A Comparative Study of Electric Vehicles Battery State of Charge Estimation Based on Machine Learning and Real Driving Data

Electric vehicles (EVs) are rising in the automotive industry, replacing combustion engines and increasing their global market presence. These vehicles offer zero emissions during operation and more straightforward maintenance. However, for such systems that rely heavily on battery capacity, precise...

Full description

Saved in:
Bibliographic Details
Main Authors: Salma Ariche, Zakaria Boulghasoul, Abdelhafid El Ouardi, Abdelhadi Elbacha, Abdelouahed Tajer, Stéphane Espié
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Journal of Low Power Electronics and Applications
Subjects:
Online Access:https://www.mdpi.com/2079-9268/14/4/59
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846104183158079488
author Salma Ariche
Zakaria Boulghasoul
Abdelhafid El Ouardi
Abdelhadi Elbacha
Abdelouahed Tajer
Stéphane Espié
author_facet Salma Ariche
Zakaria Boulghasoul
Abdelhafid El Ouardi
Abdelhadi Elbacha
Abdelouahed Tajer
Stéphane Espié
author_sort Salma Ariche
collection DOAJ
description Electric vehicles (EVs) are rising in the automotive industry, replacing combustion engines and increasing their global market presence. These vehicles offer zero emissions during operation and more straightforward maintenance. However, for such systems that rely heavily on battery capacity, precisely determining the battery’s state of charge (SOC) presents a significant challenge due to its essential role in lithium-ion batteries. This research introduces a dual-phase testing approach, considering factors like HVAC use and road topography, and evaluating machine learning models such as linear regression, support vector regression, random forest regression, and neural networks using datasets from real-world driving conditions in European (Germany) and African (Morocco) contexts. The results validate that the proposed neural networks model does not overfit when evaluated using the dual-phase test method compared to previous studies. The neural networks consistently show high predictive precision across different scenarios within the datasets, outperforming other models by achieving the lowest mean squared error (MSE) and the highest R<sup>2</sup> values.
format Article
id doaj-art-f2cbaf5cb9834862987bf9f176f0b2e0
institution Kabale University
issn 2079-9268
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Journal of Low Power Electronics and Applications
spelling doaj-art-f2cbaf5cb9834862987bf9f176f0b2e02024-12-27T14:32:42ZengMDPI AGJournal of Low Power Electronics and Applications2079-92682024-12-011445910.3390/jlpea14040059A Comparative Study of Electric Vehicles Battery State of Charge Estimation Based on Machine Learning and Real Driving DataSalma Ariche0Zakaria Boulghasoul1Abdelhafid El Ouardi2Abdelhadi Elbacha3Abdelouahed Tajer4Stéphane Espié5Université Paris-Saclay, ENS Paris-Saclay, CNRS, SATIE, 91110 Gif-sur-Yvette, FranceEngineering Systems and Applications (LISA), Cadi Ayyad University, Marrakech 40000, MoroccoUniversité Paris-Saclay, ENS Paris-Saclay, CNRS, SATIE, 91110 Gif-sur-Yvette, FranceEngineering Systems and Applications (LISA), Cadi Ayyad University, Marrakech 40000, MoroccoEngineering Systems and Applications (LISA), Cadi Ayyad University, Marrakech 40000, MoroccoUniversité Gustave Eiffel, SATIE, 91190 Gif-sur-Yvette, FranceElectric vehicles (EVs) are rising in the automotive industry, replacing combustion engines and increasing their global market presence. These vehicles offer zero emissions during operation and more straightforward maintenance. However, for such systems that rely heavily on battery capacity, precisely determining the battery’s state of charge (SOC) presents a significant challenge due to its essential role in lithium-ion batteries. This research introduces a dual-phase testing approach, considering factors like HVAC use and road topography, and evaluating machine learning models such as linear regression, support vector regression, random forest regression, and neural networks using datasets from real-world driving conditions in European (Germany) and African (Morocco) contexts. The results validate that the proposed neural networks model does not overfit when evaluated using the dual-phase test method compared to previous studies. The neural networks consistently show high predictive precision across different scenarios within the datasets, outperforming other models by achieving the lowest mean squared error (MSE) and the highest R<sup>2</sup> values.https://www.mdpi.com/2079-9268/14/4/59battery electric vehiclesstate of chargeonline estimationreal driving datamachine learningneural networks
spellingShingle Salma Ariche
Zakaria Boulghasoul
Abdelhafid El Ouardi
Abdelhadi Elbacha
Abdelouahed Tajer
Stéphane Espié
A Comparative Study of Electric Vehicles Battery State of Charge Estimation Based on Machine Learning and Real Driving Data
Journal of Low Power Electronics and Applications
battery electric vehicles
state of charge
online estimation
real driving data
machine learning
neural networks
title A Comparative Study of Electric Vehicles Battery State of Charge Estimation Based on Machine Learning and Real Driving Data
title_full A Comparative Study of Electric Vehicles Battery State of Charge Estimation Based on Machine Learning and Real Driving Data
title_fullStr A Comparative Study of Electric Vehicles Battery State of Charge Estimation Based on Machine Learning and Real Driving Data
title_full_unstemmed A Comparative Study of Electric Vehicles Battery State of Charge Estimation Based on Machine Learning and Real Driving Data
title_short A Comparative Study of Electric Vehicles Battery State of Charge Estimation Based on Machine Learning and Real Driving Data
title_sort comparative study of electric vehicles battery state of charge estimation based on machine learning and real driving data
topic battery electric vehicles
state of charge
online estimation
real driving data
machine learning
neural networks
url https://www.mdpi.com/2079-9268/14/4/59
work_keys_str_mv AT salmaariche acomparativestudyofelectricvehiclesbatterystateofchargeestimationbasedonmachinelearningandrealdrivingdata
AT zakariaboulghasoul acomparativestudyofelectricvehiclesbatterystateofchargeestimationbasedonmachinelearningandrealdrivingdata
AT abdelhafidelouardi acomparativestudyofelectricvehiclesbatterystateofchargeestimationbasedonmachinelearningandrealdrivingdata
AT abdelhadielbacha acomparativestudyofelectricvehiclesbatterystateofchargeestimationbasedonmachinelearningandrealdrivingdata
AT abdelouahedtajer acomparativestudyofelectricvehiclesbatterystateofchargeestimationbasedonmachinelearningandrealdrivingdata
AT stephaneespie acomparativestudyofelectricvehiclesbatterystateofchargeestimationbasedonmachinelearningandrealdrivingdata
AT salmaariche comparativestudyofelectricvehiclesbatterystateofchargeestimationbasedonmachinelearningandrealdrivingdata
AT zakariaboulghasoul comparativestudyofelectricvehiclesbatterystateofchargeestimationbasedonmachinelearningandrealdrivingdata
AT abdelhafidelouardi comparativestudyofelectricvehiclesbatterystateofchargeestimationbasedonmachinelearningandrealdrivingdata
AT abdelhadielbacha comparativestudyofelectricvehiclesbatterystateofchargeestimationbasedonmachinelearningandrealdrivingdata
AT abdelouahedtajer comparativestudyofelectricvehiclesbatterystateofchargeestimationbasedonmachinelearningandrealdrivingdata
AT stephaneespie comparativestudyofelectricvehiclesbatterystateofchargeestimationbasedonmachinelearningandrealdrivingdata