Smart Grid Fault Detection and Localization Using Machine Learning Techniques
Author(s): Amit R. Kulkarni1, Nilesh V. Tiwari2, Ankit K. Chauhan3
Affiliation: 1,2,3Department of Electrical Engineering, Himalayan Institute of Technology, Dehradun, Uttarakhand, India
Page No: 14-16-
Volume issue & Publishing Year: Volume 2 Issue 2,Feb-2025
Journal: International Journal of Modern Engineering and Management | IJMEM
ISSN NO: 3048-8230
DOI:
Abstract:
The increasing complexity and demand in power distribution systems have made traditional fault detection methods less efficient, often leading to delayed response times and extended outages. Smart grids, equipped with advanced sensing and communication technologies, offer a platform for real-time monitoring and intelligent fault management. This study explores the implementation of machine learning techniques for fault detection and localization in smart grids, aiming to improve reliability, reduce downtime, and enhance energy distribution efficiency. By integrating data-driven models, this approach demonstrates higher accuracy compared to conventional methods and provides scalable solutions for future grid modernization.
Keywords:
Smart Grid, Fault Detection, Machine Learning, Fault Localization, Energy Distribution
Reference:
[1] K. Patel and S. Mehra, “Machine learning for smart grid fault detection: A review,” IEEE Access, vol. 11, no. 2, pp. 3456–3467, 2023.
[2] Y. Zhang et al., “Application of convolutional neural networks in power system fault diagnosis,” Electr. Power Syst. Res., vol. 204, p. 107653, 2022.
[3] R. Singh and A. Das, “Integration of AI with SCADA systems in modern grids,” J. Electr. Eng. Res., vol. 15, no. 4, pp. 210–222, 2023.
[4] X. Li et al., “Fault localization using random forest classifiers in smart grids,” Energy Rep., vol. 8, pp. 1123–1134, 2022.
[5] N. Ahmed and M. Qureshi, “Data-driven approaches to power grid reliability,” Sustain. Energy Syst., vol. 19, no. 1, pp. 56–68, 2023.
[6] V. Kumar et al., “Comparative analysis of machine learning algorithms for grid fault detection,” IET Gener. Transm. Distrib., vol. 15, no. 14, pp. 1872–1883, 2021.
[7] P. Sharma et al., “Role of PMUs in enhancing smart grid resilience,” Int. J. Smart Grid Appl., vol. 10, no. 3, pp. 99–110, 2022.
[8] S. Rao and D. Krishnan, “SCADA and IoT integration in fault-tolerant systems,” Energy Informatics, vol. 4, p. 76, 2021.
[9] H. Wei et al., “Hybrid ML models for smart grid applications,” Appl. Energy, vol. 312, p. 118765, 2023.
[10] J. Thomas and R. George, “Big data analytics for power system monitoring,” IEEE Trans. Smart Grid, vol. 13, no. 5, pp. 3454–3465, 2022.
[11] S. Khan et al., “Predictive fault analysis in renewable integrated grids,” Renew. Energy, vol. 174, pp. 1020–1031, 2021.
[12] A. Banerjee et al., “Machine learning-based predictive maintenance for power distribution,” Energy AI, vol. 14, p. 100224, 2023.
[13] K. Desai and N. Prasad, “Review of intelligent systems in grid fault detection,” Power Syst. Technol. J., vol. 29, no. 6, pp. 455–468, 2022.
[14] Z. Luo et al., “Cybersecurity implications in AI-based smart grid systems,” Electr. Power Components Syst., vol. 51, no. 4, pp. 331–342, 2023.