A Machine Learning-Based Real-Time Battery Life estimation and Fair Pricing for EV battery swapping

Dr.Ayesha Ameen, Fariya

Publication Details

Back to Archives

A Machine Learning-Based Real-Time Battery Life estimation and Fair Pricing for EV battery swapping

Dr.Ayesha Ameen, Fariya

DOI: Not available

Year: 2026 | Volume: 26 | Issue: 9

Date of Publication: 2026/09/03
Keywords: Battery swapping station, electric vehicle, machine learning, remaining useful life, XGBoost

Abstract

The increasing adoption of electric vehicles (EVs) has created a growing need for efficient and fair battery management within battery swapping stations, where variations in battery health and degradation can lead to pricing disparities and operational inefficiencies. To address this challenge, a real-time Remaining Useful Life (RUL) estimation framework is developed using the Battery RUL Dataset from Kaggle, which includes parameters such as cycle index, discharge and charging times, voltage characteristics, and time constants that capture battery degradation behavior. Multiple regression algorithms—Random Forest, Lasso, Gradient Boosting, Kernel Ridge, Decision Tree, and XGBoost—are implemented to predict the RUL of EV batteries based on operational and electrical parameters. Among these, XGBoost delivers the highest accuracy with a test RMSE of 3.50, confirming its suitability for precise RUL estimation and fair dynamic pricing in battery swapping stations. To further enhance predictive performance and interpretability, Stacking and Voting Regressors are introduced, achieving RMSE values of 3.039 and 3.329, respectively. Additionally, LIME and SHAP are applied to interpret model outputs and highlight influential features. A Flask-based interface enables real-time input and prediction, supporting transparent, data-driven, and equitable pricing strategies for EV battery swapping systems.

References

[1] Li, X., Ming, F., Hu, J., Xu, Z., Liu, K., Gao, F., & Guan, X. (2025). A Constrained Deep Reinforcement Learning Approach for Charging Scheduling of a Battery Swapping Station. IEEE Transactions on Intelligent Transportation Systems. [2] Shi, P., Ni, G., Jin, R., Wang, H., Wang, J., & Chen, X. (2025). Economic operation optimization for electric heavy-duty truck battery swapping stations considering time-of-use pricing. Processes, 13(7), 2271. [3] Chattopadhyay, A., & Kar, S. (2025, June). Sustainable Operation of EV Battery Swapping Station with Q-Learning Considering Reneging. In 2025 IEEE 101st Vehicular Technology Conference (VTC2025-Spring) (pp. 1-5). IEEE. [4] Sultan, Y. A., Eladl, A. A., Hassan, M. A., & Gamel, S. A. (2025). Enhancing electric vehicle battery lifespan: integrating active balancing and machine learning for precise RUL estimation. Scientific Reports, 15(1), 777. [5] Huang, W., Zhou, T., Ma, J., & Chen, X. (2025). An ensemble model based on fusion of multiple machine learning algorithms for remaining useful life prediction of lithium battery in electric vehicles. Innovations in Applied Engineering and Technology, 1-12. [6] G. Dong, Y. Xu, and Z. Wei, “A hierarchical approach for finite-time H-∞ state-of-charge observer and probabilistic lifetime prediction of lithium-ion batteries,” IEEE Trans. Energy Convers., vol. 37, no. 1, pp. 718–728, Mar. 2022. [7] K. Liu, Y. Shang, Q. Ouyang, and W. D. Widanage, “A data-driven approach with uncertainty quantification for predicting future capacities and remaining useful life of lithium-ion battery,” IEEE Trans. Ind. Electron., vol. 68, no. 4, pp. 3170–3180, Apr. 2021. [8] H. Dong, “Prediction of the remaining useful life of lithium-ion batteries based on Dempster–Shafer theory and the support vector regression particle filter,” IEEE Access, vol. 9, pp. 165490–165503, 2021. [9] J. Hu, L. Weng, Z. Gao, and B. Yang, “State of health estimation and remaining useful life prediction of electric vehicles based on real-world driving and charging data,” IEEE Trans. Veh. Technol., vol. 72, no. 1, pp. 382–394, Jan. 2023. [10] Q. Xu, M. Wu, E. Khoo, Z. Chen, and X. Li, “A hybrid ensemble deep learning approach for early prediction of battery remaining useful life,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 1, pp. 177–187, Jan. 2023. [11] D. Chen, W. Hong, and X. Zhou, “Transformer network for remaining useful life prediction of lithium-ion batteries,” IEEE Access, vol. 10, pp. 19621–19628, 2022. [12] S. Khaleghi, M. S. Hosen, J. Van Mierlo, and M. Berecibar, “Towards machine-learning driven prognostics and health management of li-ion batteries. A comprehensive review,” Renew. Sustain. Energy Rev., vol. 192, Mar. 2024, Art. no. 114224. [13] Z. He, X. Shen, Y. Sun, S. Zhao, B. Fan, and C. Pan, “State-of-health estimation based on real data of electric vehicles concerning user behavior,” J. Energy Storage, vol. 41, Sep. 2021, Art. no. 102867. [14] Y. Li, D.-I. Stroe, Y. Cheng, H. Sheng, X. Sui, and R. Teodorescu, “On the feature selection for battery state of health estimation based on charging–discharging profiles,” J. Energy Storage, vol. 33, Jan. 2021, Art. no. 102122. [15] H. Karlsen, T. Dong, Z. Yang, and R. Carvalho, “Temperature-dependence in battery management systems for electric vehicles: Challenges, criteria, and solutions,” IEEE Access, vol. 7, pp. 142203–142213, 2019.