EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Causal-Enhanced LSTM-RF: Early Warning of Dynamic Overload Risk for Distribution Transformers

Hao Bai, Yipeng Liu, Yawen Zheng, Ming Dong, Qiaoyi Ding, Hao Wang

Energies · 07.03.2026 · 19 (5) · 1354

DOI: 10.3390/en19051354 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Energies, online erschienen am 07.03.2026. Verfasst von Hao Bai und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Project of China Southern Power Grid.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The frequency of extreme weather events has become higher, and electricity consumption has also become more complex. These changes increase the risk of overload in distribution transformers (DTs), and this risk threatens the stability and reliability of the power grid. Existing methods have significant limitations. Traditional static threshold methods (based on DGA gas ratios and electrical signal thresholds) fail to consider temporal changes and complex links between factors, while modern machine learning models lack cause–effect relationships over time and clear ways to describe uncertainty. With such motivations, this paper proposes a causal-enhanced hybrid framework, which combines Long Short-Term Memory (LSTM) networks and Random Forest (RF) algorithms. The framework uses causal Seasonal Trend decomposition using Loess (STL) to reveal load patterns at different time scales. The mutual information index and spatiotemporal graph convolutional network (ST-GCN) are used to explore nonlinear relations and reveal how temperature affects load changes. The LSTM model captures time dependence in load series, and the Bayesian optimized Random Forest is used to solve the problem of data imbalance and quantify uncertainty. In addition, the framework constructs an early warning system that combines data from many sources in real time. Test results show that the proposed algorithm exhibits excellent performance in multi-source data environments.

Förderung

  • Science and Technology Project of China Southern Power Grid

Zitieren

APA

Bai, H., Liu, Y., Zheng, Y., Dong, M., Ding, Q., & Wang, H. (2026). Causal-Enhanced LSTM-RF: Early Warning of Dynamic Overload Risk for Distribution Transformers. Energies, 19(5), 1354. https://doi.org/10.3390/en19051354

Vancouver

Bai H, Liu Y, Zheng Y, Dong M, Ding Q, Wang H. Causal-Enhanced LSTM-RF: Early Warning of Dynamic Overload Risk for Distribution Transformers. Energies. 2026;19(5):1354. doi:10.3390/en19051354

BibTeX
@article{Bai2026,
  author = {Bai, Hao and Liu, Yipeng and Zheng, Yawen and Dong, Ming and Ding, Qiaoyi and Wang, Hao},
  title = {Causal-Enhanced LSTM-RF: Early Warning of Dynamic Overload Risk for Distribution Transformers},
  journal = {Energies},
  year = {2026},
  volume = {19},
  number = {5},
  pages = {1354},
  doi = {10.3390/en19051354}
}
Kostenlos starten →