Real-Time Anomaly Detection in Smart Grids Using Graph Neural Networks

  • Authors

    • Dr. Muhammad Al-Azar Department of Computer Science, University of Lahore, Lahore, Pakistan. Author

    DOI:

    https://doi.org/10.67228/30713315/IJAIDT-2021PII9E6W

    Published 07-03-2021

  • Smart Grids, Anomaly Detection, Graph Neural Networks (Gnns), Real-Time Monitoring, Fault Detection, Cybersecurity, Temporal Graphs, Machine Learning In Power Systems

    Issue

    Vol. 4 No. 2 (2021)

    Section

    Articles

    How to Cite

    [1]
    M. Al-Azar, “Real-Time Anomaly Detection in Smart Grids Using Graph Neural Networks”, IJAIDT, vol. 4, no. 2, pp. 01–12, Jul. 2021, doi: 10.67228/30713315/IJAIDT-2021PII9E6W.

  • Abstract

    The increasing complexity and scale of smart grids necessitate efficient and accurate real-time anomaly detection mechanisms to ensure grid reliability and security. Traditional detection methods often fall short in capturing the complex spatial and temporal dependencies inherent in smart grid data. This paper proposes a novel approach leveraging Graph Neural Networks (GNNs) to detect anomalies in smart grids by modeling the grid as a graph where nodes represent measurement points and edges represent electrical or communication connections. Our method exploits the graph structure and temporal dynamics to identify anomalies such as faults and cyber-attacks with high accuracy and low latency. Experimental evaluations on real and synthetic datasets demonstrate that the proposed GNN-based framework outperforms conventional machine learning models, offering a scalable and effective solution for real-time anomaly detection in smart grids.

  • References

    [1] A. Y. Ding et al., “Anomaly Detection in Smart Grids: A Review,” IEEE Trans. Smart Grid, vol. 11, no. 5, pp. 3854–3866, 2020.

    [2] W. Han et al., “Graph Neural Networks for Power System Security Analysis: A Survey,” IEEE Trans. Power Syst., vol. 36, no. 6, pp. 5744–5756, 2021.

    [3] T. N. Kipf and M. Welling, “Semi-Supervised Classification with Graph Convolutional Networks,” in ICLR, 2017.

    [4] P. Veličković et al., “Graph Attention Networks,” in ICLR, 2018.

    [5] J. Hamilton, Z. Ying, and J. Leskovec, “Inductive Representation Learning on Large Graphs,” in NeurIPS, 2017.

    [6] Y. Li et al., “Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting,” in AAAI, 2018.

    [7] X. Wu et al., “A Comprehensive Survey on Graph Neural Networks,” IEEE Trans. Neural Netw. Learn. Syst., vol. 32, no. 1, pp. 4–24, 2021.

    [8] M. J. Basu et al., “Cyber-Attack Detection in Smart Grids Using Machine Learning,” IEEE Trans. Ind. Inform., vol. 16, no. 10, pp. 6476–6485, 2020.

    [9] H. Liu et al., “Real-Time Anomaly Detection for Smart Grid Using LSTM,” in IEEE Power & Energy Society General Meeting, 2019.

    [10] S. Scardapane and D. Wang, “Randomness in Neural Networks: An Overview,” Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, vol. 7, no. 2, 2017.

    [11] F. Yu et al., “Temporal Graph Networks for Anomaly Detection in Smart Grid,” IEEE Trans. Cybern., vol. 51, no. 9, pp. 4843–4853, 2021.

    [12] R. Chen et al., “Graph Autoencoders for Anomaly Detection in Power Systems,” IEEE Trans. Power Syst., vol. 36, no. 3, pp. 2681–2691, 2021.

  • Downloads