Intelligent Electric Vehicle Charging Recommendation Based on Multi-Agent Reinforcement Learning

TL;DR

This paper introduces a multi-agent reinforcement learning framework called Master for recommending EV charging stations, considering long-term spatiotemporal factors and future competition to improve charging experiences.

Contribution

The paper presents a novel multi-agent reinforcement learning approach with centralized attentive critic and dynamic gradient re-weighting for EV charging recommendation.

Findings

Master outperforms nine baseline methods in experiments.

Effective coordination among geographically distributed agents.

Incorporation of future competition improves recommendation quality.

Abstract

Electric Vehicle (EV) has become a preferable choice in the modern transportation system due to its environmental and energy sustainability. However, in many large cities, EV drivers often fail to find the proper spots for charging, because of the limited charging infrastructures and the spatiotemporally unbalanced charging demands. Indeed, the recent emergence of deep reinforcement learning provides great potential to improve the charging experience from various aspects over a long-term horizon. In this paper, we propose a framework, named Multi-Agent Spatio-Temporal Reinforcement Learning (Master), for intelligently recommending public accessible charging stations by jointly considering various long-term spatiotemporal factors. Specifically, by regarding each charging station as an individual agent, we formulate this problem as a multi-objective multi-agent reinforcement learning task. We first develop a multi-agent actor-critic framework with the centralized attentive critic to coordinate the recommendation between geo-distributed agents. Moreover, to quantify the influence of future potential charging competition, we introduce a delayed access strategy to exploit the knowledge of future charging competition during training. After that, to effectively optimize multiple learning objectives, we extend the centralized attentive critic to multi-critics and develop a dynamic gradient re-weighting strategy to adaptively guide the optimization direction. Finally, extensive experiments on two real-world datasets demonstrate that Master achieves the best comprehensive performance compared with nine baseline approaches.