• J.N.Chandra Sekhar
• Ale Shushrutha
• Lunavath Srikanth
• Parshaveni Shiva Karthik

The rapid rise in the use of electric vehicles (EVs) over the past ten years has made it necessary to accurately estimate the energy required for EV charging. Electric vehicles now mostly use lithium-ion batteries for storage; protecting these batteries from overcharging can extend their lifespan and maintain their health. This research suggests a machine learning model for predicting the length of an EV charging session that is based on the K-Nearest Neighbors classification method. By classifying the event correctly, the model predicts how long the charge will last. There are charging events in each class, and each one lasts for a specific amount of time. The program only uses the data (arrival time, starting SOC, calendar data) that is available at the start of the charging event. A sensitivity analysis is carried out to evaluate the effects of various inputs, and the model is validated using an actual dataset comprising records of charging sessions from over 100 users. An improvement in performance demonstrates the model's efficacy in comparison to the benchmark models.

Electric Vehicles, charging sessions, Classification technique, Optimized battery charge, Machine learning.

"Electric Vehicles Charging Sessions Classification Technique for Optimized Battery Charge Based on Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 4, page no.q10-q15, April-2024, Available :http://www.jetir.org/papers/JETIR2404H02.pdf

"Electric Vehicles Charging Sessions Classification Technique for Optimized Battery Charge Based on Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 4, page no. ppq10-q15, April-2024, Available at : http://www.jetir.org/papers/JETIR2404H02.pdf