Deep Reinforcement Learning-Based Optimization of Second-Life Battery Utilization in Electric Vehicles Charging Stations

TL;DR

This paper proposes a deep reinforcement learning framework using the soft actor-critic method to optimize second-life battery utilization in electric vehicle charging stations, addressing uncertainties like EV arrivals and fluctuating power prices.

Contribution

It introduces a novel DRL-based planning approach specifically designed for EVCS with second-life batteries, incorporating seasonal data and tailored rewards for real-time operation.

Findings

Enhanced system efficiency through DRL optimization

Effective handling of uncertainties in EV charging dynamics

Improved cost savings with second-life batteries

Abstract

The rapid rise in electric vehicle (EV) adoption presents significant challenges in managing the vast number of retired EV batteries. Research indicates that second-life batteries (SLBs) from EVs typically retain considerable residual capacity, offering extended utility. These batteries can be effectively repurposed for use in EV charging stations (EVCS), providing a cost-effective alternative to new batteries and reducing overall planning costs. Integrating battery energy storage systems (BESS) with SLBs into EVCS is a promising strategy to alleviate system overload. However, efficient operation of EVCS with integrated BESS is hindered by uncertainties such as fluctuating EV arrival and departure times and variable power prices from the grid. This paper presents a deep reinforcement learning-based (DRL) planning framework for EV charging stations with BESS, leveraging SLBs. We employ the advanced soft actor-critic (SAC) approach, training the model on a year's worth of data to account for seasonal variations, including weekdays and holidays. A tailored reward function enables effective offline training, allowing real-time optimization of EVCS operations under uncertainty.