AUTHOR=Cui Feifei , Lin Xixiang , Zhang Ruining , Yang Qingyu TITLE=Multi-objective optimal scheduling of charging stations based on deep reinforcement learning JOURNAL=Frontiers in Energy Research VOLUME=Volume 10 - 2022 YEAR=2023 URL=https://www.frontiersin.org/journals/energy-research/articles/10.3389/fenrg.2022.1042882 DOI=10.3389/fenrg.2022.1042882 ISSN=2296-598X ABSTRACT=With the green-oriented transition of energy, electric vehicle (EV), as the first choice to replace fuel vehicle, is in a period of rapid development. In the face of large-scale EVs accessing to grid, real-time and effective charging management has become a key problem. Considering the charging characteristics of different EVs, we propose a real-time scheduling framework for charging station with electric vehicle aggregator (EVA) as the decision-making body. However, facing multiple optimization objectives, it is challenging to formulate a strategy that can ensure the interests of each participant. In this paper, we model the charging scheduling as a Markov decision process (MDP) based on deep reinforcement learning (DRL). With continuous action space, the MDP model is solved by the twin delayed deep deterministic policy gradient algorithm (TD3). While ensuring the maximum benefit of the EVA, we also ensure the minimum fluctuations of the micro-grid exchange power. To verify the effectiveness of the proposed method, we set up two comparative experiments, using disorder charging method and deep deterministic policy gradient (DDPG) method respectively. The results show that the strategy obtained by TD3 is optimal, which can reduce power purchase cost by 10.9% and reduce the power fluctuations by 69.4%.