Graph Neural Network-Based Fault Diagnosis in Smart Power Distribution Systems

  • Authors

    • Narendra Karmarkar Mathematician and Computer Scientist, Tata Institute of Fundamental Research, India. Author

    DOI:

    https://doi.org/10.67228/30716357/IJMRSE-2025PII6N4Q

    Published 10-05-2025

  • Graph Neural Network, Smart Power Distribution System, Fault Diagnosis, Smart Grid, Deep Learning, Graph Convolutional Network, Artificial Intelligence, Predictive Maintenance

    Issue

    Vol. 8 No. 2 (2025)

    Section

    Articles

    How to Cite

    Graph Neural Network-Based Fault Diagnosis in Smart Power Distribution Systems. (2025). International Journal of Modern Research in Science & Engineering, 8(2), 01-16. https://doi.org/10.67228/30716357/IJMRSE-2025PII6N4Q

  • Abstract

    Smart power distribution systems integrate advanced sensors, intelligent electronic devices (IEDs), IoT technologies, distributed energy resources, and communication networks to enhance efficiency, reliability, and resilience. However, their increasing complexity creates significant challenges in fault diagnosis due to dynamic network topologies, hidden fault dependencies, and high-dimensional sensor data. Traditional rule-based and signal-processing techniques often struggle to adapt to these complex environments. Graph Neural Networks (GNNs) have emerged as an effective solution by modeling the electrical distribution network as a graph, where nodes represent electrical assets and edges capture their connectivity. GNNs learn both structural and operational information from measurements such as voltage, current, frequency, power flow, and phasor data, enabling accurate fault detection, localization, and classification while reducing feature engineering requirements. This paper reviews recent GNN-based fault diagnosis techniques, discusses their mathematical foundations, identifies current research gaps, and highlights future directions. GNN-driven intelligent diagnostics can significantly improve fault detection accuracy, reduce diagnostic latency, and enhance the reliability and autonomous operation of smart grids.

  • References

    [1] G. Phadke and J. S. Thorp, Computer Relaying for Power Systems. Hoboken, NJ, USA: Wiley, 2009.

    [2] M. Kezunovic, "Smart fault location for smart grids," IEEE Transactions on Smart Grid, vol. 2, no. 1, pp. 11–22, Mar. 2011.

    [3] S. R. Samantaray, "Decision tree-based fault zone identification and fault classification in flexible AC transmission-based transmission line," IET Generation, Transmission & Distribution, vol. 3, no. 5, pp. 425–436, 2009.

    [4] S. Ekici, S. Yildirim, and M. Poyraz, "Energy and entropy-based feature extraction for locating fault on transmission lines by using neural network and wavelet packet decomposition," Expert Systems with Applications, vol. 34, no. 4, pp. 2937–2944, 2008.

    [5] V. N. Vapnik, The Nature of Statistical Learning Theory. New York, NY, USA: Springer, 1995.

    [6] L. Breiman, "Random forests," Machine Learning, vol. 45, no. 1, pp. 5–32, 2001.

    [7] Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," Nature, vol. 521, no. 7553, pp. 436–444, May 2015.

    [8] S. Hochreiter and J. Schmidhuber, "Long short-term memory," Neural Computation, vol. 9, no. 8, pp. 1735–1780, 1997.

    [9] T. N. Kipf and M. Welling, "Semi-supervised classification with graph convolutional networks," in Proc. Int. Conf. Learning Representations (ICLR), 2017.

    [10] P. Velickovic et al., "Graph attention networks," in Proc. Int. Conf. Learning Representations (ICLR), 2018.

    [11] W. L. Hamilton, R. Ying, and J. Leskovec, "Inductive representation learning on large graphs," in Advances in Neural Information Processing Systems (NeurIPS), 2017, pp. 1025–1035.

    [12] Z. Wu, S. Pan, F. Chen, G. Long, C. Zhang, and S. Y. Philip, "A comprehensive survey on graph neural networks," IEEE Transactions on Neural Networks and Learning Systems, vol. 32, no. 1, pp. 4–24, Jan. 2021.

    [13] D. Bienstock, "Electrical transmission system cascading failure models," IEEE Control Systems Magazine, vol. 31, no. 5, pp. 30–43, Oct. 2011.

    [14] G. Phadke and J. S. Thorp, Synchronized Phasor Measurements and Their Applications, 2nd ed. Cham, Switzerland: Springer, 2017.

    [15] X. Chen, K. Hou, B. Xu, H. Jia, and Y. Mu, "Graph neural network-based power system applications: A review," Electric Power Systems Research, vol. 211, Art. no. 108496, 2022.

    [16] Gajula, S. (2024). Cybersecurity risk prediction using graph neural networks. Journal of Information Systems Engineering and Management.

    [17] Gajula, S. (2024). Adaptive zero trust architecture for securing financial microservices. Computer Fraud & Security, 2024(12), 643–655. https://doi.org/10.52710/cfs.845.

    [18] Kaidhapuram, S. R., Al-Akayshee, A. S., D, A., Seknametla, P. R., & M, D. (2025). Temporal convolution network with long short-term memory based predictive diagnosis for personalized healthcare. In 2025 International Conference on Intelligent Computing and Knowledge Extraction (ICICKE) (pp. 1–6). Bengaluru, India. IEEE. https://doi.org/10.1109/ICICKE65317.2025.11136460

    [19] Shashank, A. (2025). AI-Enhanced ETL Processes: Leveraging Artificial Intelligence for Optimized Data Integration Systems. Journal Of Multidisciplinary, 5(8), 219-225.

    [20] Taluri, R. (2024). A Hybrid Data Engineering and Generative AI Architecture for Intelligent Data Governance, Metadata Management, and Automated Data Quality Assessment on AWS. International Journal of Artificial Intelligence, Data Science, and Machine Learning, 5(2), 230-240. https://doi.org/10.63282/3050-9262.IJAIDSML-V5I2P126

    [21] Veershetty, G. (2019). From Legacy Back Office to Intelligent Utility Enterprise a Practitioner Case Study of SAP Cloud Transformation and Utility IT Landscape Modernization. American International Journal of Computer Science and Technology, 1(1), 23-27. https://doi.org/10.63282/3117-5481/AIJCST-V1I1P103

    [22] K. K. Sharma, S. Jeswani and S. T. Bellapukonda, "Enhancing Intrusion Detection Systems Using RNN and CNN Models on Cloud Network Data," 2025 IEEE 2nd International Conference on Communication Engineering and Emerging Technologies (ICoCET), Kuala Lumpur, Malaysia, 2025, pp. 1-4, doi: 10.1109/ICoCET66176.2025.11233064.

  • Downloads