A Deep Reinforcement Learning Based Energy Storage System Control Method for Wind farm Integrating Prediction and Decision

In electricity market, the wind power producers face the challenge that how to maximize their income with the uncertainty of wind power. This paper proposes an integrated scheduling mode that integrates the wind power prediction and the energy storage system (ESS) decision making, avoiding the loss of decision-making information in the wind power prediction. Secondly, deep Q network, a deep reinforcement learning (DRL) algorithm, is introduced to construct the end-to-end ESS controller. The uncertainty of wind power is automatically considered during the DRL-based optimization, without any assumption. Finally, the superiority of the proposed method is verified through the analysis of the case wind farm located in Jiangsu Province.