A Reinforcement Learning Approach for Rebalancing Electric Vehicle Sharing Systems

TL;DR

This paper introduces a reinforcement learning method to optimize shuttle routing for nightly rebalancing of electric vehicle sharing systems, improving efficiency and flexibility over traditional heuristics.

Contribution

It presents a novel RL framework with policy gradient training for shuttle routing in EV sharing networks, handling complex, unrestricted urban scenarios.

Findings

Reinforcement learning outperforms heuristic solutions in rebalancing time.

The method handles general network structures and charging constraints.

Learned policies significantly reduce rebalancing time.

Abstract

This paper proposes a reinforcement learning approach for nightly offline rebalancing operations in free-floating electric vehicle sharing systems (FFEVSS). Due to sparse demand in a network, FFEVSS require relocation of electrical vehicles (EVs) to charging stations and demander nodes, which is typically done by a group of drivers. A shuttle is used to pick up and drop off drivers throughout the network. The objective of this study is to solve the shuttle routing problem to finish the rebalancing work in the minimal time. We consider a reinforcement learning framework for the problem, in which a central controller determines the routing policies of a fleet of multiple shuttles. We deploy a policy gradient method for training recurrent neural networks and compare the obtained policy results with heuristic solutions. Our numerical studies show that unlike the existing solutions in the literature, the proposed methods allow to solve the general version of the problem with no restrictions on the urban EV network structure and charging requirements of EVs. Moreover, the learned policies offer a wide range of flexibility resulting in a significant reduction in the time needed to rebalance the network.