Adaptive composite frequency control of power systems using reinforcement learning. Issue 4 (17th May 2022)

• Record Type: Journal Article
• Authors: Mu, Chaoxu; Wang, Ke; Ma, Shiqian; Chong, Zhiqiang; Ni, Zhen
• Is Part Of: CAAI transactions on intelligence technology. Volume 7:Issue 4(2022)
• Page Start: 671
• Page End: 684
• Publication Date: 2022-05-17
• Subjects: Artificial intelligence -- Periodicals; Computer science -- Periodicals; Artificial intelligence; Computer science; Electronic journals; Periodicals; 006.305
• DOI: 10.1049/cit2.12103
• Languages: English
• ISSNs: 2468-6557

Abstract

Abstract: With the incorporation of renewable energy, load frequency control (LFC) becomes more challenging due to uncertain power generation and changeable load demands. The electric vehicle (EV) has been a popular transportation and can also provide flexible options to play a role in frequency regulation. In this paper, a novel adaptive composite controller is designed to solve the LFC problem for the interconnected power system with electric vehicles and wind turbine. EVs are used as regulation resources to effectively compensate the power mismatch. First, the sliding mode controller is developed to reduce the random influences caused by the wind turbine generation system. Second, an auxiliary controller with reinforcement learning is proposed to produce adaptive control signals, which will be attached to the primary proportion‐integration‐differentiation control signal in a real‐time manner. Finally, by considering random wind power, load disturbances and output constraints, the proposed scheme is verified on a two‐area power system under four different cases. Simulation results demonstrate that the proposed adaptive composite frequency control scheme has a competitive performance with regard to dynamic performance.