Battery performance prediction using supervised learning: a comparative study
- 1Department of Electronics and Communication Engineering, Vels Institute of Science Technology and Advanced Studies
Abstract
Accurate prediction of lithium-ion battery state of charge (SOC) is critical for ensuring safety, durability, and efficient energy management in electric vehicles (EVs). This study presents a systematic comparative analysis of supervised machine learning (ML) models for SOC prediction using the publicly available SiCWell battery dataset. Five regression-based algorithms—Generalized Linear Model (GLM), Gradient Boosting Machine (GBM), Extreme Gradient Boosting (XGBoost), Distributed Random Forest (DRF), and Extremely Randomized Trees (XRT)—are implemented within the H2O framework. The analysis considers six physically measurable battery features derived from voltage, resistance, charge throughput, and current direction. Model performance is evaluated using multiple regression metrics, including MAE, MSE, RMSE, RMSLE, residual deviance, and R², under a consistent train–test evaluation protocol. Results indicate that GLM achieves low prediction errors across both training and testing datasets, suggesting that the selected feature set exhibits a strong linear relationship with SOC within the evaluated operating range. However, ensemble models demonstrate higher variance and sensitivity to hyperparameter configurations, leading to reduced generalization performance. Rather than asserting a universally superior model, this study highlights how dataset characteristics, feature linearity, and model complexity influence SOC prediction accuracy. The findings provide insights into selecting appropriate ML models for battery management systems while emphasizing the importance of dataset transparency, interpretability, and generalization analysis.
Related
- Comparative performance of pre- and post-endoscopic risk scores for outcome prediction in endoscopy-confirmed upper gastrointestinal bleeding in the emergency department : A retrospective single-center study
- Leakage-aware machine learning for data-driven performance prediction of metal–organic framework systems
- Comparative Performance of Oxygenation Indices for Mortality Prediction in Patients With Acute Respiratory Distress Syndrome at a Tertiary Care Intensive Care Unit in Bangladesh.
- Comparative effects of supervised aerobic and combined training with dietary counseling on metabolic biomarkers in sedentary adult male bank employees: a randomized controlled trial
- Machine learning–assisted performance prediction of graphene–silicon twin-port band-notched wideband antenna for THz 6G communication systems
BibTeX
@article{reddy2026battery,
title = {{Battery performance prediction using supervised learning: a comparative study}},
author = {Mandeddu Sudhakar Reddy and M. Monisha},
journal = {Scientific Reports},
year = {2026},
month = aug,
doi = {10.1038/s41598-026-58099-5},
url = {https://doi.org/10.1038/s41598-026-58099-5},
note = {CC BY},
}
RIS
TY - JOUR
TI - Battery performance prediction using supervised learning: a comparative study
AU - Mandeddu Sudhakar Reddy
AU - M. Monisha
PY - 2026
DA - 2026/08/01
JO - Scientific Reports
DO - 10.1038/s41598-026-58099-5
UR - https://doi.org/10.1038/s41598-026-58099-5
AB - Accurate prediction of lithium-ion battery state of charge (SOC) is critical for ensuring safety, durability, and efficient energy management in electric vehicles (EVs). This study presents a systematic comparative analysis of supervised machine learning (ML) models for SOC prediction using the publicly available SiCWell battery dataset. Five regression-based algorithms—Generalized Linear Model (GLM), Gradient Boosting Machine (GBM), Extreme Gradient Boosting (XGBoost), Distributed Random Forest (DRF), and Extremely Randomized Trees (XRT)—are implemented within the H2O framework. The analysis considers six physically measurable battery features derived from voltage, resistance, charge throughput, and current direction. Model performance is evaluated using multiple regression metrics, including MAE, MSE, RMSE, RMSLE, residual deviance, and R², under a consistent train–test evaluation protocol. Results indicate that GLM achieves low prediction errors across both training and testing datasets, suggesting that the selected feature set exhibits a strong linear relationship with SOC within the evaluated operating range. However, ensemble models demonstrate higher variance and sensitivity to hyperparameter configurations, leading to reduced generalization performance. Rather than asserting a universally superior model, this study highlights how dataset characteristics, feature linearity, and model complexity influence SOC prediction accuracy. The findings provide insights into selecting appropriate ML models for battery management systems while emphasizing the importance of dataset transparency, interpretability, and generalization analysis.
SN - 2045-2322
ER -