Cyber-Attack Recovery Strategy for Smart Grid Based on Deep Reinforcement Learning
Document Type
Article
Date of Original Version
5-1-2020
Abstract
The integration of cyber-physical system increases the vulnerabilities of critical power infrastructures. Once the malicious attackers take the substation control authorities, they can trip all the transmission lines to block the power transfer. As a consequence, asynchrony will emerge between the separated regions which had been interconnected by these transmission lines. In order to recover from the attack, a straightforward way is to reclose these transmission lines once we detect the attack. However, this may cause severe impacts on the power system, such as current inrush and power swing. Therefore, it is critical to properly choose the reclosing time to mitigate these impacts. In this paper, we propose a recovery strategy to reclose the tripped transmission lines at the optimal reclosing time. In particular, a deep reinforcement learning (RL) framework is adopted to endow the strategy with the adaptability of uncertain cyber-attack scenarios and the ability of real-time decision-making. In this framework, an environment is established to simulate the power system dynamics during the attack-recovery process and generate the training data. With these data, the deep RL based strategy can be trained to determine the optimal reclosing time. Numerical results show that the proposed strategy can minimize the cyber-attack impacts under different scenarios.
Publication Title, e.g., Journal
IEEE Transactions on Smart Grid
Volume
11
Issue
3
Citation/Publisher Attribution
Wei, Fanrong, Zhiqiang Wan, and Haibo He. "Cyber-Attack Recovery Strategy for Smart Grid Based on Deep Reinforcement Learning." IEEE Transactions on Smart Grid 11, 3 (2020): 2476-2486. doi: 10.1109/TSG.2019.2956161.