Electric vehicle battery state of charge estimation using metaheuristic-optimized CatBoost algorithms

State of Charge (SoC) estimation plays a crucial role in battery management systems for electric vehicles, directly impacting their operational efficiency and reliability. This study presents a hybrid approach combining the CatBoost algorithm with metaheuristic optimization techniques to enhance SoC...

Full description

Saved in:
Bibliographic Details
Main Authors: Mohd Herwan Sulaiman, Zuriani Mustaffa, Ahmad Salihin Samsudin, Amir Izzani Mohamed, Mohd Mawardi Saari
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:Franklin Open
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2773186325000830
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849471675946500096
author Mohd Herwan Sulaiman
Zuriani Mustaffa
Ahmad Salihin Samsudin
Amir Izzani Mohamed
Mohd Mawardi Saari
author_facet Mohd Herwan Sulaiman
Zuriani Mustaffa
Ahmad Salihin Samsudin
Amir Izzani Mohamed
Mohd Mawardi Saari
author_sort Mohd Herwan Sulaiman
collection DOAJ
description State of Charge (SoC) estimation plays a crucial role in battery management systems for electric vehicles, directly impacting their operational efficiency and reliability. This study presents a hybrid approach combining the CatBoost algorithm with metaheuristic optimization techniques to enhance SoC estimation accuracy and robustness. The methodology was validated using an extensive dataset collected from 72 real-world driving trips of a BMW i3 (60 Ah), comprising 1053,910 instances of battery and vehicle operation metrics. A comprehensive data preprocessing pipeline was implemented, including missing value treatment, outlier removal, and feature normalization using Min-Max scaling. Three distinct metaheuristic algorithms were investigated: Barnacles Mating Optimizer (BMO), Particle Swarm Optimization (PSO), Genetic Algorithm (GA), and Whale Optimization Algorithm (WOA), each integrated with CatBoost to optimize critical parameters including learning rate, tree depth, regularization, and bagging temperature. Experimental results demonstrate that the BMOCatBoost approach achieved superior performance with best-case metrics of RMSE = 6.1031, MAE = 4.1303, and R² = 0.8211, outperforming both PSOCatBoost, GA-CatBoost, and WOA-CatBoost implementations. The framework's effectiveness was validated through rigorous testing, establishing its potential for real-world electric vehicle applications. This research contributes to the advancement of battery management technology, offering promising implications for electric vehicle energy management and broader energy storage applications.
format Article
id doaj-art-087dcb4e70614e4bb51831f55534c13e
institution Kabale University
issn 2773-1863
language English
publishDate 2025-06-01
publisher Elsevier
record_format Article
series Franklin Open
spelling doaj-art-087dcb4e70614e4bb51831f55534c13e2025-08-20T03:24:44ZengElsevierFranklin Open2773-18632025-06-011110029310.1016/j.fraope.2025.100293Electric vehicle battery state of charge estimation using metaheuristic-optimized CatBoost algorithmsMohd Herwan Sulaiman0Zuriani Mustaffa1Ahmad Salihin Samsudin2Amir Izzani Mohamed3Mohd Mawardi Saari4Faculty of Electrical and Electronics Engineering Technology, Universiti Malaysia Pahang Al-Sultan Abdullah (UMPSA), 26600 Pekan, Pahang, Malaysia; Center for Advanced Industrial Technology (AIT), Universiti Malaysia Pahang Al-Sultan Abdullah (UMPSA), 26600 Pekan, Pahang, Malaysia; Corresponding author.Faculty of Computing, Universiti Malaysia Pahang Al-Sultan Abdullah (UMPSA), 26600 Pekan, Pahang, MalaysiaIonic Materials Team, Faculty of Industrial Sciences & Technology, Universiti Malaysia Pahang Al-Sultan Abdullah (UMPSA), 26300 Gambang, Pahang, MalaysiaFaculty of Electrical and Electronics Engineering Technology, Universiti Malaysia Pahang Al-Sultan Abdullah (UMPSA), 26600 Pekan, Pahang, MalaysiaFaculty of Electrical and Electronics Engineering Technology, Universiti Malaysia Pahang Al-Sultan Abdullah (UMPSA), 26600 Pekan, Pahang, MalaysiaState of Charge (SoC) estimation plays a crucial role in battery management systems for electric vehicles, directly impacting their operational efficiency and reliability. This study presents a hybrid approach combining the CatBoost algorithm with metaheuristic optimization techniques to enhance SoC estimation accuracy and robustness. The methodology was validated using an extensive dataset collected from 72 real-world driving trips of a BMW i3 (60 Ah), comprising 1053,910 instances of battery and vehicle operation metrics. A comprehensive data preprocessing pipeline was implemented, including missing value treatment, outlier removal, and feature normalization using Min-Max scaling. Three distinct metaheuristic algorithms were investigated: Barnacles Mating Optimizer (BMO), Particle Swarm Optimization (PSO), Genetic Algorithm (GA), and Whale Optimization Algorithm (WOA), each integrated with CatBoost to optimize critical parameters including learning rate, tree depth, regularization, and bagging temperature. Experimental results demonstrate that the BMOCatBoost approach achieved superior performance with best-case metrics of RMSE = 6.1031, MAE = 4.1303, and R² = 0.8211, outperforming both PSOCatBoost, GA-CatBoost, and WOA-CatBoost implementations. The framework's effectiveness was validated through rigorous testing, establishing its potential for real-world electric vehicle applications. This research contributes to the advancement of battery management technology, offering promising implications for electric vehicle energy management and broader energy storage applications.http://www.sciencedirect.com/science/article/pii/S2773186325000830Battery state of chargeCatBoost algorithmMachine learningMetaheuristic algorithms
spellingShingle Mohd Herwan Sulaiman
Zuriani Mustaffa
Ahmad Salihin Samsudin
Amir Izzani Mohamed
Mohd Mawardi Saari
Electric vehicle battery state of charge estimation using metaheuristic-optimized CatBoost algorithms
Franklin Open
Battery state of charge
CatBoost algorithm
Machine learning
Metaheuristic algorithms
title Electric vehicle battery state of charge estimation using metaheuristic-optimized CatBoost algorithms
title_full Electric vehicle battery state of charge estimation using metaheuristic-optimized CatBoost algorithms
title_fullStr Electric vehicle battery state of charge estimation using metaheuristic-optimized CatBoost algorithms
title_full_unstemmed Electric vehicle battery state of charge estimation using metaheuristic-optimized CatBoost algorithms
title_short Electric vehicle battery state of charge estimation using metaheuristic-optimized CatBoost algorithms
title_sort electric vehicle battery state of charge estimation using metaheuristic optimized catboost algorithms
topic Battery state of charge
CatBoost algorithm
Machine learning
Metaheuristic algorithms
url http://www.sciencedirect.com/science/article/pii/S2773186325000830
work_keys_str_mv AT mohdherwansulaiman electricvehiclebatterystateofchargeestimationusingmetaheuristicoptimizedcatboostalgorithms
AT zurianimustaffa electricvehiclebatterystateofchargeestimationusingmetaheuristicoptimizedcatboostalgorithms
AT ahmadsalihinsamsudin electricvehiclebatterystateofchargeestimationusingmetaheuristicoptimizedcatboostalgorithms
AT amirizzanimohamed electricvehiclebatterystateofchargeestimationusingmetaheuristicoptimizedcatboostalgorithms
AT mohdmawardisaari electricvehiclebatterystateofchargeestimationusingmetaheuristicoptimizedcatboostalgorithms