Electric Vehicle Charging Guidance Strategy Considering "Traffic Network-Charging Station-Driver" Modeling: A Multiagent Deep Reinforcement Learning-Based Approach

• Published in: IEEE transactions on transportation electrification 2024-09, Vol.10 (3), p.4653-4666
• Main Authors: Su, Su, Li, Yujing, Yamashita, Koji, Xia, Mingchao, Li, Ning, Folly, Komla Agbenyo
• Format: Article
• Language: English
• Subjects: Algorithms; Anxiety; Anxiety disorders; Batteries; Charging guidance; charging station; Charging stations; Deep learning; Driving conditions; electric vehicle (EV); Electric vehicle charging; Electric vehicles; Guidance (motion); Machine learning; Markov processes; Mathematical models; multiagent deep reinforcement learning (DRL); Multiagent systems; Real time; Roads; Testing time; Traffic; Vehicles
• ISSN: 2332-7782; 2577-4212; 2332-7782
• DOI: 10.1109/TTE.2023.3322685

Electric vehicle (EV) drivers have experienced a charging inconvenience due to a limited number of charging facilities and mileage anxiety due to the limited driving distance for a single full charge. This article developed a user friendly online EV charging guidance algorithm to cope with the two aforementioned issues using multiagent deep reinforcement learning. First, three models, i.e., the traffic network model, charging station model, and EV driver model, are established, respectively, considering the traffic condition, the potential competition of future charging demand at charging stations, and the drivers' mileage anxiety. Second, the charging guidance process is modeled as a Markov decision process, and charging stations are taken as agents. The attentional multiagent actor-critic algorithm based on the centralized training with decentralized execution framework is built. Finally, compared to the comparison algorithm, the performance does not diminish with the increase in the number of agents, indicating that the approach has the scalability to be applied to large-scale agent systems. The model still has the generalization in extreme scenarios such as traffic road and charger failures. The testing time within various numbers of charging stations is about 23 ms per EV, which is sufficient to apply the proposed model to real-time decision-making and online recommendation.