Machine Learning Models for Trip-Level Range Forecasting in EVs

Abhishek Devgan

doi:10.5281/zenodo.20348054

Machine Learning Models for Trip-Level Range Forecasting in EVs

Author(s)	Abhishek Devgan
Country	India
Abstract	The Machine learning (ML) and deep learning (DL) solutions to the challenges of predicting electric vehicle (EV) energy consumption and estimating driving range. With battery electric vehicles (BEVs) and plug-in hybrid electric vehicles (PHEVs) spreading across the globe very quickly, the accurate prediction of energy consumption has become an urgent matter to enhance user trust, assist in route optimization, and connect with the smart grid. The wide spectrum of the algorithms including Random Forest (RF), XGBoost, Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), Mixture of Experts (MoE), probabilistic deep learning, and federated learning systems are reported in the review. Critical evaluation of key input features is presented in the research and they are the road topology, traffic conditions, weather parameters, driver behavior, battery state-of-charge (SOC) and vehicle dynamics. The results of both works indicate that ensemble-based and deep-learning-based approaches may be more effective than classical regression models and that the mean error (MAE) may not exceed 2 kWh/100km in the optimum instances with appropriately crafted features. Additionally, new privacy sensitive and communication-efficient ML models are also cited as the future outlooks of scalable fleet deployment.
Keywords	Electric Vehicle, Energy Consumption Prediction, Driving Range Estimation, Machine Learning, Deep Learning, XGBoost, LSTM, Federated Learning, Battery State of Charge, Smart Grid, Route Optimization, Transfer Learning.
Field	Engineering
Published In	Volume 6, Issue 1, January 2025
Published On	2025-01-03
DOI	https://doi.org/10.5281/zenodo.20348054

View / Download PDF File

About IJLRP Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics	Join as a Reviewer Editors & Reviewers Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijlrp.com

International Journal of Leading Research Publication

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Monthly Scholarly International Journal

Machine Learning Models for Trip-Level Range Forecasting in EVs

Share this