📄 Sciences Methods and Technologies
International Journal (SciMeTech)

Volume 2 · Issue 1 · 2026
ISSN: 3085-5284
A Comparative Study of GRU-Based Architectures for State-of-Health and Remaining Useful Life Estimation in Lithium-Ion Batteries for Renewable Energy Storage
Brahim ZRAIBI, Salah Eddine LOUKILI, Omar LAMMAMRI
Pages 149–154 · Cadi Ayyad University, EST of Safi, LAPSSII Laboratory, Morocco · Hassan First University of Settat, ENSA of Berrehid, Laboratory LAMSAD, Morocco
⬇ PDF
Abstract
Lithium-ion batteries are widely adopted in electric vehicles and renewable energy storage systems due to their high energy density and long cycle life. Accurate prediction of State of Health (SOH) and Remaining Useful Life (RUL) is essential to ensure safety, reliability, and efficient battery management - key factors for accelerating the transition to clean energy and mitigating climate change. In this study, we systematically evaluate and compare the prediction performance of three deep learning architectures: Gated Recurrent Unit (GRU), a hybrid GRU-Deep Neural Network (GRU-DNN), and a hybrid Convolutional Neural Network-GRU-DNN (CNN-GRU-DNN). Experiments are conducted using the publicly available NASA PCoE dataset under consistent preprocessing and training protocols. The results show that the proposed CNN-GRU-DNN model achieves the lowest SOH prediction errors compared to models reported in the literature. Furthermore, compared with non-optimized models, the hybrid CNN-GRU-DNN consistently delivers substantial improvements, confirming its capability to capture both nonlinear features and temporal dependencies. These findings contribute to more reliable battery lifetime prediction, thereby enhancing the viability of renewable energy storage and supporting sustainable development goals.
Keywords: Lithium-ion battery, SOH, RUL, Deep learning, Renewable energy storage, Sustainable energy systems

References

  1. M. Massaoudi, H. Abu-Rub, and A. Ghrayeb, "Advancing Lithium-Ion Battery Health Prognostics With Deep Learning: A Review and Case Study," IEEE Open Journal of Industry Applications, vol. 5, pp. 43–62, 2024, doi: 10.1109/OJIA.2024.3354899.
  2. A. P. Renold and N. S. Kathayat, "Comprehensive Review of Machine Learning, Deep Learning, and Digital Twin Data-Driven Approaches in Battery Health Prediction of Electric Vehicles," IEEE Access, vol. 12, pp. 43984–43999, 2024, doi: 10.1109/ACCESS.2024.3380452.
  3. A. Samanta and S. Williamson, "Machine Learning-based Remaining Useful Life Prediction Techniques for Lithium-ion Battery Management Systems: A Comprehensive Review," IEEJ Journal of Industry Applications, p. 22004793, 2023, doi: 10.1541/ieejjia.22004793.
  4. S. Nazaralizadeh, P. Banerjee, A. K. Srivastava, and P. Famouri, "Battery Energy Storage Systems: A Review of Energy Management Systems and Health Metrics," Mar. 01, 2024, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/en17051250.
  5. B. Zraibi, M. Mansouri, C. Okar, and H. Chaoui, "Online Fault Tolerant RUL Prediction Strategy for Lithium-Ion Batteries Using Machine Learning," IEEE Access, vol. 13, pp. 55727–55739, 2025, doi: 10.1109/ACCESS.2025.3554720.
  6. J. Wang, T. Wen, B. Cai, and C. Roberts, "A high-order strong tracking filter based on a compensated adaptive model for predicting sudden changes in remaining useful life of a lithium-ion battery," J Energy Storage, vol. 88, p. 111494, May 2024, doi: 10.1016/j.est.2024.111494.
  7. H. Liu, Y. Li, L. Luo, and C. Zhang, "A Lithium-Ion Battery Capacity and RUL Prediction Fusion Method Based on Decomposition Strategy and GRU," Batteries, vol. 9, no. 6, Jun. 2023, doi: 10.3390/batteries9060323.
  8. M. Sajjad et al., "A Novel CNN-GRU-Based Hybrid Approach for Short-Term Residential Load Forecasting," IEEE Access, vol. 8, pp. 143759–143768, 2020, doi: 10.1109/ACCESS.2020.3009537.
  9. A. Saxena, B. Bole, M. Daigle, Goebel, and Kai, "Prognostics for Batteries -- Aging Experiments and Modeling," NASA Battery Workshop 2012, 2012.
  10. H. Liu, Y. Li, L. Luo, and C. Zhang, "A Lithium-Ion Battery Capacity and RUL Prediction Fusion Method Based on Decomposition Strategy and GRU," Batteries, vol. 9, no. 6, Jun. 2023, doi: 10.3390/batteries9060323.
  11. J. Qu, F. Liu, Y. Ma, and J. Fan, "A Neural-Network-Based Method for RUL Prediction and SOH Monitoring of Lithium-Ion Battery," IEEE Access, vol. 7, pp. 87178–87191, 2019, doi: 10.1109/ACCESS.2019.2925468.
  12. B. Zraibi, M. Mansouri, and S. E. Loukili, "RUL prediction for lithium-ion batteries using improved-CGD hybrid model," Int J Dyn Control, vol. 13, no. 6, Jun. 2025, doi: 10.1007/s40435-025-01737-z.
  13. B. Zraibi, M. Mansouri, "Advancing Lithium-ion Battery Prognostics: A Novel Deep Learning Framework for Enhanced SOH and RUL Prediction Accuracy," 2024 International Conference on Ubiquitous Networking (UNet), 2025.
  14. L. Zhao, S. Song, P. Wang, C. Wang, J. Wang, and M. Guo, "A MLP-Mixer and mixture of expert model for remaining useful life prediction of lithium-ion batteries," Front Comput Sci, vol. 18, no. 5, Oct. 2024, doi: 10.1007/s11704-023-3277-4.
  15. M. Zhang, W. Chen, J. Yin, and T. Feng, "Health Factor Extraction of Lithium-Ion Batteries Based on Discrete Wavelet Transform and SOH Prediction Based on CatBoost," Energies (Basel), vol. 15, no. 15, Aug. 2022, doi: 10.3390/en15155331.
  16. The Center for Advanced Life Cycle Engineering (CALCE), "Lithium-ion battery experimental data," Jan. 2017.
  17. K. Li and X. Chen, "Machine Learning-Based Lithium Battery State of Health Prediction Research," Applied Sciences (Switzerland), vol. 15, no. 2, Jan. 2025, doi: 10.3390/app15020516.
  18. P. Yang, H. D. Yang, X. B. Meng, C. Song, T. He, J. Cai, Y. Xie, and K. Xu, "Joint evaluation and prediction of SOH and RUL for lithium batteries based on a GBLS booster multi-task model," Journal of Energy Storage, vol. 75, Article 109741, 2024, doi: 10.1016/j.est.2023.109741.
SciMeTech · Volume 2, Issue 1 · 2026 · ISSN 3085-5284