Electric vehicle charging decisions with travel distance: novel clustering algorithm integrating spatial-temporal charging and trip data

M. Emami Javanmard and Y. Tang

Applied Energy, 2026, vol. 402, issue PB, No S0306261925016319

Abstract: The adoption of electric vehicles (EV) plays a crucial role in mitigating greenhouse gas emissions and decreasing reliance on fossil fuels. This realization requires a comprehensive comprehension of EV travel distances and charging decisions in different climates to enhance infrastructure and policy optimization. This study proposed that by clustering travel trip and charging characteristics, such as trip distances and battery levels, it would be possible to identify unique behavioral patterns that connecting charging preferences on traveling distance and charging decisions. These patterns could then be used to design and plan customized electric vehicle infrastructure. In this study, we developed a novel clustering methodology known as Novel DEC VAE Clustering Cuckoo Search K-Means (DVAE-CSKM) algorithm with a customized loss function to examine patterns on travel distances and charging decisions for electric and hybrid vehicles (HV) in cold and warm months, respectively. The case study data spans from April 2021 to April 2022 and includes over 328,000 charging events and 95,000 trip logs collected from EV and hybrid vehicle users. In comparison to conventional methods, the DVAE-CSKM algorithm achieved substantial improvements in clustering quality, with silhouette scores increasing by 23.83 % to 39.5 % across vehicle types and seasons. The analysis resolved four distinct charging behavior patterns: Frequent Short-Distance Travelers, Long-Haul Travelers, Range Extenders, and Urban Commuters, each displaying clear seasonal variation. These findings indicate that the development of seasonally adaptive, user-user-oriented charging infrastructure is critical for supporting broader EV adoption and ensuring the long-term sustainability of transportation systems.

Keywords: Electric vehicles; Transportation; Multi-dimensional clustering; Machine learning; Pattern identification; Spatial-temporal (search for similar items in EconPapers)
Date: 2026
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0306261925016319
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:appene:v:402:y:2026:i:pb:s0306261925016319

Ordering information: This journal article can be ordered from
http://www.elsevier.com/wps/find/journaldescription.cws_home/405891/bibliographic
http://www.elsevier. ... 405891/bibliographic

DOI: 10.1016/j.apenergy.2025.126901

Access Statistics for this article

Applied Energy is currently edited by J. Yan

More articles in Applied Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().