Load Frequency Control Strategy of Island Microgrid with Flexible Resources Based on DQN

Abstract

The load frequency control (LFC) is of vital importance to maintain the stable operation of the island microgrid. Aiming at the frequency control problem when the microgrid is subject to strong random interference and network topology parameters change, this paper proposes a load frequency control strategy for island microgrid based on Deep Q-learning (DQN). First, a LFC model of microgrid including photovoltaic, wind power, micro gas turbine, and hydroelectric energy storage was built. Secondly, the DQN-based frequency controller structure is designed, and the definition of state space, action space and reward function are completed in turn, and the optimal hyperparameters are obtained through adjustment. Finally, the simulation experiment results show that, compared with PI control and Fuzzy control, the DQN controller proposed in this paper has online learning and experience playback capabilities, which can more effectively deal with the strong random microgrid LFC problem, and it can also better adapt to complex operating conditions with changes in system network topology parameters.