Decentralized Collaborative Pricing and Shunting for Multiple EV Charging Stations Based on Multi-Agent Reinforcement Learning

TL;DR

This paper introduces a decentralized multi-agent reinforcement learning approach to optimize EV charging station utilization and costs, considering user preferences and EV behavior to improve efficiency and balance demand.

Contribution

It presents a novel decentralized collaborative pricing and shunting strategy for multiple EV charging stations using multi-agent reinforcement learning, accounting for EV user preferences and behaviors.

Findings

Effective EV shunting achieved through the proposed method.

Reduced charging costs for EV users.

Improved balance of demand across charging stations.

Abstract

The extraordinary electric vehicle (EV) popularization in the recent years has facilitated research studies in alleviating EV energy charging demand. Previous studies primarily focused on the optimizations over charging stations (CS) profit and EV users cost savings through charge/discharge scheduling events. In this work, the random behaviors of EVs are considered, with EV users preferences over multi-CS characteristics modelled to imitate the potential CS selection disequilibrium. A price scheduling strategy under decentralized collaborative framework is proposed to achieve EV shunting in a multi-CS environment, while minimizing the charging cost through multi agent reinforcement learning. The proposed problem is formulated as a Markov Decision Process (MDP) with uncertain transition probability.