crowding theory in children, for providing insights into children's behavior, and helping researchers develop digital motivational cues for children. At the same time, the digital intervention outlined in the paper embodies an effective and scalable measure for engaging children in health prevention behavior. KW - Motivation crowding KW - Digital rewards KW - Child health KW - Behavioral field experiment ER - TY - JOUR TI - Economic assessment of photovoltaic-battery systems based household load profiles AU - Schopfer, Sandro AU - Tiefenbeck, Verena AU - Staake, Thorsten PY - 2025 SP - 229-248 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/110438 LA - eng AB - Technical advances and decreasing costs of photovoltaic (PV) and battery (B) systems are key drivers for the consumer-prosumer transition in many countries. However, the installation of a photovoltaic-battery (PVB) system is not equally profitable for all consumers. This study systematically assesses how heterogeneity in real-world electricity load profiles affects the optimal system configuration and profitability of PVB systems. To that end, we develop a techno-economic simulation model that optimizes the PVB configuration for given electricity load profiles. The analysis uses real-world energy consumption data from 4190 households and is conducted for current electricity rates and weather conditions in Zurich, Switzerland. To account for future price reductions of PV and PVB systems, we conduct a sensitivity analysis that assesses how different cost scenarios influence optimal system configuration and profitability. Finally, we develop and validate a machine learning algorithm that can predict system profitability based only on a limited set of features and on shorter measurement timeframes of smart-meter data. We find that under the current cost scenario (PV: 2000 €/kWp, B: 1000 €/kWh) and without subsidies, about 40% of the analyzed households reach a positive net present value (NPV) for a PV-system, but only for 0.1% of households is the integration of a battery profitable. Under the most optimistic cost scenario for both technologies (PV: 1000 €/kWp, B: 250 €/kWh), 99.9% of the households benefit from the integration of battery storage into their optimal system configuration, with a mean installed PV power of 4.4 kWp and a mean battery size of 9.6 kWh. In all cost scenarios, system profitability varies considerably between households, even for households with comparable total annual demand, primarily due to the heterogeneity in the load profiles. Thus, being able to identify households for whom the installation is profitable is important. The proposed machine learning algorithm predicts optimal configuration, profitability, self-sufficiency, and self-sufficiency ratios with good accuracy, even when only relatively short timeframes of smart-meter data are available. The results of this study are relevant for households making individual investment decisions as well as for utility companies to more effectively identify and approach relevant customers for the installation of PVB systems. Furthermore, the findings enable policymakers to determine the critical levers for increasing private investments into PVB systems in their region and to predict how future developments like component costs will affect the future diffusion of these systems. KW - Solar energy KW - Storage KW - Smart-meter data KW - Techno-economic simulation KW - Load profile KW - Machine learning ER - TY - JOUR TI - Predictability of electric vehicle charging : Explaining extensive user behavior-specific heterogeneity AU - Kreft, Markus AU - Brudermueller, Tobias AU - Fleisch, Elgar AU - Staake, Thorsten PY - 2025 SP - 1-15 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/111090 LA - eng AB - Smart charging systems can reduce the stress on the power grid from electric vehicles by coordinating the charging process. To meet user requirements, such systems need input on charging demand, i.e., departure time and desired state of charge. Deriving these parameters through predictions based on past mobility patterns allows the inference of realistic values that offer flexibility by charging vehicles until they are actually needed for departure. While previous studies have addressed the task of charging demand predictions, there is a lack of work investigating the heterogeneity of user behavior, which affects prediction performance. In this work we predict the duration and energy of residential charging sessions using a dataset with 59, 520real-world measurements from 267 electric vehicles. While replicating the results put forth in related work, we additionally find substantial differences in prediction performance between individual vehicles. An in-depth analysis shows that vehicles that on average start charging later in the day can be predicted better than others. Furthermore, we demonstrate how knowledge that a vehicles charges over night significantly increases prediction performance, reducing the mean absolute percentage error of plugged-in duration predictions from over 200 % to 15%. Based on these insights, we propose that residential smart charging systems should focus on predictions of overnight charging to determine charging demand. These sessions are most relevant for smart charging as they offer most flexibility and need for coordinated charging and, as we show, they are also more predictable, increasing user acceptance. KW - Electric vehicles KW - Smart charging KW - Demand response KW - Demand prediction KW - Real-world data ER - TY - CHAP TI - Digitale Kulturen der Lehre entwickeln : einleitende Verortungen AU - Mrohs, Lorenz AU - Herrmann, Dominik AU - Franz, Julia AU - Lindner, Konstantin AU - Staake, Thorsten PY - 2025 SP - 1-6 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/110328 LA - deu AB - Der Beitrag führt vor dem Hintergrund der Theorie der Kultur der Digitalität (Felix Stalder) in den vorliegenden Sammelband ein und wendet diesen theoretischen Rahmen auf Hochschulen und die Entwicklung der Hochschullehre an. Es werden die zentralen Strukturbedingungen umrissen und davon ausgehend Erfordernisse für die Entwicklung einer Kultur der Digitalität an der Universität Bamberg skizziert, die im Rahmen des Projekts „Digitale Kulturen der Lehre entwickeln (DiKuLe)“ beforscht und entwickelt werden. Abschließend gibt der Beitrag einen Ausblick auf die Beiträge des Sammelbandes, die neue Konzepte, Gestaltungsmöglichkeiten und Evaluationsergebnisse digitaler Lehr-Lernarrangements vorstellen. KW - Lehre ER - TY - JOUR TI - Estimation of energy efficiency of heat pumps in residential buildings using real operation data AU - Brudermueller, Tobias AU - Potthoff, Ugne AU - Fleisch, Elgar AU - Wortmann, Felix AU - Staake, Thorsten Robert PY - 2025 JO - Nature Communications VL - 16 IS - Article number: 2834 SP - 1-15 PB - Springer Nature CY - London SN - 2041-1723 DO - 10.1038/s41467-025-58014-y UR - https://fis.uni-bamberg.de/handle/uniba/110864 LA - eng AB - As heat pumps become more prevalent in residential buildings, effective performance monitoring is essential. Design flaws, incorrect settings, and faults can escalate energy consumption and costs, leading to discrepancies in user expectations and hindering the widespread adoption of this technology crucial for the heating transition.However, field studies using large data sets to offer insights into real-world performance and methods for identifying lowperforming systems in practical, scalable applications are lacking. In the largest field study to date, we analyze sensor data from 1023 heat pumps across Central Europe monitored over two years. Based on existing approaches for controlled laboratory conditions, we derive methods to evaluate and classify real-world performance using operational data. Applying these methods, we find that 17% of air-source and 2% of ground-source heat pumps do not meet existing efficiency standards. Additionally, around 10% of systems are oversized, while approximately 1% are undersized. This underscores the need for standardized post-installation performance evaluation procedures and digital tools to provide actionable feedback for users and installers to enhance operational efficiency and guide future installations. KW - - ER - TY - CPAPER TI - Addressing Learners’ Heterogeneity in Higher Education : An Explainable AI-Based Feedback Artifact for Digital Learning Environments AU - Haag, Felix AU - Günther, Sebastian AU - Hopf, Konstantin AU - Handschuh, Philipp AU - Klose, Maria AU - Staake, Thorsten PY - 2025 T2 - Transforming the Digitally Sustainable Enterprise : Proceedings of the 18th International Conference on Wirtschaftsinformatik, Paderborn, Germany, 2023 SP - 511-527 PB - Springer Nature Switzerland CY - Cham SN - 978-3-031-80124-2 DO - 10.1007/978-3-031-80125-9_30 UR - https://fis.uni-bamberg.de/handle/uniba/110516 LA - eng ER - TY - BOOK TI - Digitales Lehren und Lernen an der Hochschule : Strategien - Bedinungen - Umsetzung ED - Mrohs, Lorenz ED - Franz, Julia ED - Herrmann, Dominik ED - Lindner, Konstantin ED - Staake, Thorsten PY - 2025 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/106338 LA - deu AB - Die Covid-Pandemie hat den Einsatz etablierter digitaler Technologien in der Hochschullehre beschleunigt. Gegenwärtig stellen generative KI-Systeme, allen voran ChatGPT, eine weitere, diesmal technologische Zäsur dar. Die Beiträger*innen diskutieren innovative Ansätze, bewährte Praktiken, aber auch nicht weiter verfolgte Maßnahmen in der Entwicklung und Gestaltung digitalisierter Lehr- und Lernkulturen. Dabei nehmen sie die verschiedenen Ebenen der Hochschule, der Lehre und der Rahmenbedingungen in den Blick und geben fundierte Einsichten in die aktuellen Potentiale und Herausforderungen bei der Implementierung digitalen Lehrens und Lernens an Hochschulen. KW - Hochschullehre KW - Digitalisierung KW - Hochschulentwicklung KW - Digitale Kulturen KW - Digitale Lehre ER - TY - BOOK TI - Digitales Lehren und Lernen an der Hochschule : Strategien - Bedinungen - Umsetzung ED - Mrohs, Lorenz ED - Franz, Julia ED - Herrmann, Dominik ED - Lindner, Konstantin ED - Staake, Thorsten PY - 2025 SP - 350 PB - transcript CY - Bielefeld T3 - Hochschulbildung: Lehre und Forschung SN - 978-3-8376-7120-9 DO - 10.14361/9783839471203 UR - https://fis.uni-bamberg.de/handle/uniba/106817 LA - deu AB - Die Covid-Pandemie hat den Einsatz etablierter digitaler Technologien in der Hochschullehre beschleunigt. Gegenwärtig stellen generative KI-Systeme, allen voran ChatGPT, eine weitere, diesmal technologische Zäsur dar. Die Beiträger*innen diskutieren innovative Ansätze, bewährte Praktiken, aber auch nicht weiter verfolgte Maßnahmen in der Entwicklung und Gestaltung digitalisierter Lehr- und Lernkulturen. Dabei nehmen sie die verschiedenen Ebenen der Hochschule, der Lehre und der Rahmenbedingungen in den Blick und geben fundierte Einsichten in die aktuellen Potentiale und Herausforderungen bei der Implementierung digitalen Lehrens und Lernens an Hochschulen. KW - Hochschullehre KW - Digitalisierung KW - Hochschulentwicklung KW - Digitale Kulturen KW - Digitale Lehre ER - TY - JOUR TI - The group mind of hybrid teams with humans and intelligent agents in knowledge-intense work AU - Hopf, Konstantin AU - Nahr, Nora AU - Staake, Thorsten AU - Lehner, Franz PY - 2025 JO - Journal of Information Technology VL - 40 IS - 1 SP - 9-34 PB - Sage Publishing CY - London SN - 0268-3962 DO - 10.1177/02683962241296883 UR - https://fis.uni-bamberg.de/handle/uniba/104151 LA - eng AB - Studies regularly demonstrate how well intelligent agents (IAs) can support humans or are demonstrably superior to them in some areas. Given that some tasks likely remain unsuitable for even the most intelligent machines in the mid-future, work in hybrid teams of humans and IAs—where the capabilities of both are effectively combined—will most likely shape the way we work in the coming decades. In an abductive study, we investigate an early example of hybrid teams, consisting of a conversational intelligent agent (IA) and humans, that aims to improve health behavior or change personality traits. We theorize Transactive Intelligent Memory System (TIMS) as a new vision of collaboration between humans and IAs in hybrid teams, based on our empirical insights and our literature review on transactive memory systems theory. Our empirical evidence shows that IAs can develop a form of individual and external memory, and hybrid teams of humans and IAs can realize joint systems of transactive memory—a competence that current literature only ascribes to humans. We further find that whether individuals view IAs merely as external memory aids or as part of their teams’ transactive memory is moderated by the tasks’ complexity and knowledge intensity, as well as the IA’s ability to complete the task. This theorizing helps to better understand the role of IAs in future team-based working processes. Developers of IAs can use TIMS as a tool for requirements formulation to prepare their software agents for collaboration in hybrid teams. KW - transactive memory systems KW - hybrid teams KW - intelligent agents KW - digital workplace KW - in-depth qualitative case study KW - abduction ER - TY - CPAPER TI - Identifying Electric Water Heaters from Low-Resolution Smart Meter Data AU - Kreft, Markus AU - Brudermueller, Tobias AU - Anderson, Tyler AU - Staake, Thorsten PY - 2024 T2 - 2024 IEEE Conference on Technologies for Sustainability (SusTech) : Proceedings SP - 128-135 PB - IEEE CY - New York, USA SN - 979-8-3503-9434-4 DO - 10.1109/sustech60925.2024.10553590 UR - https://fis.uni-bamberg.de/handle/uniba/112334 LA - eng ER - TY - JOUR TI - The group mind of hybrid teams with humans and intelligent agents in knowledge-intense work AU - Hopf, Konstantin AU - Nahr, Nora AU - Staake, Thorsten AU - Lehner, Franz PY - 2024 SP - 9-34 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/104377 LA - eng AB - Studies regularly demonstrate how well intelligent agents (IAs) can support humans or are demonstrably superior to them in some areas. Given that some tasks likely remain unsuitable for even the most intelligent machines in the mid-future, work in hybrid teams of humans and IAs—where the capabilities of both are effectively combined—will most likely shape the way we work in the coming decades. In an abductive study, we investigate an early example of hybrid teams, consisting of a conversational intelligent agent (IA) and humans, that aims to improve health behavior or change personality traits. We theorize Transactive Intelligent Memory System (TIMS) as a new vision of collaboration between humans and IAs in hybrid teams, based on our empirical insights and our literature review on transactive memory systems theory. Our empirical evidence shows that IAs can develop a form of individual and external memory, and hybrid teams of humans and IAs can realize joint systems of transactive memory—a competence that current literature only ascribes to humans. We further find that whether individuals view IAs merely as external memory aids or as part of their teams’ transactive memory is moderated by the tasks’ complexity and knowledge intensity, as well as the IA’s ability to complete the task. This theorizing helps to better understand the role of IAs in future team-based working processes. Developers of IAs can use TIMS as a tool for requirements formulation to prepare their software agents for collaboration in hybrid teams. KW - transactive memory systems KW - hybrid teams KW - intelligent agents KW - digital workplace KW - in-depth qualitative case study KW - abduction ER - TY - JOUR TI - Predictability of electric vehicle charging : Explaining extensive user behavior-specific heterogeneity AU - Kreft, Markus AU - Brudermueller, Tobias AU - Fleisch, Elgar AU - Staake, Thorsten PY - 2024 JO - Applied Energy VL - 370 IS - 123544 SP - 1-15 PB - Elsevier CY - Amsterdam SN - 1872-9118 DO - 10.1016/j.apenergy.2024.123544 UR - https://fis.uni-bamberg.de/handle/uniba/98216 LA - eng AB - Smart charging systems can reduce the stress on the power grid from electric vehicles by coordinating the charging process. To meet user requirements, such systems need input on charging demand, i.e., departure time and desired state of charge. Deriving these parameters through predictions based on past mobility patterns allows the inference of realistic values that offer flexibility by charging vehicles until they are actually needed for departure. While previous studies have addressed the task of charging demand predictions, there is a lack of work investigating the heterogeneity of user behavior, which affects prediction performance. In this work we predict the duration and energy of residential charging sessions using a dataset with 59, 520real-world measurements from 267 electric vehicles. While replicating the results put forth in related work, we additionally find substantial differences in prediction performance between individual vehicles. An in-depth analysis shows that vehicles that on average start charging later in the day can be predicted better than others. Furthermore, we demonstrate how knowledge that a vehicles charges over night significantly increases prediction performance, reducing the mean absolute percentage error of plugged-in duration predictions from over 200 % to 15%. Based on these insights, we propose that residential smart charging systems should focus on predictions of overnight charging to determine charging demand. These sessions are most relevant for smart charging as they offer most flexibility and need for coordinated charging and, as we show, they are also more predictable, increasing user acceptance. KW - Electric vehicles KW - Smart charging KW - Demand response KW - Demand prediction KW - Real-world data ER - TY - CPAPER TI - Disaggregation of Heat Pump Load Profiles From Low-Resolution Smart Meter Data AU - Brudermueller, Tobias AU - Breer, Fabian AU - Staake, Thorsten PY - 2024 SP - 228–231 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/96520 LA - eng AB - As the number of heat pumps installed in residential buildings increases, their energy-efficient operation becomes increasingly important to reduce costs and ensure the stability of the power grid. The deployment of smart electricity meters results in large amounts of smart meter data that can be used for heat pump optimization. However, sub-metering infrastructure to monitor heat pumps’ energy consumption is costly and rarely available in practice. Non-intrusive load monitoring addresses this issue and disaggregates appliance-level consumption from aggregate measurements. However, previous studies use high-resolution data of active and reactive power and do not focus on heat pumps. In this context, our study is the first to disaggregate heat pump load profiles using commonly available smart meter data with energy measurements at 15-minute resolution. We use a sliding-window approach to train and test deep learning models on a real-world data set of 363 Swiss households with heat pumps observed over a period of 8 years. Evaluating our approach with a 5-fold cross-validation, our best model achieves a mean R2 score of 0.832 and an average RMSE of 0.169 kWh, which is similar to previous work that uses high-resolution measurements of active and reactive power. Our algorithms enable real-world applications to monitor the energy efficiency of heat pumps in operation and to estimate their flexibility for demand response programs. KW - Smart Meter Data KW - Heat Pump Optimization KW - Energy Efficiency KW - Non- Intrusive Load Monitoring KW - Load Disaggregation KW - Low Resolution ER - TY - CPAPER TI - Information Systems Research for the Next Generation : Child-Centricity in a Digital World AU - Graichen, Joanna AU - Staake, Thorsten PY - 2024 SP - 4026-4035 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/96487 LA - eng AB - Traditionally, information systems (IS) research investigates socio-technical systems in organizations and the workplace. As IS have become an integral part of our daily lives, IS research nowadays also incorporates the private space. However, efforts to date have mostly focused on adults. Children, born into a digital world today, have been mostly left out. Yet our discipline not only has the potential to contribute to the adequate and child-friendly design of IS artifacts for children but can also help to further develop theories on children's behavior. For this to succeed, IS researchers need to adapt their approach to children. Ethical considerations should address children's vulnerability, the design of interventions should happen in close collaboration with children, research methods should be child-centered, and the specificities of children should be kept present in result analyses. KW - Human-centricity in a Sustainable Digital Economy KW - methodology KW - next generation KW - research methods KW - research with children ER - TY - JOUR TI - Hand Hygiene of Kindergarten Children : Understanding the Effect of Live Feedback on Handwashing Behaviour, Self-Efficacy, and Motivation of Young Children ; Protocol for a Multi-Arm Cluster Randomized Controlled Trial AU - Dangis, Glenda AU - Terho, Kirsi AU - Graichen, Joanna AU - Günther, Sebastian A. AU - Rosio, Riitta AU - Salanterä, Sanna AU - Staake, Thorsten AU - Stingl, Carlo AU - Pakarinen, Anni PY - 2024 SP - 1-18 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/94872 LA - eng AB - Early implementation of interventions at a young age fosters behaviour changes and helps to adopt behaviours that promote health. Digital technologies may help to promote the hand hygiene behaviour of children. However, there is a lack of digital feedback interventions focusing on the hand hygiene behaviour of preschool children in childhood education and care settings. This study protocol aims to describe a study that evaluates the effectiveness of a gamified live feedback intervention and explores underlying behavioural theories in achieving better hand hygiene behaviour of preschool children in early childhood education and care settings. This study will be a four-arm cluster randomized controlled trial with three phases and a twelve-month follow-up by country stratification. The sample size is 106 children of which one cluster will have a minimum number of 40 children. During the baseline phase, all groups will have automated monitoring systems installed. In the intervention phase, the control group will have no screen activity. The intervention groups will have feedback displays during the handwashing activity. Intervention A will receive instructions, and intervention B and C groups will receive instructions and a reward. In the post-intervention phase, all the groups will have no screen activity except intervention C which will receive instructions from the screen but no reward. The outcome measures will be hand hygiene behaviour, self-efficacy, and intrinsic motivation. Outcome measures will be collected at baseline, intervention, and post-intervention phases and a 12-month follow-up. The data will be analysed with quantitative and qualitative methods. The findings of the planned study will provide whether this gamified live feedback intervention can be recommended to be used in educational settings to improve the hand hygiene behaviour of preschool children to promote health. KW - Hand Hygiene KW - Kindergarten Children ER - TY - JOUR TI - Improving hand hygiene of young children with a digital intervention : a cluster-randomised controlled field trial AU - Graichen, Joanna AU - Stingl, Carlo AU - Pakarinen, Anni AU - Rosio, Riitta AU - Terho, Kirsi AU - Günther, Sebastian AU - Salanterä, Sanna AU - Staake, Thorsten PY - 2024 SP - 1-10 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/94651 LA - eng AB - Contagious diseases that affect young children place a great burden on them and their families. Proper hand hygiene is an important measure to reduce the disease burden, however, its implementation in day care centres is challenging. This paper introduces a digital intervention to support independent and good handwashing among young children. The intervention leverages animated instructions triggered by water and soap use, together with a symbolic reward shown to children on a screen during and immediately after handwashing. We tested the intervention in a pre-registered, cluster-randomised controlled field trial in 4 day care centres in Finland and Germany with 162 children over 42 days. The intervention increased soaping time, used as a proxy for handwashing quality, by 5.30 s (+ 62%, p < 0.001). The effect occurs immediately at the onset of the intervention and is maintained throughout the intervention phase. KW - hand hygiene KW - children KW - digital intervention ER - TY - JOUR TI - Improving hand hygiene of young children with a digital intervention : a cluster-randomised controlled field trial AU - Graichen, Joanna AU - Stingl, Carlo AU - Pakarinen, Anni AU - Rosio, Riitta AU - Terho, Kirsi AU - Günther, Sebastian A. AU - Salanterä, Sanna AU - Staake, Thorsten PY - 2024 JO - Scientific reports VL - 14 IS - 1, 6157 SP - 1-10 PB - Macmillan Publishers Limited, part of Springer Nature CY - London SN - 2045-2322 DO - 10.1038/s41598-024-56233-9 UR - https://fis.uni-bamberg.de/handle/uniba/94650 LA - eng AB - Contagious diseases that affect young children place a great burden on them and their families. Proper hand hygiene is an important measure to reduce the disease burden, however, its implementation in day care centres is challenging. This paper introduces a digital intervention to support independent and good handwashing among young children. The intervention leverages animated instructions triggered by water and soap use, together with a symbolic reward shown to children on a screen during and immediately after handwashing. We tested the intervention in a pre-registered, cluster-randomised controlled field trial in 4 day care centres in Finland and Germany with 162 children over 42 days. The intervention increased soaping time, used as a proxy for handwashing quality, by 5.30 s (+ 62%, p < 0.001). The effect occurs immediately at the onset of the intervention and is maintained throughout the intervention phase. KW - hand hygiene KW - children KW - digital intervention ER - TY - JOUR TI - Complementarities in behavioral interventions : Evidence from a field experiment on resource conservation AU - Fang, Ximeng AU - Goette, Lorenz AU - Rockenbach, Bettina AU - Sutter, Matthias AU - Tiefenbeck, Verena AU - Schoeb, Samuel AU - Staake, Thorsten PY - 2024 SP - 1-20 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/93493 LA - eng AB - Behavioral policy often aims at influencing behavior by mitigating biases due to, e.g., imperfect information or inattention. We study how this is affected by the simultaneous presence of multiple biases arising from different sources, through a field experiment on resource conservation in an energy- and water-intensive everyday activity (showering). One intervention, shower energy reports, primarily targeted knowledge about environmental impacts; another intervention, real-time feedback, primarily targeted salience of resource use. We find a striking complementarity. While only the latter induced significant conservation effects when implemented in isolation, each intervention became more effective when implemented jointly. This is consistent with predictions from a theoretical framework that highlights the importance of targeting all relevant sources of bias to achieve behavioral change. KW - Behavioral public policy KW - Pro-environmental behavior KW - Limited attention KW - Information provision KW - Real-time feedback KW - Policy interactions ER - TY - CPAPER TI - Overcoming Anchoring Bias : the Potential of AI and XAI-based Decision Support AU - Haag, Felix AU - Stingl, Carlo AU - Zerfass, Katrin AU - Hopf, Konstantin AU - Staake, Thorsten PY - 2024 SP - 1-17 PB - Otto-Friedrich-Universität CY - Bamberg DO - 10.20378/irb-91986 UR - https://fis.uni-bamberg.de/handle/uniba/91986 LA - eng AB - Information systems (IS) are frequently designed to leverage the negative effect of anchoring bias to influence individuals’ decision-making (e.g., by manipulating purchase decisions). Recent advances in Artificial Intelligence (AI) and the explanations of its decisions through explainable AI (XAI) have opened new opportunities for mitigating biased decisions. So far, the potential of these technological advances to overcome anchoring bias remains widely unclear. To this end, we conducted two online experiments with a total of N=390 participants in the context of purchase decisions to examine the impact of AI and XAI-based decision support on anchoring bias. Our results show that AI alone and its combination with XAI help to mitigate the negative effect of anchoring bias. Ultimately, our findings have implications for the design of AI and XAI-based decision support and IS to overcome cognitive biases. KW - Artificial Intelligence (AI) KW - Explainable AI (XAI) KW - Decision Support KW - Anchoring Bias KW - Cognitive Bias ER - TY - CHAP TI - A feedback component that leverages counterfactual explanations for smart learning support AU - Günther, Sebastian A. AU - Haag, Felix AU - Hopf, Konstantin AU - Handschuh, Philipp AU - Klose, Maria AU - Staake, Thorsten Robert PY - 2023 T2 - Digitale Kulturen der Lehre entwickeln : Rahmenbedingungen, Konzepte und Werkzeuge SP - 285-291 PB - Springer VS CY - Wiesbaden, Germany SN - 978-3-658-43378-9 DO - 10.1007/978-3-658-43379-6_19 UR - https://fis.uni-bamberg.de/handle/uniba/105946 LA - eng AB - The growing prevalence of digital learning in higher education is accompanied by challenges regarding students’ self-regulated learning. While there is a plethora of behavioral interventions that aim at supporting students’ self-regulated learning, they often do not consider the heterogeneity of students in their intervention design. This paper presents a novel feedback intervention that leverages the potential of machine learning and counterfactual explanations for providing personalized feedback to support students’ learning. Ultimately, this approach could automatically adapt to different courses and thereby empower scalable and effective feedback. KW - Learning analytics KW - Explainable artificial intelligence KW - Counterfactual explanations KW - Feedback intervention KW - Experiment KW - Self-regulated learning ER - TY - CHAP TI - Digitale Kulturen der Lehre entwickeln : einleitende Verortungen AU - Mrohs, Lorenz AU - Herrmann, Dominik AU - Franz, Julia AU - Lindner, Konstantin AU - Staake, Thorsten Robert PY - 2023 T2 - Digitale Kulturen der Lehre entwickeln : Rahmenbedingungen, Konzepte und Werkzeuge SP - 1-6 PB - Springer CY - Wiesbaden SN - 978-3-658-43378-9 DO - 10.1007/978-3-658-43379-6_1 UR - https://fis.uni-bamberg.de/handle/uniba/95364 LA - deu AB - Der Beitrag führt vor dem Hintergrund der Theorie der Kultur der Digitalität (Felix Stalder) in den vorliegenden Sammelband ein und wendet diesen theoretischen Rahmen auf Hochschulen und die Entwicklung der Hochschullehre an. Es werden die zentralen Strukturbedingungen umrissen und davon ausgehend Erfordernisse für die Entwicklung einer Kultur der Digitalität an der Universität Bamberg skizziert, die im Rahmen des Projekts „Digitale Kulturen der Lehre entwickeln (DiKuLe)“ beforscht und entwickelt werden. Abschließend gibt der Beitrag einen Ausblick auf die Beiträge des Sammelbandes, die neue Konzepte, Gestaltungsmöglichkeiten und Evaluationsergebnisse digitaler Lehr-Lernarrangements vorstellen. KW - Lehre ER - TY - BOOK TI - Digitale Kulturen der Lehre entwickeln : Rahmenbedingungen, Konzepte und Werkzeuge ED - Mrohs, Lorenz ED - Franz, Julia ED - Herrmann, Dominik ED - Lindner, Konstantin ED - Staake, Thorsten PY - 2023 PB - Springer Fachmedien CY - Wiesbaden T3 - Perspektiven der Hochschuldidaktik SN - 9783658433789 DO - 10.1007/978-3-658-43379-6 UR - https://fis.uni-bamberg.de/handle/uniba/95238 LA - deu ER - TY - CPAPER TI - Overcoming Anchoring Bias : the Potential of AI and XAI-based Decision Support AU - Haag, Felix AU - Stingl, Carlo AU - Zerfass, Katrin AU - Hopf, Konstantin AU - Staake, Thorsten PY - 2023 T2 - ICIS 2023 Proceedings SP - 1-17 PB - AISeL CY - New York UR - https://fis.uni-bamberg.de/handle/uniba/95220 LA - eng AB - Information systems (IS) are frequently designed to leverage the negative effect of anchoring bias to influence individuals’ decision-making (e.g., by manipulating purchase decisions). Recent advances in Artificial Intelligence (AI) and the explanations of its decisions through explainable AI (XAI) have opened new opportunities for mitigating biased decisions. So far, the potential of these technological advances to overcome anchoring bias remains widely unclear. To this end, we conducted two online experiments with a total of N=390 participants in the context of purchase decisions to examine the impact of AI and XAI-based decision support on anchoring bias. Our results show that AI alone and its combination with XAI help to mitigate the negative effect of anchoring bias. Ultimately, our findings have implications for the design of AI and XAI-based decision support and IS to overcome cognitive biases. KW - Artificial Intelligence (AI) KW - Explainable AI (XAI) KW - Decision Support KW - Anchoring Bias KW - Cognitive Bias ER - TY - CPAPER TI - Disaggregation of Heat Pump Load Profiles From Low-Resolution Smart Meter Data AU - Brudermueller, Tobias AU - Breer, Fabian AU - Staake, Thorsten PY - 2023 T2 - BuildSys '23: Proceedings of the 10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation SP - 228–231 PB - Association for Computing Machinery CY - New York, NY SN - 979-8-4007-0230-3 DO - 10.1145/3600100.3623731 UR - https://fis.uni-bamberg.de/handle/uniba/94014 LA - eng AB - As the number of heat pumps installed in residential buildings increases, their energy-efficient operation becomes increasingly important to reduce costs and ensure the stability of the power grid. The deployment of smart electricity meters results in large amounts of smart meter data that can be used for heat pump optimization. However, sub-metering infrastructure to monitor heat pumps’ energy consumption is costly and rarely available in practice. Non-intrusive load monitoring addresses this issue and disaggregates appliance-level consumption from aggregate measurements. However, previous studies use high-resolution data of active and reactive power and do not focus on heat pumps. In this context, our study is the first to disaggregate heat pump load profiles using commonly available smart meter data with energy measurements at 15-minute resolution. We use a sliding-window approach to train and test deep learning models on a real-world data set of 363 Swiss households with heat pumps observed over a period of 8 years. Evaluating our approach with a 5-fold cross-validation, our best model achieves a mean R2 score of 0.832 and an average RMSE of 0.169 kWh, which is similar to previous work that uses high-resolution measurements of active and reactive power. Our algorithms enable real-world applications to monitor the energy efficiency of heat pumps in operation and to estimate their flexibility for demand response programs. KW - Smart Meter Data KW - Heat Pump Optimization KW - Energy Efficiency KW - Non- Intrusive Load Monitoring KW - Load Disaggregation KW - Low Resolution ER - TY - CHAP TI - Information Systems and Behavioural Change : Feedback Interventions to curb the consumption of natural resources AU - Staake, Thorsten Robert AU - Tiefenbeck, Verena AU - Stiefmeier, Thomas PY - 2023 T2 - Research handbook on information systems and the environment SP - 253-274 PB - Edward Elgar Publishing CY - Cheltenham SN - 978-1-80220-186-4 DO - 10.4337/9781802201864 UR - https://fis.uni-bamberg.de/handle/uniba/94023 LA - eng ER - TY - CPAPER TI - Information Systems Research for the Next Generation : Child-Centricity in a Digital World AU - Graichen, Joanna AU - Staake, Thorsten PY - 2023 T2 - Proceedings of the 56th Hawaii International Conference on System Sciences, 2023 SP - 4026-4035 CY - Honolulu, HI SN - 978-0-9981331-6-4 DO - 10.24251/HICSS.2023.492 UR - https://fis.uni-bamberg.de/handle/uniba/94024 LA - eng AB - Traditionally, information systems (IS) research investigates socio-technical systems in organizations and the workplace. As IS have become an integral part of our daily lives, IS research nowadays also incorporates the private space. However, efforts to date have mostly focused on adults. Children, born into a digital world today, have been mostly left out. Yet our discipline not only has the potential to contribute to the adequate and child-friendly design of IS artifacts for children but can also help to further develop theories on children's behavior. For this to succeed, IS researchers need to adapt their approach to children. Ethical considerations should address children's vulnerability, the design of interventions should happen in close collaboration with children, research methods should be child-centered, and the specificities of children should be kept present in result analyses. KW - Human-centricity in a Sustainable Digital Economy KW - methodology KW - next generation KW - research methods KW - research with children ER - TY - CPAPER TI - Reducing power peaks in low-voltage grids via dynamic tariffs and automatic load control AU - Kaiser, K. AU - Kreft, Markus AU - Stai, Eleni AU - Vayá, M González AU - Hug, Gabriela AU - Staake, Thorsten PY - 2023 T2 - 27th International Conference on Electricity Distribution (CIRED 2023) SP - 1475-1479 PB - IET CY - Rome, Italy SN - 978-1-83953-855-1 DO - 10.1049/icp.2023.0772 UR - https://fis.uni-bamberg.de/handle/uniba/94037 LA - eng ER - TY - JOUR TI - Complementarities in behavioral interventions : Evidence from a field experiment on resource conservation AU - Fang, Ximeng AU - Goette, Lorenz AU - Rockenbach, Bettina AU - Sutter, Matthias AU - Tiefenbeck, Verena AU - Schoeb, Samuel AU - Staake, Thorsten PY - 2023 JO - Journal of public economics VL - 228 IS - 105028 SP - 1-20 PB - Elsevier CY - Amsterdam [u.a.] SN - 0047-2727 DO - 10.1016/j.jpubeco.2023.105028 UR - https://fis.uni-bamberg.de/handle/uniba/92533 LA - eng AB - Behavioral policy often aims at influencing behavior by mitigating biases due to, e.g., imperfect information or inattention. We study how this is affected by the simultaneous presence of multiple biases arising from different sources, through a field experiment on resource conservation in an energy- and water-intensive everyday activity (showering). One intervention, shower energy reports, primarily targeted knowledge about environmental impacts; another intervention, real-time feedback, primarily targeted salience of resource use. We find a striking complementarity. While only the latter induced significant conservation effects when implemented in isolation, each intervention became more effective when implemented jointly. This is consistent with predictions from a theoretical framework that highlights the importance of targeting all relevant sources of bias to achieve behavioral change. KW - Behavioral public policy KW - Pro-environmental behavior KW - Limited attention KW - Information provision KW - Real-time feedback KW - Policy interactions ER - TY - JOUR TI - Hand Hygiene of Kindergarten Children : Understanding the Effect of Live Feedback on Handwashing Behaviour, Self-Efficacy, and Motivation of Young Children ; Protocol for a Multi-Arm Cluster Randomized Controlled Trial AU - Dangis, Glenda AU - Terho, Kirsi AU - Graichen, Joanna AU - Günther, Sebastian A. AU - Rosio, Riitta AU - Salanterä, Sanna AU - Staake, Thorsten AU - Stingl, Carlo AU - Pakarinen, Anni PY - 2023 JO - PLOS ONE VL - 18 IS - 1, e0280686 SP - 1-18 PB - Public Library of Science CY - San Francisco SN - 1932-6203 DO - 10.1371/journal.pone.0280686 UR - https://fis.uni-bamberg.de/handle/uniba/92339 LA - eng AB - Early implementation of interventions at a young age fosters behaviour changes and helps to adopt behaviours that promote health. Digital technologies may help to promote the hand hygiene behaviour of children. However, there is a lack of digital feedback interventions focusing on the hand hygiene behaviour of preschool children in childhood education and care settings. This study protocol aims to describe a study that evaluates the effectiveness of a gamified live feedback intervention and explores underlying behavioural theories in achieving better hand hygiene behaviour of preschool children in early childhood education and care settings. This study will be a four-arm cluster randomized controlled trial with three phases and a twelve-month follow-up by country stratification. The sample size is 106 children of which one cluster will have a minimum number of 40 children. During the baseline phase, all groups will have automated monitoring systems installed. In the intervention phase, the control group will have no screen activity. The intervention groups will have feedback displays during the handwashing activity. Intervention A will receive instructions, and intervention B and C groups will receive instructions and a reward. In the post-intervention phase, all the groups will have no screen activity except intervention C which will receive instructions from the screen but no reward. The outcome measures will be hand hygiene behaviour, self-efficacy, and intrinsic motivation. Outcome measures will be collected at baseline, intervention, and post-intervention phases and a 12-month follow-up. The data will be analysed with quantitative and qualitative methods. The findings of the planned study will provide whether this gamified live feedback intervention can be recommended to be used in educational settings to improve the hand hygiene behaviour of preschool children to promote health. KW - Hand Hygiene KW - Kindergarten Children ER - TY - CPAPER TI - Addressing Learners' Heterogeneity in Higher Education : an Explainable AI-based Feedback Artifact for Digital Learning Environments AU - Haag, Felix AU - Günther, Sebastian AU - Hopf, Konstantin AU - Handschuh, Philipp AU - Klose, Maria AU - Staake, Thorsten Robert PY - 2023 T2 - Proceedings of the 18th Internationale Tagung Wirtschaftsinformatik PB - AISeL CY - AIS electronic library UR - https://fis.uni-bamberg.de/handle/uniba/92292 LA - eng ER - TY - CPAPER TI - Meta-Regression Analysis of Errors in Short-Term Electricity Load Forecasting AU - Hopf, Konstantin AU - Hartstang, Hannah AU - Staake, Thorsten Robert PY - 2023 T2 - Companion Proceedings of the 14th ACM International Conference on Future Energy Systems (e-Energy) PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/91304 LA - eng AB - Forecasting electricity demand plays a critical role in ensuring reliable and cost-efficient operation of the electricity supply. With the global transition to distributed renewable energy sources and the electrification of heating and transportation, accurate load forecasts become even more important. While numerous empirical studies and a handful of review articles exist, there is surprisingly little quantitative analysis of the literature, most notably none that identifies the impact of factors on forecasting performance across the entirety of empirical studies. In this article, we therefore present a Meta-Regression Analysis (MRA) that examines factors that influence the accuracy of short-term electricity load forecasts. We use data from 421 forecast models published in 59 studies. While the grid level (esp. individual vs. aggregated vs. system), the forecast granularity, and the algorithms used seem to have a significant impact on the MAPE, bibliometric data, dataset sizes, and prediction horizon show no significant effect. We found the LSTM approach and a combination of neural networks with other approaches to be the best forecasting methods. The results help practitioners and researchers to make meaningful model choices. Yet, this paper calls for further MRA in the field of load forecasting to close the blind spots in research and practice of load forecasting. KW - Electricity Demand Forecast KW - Short-Term Forecasting KW - Meta Regression Analysis KW - Mean Absolute Percentage Error ER - TY - JOUR TI - Large-scale monitoring of residential heat pump cycling using smart meter data AU - Brudermüller, Tobias AU - Kreft, Markus AU - Fleisch, Elgar AU - Staake, Thorsten PY - 2023 SP - 1-14 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/90918 LA - eng AB - Heat pumps play an essential role in decarbonizing the building sector, but their electricity consumption can vary significantly across buildings. This variability is closely related to their cycling behavior (i.e., the frequency of on–off transitions), which is also an indicator for improper sizing and non-optimal settings and can affect a heat pump’s lifetime. Up to now it has been unclear which cycling behaviors are typical and atypical for heat pump operation in the field and importantly, there is a lack of methods to identify heat pumps that cycle atypically. Therefore, in this study we develop a method to monitor heat pumps with energy measurements delivered by common smart electricity meters, which also cover heat pumps without network connectivity. We show how smart meter data with 15-minute resolution can be used to extract key indicators about heat pump cycling and outline how atypical behavior can be detected after controlling for outdoor temperature. Our method is robust across different building characteristics and varying times of observation, does not require contextual information, and can be implemented with existing smart meter data, making it suitable for real-world applications. Analyzing 503 heat pumps in Swiss households over a period of 21 months, we further describe behavioral differences with respect to building and heat pump characteristics and study the relationship between heat pumps’ cycling behavior, energy efficiency, and appropriate sizing. Our results show that outliers in cycling behavior are more than twice as common for air-source heat pumps than for ground-source heat pumps. KW - Smart meter data KW - Heat pump KW - Cycling behavior KW - outlier detection KW - Residential buildings KW - Energy efficiency KW - Appliance monitoring KW - Real-world operation KW - Machine learning ER - TY - JOUR TI - Large-scale monitoring of residential heat pump cycling using smart meter data AU - Brudermüller, Tobias AU - Kreft, Markus AU - Fleisch, Elgar AU - Staake, Thorsten PY - 2023 JO - Applied energy VL - 350 IS - 121734 SP - 1-14 PB - Elsevier CY - Amsterdam [u.a.] SN - 0306-2619 DO - 10.1016/j.apenergy.2023.121734 UR - https://fis.uni-bamberg.de/handle/uniba/90919 LA - eng AB - Heat pumps play an essential role in decarbonizing the building sector, but their electricity consumption can vary significantly across buildings. This variability is closely related to their cycling behavior (i.e., the frequency of on–off transitions), which is also an indicator for improper sizing and non-optimal settings and can affect a heat pump’s lifetime. Up to now it has been unclear which cycling behaviors are typical and atypical for heat pump operation in the field and importantly, there is a lack of methods to identify heat pumps that cycle atypically. Therefore, in this study we develop a method to monitor heat pumps with energy measurements delivered by common smart electricity meters, which also cover heat pumps without network connectivity. We show how smart meter data with 15-minute resolution can be used to extract key indicators about heat pump cycling and outline how atypical behavior can be detected after controlling for outdoor temperature. Our method is robust across different building characteristics and varying times of observation, does not require contextual information, and can be implemented with existing smart meter data, making it suitable for real-world applications. Analyzing 503 heat pumps in Swiss households over a period of 21 months, we further describe behavioral differences with respect to building and heat pump characteristics and study the relationship between heat pumps’ cycling behavior, energy efficiency, and appropriate sizing. Our results show that outliers in cycling behavior are more than twice as common for air-source heat pumps than for ground-source heat pumps. KW - Smart meter data KW - Heat pump KW - Cycling behavior KW - outlier detection KW - Residential buildings KW - Energy efficiency KW - Appliance monitoring KW - Real-world operation KW - Machine learning ER - TY - CPAPER TI - Meta-Regression Analysis of Errors in Short-Term Electricity Load Forecasting AU - Hopf, Konstantin AU - Hartstang, Hannah AU - Staake, Thorsten Robert PY - 2023 T2 - Companion Proceedings of the 14th ACM International Conference on Future Energy Systems (e-Energy) SP - 32–39 PB - ACM digital library DO - 10.1145/3599733.3600248 UR - https://fis.uni-bamberg.de/handle/uniba/89924 LA - eng AB - Forecasting electricity demand plays a critical role in ensuring reliable and cost-efficient operation of the electricity supply. With the global transition to distributed renewable energy sources and the electrification of heating and transportation, accurate load forecasts become even more important. While numerous empirical studies and a handful of review articles exist, there is surprisingly little quantitative analysis of the literature, most notably none that identifies the impact of factors on forecasting performance across the entirety of empirical studies. In this article, we therefore present a Meta-Regression Analysis (MRA) that examines factors that influence the accuracy of short-term electricity load forecasts. We use data from 421 forecast models published in 59 studies. While the grid level (esp. individual vs. aggregated vs. system), the forecast granularity, and the algorithms used seem to have a significant impact on the MAPE, bibliometric data, dataset sizes, and prediction horizon show no significant effect. We found the LSTM approach and a combination of neural networks with other approaches to be the best forecasting methods. The results help practitioners and researchers to make meaningful model choices. Yet, this paper calls for further MRA in the field of load forecasting to close the blind spots in research and practice of load forecasting. KW - Electricity Demand Forecast KW - Short-Term Forecasting KW - Meta Regression Analysis KW - Mean Absolute Percentage Error ER - TY - JOUR TI - Value creation from analytics with limited data : a case study on the retailing of durable consumer goods AU - Hopf, Konstantin AU - Weigert, Andreas AU - Staake, Thorsten PY - 2023 SP - 1-37 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/59621 LA - eng AB - Companies are pinning high hopes on competitive advantages through data analytics. So far, value gains through analytics have been demonstrated for IT-heavy and data-rich business areas. Yet, research has paid little attention to value creation through data analytics in the plethora of companies with limited data (i.e., having transactions in the hundreds and attributes in the tens). Building on the literature of big data value creation and the resource-based view, we carried out an in-depth analytics case study with a retailer of renewable energy systems. Firms in this business area operate with expensive but few sales, so their available data are notoriously limited. Our findings demonstrate that data analytics capabilities and value creation mechanisms (democratize, contextualize, experiment with data, and execute data insights) are also effective in situations with limited data. Practice and research should therefore put not only emphasis on the volume and the variety of data but also on contextual factors related to managers (e.g., clear strategy, vision, leadership) and all employees (e.g., openness for agile working mode, data awareness). KW - data analytics KW - information systems value creation KW - value creation mechanisms KW - machine learning KW - retail KW - renewable energy systems ER - TY - JOUR TI - Value creation from analytics with limited data : a case study on the retailing of durable consumer goods AU - Hopf, Konstantin AU - Weigert, Andreas AU - Staake, Thorsten PY - 2023 JO - Journal of Decision Systems VL - 32 IS - 2 SP - 289-325 PB - Taylor & Francis CY - Abingdon SN - 2116-7052 DO - 10.1080/12460125.2022.2059172 UR - https://fis.uni-bamberg.de/handle/uniba/53754 LA - eng AB - Companies are pinning high hopes on competitive advantages through data analytics. So far, value gains through analytics have been demonstrated for IT-heavy and data-rich business areas. Yet, research has paid little attention to value creation through data analytics in the plethora of companies with limited data (i.e., having transactions in the hundreds and attributes in the tens). Building on the literature of big data value creation and the resource-based view, we carried out an in-depth analytics case study with a retailer of renewable energy systems. Firms in this business area operate with expensive but few sales, so their available data are notoriously limited. Our findings demonstrate that data analytics capabilities and value creation mechanisms (democratize, contextualize, experiment with data, and execute data insights) are also effective in situations with limited data. Practice and research should therefore put not only emphasis on the volume and the variety of data but also on contextual factors related to managers (e.g., clear strategy, vision, leadership) and all employees (e.g., openness for agile working mode, data awareness). KW - data analytics KW - information systems value creation KW - value creation mechanisms KW - machine learning KW - retail KW - renewable energy systems ER - TY - JOUR TI - Heat pump inspections result in large energy savings when a pre-selection of households is performed : A promising use case of smart meter data AU - Weigert, Andreas AU - Hopf, Konstantin AU - Günther, Sebastian AU - Staake, Thorsten PY - 2022 SP - 1-15 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/55208 LA - deu AB - Heat pumps play an important role in the energy transition. They can extract renewable energy from the air or ground and increasingly replace fossil heating systems in buildings. In operation, however, heat pumps often consume more electricity than necessary due to incorrect settings and installation deficiencies. Although many setting and installation issues are easy to fix, problems often go unnoticed, and the saving potential from quick fixes remains unclear. In a study with 297 Swiss households (41 treatment, 256 control) running for four years, we investigated an energy efficiency campaign in which the treatment group received a professional heat pump inspection and user training. We found considerable heterogeneity with respect to the savings achieved. We derived two criteria based on smart meter data that enable utilities to identify relevant households and thus boost the impact of such efficiency campaigns: For example, pre-selecting half of the households based on available information results in average savings of 1,805 kWh (15.2%) per year and household in the high-potential group compared to no savings in the low-potential group. Thus, heat pump inspections among pre-selected households can lead to large, cost-effective electricity savings, and we show that common smart meter data makes such pre-selection feasible. KW - Heat pump KW - Energy consulting KW - Energy efficiency KW - Smart meter data KW - Data analytics ER - TY - CPAPER TI - The Behavioral Mechanisms Behind Feedback : A Preliminary Model for Quantifying Cause-Effect Relationships AU - Stingl, Carlo AU - Günther, Sebastian AU - Staake, Thorsten PY - 2022 T2 - ECIS 2022: Research-in-progress-papers UR - https://fis.uni-bamberg.de/handle/uniba/57228 LA - eng ER - TY - CPAPER TI - No Longer Without a Reward : Do Digital Rewards Crowd Out Intrinsic Motivation of Young Children? AU - Graichen, Joanna AU - Stingl, Carlo AU - Günther, Sebastian AU - Staake, Thorsten AU - Pakarinen, Anni AU - Rosio, Riitta AU - Salanterä, Sanna PY - 2022 T2 - ICIS 2022 Proceedings PB - AISeL UR - https://fis.uni-bamberg.de/handle/uniba/57231 LA - eng ER - TY - CPAPER TI - Automatic Differentiation of Variable and Fixed Speed Heat Pumps With Smart Meter Data AU - Brudermüller, Tobias AU - Wirth, Florian AU - Weigert, Andreas AU - Staake, Thorsten PY - 2022 T2 - 2022 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm) SP - 412-418 PB - IEEE SN - 978-1-6654-3254-2 DO - 10.1109/SmartGridComm52983.2022.9961055 UR - https://fis.uni-bamberg.de/handle/uniba/56856 LA - eng ER - TY - CPAPER TI - Augmented Cross-Selling Through Explainable AI : a Case From Energy Retailing AU - Haag, Felix AU - Hopf, Konstantin AU - Menelau Vasconcelos, Pedro AU - Staake, Thorsten PY - 2022 SP - 1-19 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/54308 LA - eng AB - The advance of Machine Learning (ML) has led to a strong interest in this technology to support decision making. While complex ML models provide predictions that are often more accurate than those of traditional tools, such models often hide the reasoning behind the prediction from their users, which can lead to lower adoption and lack of insight. Motivated by this tension, research has put forth Explainable Artificial Intelligence (XAI) techniques that uncover patterns discovered by ML. Despite the high hopes in both ML and XAI, there is little empirical evidence of the benefits to traditional businesses. To this end, we analyze data on 220,185 customers of an energy retailer, predict cross-purchases with up to 86% correctness (AUC), and show that the XAI method SHAP provides explanations that hold for actual buyers. We further outline implications for research in information systems, XAI, and relationship marketing. KW - Cross-Selling KW - Energy Retailing KW - Explainable Artificial Intelligence KW - Machine Learning KW - Relationship Marketing KW - Task Augmentation ER - TY - JOUR TI - Heat pump inspections result in large energy savings when a pre-selection of households is performed : A promising use case of smart meter data AU - Weigert, Andreas AU - Hopf, Konstantin AU - Günther, Sebastian A. AU - Staake, Thorsten PY - 2022 JO - Energy Policy VL - 169 IS - 113156 SP - 1-15 PB - Elsevier CY - Amsterdam [u.a.] SN - 0301-4215 DO - 10.1016/j.enpol.2022.113156 UR - https://fis.uni-bamberg.de/handle/uniba/55315 LA - eng AB - Heat pumps play an important role in the energy transition. They can extract renewable energy from the air or ground and increasingly replace fossil heating systems in buildings. In operation, however, heat pumps often consume more electricity than necessary due to incorrect settings and installation deficiencies. Although many setting and installation issues are easy to fix, problems often go unnoticed, and the saving potential from quick fixes remains unclear. In a study with 297 Swiss households (41 treatment, 256 control) running for four years, we investigated an energy efficiency campaign in which the treatment group received a professional heat pump inspection and user training. We found considerable heterogeneity with respect to the savings achieved. We derived two criteria based on smart meter data that enable utilities to identify relevant households and thus boost the impact of such efficiency campaigns: For example, pre-selecting half of the households based on available information results in average savings of 1,805 kWh (15.2%) per year and household in the high-potential group compared to no savings in the low-potential group. Thus, heat pump inspections among pre-selected households can lead to large, cost-effective electricity savings, and we show that common smart meter data makes such pre-selection feasible. KW - Heat pump KW - Energy consulting KW - Energy efficiency KW - Smart meter data KW - Data analytics ER - TY - CPAPER TI - Augmented Cross-Selling Through Explainable AI : a Case From Energy Retailing AU - Haag, Felix AU - Hopf, Konstantin AU - Menelau Vasconcelos, Pedro AU - Staake, Thorsten PY - 2022 T2 - ECIS 2022 Proceedings SP - 1-19 PB - AISeL UR - https://fis.uni-bamberg.de/handle/uniba/54316 LA - eng AB - The advance of Machine Learning (ML) has led to a strong interest in this technology to support decision making. While complex ML models provide predictions that are often more accurate than those of traditional tools, such models often hide the reasoning behind the prediction from their users, which can lead to lower adoption and lack of insight. Motivated by this tension, research has put forth Explainable Artificial Intelligence (XAI) techniques that uncover patterns discovered by ML. Despite the high hopes in both ML and XAI, there is little empirical evidence of the benefits to traditional businesses. To this end, we analyze data on 220,185 customers of an energy retailer, predict cross-purchases with up to 86% correctness (AUC), and show that the XAI method SHAP provides explanations that hold for actual buyers. We further outline implications for research in information systems, XAI, and relationship marketing. KW - Cross-Selling KW - Energy Retailing KW - Explainable Artificial Intelligence KW - Machine Learning KW - Relationship Marketing KW - Task Augmentation ER - TY - JOUR TI - For better or for worse? Empirical evidence of moral licensing in a behavioral energy conservation campaign AU - Tiefenbeck, Verena AU - Staake, Thorsten AU - Roth, Kurt AU - Sachs, Olga PY - 2022 SP - 160-171 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/1920 LA - eng AB - Isolated environmental campaigns focusing on defined target behaviors are rolled out to millions of households every year. Yet it is still unclear whether these programs trigger cross-domain adoption of additional environment-friendly behaviors (positive spillover) or reduced engagement elsewhere. A thorough evaluation of the real net performance of these programs is lacking. This paper investigates whether positive or perverse side effects dominate by exemplifying the impact of a water conservation campaign on electricity consumption. The study draws on daily water (10,780 data points) and weekly electricity (1386 data points) consumption data of 154 apartments in a controlled field experiment at a multifamily residence. The results show that residents who received weekly feedback on their water consumption lowered their water use (6.0% on average), but at the same time increased their electricity consumption by 5.6% compared with control subjects. Income effects can be excluded. While follow-up research is needed on the precise mechanism of the psychological process at work, the findings are consistent with the concept of moral licensing, which can more than offset the benefits of focused energy efficiency campaigns, at least in the short-term. We advocate the adoption of a more comprehensive view in environmental program design/evaluation in order to quantify and mitigate these unintended effe KW - energy ER - TY - CHAP TI - A Feedback Information System for Improving Hand Hygiene on a Personal and Organizational Level AU - Stingl, Carlo AU - Günther, Sebastian A. AU - Staake, Thorsten Robert PY - 2021 T2 - Innovation Through Information Systems : Volume I: A Collection of Latest Research on Domain Issues SP - 88-94 PB - Springer International Publishing CY - Cham SN - 9783030867898 DO - 10.1007/978-3-030-86790-4_7 UR - https://fis.uni-bamberg.de/handle/uniba/115823 LA - eng ER - TY - CPAPER TI - Research Method Classification with Deep Transfer Learning for Semi-Automatic Meta-Analysis of Information Systems Papers AU - Anisienia, Anna AU - Mueller, Roland M. AU - Kupfer, Anna AU - Staake, Thorsten PY - 2021 T2 - Proceedings of the 54th Hawaii International Conference on System Sciences SP - 6099-6108 SN - 978-0-9981331-4-0 DO - 10.24251/hicss.2021.737 UR - https://fis.uni-bamberg.de/handle/uniba/111308 LA - eng AB - This paper presents an artifact that uses deep transfer learning methods for the multi-label classification of research methods for an Information Systems corpus. The artifact can support researchers with frequently performed yet time-consuming classification and structure-seeking tasks that are often part of literature analyses. We use a corpus of 5,388 papers from AIS journals and conferences, of which 1,766 have been manually labelled with up to five research methods. The unlabelled papers are used for finetuning the language model, whereas the labelled data are used for training and testing. Our approach outperforms state of the art research method classification that deploy SVM. We show that deep transfer learning models can lead to a better recognition of research methods than shallower word embedding approaches like word2vec or GloVe. The results illustrate the potential of establishing semiautomated methods for meta-analysis. KW - - ER - TY - GEN TI - Uni.vers Forschung : das Magazin der Otto-Friedrich-Universität Bamberg AU - Achter, Patricia AU - Braches-Chyrek, Rita AU - Düchs, Martin AU - Färber, Tanja AU - Finzel, Bettina AU - Ganesch, Franziska AU - Graichen, Joanna AU - Horn, Matthias AU - Oehler, Andreas AU - Posegga, Oliver AU - Proaño Acosta, Christian AU - Scheltjens, Werner AU - Schmid, Ute AU - Schneider, Pauline AU - Staake, Thorsten AU - Steins-Löber, Sabine AU - Stingl, Carlo AU - Stöckl, Andreas AU - Struck, Olaf AU - Velde, Caroline van der AU - Wolstein, Jörg ED - Fischbach, Kai PY - 2021 IS - April 2021, Mensch und Maschine - Bamberger Beiträge zur Digitalisierung = Man and Machine - Bamberg Scholars on Digitalisation PB - Otto-Friedrich-Universität CY - Bamberg SN - 1618-9019 UR - https://fis.uni-bamberg.de/handle/uniba/50041 LA - deu AB - Wenn Menschen die Technik weiterentwickeln, entstehen ständig neue Möglichkeiten und Herausforderungen. Die Gesellschaft ist gefragt mitzudiskutieren, wie eine immer weiter digitalisierte Welt künftig aussehen könnte. Und die Forschung hilft dabei, dass sich jede und jeder Einzelne eine fundierte Meinung bilden kann. In dieser Ausgabe schreiben die Autorinnen und Autoren über den Einsatz der Technik im Alltag, die Zusammenarbeit von Menschen und Maschinen, das Pro und Contra der Digitalisierung. KW - Digitalisierung KW - Technik KW - KI KW - Gesellschaft KW - App KW - Internet KW - Arbeitsmarkt KW - Geschichte KW - Psychologie KW - Architektur KW - Kinder KW - Medien KW - Finanzen KW - Gesundheit ER - TY - JOUR TI - Wozu Smart Meter gut sind AU - Vogel, Benedikt PY - 2021 JO - Swiss engineering : STZ Schweizerische technische Zeitschrift IS - August SP - 14-15 PB - Kömedia AG CY - St. Gallen SN - 1660-4121 UR - https://fis.uni-bamberg.de/handle/uniba/50941 LA - deu ER - TY - JOUR TI - Wozu Smart Meter gut sind AU - Vogel, Benedikt PY - 2021 JO - ET Elektrotechnik IS - 4 SP - 46-49 SN - 1015-3926 UR - https://fis.uni-bamberg.de/handle/uniba/50044 LA - deu ER - TY - CPAPER TI - A Feedback Information System for Improving Hand Hygiene on a Personal and Organizational Level AU - Stingl, Carlo AU - Günther, Sebastian AU - Staake, Thorsten PY - 2021 T2 - Wirtschaftsinformatik 2021 Proceedings PB - AIS Electronic Library (AISeL) UR - https://fis.uni-bamberg.de/handle/uniba/49800 LA - eng ER - TY - RPRT TI - Analyseverfahren zur Erkennung von Effizienz- und Selbstversorgungspotenzialen individueller Haushalte : Schlussbericht zum Teilprojekt 0350010 im Verbundvorhaben "SmartLoad" ; Projektlaufzeit: 01.06.2017-31.03.2020 AU - Weigert, Andreas AU - Hopf, Konstantin AU - Staake, Thorsten PY - 2020 PB - Technische Informationbibliothek (TIB) CY - Hannover DO - 10.2314/KXP:1754715761 UR - https://fis.uni-bamberg.de/handle/uniba/59522 LA - deu ER - TY - RPRT TI - SmartLoad : Smart Meter Data Analytics for Enhanced Energy Efficiency in the Residential Sector AU - Weigert, Andreas AU - Hopf, Konstantin AU - Staake, Thorsten AU - Rast, André AU - Marckhoff, Jan PY - 2020 PB - Bundesamt für Energie, Sektion Energieforschung und Cleantech CY - Bern UR - https://fis.uni-bamberg.de/handle/uniba/54043 LA - deu AB - Im Zuge der Digitalisierung erhoffen sich Unternehmen Wettbewerbsvorteile durch die Entwicklung datenbasierter Dienstleistungen und die Steigerung der Vertriebseffizienz. Dies gilt auch für Energieversorgungsunternehmen (EVUs), die, wenn auch in einem stark regulierten Umfeld, eine Transformation vom Versorger zum Dienstleister anstreben und zugleich eine Schlüsselrolle beim Austausch fossiler Energieträger durch Elektrizität aus erneuerbaren Quellen einnehmen. Ausgehend von den in absehbarer Zeit flächendeckend zur Verfügung stehenden Verbrauch- und Transaktionsdaten planen EVUs, auf ihre Kunden massgeschneiderte Produkte und Dienstleistungen zu entwickeln. Um den Wert dieser Daten zu heben, ist jedoch der Einsatz moderner Analysemethoden – zum Beispiel Verfahren des maschinellen Lernens – erforderlich. In den letzten Jahrzehnten wurden zwar eine Reihe von generellen Datenanalyseverfahren entwickelt, aber es fehlt nach wie vor (insbesondere in Unternehmen) das Verständnis dafür, wie die Analytik auf konkrete Anwendungen der Energiedatenanalyse anzuwenden ist. Das Projekt «SmartLoad» trug dazu bei, diese Lücke zu schliessen und hat un-tersucht, inwiefern verfügbare Daten bei Energieanbietern genutzt werden können, um Haushalte zu erkennen, die a) bereit sind, nachhaltige Stromprodukte zu nutzen und die sich b) für die Investition in Selbstversorgungs- und Speicherlösungen interessieren. Darüber hinaus hat das Projekt untersucht, wie c) Smart-Meter-Daten das Stromverbrauchs-Feedback unterstützen können, um die Energieeffizienz im Privatsektor zu erhöhen. Vor diesem Hintergrund hat die Projektgruppe detaillierte Daten von insgesamt 1’373 privaten Haushalten erhoben, mit diesen Daten maschinellen Lernverfahren trainiert und Vorhersagemodelle für das Kaufinteresse für lokalen Ökostrom, die Investition in Photovoltaikanlagen und die Anschaffung von Wärmepumpen entwickelt. Das Modell für den Kauf von Ökostrom wurde in einem Experiment mit 4’712 Privatkunden evaluiert. Die Modelle zur Prädiktion der Investitionsbereitschaft in Photovoltaikanalgen und Wärmepumpen ermöglichten die Entwicklung eines Softwareprototypen, der den Vertrieb der Technologien unterstützt. Die Erkenntnisse des Projekts liefern Energieanbietern wichtige Hinweise, unter anderen für welche Aufgaben des Vertriebs von nachhaltigen Produkten maschinelle Lernverfahren eingesetzt werden können, welche externen Datenquellen die Kaufvorhersagen verbessern, wie geeignete Trainingsdaten für die Modellentwicklung gesammelt werden sollten und wie die entwickelten Vorhersagemodelle in eine Anwendung für den Vertriebsmitarbeiter überführt werden können. KW - Energietechnik ER - TY - CPAPER TI - Leveraging Social Norms to Encourage Online Learning : Empirical Evidence from a Blended Learning Course AU - Günther, Sebastian AU - Veihelmann, Tobias AU - Staake, Thorsten PY - 2020 T2 - ICIS 2020 Proceedings IS - 1205 SP - 1-17 PB - AIS Electronic Library (AISeL) UR - https://fis.uni-bamberg.de/handle/uniba/49801 LA - eng ER - TY - CPAPER TI - Detection of heat pumps from smart meter and open data AU - Weigert, Andreas AU - Hopf, Konstantin AU - Weinig, Nicolai AU - Staake, Thorsten PY - 2020 VL - 3 IS - 1 SP - 14 PB - Springer Science and Business Media {LLC} SN - 2520-8942 DO - 10.1186/s42162-020-00124-6 UR - https://fis.uni-bamberg.de/handle/uniba/48885 LA - eng ER - TY - JOUR TI - The behavioral response to a corporate carbon offset program : A field experiment on adverse effects and mitigation strategies AU - Günther, Sebastian AU - Staake, Thorsten AU - Schöb, Samuel AU - Tiefenbeck, Verena PY - 2020 JO - Global environmental change : human and policy dimensions VL - 64 IS - 102123 SP - 1-14 PB - Elsevier CY - Amsterdam [u.a.] SN - 0959-3780 DO - 10.1016/j.gloenvcha.2020.102123 UR - https://fis.uni-bamberg.de/handle/uniba/48429 LA - eng ER - TY - CPAPER TI - Empowering personalized feedback on hot water usage : a field study with shower meters AU - Günther, Sebastian AU - Stingl, Carlo AU - Coroamă, Vlad C. AU - Schöb, Samuel AU - Staake, Thorsten PY - 2020 T2 - SAC '20: Proceedings of the 35th Annual ACM Symposium on Applied Computing SP - 763-766 PB - ACM SN - 9781450368667 DO - 10.1145/3341105.3374053 UR - https://fis.uni-bamberg.de/handle/uniba/48280 LA - eng ER - TY - RPRT TI - Methoden der Energiedatenanalyse : Schlussbericht ; Vorhaben im Rahmen des Eurostars Projekts E! 9859 BENginell "Energy Data Analytics: Increasing Service Quality and Energy Efficiency in the Residential Sector" AU - Hopf, Konstantin AU - Staake, Thorsten PY - 2020 PB - Otto-Friedrich-Universität CY - Bamberg DO - 10.20378/irb-47756 UR - https://fis.uni-bamberg.de/handle/uniba/47756 LA - deu AB - Die Steigerung der Energieeffizienz im Privatsektor und der zunehmende Wettbewerb im Energievertrieb stellt die deutsche Energiewirtschaft vor grundlegende Herausforderungen. Gleichzeitig bringt jedoch die Digitalisierung im Energiesektor, die insbesondere durch intelligente Stromnetze und die steigende Verfügbarkeit von Daten unterstützt wird, enorme Potentiale, die von Energieversorgern strategisch sinnvoll genutzt werden können. Die Forschung in diesem Verbundvorhaben zielte darauf ab, Verfahren des maschinellen Lernens zu entwickeln, um verfügbare Daten bei EVU (z.B. Energieverbrauchsdaten, Tarifinformationen), sowie frei verfügbare Daten (Geoinformationen, Wetterdaten, usw.) so zu verarbeiten, sodass wirkungsvolle, massenmarkttaugliche Energieeffizienzmaßnahmen und Dienstleistungen realisiert werden können. Hierzu wurden die Daten mit zusätzlichen Informationen aus Kundenumfragen oder früheren Kundenansprachen angereichert. Schlussendlich ermöglichen es die aus den Daten erzielten Erkenntnisse, die Servicequalität im Energievertrieb und die Energieeffizienz bei Endkunden zu steigern. Im Teilprojekt der Otto-Friedrich-Universität Bamberg wurden Verfahren der Energiedatenanalyse entwickelt, die durch die BEN Energy AG (Zürich) in die BENgine-Softwareplattform eingebettet und zu nutzbaren Lösungen für EVU im europäischen Raum weiterentwickelt wurden. Die Lösung ist zum Zeitpunkt des Projektabschlusses bei über 30 EVU in Europa im Einsatz. ER - TY - CPAPER TI - A Cognitive Computing Solution to Foster Retailing of Renewable Energy Systems AU - Weigert, Andreas AU - Hopf, Konstantin AU - Staake, Thorsten PY - 2020 PB - Otto-Friedrich-Universität CY - Bamberg DO - 10.20378/irb-47040 UR - https://fis.uni-bamberg.de/handle/uniba/47040 LA - eng AB - Renewable energy systems (RES) in the residential sector, like photovoltaic systems, heat pumps and battery storage, are corner¬stones of a sustainable energy supply. Nevertheless–and despite major fiscal stimuli–private investment in such technologies has not yet reached a satisfactory level, also because sale of such products is time-consuming and requires a high level of expertise from suppliers. In practice, small and medium-sized installation firms are often responsible for addressing customers, advising, designing and implementing the appropriate systems, but they struggle with offering the complex technology and are exposed to fierce competition in their market. In a joint research initiative with a RES supplier and a software development company, we drive the development of information systems that support installation companies in their tasks. To this end, we are using action design to develop a cognitive computing solution based on Machine Learning (ML) to promote the sale of sustainable energy products. Based on 4,909 real customer requests for RES and survey data from 666 homeowners (which we use as ground truth data for ML), a predictive model can reliably identify promising RES installations out of a list of customer requests and thereby supports an important business task. Despite these promising results, we face a number of challenges in developing our cognitive computing solution. To address these challenges, design principles for similar systems are developed, contributing to the current debate on how information systems research can support sustainable development and how artificial intelligence can be used profitably in enterprises. KW - Renewable energy systems, sales support system, cognitive computing, machine learning ER - TY - RPRT TI - SmartLoad : Smart Meter Data Analytics for Enhanced Energy Efficiency in the Residential Sector AU - Weigert, Andreas AU - Hopf, Konstantin AU - Staake, Thorsten AU - Rast, André AU - Marckhoff, Jan PY - 2020 PB - Otto-Friedrich-Universität CY - Bamberg DO - 10.20378/irb-47805 UR - https://fis.uni-bamberg.de/handle/uniba/47805 LA - deu AB - Im Zuge der Digitalisierung erhoffen sich Unternehmen Wettbewerbsvorteile durch die Entwicklung datenbasierter Dienstleistungen und die Steigerung der Vertriebseffizienz. Dies gilt auch für Energieversorgungsunternehmen (EVUs), die, wenn auch in einem stark regulierten Umfeld, eine Transformation vom Versorger zum Dienstleister anstreben und zugleich eine Schlüsselrolle beim Austausch fossiler Energieträger durch Elektrizität aus erneuerbaren Quellen einnehmen. Ausgehend von den in absehbarer Zeit flächendeckend zur Verfügung stehenden Verbrauch- und Transaktionsdaten planen EVUs, auf ihre Kunden massgeschneiderte Produkte und Dienstleistungen zu entwickeln. Um den Wert dieser Daten zu heben, ist jedoch der Einsatz moderner Analysemethoden – zum Beispiel Verfahren des maschinellen Lernens – erforderlich. In den letzten Jahrzehnten wurden zwar eine Reihe von generellen Datenanalyseverfahren entwickelt, aber es fehlt nach wie vor (insbesondere in Unternehmen) das Verständnis dafür, wie die Analytik auf konkrete Anwendungen der Energiedatenanalyse anzuwenden ist. Das Projekt «SmartLoad» trug dazu bei, diese Lücke zu schliessen und hat un-tersucht, inwiefern verfügbare Daten bei Energieanbietern genutzt werden können, um Haushalte zu erkennen, die a) bereit sind, nachhaltige Stromprodukte zu nutzen und die sich b) für die Investition in Selbstversorgungs- und Speicherlösungen interessieren. Darüber hinaus hat das Projekt untersucht, wie c) Smart-Meter-Daten das Stromverbrauchs-Feedback unterstützen können, um die Energieeffizienz im Privatsektor zu erhöhen. Vor diesem Hintergrund hat die Projektgruppe detaillierte Daten von insgesamt 1’373 privaten Haushalten erhoben, mit diesen Daten maschinellen Lernverfahren trainiert und Vorhersagemodelle für das Kaufinteresse für lokalen Ökostrom, die Investition in Photovoltaikanlagen und die Anschaffung von Wärmepumpen entwickelt. Das Modell für den Kauf von Ökostrom wurde in einem Experiment mit 4’712 Privatkunden evaluiert. Die Modelle zur Prädiktion der Investitionsbereitschaft in Photovoltaikanalgen und Wärmepumpen ermöglichten die Entwicklung eines Softwareprototypen, der den Vertrieb der Technologien unterstützt. Die Erkenntnisse des Projekts liefern Energieanbietern wichtige Hinweise, unter anderen für welche Aufgaben des Vertriebs von nachhaltigen Produkten maschinelle Lernverfahren eingesetzt werden können, welche externen Datenquellen die Kaufvorhersagen verbessern, wie geeignete Trainingsdaten für die Modellentwicklung gesammelt werden sollten und wie die entwickelten Vorhersagemodelle in eine Anwendung für den Vertriebsmitarbeiter überführt werden können. KW - Energietechnik ER - TY - JOUR TI - Enhancing energy efficiency in the residential sector with smart meter data analytics AU - Hopf, Konstantin AU - Sodenkamp, Mariya AU - Staake, Thorsten PY - 2020 PB - Otto-Friedrich-Universität CY - Bamberg DO - 10.20378/irb-47018 UR - https://fis.uni-bamberg.de/handle/uniba/47018 LA - eng AB - Tailored energy efficiency campaigns that make use of household-specific information can trigger substantial energy savings in the residential sector. The information required for such campaigns, however, is often missing. We show that utility companies can extract that information from smart meter data using machine learning. We derive 133 features from smart meter and weather data and use the Random Forest classifier that allows us to recognize 19 household classes related to 11 household characteristics (e.g., electric heating, size of dwelling) with an accuracy of up to 95% (69% on average). The results indicate that even datasets with an hourly or daily resolution are sufficient to impute key household characteristics with decent accuracy and that data from different yearly seasons does not considerably influence the classification performance. Furthermore, we demonstrate that a small training data set consisting of only 200 households already reaches a good performance. Our work may serve as benchmark for upcoming, similar research on smart meter data and provide guidance for practitioners for estimating the efforts of implementing such analytics solutions. KW - decision support systems, data analytics, energy efficiency, sustainability, green information systems ER - TY - JOUR TI - Real-time feedback reduces energy consumption among the broader public without financial incentives AU - Tiefenbeck, Verena AU - Wörner, Anselma AU - Schöb, Samuel AU - Fleisch, Elgar AU - Staake, Thorsten PY - 2019 JO - Nature energy VL - 4 IS - 10 SP - 831-832 PB - Nature Publishing Group CY - London SN - 2058-7546 DO - 10.1038/s41560-019-0480-5 UR - https://fis.uni-bamberg.de/handle/uniba/112839 LA - eng ER - TY - CPAPER TI - A Cognitive Computing Solution to Foster Retailing of Renewable Energy Systems AU - Weigert, Andreas AU - Hopf, Konstantin AU - Staake, Thorsten PY - 2019 DO - 10.20378/IRB-47040 UR - https://fis.uni-bamberg.de/handle/uniba/53971 LA - eng AB - Renewable energy systems (RES) in the residential sector, like photovoltaic systems, heat pumps and battery storage, are corner¬stones of a sustainable energy supply. Nevertheless–and despite major fiscal stimuli–private investment in such technologies has not yet reached a satisfactory level, also because sale of such products is time-consuming and requires a high level of expertise from suppliers. In practice, small and medium-sized installation firms are often responsible for addressing customers, advising, designing and implementing the appropriate systems, but they struggle with offering the complex technology and are exposed to fierce competition in their market. In a joint research initiative with a RES supplier and a software development company, we drive the development of information systems that support installation companies in their tasks. To this end, we are using action design to develop a cognitive computing solution based on Machine Learning (ML) to promote the sale of sustainable energy products. Based on 4,909 real customer requests for RES and survey data from 666 homeowners (which we use as ground truth data for ML), a predictive model can reliably identify promising RES installations out of a list of customer requests and thereby supports an important business task. Despite these promising results, we face a number of challenges in developing our cognitive computing solution. To address these challenges, design principles for similar systems are developed, contributing to the current debate on how information systems research can support sustainable development and how artificial intelligence can be used profitably in enterprises. KW - Renewable energy systems, sales support system, cognitive computing, machine learning ER - TY - RPRT TI - Methoden der Energiedatenanalyse : Schlussbericht ; Vorhaben im Rahmen des Eurostars Projekts E! 9859 BENginell "Energy Data Analytics: Increasing Service Quality and Energy Efficiency in the Residential Sector" AU - Hopf, Konstantin AU - Staake, Thorsten PY - 2019 PB - TIB CY - Hannover DO - 10.2314/KXP:1687331642 UR - https://fis.uni-bamberg.de/handle/uniba/47757 LA - deu AB - Die Steigerung der Energieeffizienz im Privatsektor und der zunehmende Wettbewerb im Energievertrieb stellt die deutsche Energiewirtschaft vor grundlegende Herausforderungen. Gleichzeitig bringt jedoch die Digitalisierung im Energiesektor, die insbesondere durch intelligente Stromnetze und die steigende Verfügbarkeit von Daten unterstützt wird, enorme Potentiale, die von Energieversorgern strategisch sinnvoll genutzt werden können. Die Forschung in diesem Verbundvorhaben zielte darauf ab, Verfahren des maschinellen Lernens zu entwickeln, um verfügbare Daten bei EVU (z.B. Energieverbrauchsdaten, Tarifinformationen), sowie frei verfügbare Daten (Geoinformationen, Wetterdaten, usw.) so zu verarbeiten, sodass wirkungsvolle, massenmarkttaugliche Energieeffizienzmaßnahmen und Dienstleistungen realisiert werden können. Hierzu wurden die Daten mit zusätzlichen Informationen aus Kundenumfragen oder früheren Kundenansprachen angereichert. Schlussendlich ermöglichen es die aus den Daten erzielten Erkenntnisse, die Servicequalität im Energievertrieb und die Energieeffizienz bei Endkunden zu steigern. Im Teilprojekt der Otto-Friedrich-Universität Bamberg wurden Verfahren der Energiedatenanalyse entwickelt, die durch die BEN Energy AG (Zürich) in die BENgine-Softwareplattform eingebettet und zu nutzbaren Lösungen für EVU im europäischen Raum weiterentwickelt wurden. Die Lösung ist zum Zeitpunkt des Projektabschlusses bei über 30 EVU in Europa im Einsatz. ER - TY - JOUR TI - Real-time feedback promotes energy conservation in the absence of volunteer selection bias and monetary incentives AU - Tiefenbeck, Verena AU - Wörner, Anselma AU - Schöb, Samuel AU - Fleisch, Elgar AU - Staake, Thorsten PY - 2019 JO - Nature Energy VL - 4 IS - 1 SP - 35-41 PB - Nature Publishing Group CY - London SN - 2058-7546 DO - 10.1038/s41560-018-0282-1 UR - https://fis.uni-bamberg.de/handle/uniba/47285 LA - eng ER - TY - JOUR TI - Who can drive electric? Segmentation of car drivers based on longitudinal GPS travel data AU - Sodenkamp, Mariya AU - Wenig, Jürgen AU - Thiesse, Frédéric AU - Staake, Thorsten PY - 2019 JO - Energy policy : the international journal of the political, economic, planning, environmental and social aspects of energy VL - 130 SP - 111-129 PB - Elsevier Science CY - Amsterdam [u.a.] SN - 0301-4215 DO - 10.1016/j.enpol.2019.03.048 UR - https://fis.uni-bamberg.de/handle/uniba/47284 LA - eng ER - TY - JOUR TI - Battery versus infrastructure: Tradeoffs between battery capacity and charging infrastructure for plug-in hybrid electric vehicles AU - Wenig, Jürgen AU - Sodenkamp, Mariya AU - Staake, Thorsten PY - 2019 JO - Applied Energy VL - 255 IS - 113787 SP - 1-12 PB - Elsevier CY - Amsterdam [u.a.] SN - 0306-2619 DO - 10.1016/j.apenergy.2019.113787 UR - https://fis.uni-bamberg.de/handle/uniba/47283 LA - eng ER - TY - CPAPER TI - Explaining and predicting annual electricity demand of enterprises – a case study from Switzerland AU - Stingl, Carlo AU - Hopf, Konstantin AU - Staake, Thorsten PY - 2018 VL - 1 IS - Suppl. 1, 50 SP - 149-166 PB - Springer International Publishing CY - Cham SN - 2520-8942 DO - 10.1186/s42162-018-0028-0 UR - https://fis.uni-bamberg.de/handle/uniba/44881 LA - eng AB - In an attempt to channel sales activities, companies often focus on ‘high value targets’ that offer attractive prospective returns. In liberalized electricity markets, commercial customers with high electricity demand constitute such high value targets. The problem when acquiring new customers, however, is that the electricity consumption is not known to the sales organization in advance. This hinders the possibility to prioritize sales targets and thus increases the acquisition cost, reduces the competitiveness within the market and ultimately leads to higher cost for electricity customers. In this study, we investigate the annual electricity consumption of enterprises by means of a dataset with 1810 company addresses in a typical town in Switzerland. We use the industry branch of the enterprises together with open big data (geographic information, online-content, social media data and governmental statistical data) to explain and predict the electricity consumption of such. Our linear regression analysis shows that information on the economic branches of the enterprises, basal area of buildings, number of opening hours and social media data can explain up to 19% of variance in electricity consumption. Economic trends (e.g., in labor market and turnover statistics) reflect changes in the electricity consumption in the investigated years 2010–2014 for several economic branches. We show, that the electricity consumption can be predicted better than a random predictor, however with a high uncertainty. Nevertheless, the open data sources can be used to identify a relevant group of companies with high consumption (more than 100,000kWh per year) with good accuracy. KW - Enterprise electricity consumption KW - Open big data KW - Load prediction KW - Machine Learning KW - High consumption customers ER - TY - CPAPER TI - Explaining and predicting annual electricity demand of enterprises : a case study from Switzerland AU - Stingl, Carlo AU - Hopf, Konstantin AU - Staake, Thorsten PY - 2018 SP - 149-166 PB - opus CY - Bamberg DO - 10.20378/irbo-53060 UR - https://fis.uni-bamberg.de/handle/uniba/44573 LA - eng AB - In an attempt to channel sales activities, companies often focus on ‘high value targets’ that offer attractive prospective returns. In liberalized electricity markets, commercial customers with high electricity demand constitute such high value targets. The problem when acquiring new customers, however, is that the electricity consumption is not known to the sales organization in advance. This hinders the possibility to prioritize sales targets and thus increases the acquisition cost, reduces the competitiveness within the market and ultimately leads to higher cost for electricity customers. In this study, we investigate the annual electricity consumption of enterprises by means of a dataset with 1810 company addresses in a typical town in Switzerland. We use the industry branch of the enterprises together with open big data (geographic information, online-content, social media data and governmental statistical data) to explain and predict the electricity consumption of such. Our linear regression analysis shows that information on the economic branches of the enterprises, basal area of buildings, number of opening hours and social media data can explain up to 19% of variance in electricity consumption. Economic trends (e.g., in labor market and turnover statistics) reflect changes in the electricity consumption in the investigated years 2010–2014 for several economic branches. We show, that the electricity consumption can be predicted better than a random predictor, however with a high uncertainty. Nevertheless, the open data sources can be used to identify a relevant group of companies with high consumption (more than 100,000kWh per year) with good accuracy. KW - Enterprise electricity consumption KW - Open big data KW - Load prediction KW - Machine Learning KW - High consumption customers ER - TY - JOUR TI - Overcoming Salience Bias: How Real-Time Feedback Fosters Resource Conservation AU - Tiefenbeck, Verena AU - Goette, Lorenz AU - Degen, Kathrin AU - Tasic, Vojkan AU - Fleisch, Elgar AU - Lalive, Rafael AU - Staake, Thorsten PY - 2018 JO - Management Science VL - 64 IS - 3 SP - 1458-1476 PB - INFORMS CY - Hanover, Md. SN - 1526-5501 DO - 10.1287/mnsc.2016.2646 UR - https://fis.uni-bamberg.de/handle/uniba/44421 LA - eng AB - Inattention and imperfect information bias behavior toward the salient and immediately visible. This distortion creates costs for individuals, the organizations in which they work, and society at large. We show that an effective way to overcome this bias is by making the implications of one’s behavior salient in real time, while individuals can directly adapt. In a large-scale field experiment, we gave participants real-time feedback on the resource consumption of a daily, energy-intensive activity (showering). We find that real-time feedback reduced resource consumption for the target behavior by 22%. At the household level, this led to much larger conservation gains in absolute terms than conventional policy interventions that provide aggregate feedback on resource use. High baseline users displayed a larger conservation effect, in line with the notion that real-time feedback helps eliminate “slack” in resource use. The approach is cost effective, is technically applicable to the vast majority of households, and generated savings of 1.2 kWh per day and household, which exceeds the average energy use for lighting. The intervention also shows how digitalization in our everyday lives makes information available that can help individuals overcome salience bias and act more in line with their preferences. KW - salience of information, digitalization, real-time feedback, green information systems, decision making, energy conservation, water conservation, environmental behavior, randomized controlled trials ER - TY - JOUR TI - NIWM: non-intrusive water monitoring to uncover heat energy use in households AU - Schöb, Samuel AU - Günther, Sebastian AU - Regensburger, Karl AU - Staake, Thorsten PY - 2018 JO - Computer Science - Research and Development VL - 33 IS - 1-2 SP - 127-133 PB - Springer CY - Berlin ; Heidelberg SN - 1865-2042 DO - 10.1007/s00450-017-0353-8 UR - https://fis.uni-bamberg.de/handle/uniba/44381 LA - eng ER - TY - CPAPER TI - The Ambiguous Boundary Between Professional and Private Use of Information Systems AU - Kupfer, Anna AU - Tiefenbeck, Verena AU - Staake, Thorsten PY - 2018 T2 - ECIS 2018 : Research Papers SP - 1-19 PB - AIS Electronic Library (AISeL) UR - https://fis.uni-bamberg.de/handle/uniba/44380 LA - eng ER - TY - JOUR TI - Economic assessment of photovoltaic-battery systems based household load profiles AU - Schopfer, Sandro AU - Tiefenbeck, Verena AU - Staake, Thorsten PY - 2018 JO - Applied Energy VL - 223 SP - 229-248 PB - Elsevier Science CY - Amsterdam [u.a.] SN - 0306-2619 DO - 10.1016/j.apenergy.2018.03.185 UR - https://fis.uni-bamberg.de/handle/uniba/44370 LA - eng AB - Technical advances and decreasing costs of photovoltaic (PV) and battery (B) systems are key drivers for the consumer-prosumer transition in many countries. However, the installation of a photovoltaic-battery (PVB) system is not equally profitable for all consumers. This study systematically assesses how heterogeneity in real-world electricity load profiles affects the optimal system configuration and profitability of PVB systems. To that end, we develop a techno-economic simulation model that optimizes the PVB configuration for given electricity load profiles. The analysis uses real-world energy consumption data from 4190 households and is conducted for current electricity rates and weather conditions in Zurich, Switzerland. To account for future price reductions of PV and PVB systems, we conduct a sensitivity analysis that assesses how different cost scenarios influence optimal system configuration and profitability. Finally, we develop and validate a machine learning algorithm that can predict system profitability based only on a limited set of features and on shorter measurement timeframes of smart-meter data. We find that under the current cost scenario (PV: 2000 €/kWp, B: 1000 €/kWh) and without subsidies, about 40% of the analyzed households reach a positive net present value (NPV) for a PV-system, but only for 0.1% of households is the integration of a battery profitable. Under the most optimistic cost scenario for both technologies (PV: 1000 €/kWp, B: 250 €/kWh), 99.9% of the households benefit from the integration of battery storage into their optimal system configuration, with a mean installed PV power of 4.4 kWp and a mean battery size of 9.6 kWh. In all cost scenarios, system profitability varies considerably between households, even for households with comparable total annual demand, primarily due to the heterogeneity in the load profiles. Thus, being able to identify households for whom the installation is profitable is important. The proposed machine learning algorithm predicts optimal configuration, profitability, self-sufficiency, and self-sufficiency ratios with good accuracy, even when only relatively short timeframes of smart-meter data are available. The results of this study are relevant for households making individual investment decisions as well as for utility companies to more effectively identify and approach relevant customers for the installation of PVB systems. Furthermore, the findings enable policymakers to determine the critical levers for increasing private investments into PVB systems in their region and to predict how future developments like component costs will affect the future diffusion of these systems. KW - Solar energy KW - Storage KW - Smart-meter data KW - Techno-economic simulation KW - Load profile KW - Machine learning ER - TY - JOUR TI - Enhancing energy efficiency in the residential sector with smart meter data analytics AU - Hopf, Konstantin AU - Sodenkamp, Mariya AU - Staake, Thorsten PY - 2018 JO - Electronic Markets VL - 28 IS - 4 SP - 453-473 PB - Springer CY - Berlin ; Heidelberg SN - 1019-6781 DO - 10.1007/s12525-018-0290-9 UR - https://fis.uni-bamberg.de/handle/uniba/43927 LA - eng AB - Tailored energy efficiency campaigns that make use of household-specific information can trigger substantial energy savings in the residential sector. The information required for such campaigns, however, is often missing. We show that utility companies can extract that information from smart meter data using machine learning. We derive 133 features from smart meter and weather data and use the Random Forest classifier that allows us to recognize 19 household classes related to 11 household characteristics (e.g., electric heating, size of dwelling) with an accuracy of up to 95% (69% on average). The results indicate that even datasets with an hourly or daily resolution are sufficient to impute key household characteristics with decent accuracy and that data from different yearly seasons does not considerably influence the classification performance. Furthermore, we demonstrate that a small training data set consisting of only 200 households already reaches a good performance. Our work may serve as benchmark for upcoming, similar research on smart meter data and provide guidance for practitioners for estimating the efforts of implementing such analytics solutions. KW - decision support systems, data analytics, energy efficiency, sustainability, green information systems ER - TY - CPAPER TI - Evaluation of Four Possible Load Shifting Strategies for Electric Vehicles Utilizing Autoregressive Moving Average Methods for Electricity Price Forecasting AU - Wenig, Jürgen AU - Staake, Thorsten PY - 2018 SP - 123-126 PB - opus CY - Bamberg DO - 10.20378/irbo-51780 UR - https://fis.uni-bamberg.de/handle/uniba/43658 LA - eng AB - - KW - Load Shifting Strategies ER - TY - CPAPER TI - Predictive Customer Data Analytics : The Value of Public Statistical Data and the Geographic Model Transferability AU - Hopf, Konstantin AU - Riechel, Sascha Jonas AU - Sodenkamp, Mariya AU - Staake, Thorsten PY - 2018 PB - opus CY - Bamberg DO - 10.20378/irbo-50522 UR - https://fis.uni-bamberg.de/handle/uniba/42808 LA - eng AB - Companies pay high prices for detailed customer information (e.g., income, household type) for gaining insights and conducting targeted marketing campaigns. We argue that companies can utilize predictive analytics artifacts to derive such information from existing customer data in combination with freely available data sources, such as open government data. In this study, we use a machine learning artifact for a specific yet highly relevant case from the utility industry, trained on data of 7,504 energy customers and investigate two important aspects for predictive business analytics: First, we identified the sparsely available open government statistics and found that even that limited amount of open data can increase our artifact’s performance. Second, we applied the predictive models, trained with a regional customer dataset, on households in other geographic regions with acceptable performance loss. The results support the development of systems aiding managerial decision-making, predictive marketing and showcase the value of open data. KW - Predictive Analytics KW - Data Integration KW - Supervised Machine Learning KW - Open Government Data KW - Public Sector Information ER - TY - CPAPER TI - A Decision Support System for Photovoltaic Potential Estimation AU - Hopf, Konstantin AU - Kormann, Michael AU - Sodenkamp, Mariya AU - Staake, Thorsten PY - 2018 PB - opus CY - Bamberg DO - 10.20378/irbo-50523 UR - https://fis.uni-bamberg.de/handle/uniba/42791 LA - eng AB - With knowledge on the photovoltaic potential of individual residential buildings, solar companies, energy service providers and electric utilities can identify suitable customers for new PV installations and directly address them in renewable energy rollout and maintenance campaigns. However, many currently used solutions for the simulation of energy generation require detailed information about houses (roof tilt, shading, etc.) that is usually not available at scale. On the other hand, the methodologies enabling extraction of such details require costly remote-sensing data from three-dimensional (3D) laser scanners or aerial images. To bridge this gap, we present a decision support system (DSS) that estimates the potential amount of electric energy that could be generated at a given location if a photovoltaic system would be installed. The DSS automatically generates insights about photovoltaic yields of individual roofs by analyzing freely available data sources, including the crowdsourced volunteered geospatial information systems OpenStreetMap and climate databases. The resulting estimates pose a valuable foundation for selecting the most prospective households (e.g., for personal visit and screening by an expert) and targeted solar panel kit offerings, ultimately leading to significant reduction of manual human efforts, and to cost-effective personalized renewables adoption. KW - Crowdsourced Data KW - Solar Potential KW - Volunteered Geographic Information KW - Renewable Energy KW - Photovoltaic ER - TY - CPAPER TI - Predictive Customer Data Analytics : The Value of Public Statistical Data and the Geographic Model Transferability AU - Hopf, Konstantin AU - Riechel, Sascha Jonas AU - Sodenkamp, Mariya AU - Staake, Thorsten PY - 2017 T2 - ICIS 2017 Proceedings SP - 1-20 PB - AIS Electronic Library UR - https://fis.uni-bamberg.de/handle/uniba/98512 LA - eng AB - Companies pay high prices for detailed customer information (e.g., income, household type) for gaining insights and conducting targeted marketing campaigns. We argue that companies can utilize predictive analytics artifacts to derive such information from existing customer data in combination with freely available data sources, such as open government data. In this study, we use a machine learning artifact for a specific yet highly relevant case from the utility industry, trained on data of 7,504 energy customers and investigate two important aspects for predictive business analytics: First, we identified the sparsely available open government statistics and found that even that limited amount of open data can increase our artifact’s performance. Second, we applied the predictive models, trained with a regional customer dataset, on households in other geographic regions with acceptable performance loss. The results support the development of systems aiding managerial decision-making, predictive marketing and showcase the value of open data. KW - Predictive Analytics KW - Data Integration KW - Supervised Machine Learning KW - Open Government Data KW - Public Sector Information ER - TY - CPAPER TI - Providing primary frequency control with residential scale photovoltaic-battery systems : A techno-economic simulation study of a virtual power plant AU - Schopfer, Sandro AU - Tiefenbeck, Verena AU - Fleisch, Elgar AU - Staake, Thorsten PY - 2017 VL - 32 IS - 1-2 SP - 105-115 PB - Springer CY - Berlin ; Heidelberg SN - 1865-2042 DO - 10.1007/s00450-016-0318-3 UR - https://fis.uni-bamberg.de/handle/uniba/44427 LA - eng ER - TY - CPAPER TI - Real-world impact of Information Systems: The effect of seemingly small design choices AU - Ableitner, Liliane AU - Tiefenbeck, Verena AU - Hosseini, Sabiölla AU - Schöb, Samuel AU - Fridgen, Gilbert AU - Staake, Thorsten PY - 2017 T2 - Proceedings of the Workshop on Information Technologies and Systems (WITS), Seoul, South Korea SP - 387-402 UR - https://fis.uni-bamberg.de/handle/uniba/44386 LA - eng ER - TY - CPAPER TI - A Decision Support System for Photovoltaic Potential Estimation AU - Hopf, Konstantin AU - Kormann, Michael AU - Sodenkamp, Mariya AU - Staake, Thorsten PY - 2017 T2 - IML '17: Proceedings of the 1st International Conference on Internet of Things and Machine Learning IS - Article No.: 3 SP - 1-10 PB - ACM Digital Library CY - New York SN - 978-1-4503-5243-7 DO - 10.1145/3109761.3109764 UR - https://fis.uni-bamberg.de/handle/uniba/43113 LA - eng AB - With knowledge on the photovoltaic potential of individual residential buildings, solar companies, energy service providers and electric utilities can identify suitable customers for new PV installations and directly address them in renewable energy rollout and maintenance campaigns. However, many currently used solutions for the simulation of energy generation require detailed information about houses (roof tilt, shading, etc.) that is usually not available at scale. On the other hand, the methodologies enabling extraction of such details require costly remote-sensing data from three-dimensional (3D) laser scanners or aerial images. To bridge this gap, we present a decision support system (DSS) that estimates the potential amount of electric energy that could be generated at a given location if a photovoltaic system would be installed. The DSS automatically generates insights about photovoltaic yields of individual roofs by analyzing freely available data sources, including the crowdsourced volunteered geospatial information systems OpenStreetMap and climate databases. The resulting estimates pose a valuable foundation for selecting the most prospective households (e.g., for personal visit and screening by an expert) and targeted solar panel kit offerings, ultimately leading to significant reduction of manual human efforts, and to cost-effective personalized renewables adoption. KW - Crowdsourced Data KW - Solar Potential KW - Volunteered Geographic Information KW - Renewable Energy KW - Photovoltaic ER - TY - CPAPER TI - Smart Meter Data Analytics for Enhanced Energy Efficiency in the Residential Sector AU - Sodenkamp, Mariya AU - Kozlovskiy, Ilya AU - Hopf, Konstantin AU - Staake, Thorsten PY - 2017 T2 - Proceedings der 13. Internationalen Tagung Wirtschaftsinformatik (WI 2017) SP - 1235-1249 PB - AIS Electronic Library (AISeL) UR - https://fis.uni-bamberg.de/handle/uniba/41817 LA - eng AB - Achievement of the ambitious environmental sustainability targets requires improvement of energy efficiency practices in private households. We demonstrate how utility companies, having access to smart electricity meter data, can automatically extract household characteristics related to energy efficiency and adoption of renewable energy technologies (e.g., water/space heating type, age of house, number and age of electric appliances, interest in installation of photovoltaic systems etc.) by using supervised-machine-learningbased green IT artifacts. The gained information enables design of customtailored interventions (such as promotion of personalized energy audits, ecologic services and products, or load shifting mechanisms) that trigger residents’ behavioral change toward environmental sustainability as well as improvement of utilities’ key performance indicators. Moreover, realizing privacy preservation concerns, we investigate the influence of smart meter data granularity and the amount of survey responses required for the artifact development on the household classification quality. KW - Green information systems (IS) KW - Smart meters KW - Data analytics KW - Energy efficiency KW - Sustainability ER - TY - JOUR TI - Supervised classification with interdependent variables to support targeted energy efficiency measures in the residential sector AU - Sodenkamp, Mariya AU - Kozlovskiy, Ilya AU - Staake, Thorsten PY - 2016 JO - Decision Analytics VL - 3 IS - 1 PB - Springer Open CY - Berlin ; Heidelberg [u.a.] SN - 2193-8636 DO - 10.1186/s40165-015-0018-2 UR - https://fis.uni-bamberg.de/handle/uniba/55807 LA - eng AB - This paper presents a supervised classification model, where the indicators of correlation between dependent and independent variables within each class are utilized for a transformation of the large-scale input data to a lower dimension without loss of recognition relevant information. In the case study, we use the consumption data recorded by smart electricity meters of 4200 Irish dwellings along with half-hourly outdoor temperature to derive 12 household properties (such as type of heating, floor area, age of house, number of inhabitants, etc.). Survey data containing characteristics of 3500 households enables algorithm training. The results show that the presented model outperforms ordinary classifiers with regard to the accuracy and temporal characteristics. The model allows incorporating any kind of data affecting energy consumption time series, or in a more general case, the data affecting class-dependent variable, while minimizing the risk of the curse of dimensionality. The gained information on household characteristics renders targeted energy-efficiency measures of utility companies and public bodies possible. KW - Household Characteristics KW - Interdependent Variables KW - Multivariate Analysis KW - Energy Consumption KW - Pattern Recognition ER - TY - CPAPER TI - Resource Conservation with Green IS : A Field Experiment on Pecuniary and Non-pecuniary Strategies AU - Ableitner, Liliane AU - Kupfer, Anna AU - Tiefenbeck, Verena AU - Schöb, Samuel AU - Staake, Thorsten PY - 2016 T2 - Proceedings of the SIG Green Pre-ICIS Workshop PB - AIS eLibrary UR - https://fis.uni-bamberg.de/handle/uniba/44385 LA - eng ER - TY - CHAP TI - Einleitung AU - Fischbach, Kai AU - Overhage, Sven AU - Staake, Thorsten AU - Weitzel, Tim PY - 2016 T2 - Geschäftsprozessorientierte Systementwicklung von der Unternehmensarchitektur zum IT-System ; [Sammlung wissenschaftlicher Beiträge zu Ehren von Herrn Prof. Dr. Elmar J. Sinz] SP - 1-7 PB - Springer Vieweg CY - Wiesbaden SN - 978-3-658-14825-6 DO - 10.1007/978-3-658-14826-3 UR - https://fis.uni-bamberg.de/handle/uniba/41736 LA - deu ER - TY - BOOK TI - Geschäftsprozessorientierte Systementwicklung : von der Unternehmensarchitektur zum IT-System ; [Sammlung wissenschaftlicher Beiträge zu Ehren von Herrn Prof. Dr. Elmar J. Sinz] AU - Bach, Alexander AU - Bader, Florian AU - Becker, Jörg AU - Benker, Thomas AU - Bork, Dominik AU - Clever, Nico AU - Duske, Armin AU - Esswein, Werner AU - Ferstl, Otto K. AU - Fischbach, Kai AU - Fischer, Gerlinde AU - Frank, Ulrich AU - Friedrich, Thomas AU - Härer, Felix AU - Hartmann, Beate AU - Herz, Richard Alan AU - Jacob, Michael AU - Jürck, Carsten AU - Karagiannis, Dimitris AU - Kiehl, Tobias AU - Knobloch, Bernd AU - Malischewski, Carsten AU - Overhage, Sven AU - Popp, Karl Michael AU - Riehle, Dennis M. AU - Robel, Martin AU - Schlauderer, Sebastian AU - Staake, Thorsten AU - Steffan, Andreas AU - Strahringer, Susanne AU - Teusch, Andree AU - Weitzel, Tim AU - Wismer, Simone AU - Wolf, Matthias AU - Xiang, Li ED - Benker, Thomas ED - Jürck, Carsten ED - Wolf, Matthias PY - 2016 PB - Springer Vieweg CY - Wiesbaden ET - 1 SN - 978-3-658-14825-6 DO - 10.1007/978-3-658-14826-3 UR - https://fis.uni-bamberg.de/handle/uniba/41628 LA - deu ER - TY - CPAPER TI - Long-lasting effects or short-term spark? : On the persistence of behaviour change induced by real-time feedback on resource consumption AU - Tiefenbeck, Verena AU - Tasic, Vojkan AU - Schöb, Samuel AU - Staake, Thorsten PY - 2016 T2 - ECIS 2016 : Research Papers SP - 1-17 PB - AIS Electronic Library (AISeL) T3 - Research in Progress Paper UR - https://fis.uni-bamberg.de/handle/uniba/41507 LA - eng ER - TY - CPAPER TI - Incentives to go green: An empirical investigation of monetary and symbolic rewards to motivate energy savings AU - Lossin, Felix AU - Kozlovskiy, Ilya AU - Sodenkamp, Mariya AU - Staake, Thorsten PY - 2016 T2 - ECIS 2016 : Research Papers SP - 1-16 PB - AIS Electronic Library (AISeL) T3 - Research Papers UR - https://fis.uni-bamberg.de/handle/uniba/41402 LA - eng ER - TY - JOUR TI - Smart-Meter-Datenanalyse für massenmarkttaugliche Energiedienstleistungen AU - Sodenkamp, Mariya AU - Staake, Thorsten PY - 2016 JO - asut-Bulletin, Organ der asut (Schweizerischer Verband der Telekommunikation) IS - 3 SP - 32-33 CY - Bern UR - https://fis.uni-bamberg.de/handle/uniba/41010 LA - deu AB - Intelligente Stromzähler ermöglichen die Erfassung von Lastprofilen einzelner Haushalte. Mit dem Einsatz von Analyse-Verfahren aus dem Bereich des maschinellen Lernens können Energieversorger aus Smart-Meter-Daten detaillierte Kundeninformationen (z.B. Heizungstyp oder Anzahl der Kinder) automatisch ableiten, die als Grundlage für eine personalisierte Energieberatungsleistung und zur Optimierung der Vertriebsaktivitäten dienen. ER - TY - JOUR TI - Conseil en énergie assisté par ordinateur - Conjonction du smart metering et du machine learning AU - Vogel, Benedikt PY - 2016 JO - Bulletin : Fachzeitschrift und Verbandsinformationen von Electrosuisse und VSE IS - 107 (2016), 9 SP - 48-52 PB - Electrosuisse CY - Fehraltorf ; Zürich SN - 1660-6728 UR - https://fis.uni-bamberg.de/handle/uniba/40963 LA - fra AB - Die Erfahrung hat gezeigt, dass Personen, die eine Energieberatung in Anspruch nehmen, ihren Energieverbrauch und damit die entsprechenden Kosten häufig erheblich reduzieren können. Aber wie können Energieberater Haushalte ausfindig machen, deren Energieverbrauch unnötig hoch ist? Die Forscher der ETH Zürich und der Universität Bamberg (Bayern) wenden einen Algorithmus an, der die Daten intelligenter Stromzähler auswertet. Mithilfe des durch maschinelles Lernen trainierten und getesteten Algorithmus können seitdem mit einer gewissen Zuverlässigkeit 22 Merkmale aus den Lastprofilen der mit intelligenten Stromzählern ausgestatteten Haushalte abgeleitet werden. In den meisten Fällen ist eine weitere Verbesserung der Zuverlässigkeit möglich, wenn der Algorithmus zusätzlich über meteorologische und geografische Daten verfügt. Diese Methode ermöglicht es, die richtigen Personen mit den für sie relevanten Energiespartipps zu versorgen, und zwar ohne kostspielige Umfragen zur Bestimmung der Merkmale und der Ausstattung der Haushalte. ER - TY - CPAPER TI - Energy Informatics for Environmental, Economic and Societal Sustainability: A Case of the Large-Scale Detection of Households with Old Heating Systems AU - Kozlovskiy, Ilya AU - Sodenkamp, Mariya AU - Hopf, Konstantin AU - Staake, Thorsten PY - 2016 T2 - ECIS 2016 : Research Papers SP - 1-16 PB - AIS Electronic Library (AISeL) T3 - Research Papers UR - https://fis.uni-bamberg.de/handle/uniba/40958 LA - eng ER - TY - JOUR TI - IT-unterstützte Energieberatung AU - Vogel, Benedikt PY - 2016 JO - Haus-Tech : Magazin für Bauherren, Planer und Installateure ; Magazin für Energie und Wohnkomfort VL - 29 IS - 9 SP - 56-59 PB - AZ-Fachverl. CY - Aarau SN - 1015-9894 UR - https://fis.uni-bamberg.de/handle/uniba/40962 LA - deu AB - Wer eine Energieberatung in Anspruch nimmt, kann seinen Energieverbrauch und die damit verbundenen Energiekosten erfahrungsgemäss oft erheblich senken. Wie aber gelingt es Energieberatern, Haushalte mit unnötig hohem Energieverbrauch ausfindig zu machen? Forscher der ETH Zürich und der Universität Bamberg (Bayern) ermöglichen das mit einem Algorithmus, der Stromzähler-Daten auswertet. Die Methode macht es möglich, die richtigen Personen mit den relevanten Energiespartipps zu versorgen. ER - TY - RPRT TI - Smart-Meter-Datenanalyse für automatisierte Energieberatungen ("Smart Grid Data Analytics") - Schlussbericht AU - Sodenkamp, Mariya AU - Hopf, Konstantin AU - Kozlovskiy, Ilya AU - Staake, Thorsten PY - 2016 PB - opus CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/40961 LA - deu AB - Kommunikationsfähige Stromzähler ermöglichen die Erfassung individueller Lastprofile mit hoher zeitlicher Auflösung (typischerweise in 15-Minuten-Intervallen). Projektgegenstand ist die Weiterentwicklung von Methoden des maschinellen Lernens, um aus Lastprofilen und zusätzlichen verbrauchs-relevanten Informationen (Wetter, soziodemographische Daten, Adressinformationen, usw.) automatisiert Merkmale von Haushalten abzuleiten, welche für eine individuelle und spezifische Energieberatung von Nutzen sind. Mit den im Rahmen des Projektes entwickelten Smart-Meter-Klassifikations-Verfahren konnten 38 Eigenschaften privater Haushalte mit zum Teil hoher Sicherheit (über 70%) aus Lastprofilen und zusätzlichen frei verfügbaren Daten unter Einhaltung von Datenschutzbestimmungen vorhergesagt werden. Neben Umständen der Lebenssituation (z.B. Familien, Rentner, Kinder, sozialer Status) lassen sich auch Energieeffizienz-Charakteristika (z.B. Heizungstyp, Hausalter und -grösse, Geräte im Haushalt) sowie Einstellungen (z.B. gegenüber erneuerbaren Energieträgern, Interesse an Ökostrom oder an Solaranlagen) mit den entwickelten Algorithmen abschätzen. Mit Hilfe der Projektresultate können autorisierte Energiedienstleister wirkungsvolle und skalierbare Effizienzkampagnen realisieren. Zugleich unterstützen die Projektresultate eine faktenbasierte Diskussion über die Vorteile (z.B. Steigerung der Energieeffizienz) und Kosten (z.B. Wirkung auf die Privatsphäre) solcher Verfahren. ER - TY - JOUR TI - Supervised classification with interdependent variables to support targeted energy efficiency measures in the residential sector AU - Sodenkamp, Mariya AU - Kozlovskiy, Ilya AU - Staake, Thorsten PY - 2016 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/40965 LA - eng AB - This paper presents a supervised classification model, where the indicators of correlation between dependent and independent variables within each class are utilized for a transformation of the large-scale input data to a lower dimension without loss of recognition relevant information. In the case study, we use the consumption data recorded by smart electricity meters of 4200 Irish dwellings along with half-hourly outdoor temperature to derive 12 household properties (such as type of heating, floor area, age of house, number of inhabitants, etc.). Survey data containing characteristics of 3500 households enables algorithm training. The results show that the presented model outperforms ordinary classifiers with regard to the accuracy and temporal characteristics. The model allows incorporating any kind of data affecting energy consumption time series, or in a more general case, the data affecting class-dependent variable, while minimizing the risk of the curse of dimensionality. The gained information on household characteristics renders targeted energy-efficiency measures of utility companies and public bodies possible. KW - Household Characteristics KW - Interdependent Variables KW - Multivariate Analysis KW - Energy Consumption KW - Pattern Recognition ER - TY - CPAPER TI - Household classification using annual electricity consumption data AU - Hopf, Konstantin AU - Sodenkamp, Mariya AU - Kozlovskiy, Ilya AU - Staake, Thorsten PY - 2016 PB - opus CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/39979 LA - eng AB - Introduction: The knowledge about household properties (such as number of inhabitants, living area, heating type, etc.) is highly desirable for utility companies to pave the way to targeted energy efficiency programs, products and services. Raising individual household data via surveys or purchasing it is expensive and time consuming, and often only a small fraction of customers participate. Recently, data mining methods have been developed to automatically infer house-hold characteristics from smart meter consumption data. However, the slow smart metering rollout hampers practical implementation of these methods in many countries. In this work, we present a machine learning approach that reveals household properties from conventional annual electricity consumption data currently available at a large scale. KW - Household classification ER - TY - JOUR TI - Feature extraction and filtering for household classification based on smart electricity meter data AU - Hopf, Konstantin AU - Sodenkamp, Mariya AU - Kozlovskiy, Ilya AU - Staake, Thorsten PY - 2016 JO - Computer Science - Research and Development VL - 31 SP - 141–148 PB - Springer CY - Berlin ; Heidelberg, SN - 1865-2042 DO - 10.1007/s00450-014-0294-4 UR - https://fis.uni-bamberg.de/handle/uniba/21134 LA - eng ER - TY - CPAPER TI - Data-based Assessment of Plug-in Electric Vehicle Driving AU - Wenig, Jürgen AU - Sodenkamp, Mariya AU - Staake, Thorsten PY - 2015 T2 - Energy Informatics : 4th D-A-CH Conference, EI 2015, Karlsruhe, Germany, November 12-13, 2015, Proceedings SP - 115-126 PB - Springer International Publishing CY - Cham T3 - Lecture Notes in Computer Science ET - 1 SN - 978-3-319-25875-1 DO - 10.1007/978-3-319-25876-8_10 UR - https://fis.uni-bamberg.de/handle/uniba/40448 LA - eng ER - TY - CPAPER TI - Gaining IS Business Value through Big Data Analytics: A Case Study of the Energy Sector AU - Sodenkamp, Mariya AU - Kozlovskiy, Ilya AU - Staake, Thorsten PY - 2015 T2 - ICIS 2015 Proceedings PB - AIS Electronic Library (AISeL) UR - https://fis.uni-bamberg.de/handle/uniba/40416 LA - eng AB - Following decades of stability and comfortable margins, utility companies today face strong pressure from regulatory bodies and competitors. As a response to the market dynamics, many have initiated a transformation from a “provider” to a service company, yet realize that their customer insights that would be necessary to successfully develop and market new services are sparse. We argue that the required information is contained in consumption data that is available to utility companies. We demonstrate how data analytics and machine learning make sense out of such data and add value to organizations. Using datasets containing annual electricity consumption information of private households, we apply and test in field experiments a Support Vector Machines algorithm that predicts probabilities of individual costumers to sign up on an energy efficiency portal. We show that signup rates can be doubled and argue that classification tools provide customer insights at low cost and at scale. KW - Business value of IS/value of IS KW - Decision Support Systems (DSS) KW - Data analysis KW - Green IT/IS ER - TY - JOUR TI - Assessing distorted trading incentives of balance responsible parties based on the example of the Swiss power system AU - Scherer, Marc AU - Haubensak, Oliver AU - Staake, Thorsten PY - 2015 JO - Energy policy : the international journal of the political, economic, planning, environmental and social aspects of energy VL - 86 SP - 792-801 PB - Elsevier Science CY - Amsterdam [u.a.] SN - 0301-4215 DO - 10.1016/j.enpol.2015.08.025 UR - https://fis.uni-bamberg.de/handle/uniba/40409 LA - eng ER - TY - CPAPER TI - Short-term Spark or Sustained Impact? : Investigating the Long-term Effect of Real-time Feedback AU - Tasic, Vojkan AU - Tiefenbeck, Verena AU - Schöb, Samuel AU - Staake, Thorsten PY - 2015 T2 - ECIS 2015 Proceedings SP - 1-10 PB - AIS Electronic Library (AISeL) T3 - ECIS 2015 Research-in-Progress Papers SN - 978-3-00-050284-2 UR - https://fis.uni-bamberg.de/handle/uniba/39467 LA - eng ER - TY - CHAP TI - Using Supervised Machine Learning to Explore Energy Consumption Data in Private Sector Housing AU - Sodenkamp, Mariya AU - Hopf, Konstantin AU - Staake, Thorsten PY - 2015 T2 - Handbook of Research on Organizational Transformations through Big Data Analytics SP - 320-333 PB - IGI Global CY - Hershey, Pennsylvania (USA) SN - 9781466672727 DO - 10.4018/978-1-4666-7272-7 UR - https://fis.uni-bamberg.de/handle/uniba/21416 LA - eng AB - Smart electricity meters allow capturing consumption load profiles of residential buildings. Besides several other applications, the retrieved data renders it possible to reveal household characteristics including the number of persons per apartment, age of the dwelling, etc., which helps to develop targeted energy conservation services. The goal of this chapter is to develop further related methods of smart meter data analytics that infer such household characteristics using weekly load curves. The contribution of this chapter to the state of the art is threefold. The authors first quadruplicate the number of defined features that describe electricity load curves to preserve relevant structures for classification. Then, they suggest feature filtering techniques to reduce the dimension of the input to a set of a few significant ones. Finally, the authors redefine class labels for some properties. As a result, the classification accuracy is elevated up to 82%, while the runtime complexity is significantly reduced. ER - TY - JOUR TI - DAIAD: Open Water Monitoring AU - Athanasiou, S. AU - Staake, Thorsten AU - Stiefmeier, Thomas AU - Sartorius, C. AU - Tompkins, J. AU - Lytras, E. PY - 2014 JO - Procedia Engineering VL - 89 SP - 1044-1049 PB - Elsevier BV CY - Amsterdam SN - 1877-7058 DO - 10.1016/j.proeng.2014.11.223 UR - https://fis.uni-bamberg.de/handle/uniba/109440 LA - eng AB - DAIAD is an FP7 research project addressing the challenge of improving the management of water resources through real-time knowledge of water consumption in order to improve societal awareness, induce sustainable changes in consumer behavior, and explore new water demand management strategies. In this paper we present the motivation of our work, our vision and objectives, along with an early architectural overview of the planned DAIAD system. KW - Real time water monitoring KW - Big Data KW - Interventions KW - Water Demand Management ER - TY - CPAPER TI - Evaluation of Four Possible Load Shifting Strategies for Electric Vehicles Utilizing Autoregressive Moving Average Methods for Electricity Price Forecasting AU - Wenig, Jürgen AU - Staake, Thorsten PY - 2014 T2 - MMB & DFT 2014 : Proceedings of the International Workshops ; Modeling, Analysis and Management of Social Networks and their Applications (SOCNET 2014) & Demand Modeling and Quantitative Analysis of Future Generation Energy Networks and Energy-Efficient Systems (FGENET 2014) SP - 123-126 PB - University of Bamberg Press CY - Bamberg T3 - Schriften aus der Fakultät Wirtschaftsinformatik und Angewandte Informatik der Otto-Friedrich-Universität Bamberg SN - 978-3-86309-208-5 UR - https://fis.uni-bamberg.de/handle/uniba/6378 LA - eng AB - - KW - Load Shifting Strategies ER - TY - CHAP TI - Preface AU - Fischbach, Kai AU - Krieger, Udo R. AU - Staake, Thorsten PY - 2014 T2 - MMB & DFT 2014 : Proceedings of the International Workshops ; Modeling, Analysis and Management of Social Networks and their Applications (SOCNET 2014) & Demand Modeling and Quantitative Analysis of Future Generation Energy Networks and Energy-Efficient Systems (FGENET 2014) SP - V-VII PB - University of Bamberg Press CY - Bamberg T3 - Schriften aus der Fakultät Wirtschaftsinformatik und Angewandte Informatik der Otto-Friedrich-Universität Bamberg SN - 978-3-86309-208-5 UR - https://fis.uni-bamberg.de/handle/uniba/6349 LA - eng ER - TY - CPAPER TI - MMB & DFT 2014 : Proceedings of the International Workshops ; Modeling, Analysis and Management of Social Networks and their Applications (SOCNET 2014) & Demand Modeling and Quantitative Analysis of Future Generation Energy Networks and Energy-Efficient Systems (FGENET 2014) AU - Avrachenkov, Konstantin AU - Bazan, Peter AU - Bisconti, Cristian AU - Brandes, Ulrik AU - Colle, Didier AU - Corallo, Angelo AU - De Turck, Koen AU - Demeester, Piet AU - Duboz, Raphael AU - Eger, Kolja AU - Feuchtinger, Ullrich AU - Fiems, Dieter AU - Fortunato, Laura AU - Frank, Reinhard AU - Gentile, Antonio A. AU - German, Reinhard AU - Gloor, Peter A. AU - Grahl, Jörn AU - Haverkort, Boudewijn R. AU - Heimgärtner, Florian AU - Herrmann, Sebastian AU - Hevenstone, Debra AU - Höfling, Michael AU - Lambert, Sofie AU - Lannoo, Bart AU - Litfinski, Benjamin AU - Martin, Alexander AU - Menth, Michael AU - Nasim, Mehwish AU - Pickavet, Mario AU - Postema, Björn AU - Prabhu, Balakrishna J. AU - Pruckner, Marco AU - Riedl, Johannes AU - Rothlauf, Franz AU - Schoch, David AU - Staake, Thorsten AU - Takeda, Hideaki AU - Thurner, Christoph AU - Timilsina, Mohan AU - Van Heddeghem, Ward AU - Vereecken, Willem AU - Wenig, Jürgen AU - Zweig, Katharina A. ED - Fischbach, Kai ED - Großmann, Marcel ED - Krieger, Udo R. ED - Staake, Thorsten PY - 2014 PB - University of Bamberg Press CY - Bamberg T3 - Schriften aus der Fakultät Wirtschaftsinformatik und Angewandte Informatik der Otto-Friedrich-Universität Bamberg SN - 978-3-86309-208-5 DO - 10.20378/irb-2869 UR - https://fis.uni-bamberg.de/handle/uniba/2869 LA - eng AB - At present, a comprehensive set of measurement, modeling, analysis, simulation, and performance evaluation techniques are employed to investigate complex networks. A direct transfer of the developed engineering methodologies to related analysis and design tasks in next-generation energy networks, energy-efficient systems and social networks is enabled by a common mathematical foundation. The International Workshop on "Demand Modeling and Quantitative Analysis of Future Generation Energy Networks and Energy-Efficient Systems" (FGENET 2014) and the International Workshop on "Modeling, Analysis and Management of Social Networks and their Applications" (SOCNET 2014) were held on March 19, 2014, at University of Bamberg in Germany as satellite symposia of the 17th International GI/ITG Conference on "Measurement, Modelling and Evaluation of Computing Systems" and "Dependability and Fault-Tolerance" (MMB & DFT 2014). They dealt with current research issues in next-generation energy networks, smart grid communication architectures, energy-efficient systems, social networks and social media. The Proceedings of MMB & DFT 2014 International Workshops summarizes the contributions of 3 invited talks and 13 reviewed papers and intends to stimulate the readers’ future research in these vital areas of modern information societies. KW - Future Generation Energy Networks KW - Energy-Efficient Systems KW - Social Networks KW - Demand Modeling KW - Quantitative Analysis ER - TY - JOUR TI - For better or for worse? Empirical evidence of moral licensing in a behavioral energy conservation campaign AU - Tiefenbeck, Verena AU - Staake, Thorsten AU - Roth, Kurt AU - Sachs, Olga PY - 2013 JO - Energy policy VL - 57 SP - 160-171 PB - Elsevier CY - Oxford SN - 0301-4215 DO - 10.1016/j.enpol.2013.01.021 UR - https://fis.uni-bamberg.de/handle/uniba/53873 LA - eng AB - Isolated environmental campaigns focusing on defined target behaviors are rolled out to millions of households every year. Yet it is still unclear whether these programs trigger cross-domain adoption of additional environment-friendly behaviors (positive spillover) or reduced engagement elsewhere. A thorough evaluation of the real net performance of these programs is lacking. This paper investigates whether positive or perverse side effects dominate by exemplifying the impact of a water conservation campaign on electricity consumption. The study draws on daily water (10,780 data points) and weekly electricity (1386 data points) consumption data of 154 apartments in a controlled field experiment at a multifamily residence. The results show that residents who received weekly feedback on their water consumption lowered their water use (6.0% on average), but at the same time increased their electricity consumption by 5.6% compared with control subjects. Income effects can be excluded. While follow-up research is needed on the precise mechanism of the psychological process at work, the findings are consistent with the concept of moral licensing, which can more than offset the benefits of focused energy efficiency campaigns, at least in the short-term. We advocate the adoption of a more comprehensive view in environmental program design/evaluation in order to quantify and mitigate these unintended effe KW - energy ER - TY - CPAPER TI - Mechatronics to drive environmental sustainability : measuring, visualizing and transforming consumer patterns on a large scale AU - Tiefenbeck, Verena AU - Tasic, Vojkan AU - Staake, Thorsten AU - Schöb, Samuel PY - 2013 T2 - Energieinformatik 2013 : Tagungsband SP - 24-29 PB - OCG CY - Wien SN - 978-3-85403-298-4 UR - https://fis.uni-bamberg.de/handle/uniba/3189 LA - eng ER - TY - CPAPER TI - Occupancy Detection from Electricity Consumption Data AU - Kleiminger, Wilhelm AU - Beckel, Christian AU - Staake, Thorsten AU - Santini, Silvia PY - 2013 T2 - BuildSys'13: Proceedings of the 5th ACM Workshop on Embedded Systems For Energy-Efficient Buildings SP - 1-8 PB - ACM CY - New York, NY, USA SN - 978-1-4503-2431-1 DO - 10.1145/2528282.2528295 UR - https://fis.uni-bamberg.de/handle/uniba/3176 LA - eng AB - Detecting when a household is occupied by its residents is fundamental to enable a number of home automation applications. Current systems for occupancy detection usually require the installation of dedicated sensors, like passive infrared sensors, magnetic reed switches, or cameras. In this paper, we investigate the suitability of digital electricity meters -- which are already available in millions of households worldwide -- to be used as occupancy sensors. To this end, we have collected fine-grained electricity consumption data along with ground-truth occupancy information for 5 households during a period of about 8 months. Our results show that using common classification methods it is possible to achieve occupancy detection accuracies of more than 80%. ER - TY - JOUR TI - Motivating Energy-Efficient Behavior with Green IS: An Investigation of Goal Setting and the Role of Defaults AU - Loock, Claire-Michelle AU - Staake, Thorsten AU - Thiesse, Frédéric PY - 2013 JO - MIS Quarterly VL - 37 IS - 4 SP - 1313-1332 CY - Minneapolis, Minn. SN - 0276-7783 UR - https://fis.uni-bamberg.de/handle/uniba/2964 LA - eng ER - TY - RPRT TI - Steigerung der Energieeffizienz durch Verbrauchsfeedback bei der Warmwassernutzung : Abschlussbericht der ewz-Amphiro-Studie ; 27.November 2013 AU - Tiefenbeck, Verena AU - Tasic, Vojkan AU - Schöb, Samuel AU - Degen, Kathrin AU - Goette, Lorenz AU - Fleisch, Elgar AU - Staake, Thorsten PY - 2013 CY - Zürich UR - https://fis.uni-bamberg.de/handle/uniba/2720 LA - deu ER - TY - CPAPER TI - The influence of reference frame and population density on the effectiveness of social normative feedback on electricity consumption AU - Loock, Claire-Michelle AU - Landwehr, Jan AU - Staake, Thorsten AU - Fleisch, Elgar AU - Pentland, Alexander PY - 2012 T2 - Proceedings of the 33rd International Conference on Information Systems (ICIS) PB - AIS Electronic Library (AISeL) UR - https://fis.uni-bamberg.de/handle/uniba/3209 LA - eng AB - The strong effects of descriptive normative feedback (“how you compare to others”) on an individual’s electricity consumption have been documented in the IS literature. Here, we extend prior research on reference group effects (“whom to compare with”) by defining the relevance of the reference group in terms of similarity in contextual factors as opposed to personal characteristics. Specifically, we manipulate the spatial proximity of reference groups and test whether population density moderates the effects of feedback. In a field study with 560 energy customers, we find that reference groups that are close in terms of geographical proximity are more effective than more distant groups. However, population density does not moderate this effect. Designer of green information systems should therefore use reference groups that are close to the energy consumer with regard to geographical proximity, but they do not need to tailor the intervention to the energy consumer’s location. KW - Green IT / IS KW - social norms KW - feedback KW - field experiment KW - design science ER - TY - CPAPER TI - Providing eco-driving feedback to corporate car drivers : what impact does a smartphone application have on their fuel efficiency. AU - Tulusan, Johannes AU - Staake, Thorsten AU - Fleisch, Elgar PY - 2012 T2 - UbiComp '12: Proceedings of the 2012 ACM Conference on Ubiquitous Computing SP - 212-215 PB - ACM CY - New York, NY, USA SN - 978-1-4503-1224-0 DO - 10.1145/2370216.2370250 UR - https://fis.uni-bamberg.de/handle/uniba/3197 LA - eng AB - The personal transport sector constitutes an important target of energy conservation and emission reduction programs. In this context, eco-feedback technologies that provide information on the driving behavior have shown to be an effective means to stimulate changes in driving in favor of both, reduced costs and environmental impact. This study extends the literature on eco-feedback technologies as it demonstrates that a smartphone application can improve fuel efficiency even under conditions where monetary incentives are not given, i.e. where the drivers do not pay for fuel. The field test, which took place with 50 corporate car drivers, demonstrates an improvement in the overall fuel efficiency by 3.23%. The theoretical contribution underlines the assumption that context-related feedback can favorably influence behavior even without direct financial benefits for the agent. Given the large share of corporate cars, findings are also of high practical importance and motivate future research on eco-driving feedback technologies. ER - TY - CPAPER TI - Self-powered Water Meter for Direct Feedback AU - Tasic, Vojkan AU - Staake, Thorsten AU - Stiefmeier, Thomas AU - Tiefenbeck, Verena AU - Fleisch, Elgar AU - Tröster, Gerhard PY - 2012 T2 - Proceedings of 2012 International Conference on the Internet of Things SP - 24-30 PB - IEEE CY - Piscataway, N.J. SN - 978-1-4673-1345-2 DO - 10.1109/IOT.2012.6402300 UR - https://fis.uni-bamberg.de/handle/uniba/3202 LA - eng ER - TY - JOUR TI - Supporting eco-driving with eco-feedback technologies : Recommendations targeted at improving corporate car drivers’ intrinsic motivation to drive more sustainable AU - Tulusan, Johannes AU - Steggers, Hannah AU - Staake, Thorsten AU - Fleisch, Elgar PY - 2012 JO - Proceedings of Energy Informatics : Sprouts ; Working Papers on Information Systems VL - 12 IS - 3 PB - Sprouts CY - Amsterdam SN - 1535-6078 UR - https://fis.uni-bamberg.de/handle/uniba/3207 LA - eng ER - TY - CPAPER TI - Identifying individuals’ preferences using games : A field experiment in promoting sustainable energy consumption AU - Baeriswyl, Michael AU - Przepiorka, Wojtek AU - Staake, Thorsten AU - Fleisch, Elgar PY - 2012 T2 - ICIS 2011 Proceedings SP - 1029-1039 PB - Curran CY - Red Hook, NY, USA SN - 978-1-61839-472-9 UR - https://fis.uni-bamberg.de/handle/uniba/3033 LA - eng ER - TY - CPAPER TI - Evaluating Mobile Phones as Energy Consumption Feedback Devices AU - Weiß, Markus AU - Loock, Claire-Michelle AU - Staake, Thorsten AU - Mattern, Friedemann AU - Fleisch, Elgar PY - 2012 T2 - Mobile and ubiquitous systems : computing, networking, and service ; 7th international ICST conference ; revised selected papers SP - 63-77 PB - Springer CY - Berlin, New York SN - 978-3-642-29153-1 DO - 10.1007/978-3-642-29154-8_6 UR - https://fis.uni-bamberg.de/handle/uniba/2851 LA - eng ER - TY - CPAPER TI - Einsatz ubiquitärer Informationssysteme in der Versicherungswirtschaft : Gestaltung von Pay-Per-Risk Tarifierungsmodellen AU - Paefgen, Johannes AU - Skorna, Alexander C.H. AU - Staake, Thorsten AU - Fleisch, Elgar PY - 2012 T2 - MMS 2012 : Mobile und ubiquitäre Informationssysteme SP - 83-95 PB - Gesellschaft für Informatik CY - Bonn SN - 978-3-88579-296-3 UR - https://fis.uni-bamberg.de/handle/uniba/2820 LA - deu ER - TY - JOUR TI - Business Strategies in the Counterfeit Market AU - Staake, Thorsten AU - Thiesse, Frédéric AU - Fleisch, Elgar PY - 2012 JO - Journal of Business Research : JBR VL - 65 IS - 5 SP - 658-665 PB - Elsevier CY - New York, NY SN - 0148-2963 DO - 10.1016/j.jbusres.2011.03.008 UR - https://fis.uni-bamberg.de/handle/uniba/2741 LA - eng ER - TY - JOUR TI - PowerPedia : changing energy usage with the help of a community-based smartphone application AU - Weiß, Markus AU - Staake, Thorsten AU - Mattern, Friedemann AU - Fleisch, Elgar PY - 2012 JO - Personal and Ubiquitous Computing VL - 16 IS - 6 SP - 655-664 PB - Springer CY - London SN - 1617-4909 DO - 10.1007/s00779-011-0432-y UR - https://fis.uni-bamberg.de/handle/uniba/2748 LA - eng ER - TY - CPAPER TI - Direct or indirect sensor enabled eco-driving feedback : Which preference do corporate car drivers have? AU - Tulusan, Johannes AU - Staake, Thorsten AU - Fleisch, Elgar ED - Wang, Junyu PY - 2012 T2 - Proceedings of 2012 International Conference on the Internet of Things SP - 39-46 PB - IEEE CY - Piscataway, NJ, USA SN - 978-1-4673-1347-6 DO - 10.1109/IOT.2012.6402302 UR - https://fis.uni-bamberg.de/handle/uniba/2727 LA - eng AB - The increasing demand for energy is rapidly exhausting our planet's natural resources (e.g. fossil fuels). Corporations with increasingly large car fleets significantly contribute to the volume of CO2 emissions released into the atmosphere. Further investigation is needed to help reduce this escalation in global warming utilizing eco-friendly yet cost effective measures. Internet of Things solutions, using sensor enabled feedback technologies with GPS and accelerometer, offer a medium which provides drivers with eco-driving feedback services. A field-test with 50 corporate car drivers demonstrated an overall improvement in fuel efficiency, supporting literature findings claiming that direct feedback has a greater impact on energy savings than indirect feedback approaches. In this study monetary incentives were irrelevant, as corporate car drivers fuel costs are reimbursed by the company. This provides an attractive opportunity for corporations looking to reduce their CO2 footprint and petrol costs by offering their employees eco-driving applications at minimum costs. ER - TY - CPAPER TI - The effects of user identity and sanctions in online communities on real-world behavior AU - Baeriswyl, Michael AU - Staake, Thorsten AU - Loock, Claire-Michelle PY - 2011 T2 - ICIS 2011 Proceedings PB - AIS Electronic Library (AISeL) T3 - ICIS 2011 Proceedings UR - https://fis.uni-bamberg.de/handle/uniba/3205 LA - eng AB - This paper describes a field study to investigate whether and to what extent individuals conserve more electricity if they have the opportunity to signal their behavior to others in the online community. Moreover, the study intends to reveal how positive social sanctions (e.g., publicly rewarding people who reduce their energy consumption) and negative social sanctions (e.g., publicly warning people who increase their consumption) cause individuals to alter both their energy demand and their time dedicated to the online community. We discuss related work on identity disclosure in online communities, on promoting sustainable behavior with information systems, and on economic theory explaining the effects of prosocial motives on behavior. The study will be conducted as field experiment using an energy efficiency portal developed by us and operated by an Austrian utility company that currently facilitates 9,899 active users out of which 1,400 will be randomly selected as study participants. ER - TY - JOUR TI - The rise of the next-generation bar code : an international RFID adoption study AU - Thiesse, Frédéric AU - Staake, Thorsten AU - Schmitt, Patrick AU - Fleisch, Elgar PY - 2011 JO - Supply Chain Management : An International Journal VL - 16 IS - 5 SP - 328-345 PB - Emerald CY - Bingley SN - 1359-8546 DO - 10.1108/13598541111155848 UR - https://fis.uni-bamberg.de/handle/uniba/3204 LA - eng ER - TY - JOUR TI - Mit Verhaltenswissenschaft zum erfolgreichen Kundenportal : Wie Velix die Vorarlberger zum Energiesparen bringt AU - Staake, Thorsten AU - Graml, Tobias AU - Loock, Claire-Michelle AU - Baeriswyl, Michael PY - 2011 JO - Bulletin : Fachzeitschrift und Verbandsinformationen von Electrosuisse und VSE IS - 1 SP - 8-10 PB - Electrosuisse CY - Fehraltorf ; Zürich SN - 1420-7028 UR - https://fis.uni-bamberg.de/handle/uniba/3184 LA - deu AB - Die Herausforderungen sind bekannt: Energiesparkampagnen sprechen lediglich einen kleinen Teil der Bevölkerung an, EVUs finden nur schwer Teilnehmer für Smart-Metering-Pilotprojekte, Online-Portale werden kaum genutzt – und dennoch kann es gelingen, Kunden für die Kontrolle ihres Energieverbrauchs zu begeistern. Allerdings braucht es dazu mehr als eine rein technisch durchdachte Lösung. Ein unkonventionelles Forschungsprojekt zeigt den möglichen Weg. ER - TY - CPAPER TI - I am green: The role of effort and image on green identity signaling AU - Loock, Claire-Michelle AU - Landwehr, Jan AU - Staake, Thorsten AU - Fleisch, Elgar AU - Herrmann, Andreas ED - Makovec Brenčič, Maja ED - Dmitrović, Tanja ED - Lapanja, Monika ED - Seničar, Ajda PY - 2011 T2 - EMAC 2011: The day after : inspiration, innovation, implementation : conference proceedings PB - Faculty of Economics CY - Ljubljana SN - 9789612402112 UR - https://fis.uni-bamberg.de/handle/uniba/3032 LA - eng AB - Identity signaling is a strong motivator for human behavior. We investigate whether we can nudge people to higher goals with regard to showering time reduction if they perceive a possibility to signal their green identity. In a fictional saving campaign by a utility company people saw a postcard displaying either a trendy or a non-mainstream greenie and the amount of effort (shower time reduction) that is associated with a certain reference saving goal. They chose their individual goal on the back side. We suggest that people who aim at signaling their identity choose higher goals when energy saving is associated with a non-mainstream greenie and medium effort in order to send clear identity signals to others. Our results confirm our hypotheses. Identity signaling therefore nudges people towards higher saving goals KW - Identity Signaling KW - Energy Conservation KW - Goal Setting KW - Image KW - Effort ER - TY - CPAPER TI - How to motivate energy efficiency online AU - Loock, Claire-Michelle AU - Graml, Tobias AU - Baeriswyl, Michael AU - Staake, Thorsten ED - Hosni, Yasser PY - 2011 T2 - IAMOT 2011: Conference proceedings PB - International Association for Management of Technology (IAMOT) CY - Miami SN - 9780981581743 UR - https://fis.uni-bamberg.de/handle/uniba/3001 LA - eng AB - For energy conservation purposes it is not sufficient to rely on energy efficient technology, energy savings also require changes of behavior and daily routines. However, ICT can play an important role in supporting behavior change. A first step to behavior change is to actively deal with one’s energy consumption. We present an interactive online application called aWattgarde which provides customers of an Austrian utility company with insights about their electricity consumption and with suggestions on how to reduce it. Customers are incentivized for reading their electricity meters and entering the readings online on a weekly basis. In this paper, we use aWattgarde as a tool to evaluate the effects of various motivational elements on usage. The evaluation bases on usage data of almost 7’000 customers who have been using the website for six months. In our evaluation we focused on different incentive systems as well as commitment- and infotainment strategies. We found that online applications that aim at motivating energy conservation should incorporate bonus points to reward desirable action immediately, commitment features to get people into a routine and using the application regularly and in the end should provide information in a playful and interactive way. KW - ICT KW - energy conservation KW - consumer behavior KW - rewards KW - commitment ER - TY - CPAPER TI - Improving residential energy consumption at large using persuasive systems AU - Graml, Tobias AU - Loock, Claire-Michelle AU - Baeriswyl, Michael AU - Staake, Thorsten PY - 2011 T2 - ECIS 2011 Proceedings CY - Helsinki SN - 978-952-603574-1 UR - https://fis.uni-bamberg.de/handle/uniba/3005 LA - eng ER - TY - CPAPER TI - Green IS Design and Energy Conservation: An Empirical Investigation of Social Normative Feedback AU - Loock, Claire-Michelle AU - Staake, Thorsten AU - Landwehr, Jan PY - 2011 T2 - ICIS 2011 Proceedings PB - AIS Electronic Library (AISeL) T3 - ICIS 2011 Proceedings : Paper 10 UR - https://fis.uni-bamberg.de/handle/uniba/2993 LA - eng ER - TY - CPAPER TI - GPS Trajectory Feature Extraction for Driver Risk Profiling AU - Paefgen, Johannes AU - Michahelles, Florian AU - Staake, Thorsten PY - 2011 T2 - Proceedings of the 2011 international workshop on Trajectory data mining and analysis SP - 53-56 PB - ACM CY - New York, NY, USA DO - 10.1145/2030080.2030091 UR - https://fis.uni-bamberg.de/handle/uniba/2979 LA - eng AB - In this paper we develop a method and relevant feature constructs for the measurement of accident risk exposure from a large sample of real-world GPS data that includes accident and accident-free drivers. For trip frequency and accumulated driven distance features, an evaluation of their discriminatory power is given based on computational results. In our conclusion, we briefly discuss suitable classification approaches and limitations arising from external validity considerations. KW - Usage-based Insurance KW - Feature Extraction KW - Accident Risk KW - Spatio-temporal Trajectories KW - Driver Behavior ER - TY - JOUR TI - Durch Online-Interaktion Kunden für Energiedienstleistungen begeistern AU - Staake, Thorsten AU - Graml, Tobias AU - Loock, Claire-Michelle AU - Baeriswyl, Michael PY - 2011 JO - e|m|w Zeitschrift für Energie, Markt, Wettbwerb IS - 2 SP - 54-57 PB - Energieportal GmbH & Co KG CY - Essen UR - https://fis.uni-bamberg.de/handle/uniba/2815 LA - deu ER - TY - CPAPER TI - Eco-efficient feedback technologies: Which eco-feedback types prefer drivers most? AU - Tulusan, Johannes AU - Staake, Thorsten AU - Soi, Lito AU - Paefgen, Johannes AU - Brogle, Marc PY - 2011 T2 - 2011 IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM 2011) SP - 268-275 PB - IEEE CY - Piscataway, NJ SN - 978-1-4577-0352-2 DO - 10.1109/WoWMoM.2011.5986187 UR - https://fis.uni-bamberg.de/handle/uniba/2802 LA - eng ER - TY - CPAPER TI - Reducing Environmental Impact in Procurement by Integrating Material Parameters in Information Systems : The Example of Apple Sourcing AU - Dada, Ali AU - Staake, Thorsten AU - Fleisch, Elgar PY - 2010 T2 - AMCIS 2010 Proceedings PB - AIS Electronic Library (AISeL) T3 - Proceedings. Paper UR - https://fis.uni-bamberg.de/handle/uniba/3192 LA - eng AB - Legislation, customer pressure, and energy costs are increasing the interest of enterprises in environmental performance indicators such as greenhouse gas emissions and energy usage. Currently, business users take decisions across the value chain, from product design to disposal, without the ability to compare the environmental impact of alternatives within their information systems, thus limiting the optimization potential. In this paper we consider procurement as an example business operation and show how capturing previously-unknown material parameters in the respective information system can significantly increase the achievable optimizations. We use apple procurement into the U.K. to illustrate the paper’s idea, and conduct Monte Carlo analysis to quantify the realizable impact reductions as each additional life cycle parameter is tracked. The results show that taking into account the production country alone achieves a decrease in energy consumption of around 1250MJ per ton of apples, equivalent to 28% reduction from the base case. ER - TY - CPAPER TI - Towards a PowerPedia : A collaborative energy encyclopedia AU - Weiß, Markus AU - Staake, Thorsten AU - Fleisch, Elgar AU - Merkle, Adrian PY - 2010 T2 - 12th ACM International Conference on Ubiquitous Computing : Workshop Papers UR - https://fis.uni-bamberg.de/handle/uniba/3200 LA - eng AB - When it comes to conserving electricity, it is crucial for users to understand how much electricity is used by single appliances. However, the rather technical feed- back in pure numbers and intangible units of existing energy feedback systems is not appropriate for most users. To improve this situation, we present PowerPedia, a system that aims at providing action guiding feedback beyond pure consumption values. PowerPedia enables users to identify and compare the consumption of their residential appliances to those of others. It thus helps users to better assess their electricity consumption and draw effective measures to save electricity. KW - Energy use KW - visualization KW - smart meter KW - mobile computing KW - feedback systems ER - TY - CHAP TI - Produkt & Inovation : Energieeffizienz-Dienstleistungen AU - Graml, Tobias AU - Wieß, Markus AU - Staake, Thorsten AU - Fleisch, Elgar PY - 2010 T2 - Managementguide für Schweizer Energieversorgungsunternehmen (EVU) : Herausforderungen des Strommarktwandels richtig begegnen SP - 253-261 PB - Haupt CY - Bern SN - 978-3-258-07574-7 UR - https://fis.uni-bamberg.de/handle/uniba/3185 LA - deu ER - TY - CPAPER TI - ICT for Green : How computers can help us to conserve energy AU - Mattern, Friedemann AU - Staake, Thorsten AU - Weiß, Markus PY - 2010 T2 - Proceedings of the 1st International Conference on Energy-Efficient Computing and Networking SP - 1-10 PB - ACM CY - New York, NY, USA SN - 9781450300421 UR - https://fis.uni-bamberg.de/handle/uniba/3014 LA - eng AB - Information and communication technology (ICT) consumes energy, but is also an important means of conserving energy. Conventionally, it has done so by optimizing the performance of energy-using systems and processes in industry and commerce. In the near future, ICT will also play a critical role in supporting the necessary paradigm shifts within the energy sector towards more sustainable electricity generation. However, with the advent of "smart" technology from the field of ubiquitous computing, further ways of reducing growing levels of domestic energy consumption are now emerging. With this in mind, we discuss how getting consumers "into the loop" can achieve energy savings on top of the efficiency gains resulting from automated systems, and we describe a prototype application aimed at inducing behavioral change by providing direct feedback on household electricity consumption. KW - Smart meter KW - advanced metering KW - smart grid KW - energy conservation KW - feedback systems ER - TY - JOUR TI - The value of RFID for RTI management AU - Ilic, Alexander AU - Ng, Jason W. P. AU - Bowman, Paul AU - Staake, Thorsten PY - 2009 JO - Electronic Markets : EM ; the international journal of electronic commerce and business media VL - 19 IS - 2-3 SP - 125-135 PB - Springer CY - Berlin ; Heidelberg SN - 1422-8890 DO - 10.1007/s12525-009-0011-5 UR - https://fis.uni-bamberg.de/handle/uniba/3215 LA - eng ER - TY - JOUR TI - Using Sensor Information to Reduce the Carbon Footprint of Perishable Goods AU - Ilic, Alexander AU - Staake, Thorsten AU - Fleisch, Elgar PY - 2009 JO - IEEE pervasive computing : mobile and ubiquitous systems VL - 8 IS - 1 SP - 22-29 PB - IEEE Computer Society CY - New York, NY SN - 1536-1268 DO - 10.1109/MPRV.2009.20 UR - https://fis.uni-bamberg.de/handle/uniba/3217 LA - eng ER - TY - JOUR TI - The Emergence of Counterfeit trade : A Literature Review AU - Staake, Thorsten AU - Thiesse, Frédéric AU - Fleisch, Elgar PY - 2009 JO - European Journal of Marketing VL - 43 IS - 3/4 SP - 320-349 PB - Emerald CY - Bradford SN - 0309-0566 UR - https://fis.uni-bamberg.de/handle/uniba/3199 LA - eng ER - TY - JOUR TI - Kundenportale in der Energiebranche : Bestandsaufnahme und Entwicklungspotenziale AU - Loock, Claire-Michelle AU - Staake, Thorsten AU - Fleisch, Elgar PY - 2009 JO - Zeitschrift für Energiewirtschaft VL - 33 IS - 3 SP - 268-274 PB - Vieweg CY - Wiesbaden SN - 1866-2765 DO - 10.1007/s12398-009-0032-y UR - https://fis.uni-bamberg.de/handle/uniba/3172 LA - deu ER - TY - CPAPER TI - Handy feedback : Connecting smart meters with mobile phones AU - Weiß, Markus AU - Graml, Tobias AU - Staake, Thorsten AU - Mattern, Friedemann AU - Fleisch, Elgar PY - 2009 T2 - Proceedings of the 8th International Conference on Mobile and Ubiquitous Multimedia PB - ACM Press CY - New York, NY, USA SN - 9781605588469 UR - https://fis.uni-bamberg.de/handle/uniba/3028 LA - eng ER - TY - CPAPER TI - The Potential of UbiComp Technologies to Determine the Carbon Footprints of Products AU - Dada, Ali AU - Staake, Thorsten AU - Fleisch, Elgar PY - 2008 T2 - International Conference on Pervasive Computing : Workshoppaper CY - Sydney, Australia UR - https://fis.uni-bamberg.de/handle/uniba/3211 LA - eng ER - TY - CHAP TI - Product Specific Security Based on RFID Technology AU - Staake, Thorsten AU - Nochta, Zoltan AU - Fleisch, Elgar PY - 2008 T2 - Networked RFID Systems and Lightweight Cryptography : Raising Barriers to Product Counterfeiting SP - 249-252 PB - Springer CY - Berlin [u.a.] SN - 978-3-540-71641-9 DO - 10.1007/978-3-540-71641-9_13 UR - https://fis.uni-bamberg.de/handle/uniba/3198 LA - eng AB - The following contribution introduces an approach to avert removal-reapplication attacks of RIFD transponders. This is achieved by tightly coupling security tags with individual objects using object specific data. ER - TY - CHAP TI - Strengthening the Security of Machine-Readable Documents AU - Lehtonen, Mikko AU - Staake, Thorsten AU - Michahelles, Florian AU - Fleisch, Elgar PY - 2008 T2 - Networked RFID Systems and Lightweight Cryptography : Raising Barriers to Product Counterfeiting SP - 253-267 PB - Springer CY - Berlin, Heidelberg SN - 978-3-540-71641-9 DO - 10.1007/978-3-540-71641-9_14 UR - https://fis.uni-bamberg.de/handle/uniba/3194 LA - eng AB - There is an on-going trend towards turning paper documents that store personal information or other valuable data into machine-readable form. An example of this trend is the electronic passport that will become common in the near future. In this paper we show how the security of these machine readable documents could be improved by combining RFID with optical memory devices. We propose integrating an optical memory device into the RFID enabled smart document and present methods how these two storage media can be combined to secure the document against threats like illicit scanning, eavesdropping and forgery. The presented approaches make use of the optical document-to-reader channel which is more secure than the radio-frequency communication interface. To demonstrate the potential of our approaches we show how they could overcomea number of existing security and privacy threats of electronic passports. ER - TY - CHAP TI - The application of RFID as anti-counterfeiting technique : issues and opportunities AU - Staake, Thorsten AU - Michahelles, Florian AU - Fleisch, Elgar PY - 2008 T2 - RFID Technology and Applications SP - 157-168 PB - Cambridge University Press CY - Cambridge SN - 9780511541155 UR - https://fis.uni-bamberg.de/handle/uniba/3190 LA - eng AB - In industries including aerospace, pharmaceuticals, and perishables, as covered in the preceding chapters, counterfeit trade has developed into a severe problem. While established security features such as holograms, micro printings, and chemical markers do not seem to efficiently avert trade in illicit imitation products, RFID technology, with its potential to automate product authentications, may become a powerful tool to enhance brand and product protection. The following contribution aims at structuring the requirement definition for such a system by providing a non-formal attack model, and outlines several principal approaches to RFID-based solutions. ER - TY - CHAP TI - The Potential of RFID and NFC in Anti-Counterfeiting AU - Lehtonen, Mikko AU - Staake, Thorsten AU - Michahelles, Florian AU - Fleisch, Elgar PY - 2008 T2 - Networked RFID Systems and Lightweight Cryptography : Raising Barriers to Product Counterfeiting SP - 211-222 PB - Springer CY - Berlin [u.a.] SN - 978-3-540-71641-9 DO - 10.1007/978-3-540-71641-9_11 UR - https://fis.uni-bamberg.de/handle/uniba/3195 LA - eng AB - In this paper, we investigate how RFID and NFC could improve current customs processes to fight illicit trade. During the import process, customs officers have to evaluate which consignments are inspected and, when an inspection takes place, whether intellectual property rights have been infringed. We propose and evaluate new micro processes that leverage the dualexistence of products and logistic units in order to enable easier, faster and more reliable inspection of goods. The impact of the improved processes is analyzed with an example case. ER - TY - CHAP TI - Anti-Counterfeiting and Supply Chain Security AU - Staake, Thorsten AU - Michahelles, Florian AU - Fleisch, Elgar AU - Williams, John R. AU - Min, Hao AU - Cole, Peter H. AU - Lee, Sang-Gug AU - McFarlane, Duncan AU - Murai, Jun PY - 2008 T2 - Networked RFID Systems and Lightweight Cryptography : Raising Barriers to Product Counterfeiting SP - 33-43 PB - Springer CY - Berlin [u.a.] SN - 978-3-540-71640-2 UR - https://fis.uni-bamberg.de/handle/uniba/2709 LA - eng AB - Counterfeit trade developed into a severe problem for many industries. While established security features such as holograms, micro printings or chemical markers do not seem to efficiently avert trade in illicit imitation products, RFID technology, with its potential to automate product authentications, may become a powerful tool to enhance brand and product protection. The following contribution contains an overview on the implication of product counterfeiting on affected companies, provides a starting point for a structured requirements definition for RFID-based anti-counterfeiting systems, and outlines several principal solution approaches that are discussed in greater detail in the subsequent chapters. ER - TY - CPAPER TI - On The Design of A Dynamically Reconfigurable Function-Unit for Error Detection And Correction AU - Pionteck, Thilo AU - Stiefmeier, Thomas AU - Staake, Thorsten AU - Glesner, Manfred PY - 2007 T2 - VLSI-SoC : From Systems to Silicon SP - 283-297 PB - Springer CY - New York T3 - IFIP Advances in Information and Communication Technology (IFIPAICT) SN - 978-0-387-73660-0 DO - 10.1007/978-0-387-73661-7_18 UR - https://fis.uni-bamberg.de/handle/uniba/3193 LA - eng ER - TY - CPAPER TI - Strengthening the Security of Machine Readable Documents by Combining RFID and Optical Memory Devices AU - Lehtonen, Mikko AU - Staake, Thorsten AU - Michahelles, Florian AU - Fleisch, Elgar ED - Maña, Antonio PY - 2006 T2 - Developing Ambient Intelligence : Proceedings of the First International Conference on Ambient Intelligence Developments (AmID'06) SP - 77-92 PB - Springer CY - Paris SN - 978-2-287-47610-5 DO - 10.1007/978-2-287-47610-5_6 UR - https://fis.uni-bamberg.de/handle/uniba/3201 LA - eng AB - There is an on-going trend towards turning paper documents that store personal information or other valuable data into machine-readable form. An example of this trend is the electronic passport that will become common in the near future. In this paper we show how the security of these machine readable documents could be improved by combining RFID with optical memory devices. We propose integrating an optical memory device into the RFID enabled smart document and present methods how these two storage media can be combined to secure the document against threats like illicit scanning, eavesdropping and forgery. The presented approaches make use of the optical document-to-reader channel which is more secure than the radio-frequency communication interface. To demonstrate the potential of our approaches we show how they could overcome a number of existing security and privacy threats of electronic passports. ER - TY - CPAPER TI - Product Specific Security Features Based on RFID Technology AU - Nochta, Zoltan AU - Staake, Thorsten AU - Fleisch, Elgar PY - 2006 T2 - Proceedings : International Symposium on Applications and the Internet workshops SP - 72-75 PB - IEEE Computer Society CY - Los Alamitos, CA, USA SN - 0-7695-2510-5 DO - 10.1109/SAINT-W.2006.34 UR - https://fis.uni-bamberg.de/handle/uniba/3180 LA - eng ER - TY - CHAP TI - Nutzen von RFID zur Sicherung der Supply Chain der Pharma-Indistrie AU - Koh, Robin AU - Staake, Thorsten PY - 2005 T2 - Das Internet der Dinge : Ubiquitous Computing und RFID in der Praxis ; Visionen, Technologien, Anwendungen, Handlungsanleitungen SP - 161-175 PB - Springer CY - Berlin, Heidelberg SN - 978-3-540-24003-7 DO - 10.1007/3-540-28299-8_8 UR - https://fis.uni-bamberg.de/handle/uniba/3196 LA - deu AB - Gefälschte Arzneimittel stellen ein großes gesundheitliches Risiko für Patienten dar und verursachen einen erheblichen finanziellen Schaden bei den etablierten Unternehmen der pharmazeutischen Industrie. In diesem Beitrag wird ein dynamisches Tracking- und Tracing-Verfahren zur Sicherung der Supply Chain aller betroffenen Unternehmen vorgestellt. Es basiert auf der RFID-Technologie sowie einer geeigneten IT-Infrastruktur und ermöglicht eine effiziente Rückverfolgung und Lokalisierung von Arzneimitteln innerhalb der Lieferkette. ER - TY - CPAPER TI - On the Design of a Function Specific Reconfigurable Hardwre Accelerator for the MAC-Layer in WLANs AU - Pionteck, Thilo AU - Staake, Thorsten AU - Stiefmeier, Thomas AU - Kabulepa, Lukusa D. AU - Glesner, Manfred PY - 2004 T2 - Proceedings of the 2004 ACMSIGDA 12th international symposium on Field programmable gate arrays SP - 258 PB - ACM CY - New York, NY, USA SN - 1-58113-829-6 DO - 10.1145/968280.968352 UR - https://fis.uni-bamberg.de/handle/uniba/3188 LA - eng AB - This work presents the hardware design of a dynamically reconfigurable function unit (RFU) to accelerate computation-intensive tasks in Medium Access Control (MAC) layers of WLANs. The function unit is integrated in a pipelined 32 bit RISC processor and provides full hardware support for the Advanced Encryption Standard (AES) as specified in upcoming WLAN standards such as IEEE 802.11i. Dynamic reconfiguration allows the processor to use arithmetic components and memory elements of the RFU not only for AES, but also for additional tasks common in the MAC-layer. With our approach it is possible to accelerate Reed-Solomon-Code generation, Cyclic Redundancy Checks as well as other encryption standards like SQUARE, Magenta and Twofish by supporting Galois Field multiplication and table look-ups. The integration of the reconfigurable unit in the processor core results in an architecture that can simultaneously support control-flow and data-flow oriented tasks. This architecture was prototyped onto a Virtex2 FPGA. ER -