Scholarlink

Li-ion batteries are an essential and vital component of Electric Vehicles (EVs). SOC estimation of these batteries is critical to ensure optimal vehicle performance and avoid potential safety hazards. SOC variation is highly nonlinear, where machine learning (ML) algorithms are suitable for estimation. This paper presents a comparative analysis of seven different ML algorithms for predicting SOC. The performance of the algorithms is evaluated using Mean Squared Logarithmic Error (MSLE), Adjusted R2 score, Pearson Correlation Coefficient, Geometric Mean Absolute Error, and Theil U Statistic. The results show that random forest regression (RFR), support vector regression (SVR), and K-nearest neighbor (KNN) regression provide better results, with much effort to tuning the algorithm.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Comparative Analysis of SOC Prediction Using Machine Learning Algorithms

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Utsab Bhattacharya,
  • Pradeep Kumar

摘要

Li-ion batteries are an essential and vital component of Electric Vehicles (EVs). SOC estimation of these batteries is critical to ensure optimal vehicle performance and avoid potential safety hazards. SOC variation is highly nonlinear, where machine learning (ML) algorithms are suitable for estimation. This paper presents a comparative analysis of seven different ML algorithms for predicting SOC. The performance of the algorithms is evaluated using Mean Squared Logarithmic Error (MSLE), Adjusted R2 score, Pearson Correlation Coefficient, Geometric Mean Absolute Error, and Theil U Statistic. The results show that random forest regression (RFR), support vector regression (SVR), and K-nearest neighbor (KNN) regression provide better results, with much effort to tuning the algorithm.