Frequency response of wind turbine generators (WTGs) is a crucial technology to ensure safe integration of increasing future wind power into power grids. WTGs' regulation capabilities are variable compared to conventional generations due to uncertain wind speed and dynamic deloading factors, which affects the design of their frequency response strategy. This paper proposes a novel deep reinforcement learning (DRL)-based frequency response framework of WTGs, combining a deep deterministic policy gradient (DDPG)based control and a proportional power sharing (PPS) strategy. The DDPG-based control dynamically determines the optimal total regulation power of WTGs and the PPS strategy allocates the total regulation power to each WTG. Benefiting from the ability of DDPG algorithm to handle multi-dimensional continuous system states and actions, the proposed DDPG-control enables a wind farm to dynamically determine the optimal total frequency regulation power under WTGs' variable regulation capabilities. Besides, the application of deep neural networks (DNN) in DDPG algorithm makes the DDPG-based control possible to be implemented in complex nonlinear systems. Simulations on an IEEE 39bus system demonstrate that effectiveness of the proposed frequency response strategy of WTGs.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.