EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DG-LSTM-SA model: A deep gated LSTM network with self-attention mechanism for power generation and load forecasting

Guoqiang Sun, Yang Zhao, Jianglong Li, Junfu Cui, Xiaoyan Qi iD

PLOS One · 03.06.2026 · 21 (6) · e0350071

DOI: 10.1371/journal.pone.0350071 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 03.06.2026. Verfasst von Guoqiang Sun und 4 weiteren Autor:innen. Beteiligte Einrichtung: Naval Aviation University, Qingdao, People's Republic of China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Shandong Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate forecasting of power generation and load demand is essential for the reliable operation of modern energy systems. Traditional recurrent neural networks (RNNs) often struggle to capture long-term dependencies in complex power time series, whereas recent Transformer-based models can introduce substantial computational overhead. To address these limitations, we propose a Deep Gated Long Short-Term Memory network with Self-Attention (DG-LSTM-SA). The proposed model combines a multi-layer gated architecture with hierarchically embedded self-attention modules, enabling it to adaptively emphasize informative time steps and capture complex temporal patterns without a prohibitive increase in parameters. We evaluated DG-LSTM-SA on three real-world energy datasets (NEPOOL, Yichang, and Solar-Energy). The results demonstrate that DG-LSTM-SA consistently outperforms ten baseline models. Compared with standard RNN variants such as LSTM and GRU, DG-LSTM-SA substantially reduces forecasting errors, decreasing Mean Absolute Error by more than 75%. Furthermore, relative to state-of-the-art attention-based models (e.g., Informer and Crossformer), DG-LSTM-SA achieves competitive accuracy while maintaining a distinct advantage in computational efficiency and training speed. Comprehensive ablation studies further confirm that the proposed design is robust, accurate, and practical for real-world grid dispatch and operational decision-making.

Autor:innen und Institutionen

  • Naval Aviation University, Qingdao, People's Republic of China.
  • School of Information Science and Engineering, Shandong University, Qingdao, People's Republic of China.
  • Department of Biochemistry and Molecular Biology, Shandong Medical and Pharmaceutical University, Yantai, People's Republic of China.

ORCID-Profile: Xiaoyan Qi

Förderung

  • Natural Science Foundation of Shandong Province

Zitieren

APA

Sun, G., Zhao, Y., Li, J., Cui, J., & Qi, X. (2026). DG-LSTM-SA model: A deep gated LSTM network with self-attention mechanism for power generation and load forecasting. PLOS One, 21(6), e0350071. https://doi.org/10.1371/journal.pone.0350071

Vancouver

Sun G, Zhao Y, Li J, Cui J, Qi X. DG-LSTM-SA model: A deep gated LSTM network with self-attention mechanism for power generation and load forecasting. PLOS One. 2026;21(6):e0350071. doi:10.1371/journal.pone.0350071

BibTeX
@article{Sun2026,
  author = {Sun, Guoqiang and Zhao, Yang and Li, Jianglong and Cui, Junfu and Qi, Xiaoyan},
  title = {DG-LSTM-SA model: A deep gated LSTM network with self-attention mechanism for power generation and load forecasting},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {6},
  pages = {e0350071},
  doi = {10.1371/journal.pone.0350071}
}
Kostenlos starten →