A Reinforcement Learning Approach for Rebalancing Electric Vehicle Sharing Systems
- 16 June 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 23 (7) , 8704-8714
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 requires 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 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 solving 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.Keywords
All Related Versions
Funding Information
- University of South Florida Nexus Initiative (UNI) Award
This publication has 24 references indexed in Scilit:
- Cooperative Multi-agent Control Using Deep Reinforcement Learning2017
- One-Way Free Floating Car-Sharing: Applying Vehicle-Generated Data to Assess the Market Demand Potential of Urban Zones2017
- Vehicle relocation problem in free floating carsharing using multiple shuttles2017
- A Concise Introduction to Decentralized POMDPs2016
- A practice-ready relocation model for free-floating carsharing systems with electric vehicles – Mesoscopic approach and field trial resultsTransportation Research Part C: Emerging Technologies, 2015
- Decision Support for Environmental-friendly Vehicle Relocations in Free- Floating Car Sharing Systems: The Case of Car2goProcedia CIRP, 2015
- DeepWalk2014
- Increasing Acceptance of Free-Floating Car Sharing Systems Using Smart Relocation Strategies: A Survey Based Study of car2go Hamburg2014
- Relocation Strategies and Algorithms for Free-Floating Car Sharing SystemsIEEE Intelligent Transportation Systems Magazine, 2013
- Simple statistical gradient-following algorithms for connectionist reinforcement learningMachine Learning, 1992