A comprehensive exploration on different machine learning techniques for state of charge estimation of EV battery

A. T. Mithul Raaj, Justin Ratnam, S. Niranjan Kumar, Tanya Gupta, Keerthi Balaji, C. Rani, M. Rajesh Kumar, Mohamed Farrag

Research output: Chapter in Book/Report/Conference proceedingConference contribution

26 Downloads (Pure)

Abstract

The State of Charge (SoC) is a measurement of the amount of energy available in a battery at a specific interval of time, mostly expressed as percentage. Proportional relationships between the electromotive force of a battery, current, terminal voltage and temperature determine the SoC. There can be a considerable error in the calculations due to a sharp drop of the terminal voltage at the end of discharge. This research has explored how important SoC is, as a factor in Battery Management Systems. The work focuses on using machine learning techniques to obtain an accurate and reliable status of battery charge, this includes Random Forest, Decision Tree, Gradient Boosting, Support Vector Regression, Polynomial Regression and Multilayer Perceptron. In this paper, these techniques are tested and compared with two real world captured datasets of Lithium-ion batteries which includes LG Battery and Unibo Powertools Battery. For supporting this study, statistical methods like K-fold cross validation and Grid Search cross validation techniques are used to estimate the skill of machine learning models. After implementing these techniques, it is found that Random Forest model returns the best Accuracy and Decision Tree returns the least Mean Absolute Error.

Original languageEnglish
Title of host publication2023 58th International Universities Power Engineering Conference (UPEC)
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350316834
ISBN (Print)9798350316841
DOIs
Publication statusPublished - 1 Nov 2023
Event58th International Universities Power Engineering Conference - Technological University Dublin, Dublin, Ireland
Duration: 29 Aug 20231 Sept 2023
https://upec2023.com/ (Link to conference website)

Publication series

Name58th International Universities Power Engineering Conference, UPEC 2023

Conference

Conference58th International Universities Power Engineering Conference
Abbreviated titleUPEC 2023
Country/TerritoryIreland
CityDublin
Period29/08/231/09/23
Internet address

Keywords

  • Battery Management Systems
  • Electric Vehicles Machine Learning
  • Lithium-Ion Batteries
  • State of Charge (SoC)

ASJC Scopus subject areas

  • Artificial Intelligence
  • Energy Engineering and Power Technology
  • Renewable Energy, Sustainability and the Environment
  • Electrical and Electronic Engineering
  • Modelling and Simulation

Fingerprint

Dive into the research topics of 'A comprehensive exploration on different machine learning techniques for state of charge estimation of EV battery'. Together they form a unique fingerprint.

Cite this