A Deep Reinforcement Learning-Based Multiobjective Charging Scheduling Method for Electric Vehicle Charging Station

This paper investigates the charging scheduling problem within an Electric Vehicle Charging Station (EVCS), aiming to coordinate multiple charging piles to optimize the charging process. The objectives are to increase the profit for the Charging Station Operator (CSO) and enhance user satisfaction while mitigating significant fluctuations in grid load. However, since these objectives originate from different stakeholders, they are inherently conflicting; a strategy trained using fixed objective weights cannot satisfy all of them simultaneously. Additionally, uncertainties such as vehicle arrival and departure times, power requirements, and grid tariffs complicate the modeling of this process. To address these challenges, this paper reformulates the scheduling process as a Markov Decision Process (MDP) and proposes a novel model-free reinforcement learning method. By integrating randomly varying objective preferences into the inputs of agents, a set of policies corresponding to different objective preferences can be learned through a single training session. As a result, agents can execute various policies to satisfy the stakeholders’ needs based on these preferences. Moreover, a sampling adjustment strategy is introduced to improve the uniformity of the final non-dominated solution set and enhance the ability of the agent to explore the objective space. Experiments show that the proposed method can effectively solve the multi-objective problem of cooperative charging within an EVCS. Compared to the baseline method, the proposed method can achieve superior results while simultaneously reducing the computational cost to a significant extent.