Abstract :

Given How Quickly EV Use Has Increased Over The Past Ten Years, It Is Now Necessary To Accurately Estimate How Much Energy An EV Will Use When Charging. The Primary Energy Source For Electric Cars Nowadays Is Lithiumion Batteries; Keeping Them From Being Overcharged Can Protect Them And Increase Their Lifespan. The Machine Learning Model For EV Charging Session Length Prediction Presented In This Paper Is Based On The K-Nearest Neighbors Classification Technique. Assigning The Event To The Appropriate Class Allows The Model To Predict How Long The Charge Would Last. The Charging Events, Which Last For A Specific Amount Of Time, Are Included In Each Class. The Program Only Uses The Data (arrival Time, Starting SOC, Calendar Data) That Is Available At The Start Of The Charging Event. The Model Has Been Proved Accurate A Sensitivity Analysis Is Conducted To Evaluate The Effects Of Various Input Data Sets On A Real-world Dataset That Includes Records Of Charging Sessions From Over 100 Users. A Performance Gain Indicates How Effective The Model Is In Comparison To The Benchmark Models.

Published:

10-11-2025

Issue:

Vol. 25 No. 11 (2025)

Page Nos:

73-77

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite