Data-Driven Active Corrective Control in Power Systems: An Interpretable deep reinforcement learning Approach Provisionally Accepted
Tianlu Gao2*
Li Yang1
- 1State Grid Hubei Electric Power Co., Ltd., China
- 2Wuhan University, China
With the successful application of artificial intelligence (AI) technology in various fields, deep reinforcement learning (DRL) algorithms have applied in active corrective control in the power system to improve accuracy and efficiency. However, the "black-box" nature of DRL models reduces their reliability in practical applications, making it difficult for operators to comprehend the decision-making mechanism. process of these models, thus undermining their credibility.In this paper, a DRL model is constructed based on the Markov decision process (MDP) to effectively address active corrective control issues in a 36-bus system. Furthermore, a feature importance explainability method is proposed, validating that the proposed feature importancebased explainability method enhances the transparency and reliability of the DRL model for active corrective control.
Keywords: power systems, Active corrective control, deep reinforcement learning, Feature importance explainability method, Explainable artificial intelligence
Received: 21 Feb 2024;
Accepted: 15 Apr 2024.
Copyright: © 2024 Li, Liu, Hong, He, Zhang, He, Feng, Gao and Yang. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Mx. Tianlu Gao, Wuhan University, Wuhan, China