Skip to content

Read-only version: For security reasons, the Research Information System (FIS) has been temporarily replaced by this read-only version. All public content and full texts remain available; login, editing, submission and statistics are not available. Questions: fis@uni-bamberg.de

Home › Publications › Half-hourly electricity price prediction model with explainable-decomposition hybrid deep learning approach

Publication

Half-hourly electricity price prediction model with explainable-decomposition hybrid deep learning approach

Ghimire, Sujan; Deo, Ravinesh C.; Hopf, Konstantin; u. a. (2025): Half-hourly electricity price prediction model with explainable-decomposition hybrid deep learning approach, in: Energy and AI, Amsterdam: Elsevier BV, Jg. 20, Nr. 100492, S. 1–34, doi: 10.1016/j.egyai.2025.100492.

Details

Faculty/Chair
Faculty/Professorship
Author
Ghimire, Sujan; Deo, Ravinesh C.; Hopf, Konstantin; Liu, Hangyue; Casillas-Pérez, David; Helwig, Andreas; Prasad, Salvin S.; Pérez-Aracil, J.; Barua, Prabal Datta; Salcedo-Sanz, Sancho
Title of the Journal
Energy and AI
ISSN
2666-5468
Publisher Information
Elsevier BV : Amsterdam
Year of publication
2025
Volume
20
Issue
100492
Language
English
DOI
Abstract

Accurate prediction of electricity price (𝐸𝑃 ) is crucial for energy utilities and grid operators for enhancing the energy trading, grid stability studies, resource allocations and pricing strategies, thereby improving the overall grid reliability, efficiency, and cost-effectiveness. This study introduces a novel D3Net model for halfhourly 𝐸𝑃 prediction, integrating Seasonal-Trend decomposition using LOESS (STL) and Variational Mode Decomposition (VMD) with Multi-Layer Perceptron (MLP), Random Forest Regression (RFR), and Tabular Neural Network (TabNet). The methodology involves applying STL to the 𝐸𝑃 time-series to extract trend, seasonal, and residual components. The trend is predicted using an MLP model, the seasonal component is further decomposed with VMD into 20 Variational Mode Functions (VMFs) and predicted using an RFR model, and the residual component is decomposed with VMD and predicted using the TabNet model. Input features are identified using the Partial Autocorrelation Function, and models are optimized using the Optuna algorithm.

Keywords
Tabular neural network
SHAP
Optuna algorithm
Deep learning
Machine learning
Convolutional neural network
LIME
Peer Reviewed
yes
International Distribution
yes
Open Access Journal
yes
Type
Article
URI
Activation date
2025-04-01

Permalink: https://fis.uni-bamberg.de/handle/uniba/107283 · Data as JSON · Cite: BibTeX · RIS

Data as of: 2026-11-16

Restricted read-only access: login, editing and submission are temporarily disabled.