Advancing urban electric vehicle charging stations: AI-driven day-ahead optimization of pricing and Nudge strategies utilizing multi-agent deep reinforcement learning

Abstract

Public charging stations (CSs) serve for electric vehicles (EVs) to charge during urban travel. Optimizing the charging time, location distribution, and power of EVs can increase the revenue of charging system operators (CSOs) and provide flexible regulation resources for the power grid. However, the optimization scheduling of CSs involves the charging choices of various users, which are influenced by their autonomy and bounded rationality. To guide users and encourage their participation in the charging schedule, we introduce the Nudge method from behavioral economics. To achieve collaborative optimization of non-economic Nudges and economic incentive strategies applying to multiple charging stations in a complex nonlinear environment involving users, CSO, and the transportation network, we leverage multi-agent deep reinforcement learning (MADRL). We construct a simulation environment using historical and survey data tailored to real users. This environment facilitates the training of agent groups to enhance decision-making processes. Case studies in a metropolis demonstrate that the agent group aimed at revenue improvement yields significant improvements in the CSO's revenue compared to fixed service fees and pricing strategies without Nudges. Moreover, the agent group aimed at power curve tracking achieves a lower average relative error in aligning the total charging power with the desired curve of the power system. This paper integrates sociological methods into the optimization of physical systems by MADRL, providing a new approach for the scheduling of EV charging considering user behavior.