Citation

Hossen, Md Sabbir and Ramasamy, Gobbi and Al Qwaid, Marran (2026) A Sustainable Charging Session Index (SCSI): A Data-Driven Framework for Evaluating Electric Vehicle Charging Session Sustainability. Energies, 19 (14). p. 3366. ISSN 1996-1073

Text A Sustainable Charging Session Index (SCSI)_ A Data-Driven Framework for Evaluating Electric Vehicle Charging Session Sustainability.pdf - Published Version Restricted to Repository staff only Download (5MB)

Abstract

The rapid growth of electric vehicle (EV) adoption has increased the importance of understanding charging behavior and improving the operational sustainability of charging infrastructure. Although existing studies have extensively investigated charging demand forecasting, charging load prediction, and charging behavior analysis, limited attention has been given to evaluating the sustainability of individual charging sessions. To address this gap, this study proposes a Sustainable Charging Session Index (SCSI) framework for assessing and classifying real-world EV charging behaviors based on operational charging characteristics. The proposed framework integrates the Entropy Weight Method (EWM), K-Means clustering, Principal Component Analysis (PCA), Random Forest feature importance analysis, and statistical validation techniques. A real-world dataset comprising 1929 EV charging sessions was analyzed, from which 1795 valid charging records were retained after preprocessing. Charging energy usage, average output power, and charging duration were selected as complementary indicators representing energy delivery effectiveness, charging efficiency, and temporal efficiency, respectively. The EWM assigned the highest weights to charging energy usage (0.5119) and average output power (0.4340), reflecting their greater discriminatory capability within the analyzed dataset. Clustering analysis identified three charging behavior archetypes, namely High-Sustainability Charging Sessions, Low-Sustainability Charging Sessions, and Efficient Charging Sessions. PCA demonstrated clear cluster separation, with the first two principal components explaining 97.9% of the total variance. Statistical analyses confirmed significant differences among the identified charging behavior groups (p < 0.001), while one-way ANOVA demonstrated strong internal consistency between the charging behavior clusters and SCSI scores (η 2 = 0.730). Furthermore, Random Forest analysis identified charging power as the most influential factor in differentiating charging behaviors. The proposed SCSI framework provides an objective and data-driven approach for charging session sustainability assessment, charging behavior characterization, and sustainable charging infrastructure management.

Item Type:	Article
Uncontrolled Keywords:	Electric vehicles, EV charging
Subjects:	T Technology > TL Motor vehicles. Aeronautics. Astronautics > TL1-484 Motor vehicles. Cycles
Divisions:	Faculty of Artificial Intelligence & Engineering (FAIE)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	02 Sep 2026 06:29
Last Modified:	02 Sep 2026 06:29
URII:	http://shdl.mmu.edu.my/id/eprint/16530

Downloads

Edit (login required)