Reservoir Spiking Neural Networks for Accurate State-of-Charge Estimation in Battery Management Systems

Year 2026, Volume: 10 Issue: 2 , 407 - 417 , 01.05.2026

Muhammad Raihaan Kamarudin , Mohd Syafiq Mispan , Muhammad Noorazlan Shah Zainudin , Hazrina Sofian

https://doi.org/10.31127/tuje.1804828

https://izlik.org/JA94TL84PB

Abstract

The growing integration of electric vehicles and renewable energy systems has heightened the need for efficient and reliable battery management systems (BMS). Accurate state-of-charge (SoC) estimation is a crucial element in maintaining battery performance and longevity, yet conventional model-based and neural network approaches often struggle to capture complex and nonlinear battery dynamics. To address these limitations, this study presents a proof of concept based on a Reservoir Spiking Neural Network (RSNN) designed to improve SoC estimation accuracy through biologically inspired computation. The proposed model combines the temporal processing strength of spiking neural networks with the dynamic memory of reservoir computing, enabling the network to effectively represent temporal dependencies in battery discharge patterns. Different spike encoding strategies were explored to optimise the transformation of continuous battery data into spiking activity. The analysis reveals that population-based encoding enhances prediction accuracy by enriching the internal spiking representation within the reservoir, though it requires slightly higher synaptic activity. Experimental results demonstrate that the RSNN provides competitive SoC estimation performance during critical discharge stages, without a significant increase in training time. These findings establish RSNNs as a promising alternative for SoC estimation, offering improved adaptability, high computational efficiency, and suitability for low-power embedded implementations in advanced BMS applications.

Keywords

Reservoir Spiking Neural Network , State-of-charge prediction , Neuromorphic computing , Battery Management System

Ethical Statement

This research did not involve human participants, animals, or any ethically sensitive data. All experimental procedures were conducted in accordance with institutional and international ethical standards for research integrity and data management.

Supporting Institution

Centre for Research and Innovation Management (CRIM), Universiti Teknikal Malaysia Melaka (UTeM)

Project Number

This project was supported by Grant No. PJP/2024/FTKEK/PERINTIS/SA0015

Thanks

The authors would like to express their sincere gratitude to the Machine Learning and Signal Processing (MLSP) Research Group, Universiti Teknikal Malaysia Melaka (UTeM), for providing the facilities and support necessary to conduct this research.

References

• Ardeshiri, R. R., Balagopal, B., Alsabbagh, A., Ma, C., & Chow, M. Y. (2020). Machine learning approaches in battery management systems: State of the art—Remaining useful life and fault detection. In Proceedings of the 2020 2nd IEEE International Conference on Industrial Electronics for Sustainable Energy Systems (IESES), Cagliari, Italy, 1, 61–66. https://doi.org/10.1109/IESES45645.2020.9210642
• Cicek, M., Gencturk, M., Balci, S., & Sabanci, K. (2022). The modelling, simulation, and implementation of wireless power transfer for an electric vehicle charging station. Turkish Journal of Engineering, 6(3), 223-229. https://doi.org/10.31127/tuje.930933
• Hannan, M. A., Hoque, M. M., Hussain, A., Yusof, Y., & Ker, P. J. (2018). State-of-the-art and energy management system of lithium-ion batteries in electric vehicle applications: Issues and recommendations. IEEE Access, 6, 19362–19378. https://doi.org/10.1109/ACCESS.2018.2817655
• Lipu, M. S. H., Ansari, S., Miah, M. S., Meraj, S. T., Hasan, K., Shihavuddin, A. S. M., Hannan, M. A., Muttaqi, K. M., & Hussain, A. (2022). Deep learning enabled state of charge, state of health and remaining useful life estimation for smart battery management system: Methods, implementations, issues and prospects. Journal of Energy Storage, 55, 105752. https://doi.org/10.1016/j.est.2022.105752
• Kumar, R. R., Bharatiraja, C., Udhayakumar, K., Devakirubakaran, S., Sekar, K. S., & Mihet-Popa, L. (2023). Advances in batteries, battery modeling, battery management system, battery thermal management, SOC, SOH, and charge/discharge characteristics in EV applications. IEEE Access, 11, 105761–105809. https://doi.org/10.1109/ACCESS.2023.3318121
• Rivera-Barrera, J. P., Muñoz-Galeano, N., & Sarmiento-Maldonado, H. O. (2017). SoC estimation for lithium-ion batteries: Review and future challenges. Electronics, 6(4), 102. https://doi.org/10.3390/electronics6040102
• Ali, M. U., Zafar, A., Nengroo, S. H., Hussain, S., Alvi, M. J., & Kim, H. J. (2019). Towards a smarter battery management system for electric vehicle applications: A critical review of lithium-ion battery state of charge estimation. Energies, 12(3), 446. https://doi.org/10.3390/en12030446
• Xu, J., Wang, D., & Jiao, M. (2022). SOC estimation of lithium battery with weighted multi-innovation adaptive Kalman filter algorithm. In Proceedings of the 2022 IEEE 5th International Electrical and Energy Conference (CIEEC), Beijing, China, 624–629. https://doi.org/10.1109/CIEEC54735.2022.9845846
• Shenghao, W. (2021). Improved algorithm combining wavelet transform and Kalman filter for estimating SOC of lithium-ion battery in vehicle. In Proceedings of the 2021 IEEE 2nd International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE), Nanchang, China, 175–179. https://doi.org/10.1109/ICBAIE52039.2021.9390009
• Afandi, A., Sumantri, B., & Windarko, N. A. (2020). Estimation state of charge (SOC) of ultracapacitor based on classical equivalent circuit using extended Kalman filter. In Proceedings of the 2020 International Electronics Symposium (IES), Surabaya, Indonesia, 31–36. https://doi.org/ 10.1109/IES50839.2020.9231736
• Wang, J., & Zhang, Z. (2020). Lithium-ion battery SOC estimation based on weighted adaptive recursive extended Kalman filter joint algorithm. In Proceedings of the 2020 IEEE 8th International Conference on Computer Science and Network Technology (ICCSNT), Dalian, China, 11–15. https://doi.org/ 10.1109/ICCSNT50940.2020.9304993
• Espedal, I. B., Jinasena, A., Burheim, O. S., & Lamb, J. J. (2021). Current trends for state-of-charge (SoC) estimation in lithium-ion battery electric vehicles. Energies, 14(11), 3284. https://doi.org/10.3390/en14113284
• Fan, Y., Chi, Q., Fang, X., Tian, J., Li, M., & Liu, X. (2025). State-of-charge estimation of lithium-ion batteries using an adaptive particle filter based on an improved particle swarm optimization algorithm. IEEE Transactions on Transportation Electrification. https://doi.org/10.1109/TTE.2025.3548636
• Gole, A. C., Aher, P. K., & Patil, S. L. (2023). SOC estimation of a Li-ion battery using deep learning method: A comparative study of LSTM and GRU architecture. In Proceedings of the 2023 11th National Power Electronics Conference (NPEC), Mumbai, India, 1–6. https://doi.org/10.1109/NPEC57805.2023.10384964
• Al-Alawi, M. K., Jaddoa, A., Cugley, J., & Hassanin, H. (2024). A novel enhanced SOC estimation method for lithium-ion battery cells using cluster-based LSTM models and centroid proximity selection. Journal of Energy Storage, 97, 112866. https://doi.org/10.1016/j.est.2024.112866
• Wang, F., Pang, H., Liu, J., Chen, K., & Nan, W. (2023). Lithium-ion battery SOC estimation by integrating electrochemical model with deep learning. In Proceedings of the 2023 3rd New Energy and Energy Storage System Control Summit Forum (NEESSC), Nanjing, China, 418–422. https://doi.org/ 10.1109/NEESSC59976.2023.10349281
• Saravanan, M., Ajaykumar, J., Arun, K. S., Sibhiecharan, S. P., & Ananthan, T. (2024). Lithium-ion battery SoC prediction using deep learning. In Proceedings of the 2024 15th International Conference on Computing Communication and Networking Technologies (ICCCNT), Delhi, India, 1–6. https://doi.org/10.1109/ICCCNT61001.2024.10725170
• Zhang, M., & Wang, Z. (2025). SOC estimation for lithium batteries using a CNN-attention-LSTM model. Journal of Energy Storage, 130, 117479. https://doi.org/10.1016/j.est.2025.117479
• Eren, A., & Doğan, H. (2022). Design and implementation of a cost effective vacuum cleaner robot. Turkish Journal of Engineering, 6(2), 166-177. https://doi.org/10.31127/tuje.830282
• Ulvi, A. (2020). Importance of unmanned aerial vehicles (UAVs) in the documentation of cultural heritage. Turkish Journal of Engineering, 4(3), 104-112. https://doi.org/10.31127/tuje.637050
• Taş, İ. Ç., Bozdoğan, A. M., & Arıca, S. (2025). Application of convolutional neural networks for watermelon detection in UAV aerial images: A case study. Turkish Journal of Engineering, 9(1), 1-11. https://doi.org/10.31127/tuje.1481696
• Guo, W., Fouda, M. E., Eltawil, A. M., & Salama, K. N. (2021). Neural coding in spiking neural networks: A comparative study for robust neuromorphic systems. Frontiers in Neuroscience, 15, 638474. https://doi.org/10.3389/fnins.2021.638474
• Pfeiffer, M., & Pfeil, T. (2018). Deep learning with spiking neurons: Opportunities and challenges. Frontiers in Neuroscience, 12, 409662. https://doi.org/10.3389/fnins.2018.00774
• Wang, H., Li, Y. F., & Zhang, Y. (2023). Bioinspired spiking spatiotemporal attention framework for lithium-ion batteries state-of-health estimation. Renewable and Sustainable Energy Reviews, 188, 113728. https://doi.org/10.1016/j.rser.2023.113728
• George, A. M., Dey, S., Banerjee, D., Mukherjee, A., & Suri, M. (2023). Online time-series forecasting using spiking reservoir. Neurocomputing, 518, 82–94. https://doi.org/10.1016/j.neucom.2022.10.067
• Reis, G., Strange, C., Yadav, M., & Li, S. (2021). Lithium-ion battery data and where to find it. Energy and AI, 5, 100081. https://doi.org/10.1016/j.egyai.2021.100081
• Eşsiz, E. S., Kılıç, V. N., & Oturakçı, M. (2023). Firefly-Based feature selection algorithm method for air pollution analysis for Zonguldak region in Turkey. Turkish Journal of Engineering, 7(1), 17-24. https://doi.org/10.31127/tuje.1005514
• Du, X., Meng, J., Amirat, Y., Gao, F., & Benbouzid, M. (2025). Feature selection strategy optimization for lithium-ion battery state of health estimation under impedance uncertainties. Journal of Energy Chemistry, 101, 87-98. https://doi.org/10.1016/j.jechem.2024.09.032
• Rauf, H., Khalid, M., & Arshad, N. (2023). A novel smart feature selection strategy of lithium-ion battery degradation modelling for electric vehicles based on modern machine learning algorithms. Journal of Energy Storage, 68, 107577. https://doi.org/10.1016/j.est.2023.107577
• Viehweg, J., Walther, D., & Maeder, P. (2025). Temporal convolution derived multi-layered reservoir computing. Neurocomputing, 617, 128938. https://doi.org/10.1016/j.neucom.2024.128938