Distributed Meta-Deep Reinforcement Learning for Wide Area Frequency Control of Interconnected Grid Considering Multi-Time Scale Coordination

作     者：Li, Jiawen Dai, Jichao 

作者机构：Shanghai Univ Elect Power Shanghai 201306 Peoples R China Shanghai Jiao Tong Univ Shanghai 200240 Peoples R China 

出 版 物：《IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS》 (IEEE Trans. Circuits Syst. Regul. Pap.)

年 卷 期：2025年

核心收录：

学科分类：0808[工学-电气工程] 08[工学] 

基　　金：National Natural Science Foundation of China 

主　　题：Frequency control Frequency measurement Automatic generation control Accuracy Reliability Regulation Real-time systems Accidents Time-frequency analysis Power grids emergency frequency control performance-based frequency regulation market automatic generation control distributed meta-actor critic 

摘      要：To solve the problems of over-shedding for loads in conventional frequency emergency control and prevent constraint violations in power systems, a data-driven wide-area frequency control strategy (WA-FCS) is proposed. The WA-FCS includes an emergency frequency control (EFC) module and a wide automatic generation control (WAGC) module. In online decisions, the EFC can consider the impact of WAGC on the system frequency and prevent system constraint violations. WAGC helps EFC quickly solve the problem of line power overload. By coordinating EFC with WAGC, the load loss following grid failure can be reduced. In addition, to improve the strategy s robustness, a distributed meta-actor critic (DMAC) algorithm is proposed, which draws on meta-learning and distributed exploration to obtain the optimal WA-FCS strategy in a random environment. The simulation results of this paper verify the effectiveness and feasibility of the proposed strategy for the performance-based frequency regulation market.