A user behavior and reinforcement learning based dynamic pricing method for idle connection time reduction at charging stations

Xizhen Zhou, Yutong Cai, Qiang Meng and Yanjie Ji

Transportation Research Part A: Policy and Practice, 2025, vol. 192, issue C

Abstract: Reducing idle connection time is crucial for improving the operational efficiency of charging stations and enhancing the satisfaction of electric vehicle (EV) users. During idle connection time, EVs occupy charging spots without actively charging, thus preventing other vehicles from accessing them. However, there has been limited research focusing on how to shorten the idle connection time of charging stations. This study employed a stated preference survey to develop four separate logit models within the framework of mixed logit model that examines the impact of pricing strategies on the choice behavior of idle connection time and the underlying mechanisms behind drivers’ choice behavior in various durations of idle connection time (brief, moderate, lengthy, and extra-lengthy). Taking a charging station in Suzhou, China as a case study area, we developed a dynamic pricing algorithm based on Deep Q-Network reinforcement learning and choice behavior to minimize idle connection time and pricing at the charging station. The results indicate that factors such as pricing, location, charging start time, and the search time for available parking spaces have a significant impact on reducing idle connection time. Additionally, such impact varies across different durations of idle connection time, and the dynamic pricing strategy proves to be effective in reducing idle connection time. Compared to fixed pricing and semi-fixed pricing strategies, the dynamic pricing strategy can accommodate more potential charging demands at lower fee rates. The findings of this study offer valuable insights and a theoretical foundation for the real-time proactive management of EV charging stations.

Keywords: Idle connection Time; Electric vehicle; Dynamic pricing; Mixed Logit model; Reinforcement learning (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0965856424004063
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:transa:v:192:y:2025:i:c:s0965856424004063

Ordering information: This journal article can be ordered from
http://www.elsevier.com/wps/find/supportfaq.cws_home/regional
https://shop.elsevie ... _01_ooc_1&version=01

DOI: 10.1016/j.tra.2024.104358

Access Statistics for this article

Transportation Research Part A: Policy and Practice is currently edited by John (J.M.) Rose

More articles in Transportation Research Part A: Policy and Practice from Elsevier
Bibliographic data for series maintained by Catherine Liu ().