Explainable Artificial Intelligence Feedback and Latent‐Space Bidirectional Long Short‐Term Memory‐Transformer for Improved Short‐Term Load Forecasting
Energy Technology · 2026-11 · 14 (11)
DOI: 10.1002/ente.70698 ↗Kurz gefasst
Fachartikel in der Zeitschrift Energy Technology, online erschienen am 15.11.2026. Verfasst von Abid Ali und 4 weiteren Autor:innen. Die Arbeit nennt 49 Literaturangaben. Gefördert von: Beijing Municipal Natural Science Foundation, National Natural Science Foundation of China, Natural Science Foundation of Shandong Province.
Abstract (Originalsprache)
Accurate short‐term load forecasting is important for the reliable operation of smart grids, particularly with the increasing integration of intermittent renewable energy sources, energy storage systems, and electric vehicles. Therefore, this paper proposes a hybrid deep learning model, that combines (i) an autoencoder to obtain more meaningful features from the raw dataset by mapping the dataset into a latent space; (ii) a bidirectional long short‐term memory network enhanced with a multihead transformer attention mechanism to capture critical temporal dependencies and salient patterns; and (iii) an explainable AI feedback loop based on Shapley additive explanations to iteratively optimize model hyperparameters and interpret feature contributions. Extensive benchmarking is performed to evaluate the effectiveness of the proposed model. The experimental results demonstrate that the proposed model outperforms state‐of‐the‐art methods and achieves a mean absolute error of 161.58–423.29, a root mean square error of 283.14–3346.49, and a mean absolute percentage error of 1.37%–5.40% across different geographical datasets. These results confirm the superior accuracy, robustness, and interpretability of the proposed model for short‐term load forecasting in diverse geographical contexts.
Förderung
- Beijing Municipal Natural Science Foundation
- National Natural Science Foundation of China
- Natural Science Foundation of Shandong Province
Zitieren
APA
Ali, A., Xia, Y., Zia, M. F., Manzoor, T., & Benbouzid, M. (2026). Explainable Artificial Intelligence Feedback and Latent‐Space Bidirectional Long Short‐Term Memory‐Transformer for Improved Short‐Term Load Forecasting. Energy Technology, 14(11). https://doi.org/10.1002/ente.70698
Vancouver
Ali A, Xia Y, Zia MF, Manzoor T, Benbouzid M. Explainable Artificial Intelligence Feedback and Latent‐Space Bidirectional Long Short‐Term Memory‐Transformer for Improved Short‐Term Load Forecasting. Energy Technology. 2026;14(11). doi:10.1002/ente.70698
BibTeX
@article{Ali2026,
author = {Ali, Abid and Xia, Yuanqing and Zia, Muhammad Fahad and Manzoor, Tayyab and Benbouzid, Mohamed},
title = {Explainable Artificial Intelligence Feedback and Latent‐Space Bidirectional Long Short‐Term Memory‐Transformer for Improved Short‐Term Load Forecasting},
journal = {Energy Technology},
year = {2026},
volume = {14},
number = {11},
doi = {10.1002/ente.70698}
}
EUVIMED