Federated Learning-Based Battery Management System for Privacy-Preserving State-of-Health Estimation in Electric Vehicles

Abstract

The rising adoption of electric vehicles is posing demands for efficient battery management systems to accurately estimate the State-of-Health (SOH) of batteries while ensuring security and privacy of battery information. Traditional machine learning-based solutions in a centralized manner require transmission of the battery information from multiple EVs to the central server and pose threats in terms of privacy and security. The research presents a novel Federated Learning-Based Battery Management System (FL-BMS) to perform privacy-preserving estimation of the SOH of EVs using the framework of federated learning. Quantitative experimental research design was adopted in this research using about 24,000 instances of the battery operational data that were collected from 120 lithium-ion battery cells and are spread across 12 federated clients. The research framework adopts a Long Short-Term Memory (LSTM) neural network along with the Federated Averaging (FedAvg) algorithm to predict battery SOH without the need of transmitting raw battery data. Performance of the models was measured based on prediction accuracy, Mean Absolute Error (MAE), Root Mean Square Error (RMSE), communication cost, and privacy preserving aspects. The federated model presented by this research achieves 97.2% accuracy, 0.028 MAE, and 0.043 RMSE which shows that the performance is at par with centralized learning models. In addition, the proposed federated learning framework reduces the communication cost by 67.4% while avoiding sharing of any raw battery data to completely preserve the privacy of the batteries. Comparisons prove that federated learning framework is a reliable approach to provide a balance among estimation accuracy, computational efficiency, scalability, and cybersecurity. Although the accuracy of centralized learning is slightly better than that of federated learning, federated learning offers more advantages in terms of privacy protection and distributed intelligence.

REFERENCES

[1] B. Azam and S. Mehar, “Performance evaluation of battery management systems in lithium-ion battery-powered electric vehicles,” Journal of Engineering and Computational Intelligence Review, vol. 3, no. 2, pp. 81–95, 2025.

[2] V. S. Naresh, V. S. Sriram, V. J. Krishna, V. D. Chandini, R. N. Sri, K. J. Durga, and V. Poojitha, “Privacy-preserving state of health prediction for electric vehicle batteries: A comprehensive review,” Computers and Electrical Engineering, vol. 118, Art. no. 109416, 2024.

[3] J. Ren, M. Li, Y. Wang, Y. Xin, Y. Yuan, G. Ye, et al., “Advanced battery state monitoring in electric vehicles: A comprehensive review of spatiotemporal dynamics and federated learning approaches,” IEEE Internet of Things Journal, 2026.

[4] A. J. Ghazi, H. H. Abbas, Z. J. Oleiwi, B. Al-Attar, and L. A. Hamdi, “Explainable AI-based battery management system with federated learning for multi-chemistry state-of-health estimation in heterogeneous EV fleets,” International Journal of Advances in Signal and Image Sciences, pp. 716–733, 2026.

[5] J. Li, A. Khalatbarisoltani, Y. Che, Y. Yang, and X. Hu, “Data-secure and privacy-protected electric vehicle battery fault detection using decentralized federated learning with differential privacy,” Energy Storage Materials, Art. no. 104681, 2025.

[6] W. Fang, J. Zhang, X. Lin, J. Hu, L. Huang, and G. Yuan, “A study on data privacy protection in power battery SOH prediction based on federated learning,” Ionics, vol. 31, no. 10, pp. 10579–10595, 2025.

[7] S. Akter, “Exploring the role of artificial intelligence in food waste reduction: Implications for public health, social behavior, and sustainable communities,” Journal of Computational Systems & Engineering Insights, vol. 1, no. 1, pp. 25–36, 2023.

[8] A. Khalatbarisoltani, J. Han, M. Saeed, C. Z. Liu, and X. Hu, “Privacy-preserving integrated thermal and energy management of multi-connected hybrid electric vehicles with federated reinforcement learning,” Applied Energy, vol. 385, Art. no. 125386, 2025.

[9] X. Chen, Z. Chen, M. Zhang, Z. Wang, M. Liu, M. Fu, and P. Wang, “A remaining useful life estimation method based on long short-term memory and federated learning for electric vehicles in smart cities,” PeerJ Computer Science, vol. 9, Art. no. e1652, 2023.

[10] S. T. Hasan, “Natural language processing for employee relations case management: Analyzing workplace complaints, grievances, and investigation narratives in healthcare organizations,” Journal of Computational Systems & Engineering Insights, vol. 1, no. 1, pp. 11–24, 2023.

[11] A. A. Korba, M. A. Bouchiha, and Y. Ghamri-Doudane, “Split multi-task federated learning for battery health and capacity estimation in electric vehicles,” IEEE Transactions on Consumer Electronics, 2026.

[12] T. Wang, Z. Zhang, Y. Tao, and Z. Y. Dong, “Robust state of health estimation for heterogeneous batteries with privacy preserving,” IEEE Transactions on Vehicular Technology, vol. 74, no. 6, pp. 8921–8937, 2025.

[13] O. A. Malik, “Agentic AI deployment in infrastructure-limited environments: Observability gaps, failure modes, and AI governance primitives,” Journal of Engineering and Computational Intelligence Review, vol. 4, no. 1, pp. 1–11, 2026.

[14] A. Karim, “Transforming US food supply chains through Internet of Things technologies: Advancing food safety, quality, and traceability,” Journal of Computational Systems & Engineering Insights, vol. 2, no. 1, pp. 11–22, 2024.

[15] U. Iqbal, S. Bekmez, and F. A. Qurashi, “Operational risk management through machine learning and business intelligence in U.S. businesses,” Spanish Journal of Innovation and Integrity, vol. 54, pp. 239–253, 2026.

[16] I. Alim, R. N. Meghla, T. F. Matin, and T. M. M. H. Prodhan, “A semantic and behavioral AI framework for detecting invoice fraud in automated accounts payable,” International Journal of Science and Research Archive, vol. 19, no. 2, pp. 1356–1380, 2026.

[17] U. Imtiaz, F. Amin, and A. Khan, “Crash2Compromise: CrashGuard-FS for security-aware Linux file updates,” Multidisciplinary Research in Computing Information Systems, vol. 6, no. 2, pp. 294–310, 2026.

[18] U. Iqbal and Y. Bhutto, “Digital transformation through artificial intelligence and advanced business analytics in American operational management,” Journal of Theoretical and Applied Econometrics, vol. 3, no. 1, pp. 37–50, 2026.

[19] M. R. Islam, I. A. Badhan, M. H. Rahman, and M. N. Hasnain, “The economics of global renewable energy supply chains: Opportunities and vulnerabilities for the U.S.,” International Journal of AI, Engineering and Management Studies (IJAIEMS), vol. 1, no. 1, pp. 108–136, 2026.

[20] V. S. Naresh and V. S. Sriram, “PPDNN-SoH: Privacy-preserving deep neural network for sustainable electric vehicle battery state of health prediction,” Neural Computing and Applications, vol. 37, no. 32, pp. 27445–27473, 2025.

[21] F. Amin, “Adaptive cyber risk management framework for critical infrastructures: Integrating IDS, SOC, and CSIRT for resilient threat mitigation,” in International Conference on Data Science, Computation and Security, Cham, Switzerland: Springer Nature Switzerland, 2025, pp. 222–239.

[22] M. A. U. H. Khan, R. Parveen, I. Ahmed, M. H. Milon, and T. A. Khan, “High-accuracy breast cancer diagnosis using neural networks and dimensionality reduction techniques,” in Proc. IEEE 19th Int. Conf. Open Source Syst. Technol. (ICOSST), Piscataway, NJ, USA: IEEE, Dec. 2025, pp. 1–6

[23] X. Chen, X. Wang, and Y. Deng, “Federated learning-based prediction of electric vehicle battery pack capacity using time-domain and frequency-domain feature extraction,” Energy, vol. 319, Art. no. 135002, 2025.

[24] R. Parveen, “Exploring the role of data analytics through digital platforms and IT in promoting transparency and accountability in civil service delivery: Lessons from Bangladesh,” International Journal of Humanities & Social Science Studies (IJHSSS), vol. 11, no. 1, pp. 127–146, 2025, doi: 10.29032/ijhsss.vol.11.issue.01w.015.

[25] M. R. Islam, M. M. Islam, I. A. Badhan, and M. N. Hasnain, “The role of artificial intelligence in carbon pricing policies: Economic and environmental implications,” Journal of Engineering and Computational Intelligence Review, vol. 3, no. 2, pp. 1–19, 2025.

[26] T. Han, S. Yue, P. Yang, R. Zhou, and J. Yu, “Source-free dynamic weighted federated transfer learning for state-of-health estimation of lithium-ion batteries with data privacy,” IEEE Transactions on Power Electronics, vol. 39, no. 11, pp. 15085–15100, 2024.

[27] T. Han, S. Yue, P. Yang, R. Zhou, and J. Yu, “Source-free dynamic weighted federated transfer learning for state-of-health estimation of lithium-ion batteries with data privacy,” IEEE Transactions on Power Electronics, vol. 39, no. 11, pp. 15085–15100, 2024.

[28] V. S. Naresh, V. S. Sriram, and A. Dullam, “Encrypted dynamic RVFLN ensemble learning for privacy-preserving state-of-health prediction in electric vehicle batteries using fully homomorphic encryption CKKS,” Transactions on Emerging Telecommunications Technologies, vol. 37, no. 3, Art. no. e70388, 2026.