A Control Strategy Based on Deep Reinforcement Learning Under the Combined Wind-Solar Storage System

The cooperation of hybrid system composed of wind power, photovoltaic power and energy storage system(ESS) in the power market can effectively help improve the income of renewable generation. The traditional power network scheduling approach usually starts with power prediction and then optimizes the scheduling, which can easily lead to information loss and modeling error. To solve this problem, this paper proposes an energy storage system control strategy based on deep reinforcement learning (DRL) in the scene of the combined wind-solar storage system. Deep Q Network (DQN) algorithm is introduced to realize the coordination of the control of the ESS with the output of wind power and photovoltaic power, so as to maximize the benefits of renewable energy generators in the power market.