A Data-driven Agent-based Planning Strategy of Fast-Charging Stations for Electric Vehicles

Electric vehicles (EVs) are believed to play an important role in mitigating carbon emissions. To accommodate the increasing number of EVs, the co-planning of electrical distribution networks and the charging infrastructure, such as fast-charging stations (FCSs), becomes an emergent task. Both the charging demand of EVs and the stability of the electricity network should be satisfied. In this paper, we proposed a data-driven agent-based planning strategy for FCSs. Different from the conventional planning strategy, we utilized machine learning tools to consider EV behaviors at the microscopic level in a planning problem. First, a Partially Observable Markov Decision Process of EVs is established, and multi-agent deep reinforcement learning is utilized to learn the charging and driving decisions of EVs under different transportation network typologies and FCSs planning schemes. Second, a data-driven agent-based traffic assignment model (DA-TAM) is proposed to aggregate the atomic behaviors of EVs, which can present the sensitivity of the traffic flow and EV charging demand to the FCS planning schemes. Third, the DA-TAM is adapted to the proposed planning model to ensure the quality of service and prevent unbalanced traffic flow. Through the proposed method, microscopic behaviors of EVs can be reflected, and the impact of the planning scheme on the traffic condition can be revealed. The proposed methodologies are verified in the case studies. The presented agent-based planning strategy can serve more EV charging demands, cause less waiting time in FCSs to enhance the quality of service, and encounter less severe traffic unbalance problems.