Sustainable Energy and Artificial Intelligence

Optimized Hybrid LSTM-XGBoost Technique for Real Time Disturbance Detection in MT-HVDC Systems

Document Type : Original Article

Authors

Reza Talebi 1
Mohammad Hassan Moradi 2
Farhad Namdari 3

1 Department of Electrical Engineering, Faculty of Engineering, Bu-Ali Sina University, Hamedan, Iran.

2 Department of Electrical Engineering, Faculty of Engineering, Bu-Ali Sina University Hamedan, Iran

3 Department of Engineering, Faculty of Environment, Science, and Economy, University of Exeter, Exeter, UK

https://doi.org/10.66224/seai.2601-1040
Abstract
Modern Multi Terminal HVDC (MT HVDC) grids are expanding rapidly with large scale renewable integration, yet disturbance detection still faces challenges in achieving the required speed, adaptability, and selectivity. Recent advances highlight a shift toward data driven approaches that learn disturbance signatures directly from measurements, reducing reliance on handcrafted features, threshold tuning, and complex signal processing pipelines.
This study proposes a hybrid AI based disturbance detection method that integrates a lightweight LSTM network with an XGBoost classifier for real time operation in MT HVDC systems. The method relies solely on voltage measurements sampled at 1 kHz, significantly reducing data rate requirements while preserving the temporal resolution necessary for fast decision making. Voltage waveforms are segmented into 1 ms windows, from which integrated voltage and rate of change features are extracted and encoded into compact temporal embeddings by the LSTM. These embeddings are subsequently classified by XGBoost to provide fast, interpretable, and probabilistic disturbance decisions.
A detailed MT‑HVDC test system was developed in PSCAD to generate a wide range of fault scenarios and operating conditions. Comprehensive benchmarking and multi‑objective hyperparameter optimization identified an efficient single‑layer LSTM with hidden size 8 and batch size 32 as the optimal balance between accuracy and computational efficiency. Results demonstrate strong generalization capability and robust performance under non‑ideal conditions.
Overall, the proposed method offers a scalable, data centric and deployment ready solution that enhances disturbance detection speed, improves fault clearance verification, and contributes to reducing Total Fault Clearance Time in next generation HVDC protection architectures.

Keywords

Disturbance
LSTM
XGBoost
HVDC
Fault, Machine Learning
Artificial Intelligence
Subjects
1. Leterme, W., Pirooz Azad, S., & Van Hertem, D. (2015). Fast breaker failure backup protection for HVDC grids. Proc. IPST 2015, 1-6.
2. Wang, M., Leterme, W., Beerten, J., & Van Hertem, D. (2017, February). Robustness evaluation of fast breaker failure backup protection in bipolar HVDC grids. In 13th IET International Conference on AC and DC Power Transmission (ACDC 2017) (p. 76). Stevenage UK: IET.
3. Li, A., Li, B., Wen, W., Li, B., & Chen, X. (2023). Research on circuit breaker failure protection and the secondary accelerated fault isolation scheme of VSC-HVDC grids. Frontiers in Energy Research, 11, 1211269.
4. Pérez-Molina, M. J., Larruskain, D. M., Eguia, P., & Abarrategi, O. (2021). Circuit breaker failure protection strategy for HVDC grids. Energies, 14(14), 4326.
5. Jawad, R., & Abid, H. (2023). Hvdc fault detection and classification with artificial neural network based on aco-dwt method. energies 2023 16 1064.
6. Huang, N. E., Shen, Z., & Long, S. R. (1999). A new view of nonlinear water waves: The Hilbert spectrum. Annual Review of Fluid Mechanics, 31, 417–457.
7. Zhang, J., Liu, M., Wang, K., & Sun, L. (2015). Mechanical fault diagnosis for HV circuit breakers based on ensemble empirical mode decomposition energy entropy and support vector machine. Mathematical Problems in Engineering, 2015(1), 101757.
8. Leterme, W., Azad, S. P., & Van Hertem, D. (2016). A local backup protection algorithm for HVDC grids. IEEE Transactions on Power Delivery, 31(4), 1767-1775.
9. Flavin, T., Mitra, B., Nagaraju, V., & Meyur, R. (2022). Fault location in high voltage multi-terminal DC networks using ensemble learning. arXiv preprint arXiv:2201.08263.
10. Hazim Hameed Hameed, O., Kutbay, U., Rahebi, J., Hardalaç, F., & Mahariq, I. (2024). Enhancing Fault Detection and Classification in MMC‐HVDC Systems: Integrating Harris Hawks Optimization Algorithm with Machine Learning Methods. International Transactions on Electrical Energy Systems, 2024(1), 6677830.
11. Liang, Y., Zhang, J., Shi, Z., Zhao, H., Wang, Y., Xing, Y., ... & Zhu, H. (2024). A fault identification method of hybrid HVDC system based on wavelet packet energy spectrum and CNN. Electronics, 13(14), 2788.
12. Yousaf, M. Z., Mirsaeidi, S., Khalid, S., Raza, A., Zhichu, C., Rehman, W. U., & Badshah, F. (2023). Multisegmented intelligent solution for MT-HVDC grid protection. Electronics, 12(8), 1766.
13. Eladl, A. A., Saeed, M. A., Sedhom, B. E., & Guerrero, J. M. (2021). IoT technology-based protection scheme for MT-HVDC transmission grids with restoration algorithm using support vector machine. IEEE Access, 9, 86268-86284.
14. Poursaeed, A. H., & Namdari, F. (2025). Explainable AI-driven quantum deep neural network for fault location in DC microgrids. Energies, 18(4), 908.
15. Kong, W., Xu, Y., & Hill, D. J. (2019). Short-term residential load forecasting based on LSTM recurrent neural network IEEE Trans. Smart Grid.
16. Wang, Z., Chen, B., & Liu, Y., (2020). LSTM‑based fault detection in power systems, IEEE Trans. Power Syst., 35(3), 2399–2408.
17. Li, H., Wang, X., & Zhao, J., (2021). End‑to‑end deep learning for HVDC fault identification. Electr. Power Syst. Res., 190, p. 106690.
18. Zhou, Q., Xu, L., & Rao, H., (2022). Deep learning‑based protection for MMC‑HVDC systems. IEEE Trans. Ind. Electron., 69(4), 3452–3463.
19. Pan, S. J., & Yang, Q. (2009). A survey on transfer learning. IEEE Transactions on knowledge and data engineering, 22(10), 1345-1359.
20. Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 25.
21. Niaki, S. H. A., Chen, Z., Bak-Jensen, B., Sharifabadi, K., Liu, Z., & Hu, S. (2024). DC protection criteria for multi-terminal HVDC system considering transient stability of embedded AC grid. International Journal of Electrical Power & Energy Systems, 157, 109815.
22. Radwan, M., & Azad, S. P. (2024). A Fast and Setting-less Breaker Failure Backup Protection Scheme for Multi-terminal HVDC Grids. IEEE Transactions on Power Delivery.
23. Sun, J., Saeedifard, M., & Meliopoulos, A. S. (2018). Backup protection of multi-terminal HVDC grids based on quickest change detection. IEEE Transactions on Power Delivery, 34(1), 177-187.
24. Wang, M., Jovcic, D., Leterme, W., Van Hertem, D., Zaja, M., & Jahn, I. (2019, June). Pre-standardisation of interfaces between DC circuit breaker and intelligent electronic device to enable multivendor interoperability. In Cigrè Aalborg Symposium. Cigre.
25. Wang, M., Zaja, M., Beerten, J., Jovcic, D., & Van Hertem, D. (2020). Backup protection algorithm for failures in modular DC circuit breakers. IEEE Transactions on Power Delivery.
26. Leterme, W., & Van Hertem, D. (2015, May). Classification of fault clearing strategies for HVDC grids. In CIGRE, Date: 2015/05/27-2015/05/28, Location: Lund.
27. Fayazi, M., Saffarian, A., Joorabian, M., & Monadi, M. (2025). An AI-based fault detection and classification method for hybrid parallel HVAC/HVDC overhead transmission lines. Electric Power Systems Research, 238, 111083.
28. Tsotsopoulou, E., Karagiannis, X., Papadopoulos, T., Chrysochos, A., Dyśko, A., & Tzelepis, D. (2023). Protection scheme for multi-terminal HVDC system with superconducting cables based on artificial intelligence algorithms. International Journal of Electrical Power & Energy Systems, 149, 109037.
29. Zeng, S., Liu, C., Zhang, H., Zhang, B., & Zhao, Y. (2025). Short-term load forecasting in power systems based on the Prophet–BO–XGBoost model. Energies, 18(2), 227.
30. Keskar, N. S., et al. (2017). On large-batch training for deep learning: Generalization gap and sharp minima. ICLR.
31. Süpürtülü, M., Hatipoğlu, A., & Yılmaz, E. (2025). An analytical benchmark of feature selection techniques for industrial fault classification leveraging time-domain features. Applied Sciences, 15(3), 1457.
32. Greff, K., Srivastava, R. K., Koutník, J., Steunebrink, B. R., & Schmidhuber, J. (2016). LSTM: A search space odyssey. IEEE transactions on neural networks and learning systems, 28(10), 2222-2232.
33. Deb, K., Pratap, A., Agarwal, S., & Meyarivan, T. A. M. T. (2002). A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE transactions on evolutionary computation, 6(2), 182-197.
34. Bergstra, J., & Bengio, Y. (2012). Random search for hyper-parameter optimization. Journal of Machine Learning Research, 13(Feb), 281–305.
Sustainable Energy and Artificial Intelligence
Volume 2, Issue 2
Spring 2026
Pages 107-119

  • Receive Date 27 January 2026
  • Revise Date 15 February 2026
  • Accept Date 23 February 2026
  • First Publish Date 23 February 2026

Home

Guide for Authors

Submit Manuscript

Reviewers

Contact Us