AI Pipeline Design for Early Fault Detection in Modern Power Grids
DOI:
https://doi.org/10.5281/3xv5j551Keywords:
Smart grid · Fault detection · Data engineering · Artificial intelligence · Supervised learning · Unsupervised learning · Semi-supervised learning,AI Use academic tone with objective, evidence-based arguments, and formal structure; present clarity, rigor, and precise terminology throughout the manuscript.Abstract
Research on smart grids has drawn attention due to the increasing reliance on multiple sources of generation, such as solar and wind farms, and the decentralization of decision-making due to the increase in distributed generators. The implementation of new technologies such as machine learning (ML), available within the framework of artificial intelligence (AI), promises to increase reliability and efficiency by anticipating events and acting before they occur. AI-enabled data engineering pipelines integrate data-processing procedures—such as quality assurance, governance, ingestion, transformation, and preparation—with AI modeling techniques addressing applications such as fault detection and predictive maintenance. These pipelines embed advanced data-processing techniques and tools into a reliable management framework. Smart grids monitor power distribution, detect faults, and feed data, including that from phasor measurement units (PMUs), supervisory control and data acquisition (SCADA), and weather-related sensors.
Data flowing through the pipelines is analyzed in real-time using a fixed library of ML fault-detection models. Fixed models, configured in a lawyer-and-create manner, allow some level of exploration during the training phase of the pipeline. Delays in the deployment of fixed models represent a serious concern for many businesses; the situation is more critical for companies with a mature AI practice—the latency is built into the model and processes association—and is nevertheless significant for business pipelines. Stream processing pipelines execute each processing step as soon as new data arrive for that step. However, model evaluation requires more than a supervised test data set; measures are needed to control the false-positive rate in a business pipeline and assess model robustness against rare events such as blackouts or smaller events such as terminal failures.
References
1. Rafique, F., Fu, L., & Mai, R. (2021). End to end machine learning for fault detection and classification in power transmission lines. Electric Power Systems Research, 199, 107430.
2. Ghaemi, A., Safari, A., Afsharirad, H., & Shayeghi, H. (2021). Accuracy enhance of fault classification and location in a smart distribution network based on stacked ensemble learning. Electric Power Systems Research, 200, 107766.
3. Simões, L. D., Costa, H. J. D., Aires, M. N. O., Medeiros, R. P., Costa, F. B., & Bretas, A. S. (2021). A power transformer differential protection based on support vector machine and wavelet transform. Electric Power Systems Research, 197, 107297.
4. Taha, I. B. M., & Mansour, D. A. (2021). Novel power transformer fault diagnosis using optimized machine learning methods. Intelligent Automation & Soft Computing, 28(3), 739–752.
5. Mattaparthi, R. (2024). Transformer-Based Fault Diagnosis for Large-Scale Standby Power Generators: Partial Discharge Pattern Recognition at Hyperscale Data Center Installations. Journal of Computational Analysis and Applications (JoCAAA), 33(08), 8781-8799.
6. Shabad, P. K. R., Alrashide, A., & Mohammed, O. (2021). Anomaly detection in smart grids using machine learning. In Proceedings of the 47th Annual Conference of the IEEE Industrial Electronics Society.
7. Preethi, G., & Anitha Kumari, K. (2021). An introductory review of anomaly detection methods in smart grids. In Proceedings of the First International Conference on Combinatorial and Optimization.
8. Sahu, A., Mao, Y., & colleagues. (2021). Machine learning applications in power system fault diagnosis: Research advancements and perspectives. Engineering Applications of Artificial Intelligence, 106, 104504.
9. Elmasry, W., & Wadi, M. (2022). EDLA-EFDS: A novel ensemble deep learning approach for electrical fault detection systems. Electric Power Systems Research, 207, 107834.
10. Mohammadi Shakiba, F., Azizi, S. M., Zhou, M., & Abusorrah, A. (2023). Application of machine learning methods in fault detection and classification of power transmission lines: A survey. Artificial Intelligence Review, 56, 5799–5836.
11. Reddy, V. A. R. (2024). Generative Intelligence for Healthcare Claims Processing and Personalized Benefits Management. International Journal of Advanced Engineering Science and Information Technology (IJAESIT), 7(3), 14099.
12. Gutiérrez Rojas, D., Christou, T., Dantas, D., & Narayanan, A. (2022). Performance evaluation of machine learning for fault selection in power transmission lines. Knowledge and Information Systems, 64(2), 427–451.
13. Rodríguez, A., García, M., & colleagues. (2022). A machine learning-based approach for comprehensive fault diagnosis in transmission lines. Computers & Electrical Engineering, 101, 108107.
14. Deng, X., Zhang, Z., Zhu, H., & Yan, K. (2023). Early fault diagnosis of transformer winding based on leakage magnetic field and DSAN learning method. Frontiers in Energy Research, 10, 1058378.
15. Hu, J., Liu, Z., Chen, J., Hu, W., Zhang, Z., & Chen, Z. (2023). A novel deep learning-based fault diagnosis algorithm for preventing protection malfunction. International Journal of Electrical Power & Energy Systems, 144, 108622.
16. Xu, F., Liu, Y., & Wang, L. (2023). An improved ELM-WOA-based fault diagnosis for electric power. Frontiers in Energy Research, 11, 1135741.
17. Jithish, J., Alangot, B., Mahalingam, N., & Yeo, K. S. (2023). Distributed anomaly detection in smart grids: A federated learning-based approach. IEEE Access, 11, 7157–7179.
18. Kolla, S. H., & Peddi, R. K. (2024). Designing Governance-Aligned GenAI Pipelines Using Small Language Models for Enterprise Workflow Intelligence. International Journal of Science, Research and Technology, 7(6), 13256-13268.
19. Dutta, S., Sahu, S. K., Roy, M., & Dutta, S. (2023). A data driven fault detection approach with an ensemble classifier based smart meter in modern distribution system. Sustainable Energy, Grids and Networks, 34, 101012.
20. Alhanaf, A. S., Balik, H. H., & Farsadi, M. (2023). Intelligent fault detection and classification schemes for smart grids based on deep neural networks. Energies, 16(22), 7680.
21. Arif, M., Hasan, M. J., & colleagues. (2023). Fault detection and classification using deep learning method and neuro-fuzzy algorithm in a smart distribution grid. The Journal of Engineering, 2023, 12324.
22. Santamaria-Bonfil, G., Arroyo-Figueroa, G., Zuniga-Garcia, M. A., Azcarraga Ramos, C. G., & Bassam, A. (2024). Power transformer fault detection: A comparison of standard machine learning and autoML approaches. Energies, 17(1), 77.
23. Guato Burgos, M. F., Morato, J., & Vizcaino Imacaña, F. P. (2024). A review of smart grid anomaly detection approaches pertaining to artificial intelligence. Applied Sciences, 14(3), 1194.
24. Najafzadeh, M., Pouladi, J., Daghigh, A., Beiza, J., & Abedinzade, T. (2024). Fault detection, classification and localization along the power grid line using optimized machine learning algorithms. International Journal of Computational Intelligence Systems, 17, 49.
25. Bhagwat, A., Dutta, S., Jadoun, V. K., Veerendra, A. S., & Sahu, S. K. (2024). A customised artificial neural network for power distribution system fault detection. IET Generation, Transmission & Distribution, 18(11), 2105–2118.
26. Sharma, A., & Tiwari, R. (2024). Anomaly detection in smart grid using optimized extreme gradient boosting with SCADA system. Electric Power Systems Research, 235, 110876.
27. Arsoniadis, C. G., & Nikolaidis, V. C. (2024). A machine learning based fault location method for power distribution systems using wavelet scattering networks. Sustainable Energy, Grids and Networks, 40, 101551.
28. Aravind, R. (2024). Integrating controller area network (CAN) with cloud-based data storage solutions for improved vehicle diagnostics using AI. Educational Administration: Theory and Practice, 30(1), 992-1005.
29. Deng, W., Xiong, W., Lu, Z., Yuan, X., Zhang, C., & Wang, L. (2024). Few-shot power transformers fault diagnosis based on Gaussian prototype network. International Journal of Electrical Power & Energy Systems, 160, 110146.
Additional Files
Published
Data Availability Statement
None
Issue
Section
License
Copyright (c) 2025 Luca Bianchi (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons
Attribution 4.0 International License (CC BY 4.0).
You are free to:
- Share: copy and redistribute the material
- Adapt: remix, transform, and build upon the material
for any purpose, even commercially.
Under the following terms:
Attribution — You must give appropriate credit to
the original author(s) and source.
Full license text: https://creativecommons.org/licenses/by/4.0/
