An interpretable framework for power grid dispatch risk identification integrating domain knowledge and reinforcement learning
International Journal of Low-Carbon Technologies · 27.01.2026 · 21
DOI: 10.1093/ijlct/ctag151 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Low-Carbon Technologies, online erschienen am 05.11.2026. Verfasst von Zhihua He und 7 weiteren Autor:innen. Die Arbeit nennt 547 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
To address the limited interpretability and adaptability of conventional power grid dispatch risk identification, this paper proposes an interpretable framework integrating domain knowledge with reinforcement learning. Grid topology, operational constraints, dispatch rules, and risk propagation knowledge are embedded into state representation and policy evaluation to guide risk-sensitive learning. A knowledge-driven explanation mechanism traces risk sources, affected equipment, and potential consequences. Case studies show that the improved model reaches a mean Average Precision of ~0.72–0.73, while the optimal learning-rate configuration achieves 0.77 accuracy and 0.72 AUC (Area Under Curve), demonstrating effective and interpretable risk identification.
Zitieren
APA
He, Z., Zhang, P., Liao, B., Lu, Q., Li, J., Liu, S., Hu, R., & Gao, Q. (2026). An interpretable framework for power grid dispatch risk identification integrating domain knowledge and reinforcement learning. International Journal of Low-Carbon Technologies, 21. https://doi.org/10.1093/ijlct/ctag151
Vancouver
He Z, Zhang P, Liao B, Lu Q, Li J, Liu S, et al. An interpretable framework for power grid dispatch risk identification integrating domain knowledge and reinforcement learning. International Journal of Low-Carbon Technologies. 2026;21. doi:10.1093/ijlct/ctag151
BibTeX
@article{He2026,
author = {He, Zhihua and Zhang, Peng and Liao, Binjie and Lu, Qiang and Li, Juelong and Liu, Shudi and Hu, Rong and Gao, Qian},
title = {An interpretable framework for power grid dispatch risk identification integrating domain knowledge and reinforcement learning},
journal = {International Journal of Low-Carbon Technologies},
year = {2026},
volume = {21},
doi = {10.1093/ijlct/ctag151}
}
EUVIMED