Driven by the recent advances in electric vehicle (EV) technologies, EVs have become important for smart grid economy. When EVs participate in demand response program which has real-time pricing signals, the charging cost can be greatly reduced by taking full advantage of these pricing signals. However, it is challenging to determine an optimal charging strategy due to the existence of randomness in traffic conditions, user's commuting behavior, and the pricing process of the utility. Conventional model-based approaches require a model of forecast on the uncertainty and optimization for the scheduling process. In this paper, we formulate this scheduling problem as a Markov Decision Process (MDP) with unknown transition probability. A model-free approach based on deep reinforcement learning is proposed to determine the optimal strategy for this problem. The proposed approach can adaptively learn the transition probability and does not require any system model information. The architecture of the proposed approach contains two networks: a representation network to extract discriminative features from the electricity prices and a Q network to approximate the optimal action-value function. Numerous experimental results demonstrate the effectiveness of the proposed approach. Index Terms-Deep reinforcement learning, model-free, EV charging scheduling. I. INTRODUCTION W ITH the recent advances in EV technologies, EVs are becoming popular because of its various benefits [1], [2]. EVs provide a sustainable alternative to fossil-fuel vehicles and can significantly reduce the transport-related pollution. Another benefit of EVs is the cost reduction for consumers since it is cheaper to charge an EV than fill up with gasoline [3]. As the real-time electricity price has been adopted by many utility companies to encourage shifting energy usage to off-peak hours [4], the charging cost can be reduced by optimizing the charging schedules [5]. In addition, an EV

No abstract

No abstract

No abstract

No abstract