Optimizing Lithium-Ion Battery Performance: Integrating Machine Learning and Explainable AI for Enhanced Energy Management
Open Access
- 3 June 2024
- journal article
- research article
- Published by MDPI AG in Sustainability
- Vol. 16 (11) , 4755
Abstract
Managing the capacity of lithium-ion batteries (LiBs) accurately, particularly in large-scale applications, enhances the cost-effectiveness of energy storage systems. Less frequent replacement or maintenance of LiBs results in cost savings in the long term. Therefore, in this study, AdaBoost, gradient boosting, XGBoost, LightGBM, CatBoost, and ensemble learning models were employed to predict the discharge capacity of LiBs. The prediction performances of each model were compared based on mean absolute error (MAE), mean squared error (MSE), and R-squared values. The research findings reveal that the LightGBM model exhibited the lowest MAE (0.103) and MSE (0.019) values and the highest R-squared (0.887) value, thus demonstrating the strongest correlation in predictions. Gradient boosting and XGBoost models showed similar performance levels but ranked just below LightGBM. The competitive performance of the ensemble model indicates that combining multiple models could lead to an overall performance improvement. Furthermore, the study incorporates an analysis of key features affecting model predictions using SHAP (Shapley additive explanations) values within the framework of explainable artificial intelligence (XAI). This analysis evaluates the impact of features such as temperature, cycle index, voltage, and current on predictions, revealing a significant effect of temperature on discharge capacity. The results of this study emphasize the potential of machine learning models in LiB management within the XAI framework and demonstrate how these technologies could play a strategic role in optimizing energy storage systems.Keywords
Funding Information
- European Union’s Horizon Europe research and innovation programme under “Next Generation of Multifunctional, Modular and Scalable Solid State Batteries System” (EXTENDED) (101102278)
This publication has 34 references indexed in Scilit:
- A comprehensive review on ensemble deep learning: Opportunities and challengesJournal of King Saud University Computer and Information Sciences, 2023
- An explainable predictive model for suicide attempt risk using an ensemble learning and Shapley Additive Explanations (SHAP) approachAsian Journal of Psychiatry, 2022
- High electrode performance of hydrothermally developed activated C coated O3–NaFeO2 electrode for Na-ion batteries applicationsCeramics International, 2022
- Explainable Artificial Intelligence (XAI) techniques for energy and power systems: Review, challenges and opportunitiesEnergy and AI, 2022
- Combining empirical mode decomposition and deep recurrent neural networks for predictive maintenance of lithium-ion batteryAdvanced Engineering Informatics, 2021
- A comparative analysis of gradient boosting algorithmsArtificial Intelligence Review, 2020
- Applications of Lithium-Ion Batteries in Grid-Scale Energy Storage SystemsTransactions of Tianjin University, 2020
- Density Functional Theory for Battery MaterialsEnergy & Environmental Materials, 2019
- Capturing lithium-ion battery dynamics with support vector machine-based battery modelJournal of Power Sources, 2015
- A review on the key issues for lithium-ion battery management in electric vehiclesJournal of Power Sources, 2013