Dynamic Adjacency Matrix-Optimized SGC-DySAT Collaborative Framework: Ultra-Large-Scale Power Grid Topology State Assessment and Efficient Fault Localization
DOI:
https://doi.org/10.52152/4320Keywords:
Dynamic self-attention network, Ultra-large-scale power grid, Fault localization, Sparse topology optimization, Temporal modelingAbstract
Ultra-large-scale power grids present a critical problem: the inherent contradiction between the need for accurate dynamic modeling and the demand for real-time performance in crucial tasks such as topology state assessment and fault location. This paper aims to resolve this challenge by introducing a collaborative method leveraging SGC (Simplified Graph Convolution) and an improved DySAT (Dynamic Self-Attention Network). The core objective is to provide an efficient and precise solution for both rapid topological state evaluation and accurate fault localization in such complex systems. To achieve this, a sparse adjacency matrix is first constructed based on adjacency truncation and Kirchhoff's law dynamic pruning. SGC then quickly outputs topological state evaluation through double-layer graph convolution and time window splicing. Subsequently, when an anomaly is triggered, the improved DySAT is called to locate the fault. This DySAT incorporates dynamic adjacency matrix generation, a timing attenuation mechanism, and multi-head attention optimization to strengthen the coupling of spatiotemporal features. Experiments show that SGC achieves a 0.92 accuracy rate in detecting two-phase short-circuit faults at the node level, with a single inference taking 2.85ms; the improved model achieves a fault localization error of 110.59 meters on the high-voltage line, approximately 21.9% lower than the benchmark DySAT, thereby offering an efficient and accurate solution for smart grid operation and maintenance.
References
N.M. Khoa, M.V. Cuong, H.Q. Cuong, N.T.T. Hieu. Performance comparison of impedance-based fault location methods for transmission line. International Journal of Electrical and Electronic Engineering & Telecommunications, 2022, 11(3), 234-241. DOI: 10.18178/ijeetc.11.3.234-241
Y. Liu, A.K. Singh, J.B. Zhao, A.P.S. Meliopoulos, B. Pal, M.A b.M. Ariff, et al. Dynamic state estimation for power system control and protection. IEEE Transactions on Power Systems, 2021, 36(6), 5909-5921. DOI: 10.1109/TPWRS.2021.3079395
D. Deka, V. Kekatos, G. Cavraro. Learning distribution grid topologies: A tutorial. IEEE Transactions on Smart Grid, 2023, 15(1), 999-1013. DOI: 10.1109/TSG.2023.3271902
R.R. Hossain, Q.H. Huang, R.K. Huang. Graph convolutional network-based topology embedded deep reinforcement learning for voltage stability control. IEEE Transactions on Power Systems, 2021, 36(5), 4848-4851. DOI: 10.1109/TPWRS.2021.3084469
B. Fan, N. Shu, Z.W. Li, F.X. Li. Critical nodes identification for power grid based on electrical topology and power flow distribution. IEEE Systems Journal, 2022, 17(3), 4874-4884. DOI: 10.1109/JSYST.2022.3227632
S.M. Li, A. Pandey, B. Hooi, C. Faloutsos, L. Pileggi. Dynamic graph-based anomaly detection in the electrical grid. IEEE Transactions on Power Systems, 2021, 37(5), 3408-3422. DOI: 10.1109/TPWRS.2021.3132852
B.Z. Ti, G.Y. Li, M. Zhou, J.X. Wang. Resilience assessment and improvement for cyber-physical power systems under typhoon disasters. IEEE Transactions on Smart Grid, 2021, 13(1), 783-794. DOI: 10.1109/TSG.2021.3114512
B. Huang, J.H. Wang. Applications of physics-informed neural networks in power systems-a review. IEEE Transactions on Power Systems, 2022, 38(1), 572-588. DOI: 10.1109/TPWRS.2022.3162473
H. Yin, Z.Q. Wang, Y.B. Liu, Y. Qudaih, D.L. Tang, J. Liu, et al. Operational reliability assessment of distribution network with energy storage systems. IEEE Systems Journal, 2022, 17(1), 629-639. DOI: 10.1109/JSYST.2021.3137979
W.L. Liao, B. Bak-Jensen, J.R. Pillai, Y.L. Wang, Y.S. Wang. A review of graph neural networks and their applications in power systems. Journal of Modern Power Systems and Clean Energy, 2021, 10(2), 345-360. DOI: 10.35833/MPCE.2021.000058
X. Wang, S.Z. Yang, G.P. Adam, H.B. Zhang, W.P. Zuo, J.Y. Wen. DC fault protection algorithms of MMC-HVDC grids: Fault analysis, methodologies, experimental validations, and future trends. IEEE Transactions on Power Electronics, 2021, 36(10), 11245-11264. DOI: 10.1109/TPEL.2021.3071184
Y.X. Liu, N. Zhang, D. Wu, A. Botterud, R. Yao, C.Q. Kang. Searching for critical power system cascading failures with graph convolutional network. IEEE Transactions on Control of Network Systems, 2021, 8(3), 1304-1313. DOI: 10.1109/TCNS.2021.3063333
A. Pandey, S.R. Mohanty. Graph convolutional network based fault detection and identification for low-voltage DC microgrid. Journal of Modern Power Systems and Clean Energy, 2022, 11(3), 917-926. DOI: 10.35833/MPCE.2022.000251
D.Y. Huang, H. Liu, T.S. Bi, Q.X. Yang. GCN-LSTM spatiotemporal-network-based method for post-disturbance frequency prediction of power systems. Global Energy Interconnection, 2022, 5(1), 96-107. DOI: 10.1016/j.gloei.2022.04.008
J.X. Hu, W.H. Hu, J.J. Chen, D. Cao, Z.Y. Zhang, Z. Liu, et al. Fault location and classification for distribution systems based on deep graph learning methods. Journal of Modern Power Systems and Clean Energy, 2022, 11(1), 35-51. DOI: 10.35833/MPCE.2022.000204
A. Presekal, A. Ştefanov, V.S. Rajkumar, P. Palensky. Attack graph model for cyber-physical power systems using hybrid deep learning. IEEE Transactions on Smart Grid, 2023, 14(5), 4007-4020. DOI: 10.1109/TSG.2023.3237011
S.W. Xie, Y. Xu, X.D. Zheng. On dynamic network equilibrium of a coupled power and transportation network. IEEE Transactions on Smart Grid, 2021, 13(2), 1398-1411. DOI: 10.1109/TSG.2021.3130384
D. Cao, J.B. Zhao, J.X. Hu, Y.S. Pei, Q. Huang, Z. Chen, et al. Physics-informed graphical representation-enabled deep reinforcement learning for robust distribution system voltage control. IEEE Transactions on Smart Grid, 2023, 15(1), 233-246. DOI: 10.1109/TSG.2023.3267069
T.Q. Zhao, M. Yue, J.H. Wang. Structure-informed graph learning of networked dependencies for online prediction of power system transient dynamics. IEEE Transactions on Power Systems, 2022, 37(6), 4885-4895. DOI: 10.1109/TPWRS.2022.3153328
E. Mohammadi, M. Alizadeh, M. Asgarimoghaddam, X.Y. Wang, M. G. Simões. A review on application of artificial intelligence techniques in microgrids. IEEE Journal of Emerging and Selected Topics in Industrial Electronics, 2022, 3(4), 878-890. DOI: 10.1109/JESTIE.2022.3198504
Y.P. Deng, L. Wang, H. Jia, X.H. Zhang, Tong Xiangqian. A deep learning method based on bidirectional wavenet for voltage sag state estimation via limited monitors in power system. Energies, 2022, 15(6), 2273-2273. DOI: 10.3390/en15062273
C. Galvez, A. Abur. Fault location in power networks using a sparse set of digital fault recorders. IEEE Transactions on Smart Grid, 2022, 13(5), 3468-3480. DOI: 10.1109/TSG.2022.3168904
Y.Z. Chen, R.A. Jacob, Y.R. Gel, J. Zhang, H.V. Poor. Learning power grid outages with higher-order topological neural networks. IEEE Transactions on Power Systems, 2023, 39(1), 720-732. DOI: 10.1109/TPWRS.2023.3266956
H.Y. Wui, M.H. Wang, Z. Xu, Y.W. Jia. Graph attention enabled convolutional network for distribution system probabilistic power flow. IEEE Transactions on Industry Applications, 2022, 58(6), 7068-7078. DOI: 10.1109/TIA.2022.3202159
Y. Zhang, M. Yue, J.H. Wang, S. Yoo. Multi-agent graph-attention deep reinforcement learning for post-contingency grid emergency voltage control. IEEE Transactions on Neural Networks and Learning Systems, 2024, 35(3), 3340-3350. DOI: 10.1109/TNNLS.2023.3341334
Z. Li, L. Ye, Y.N. Zhao, M. Pei, P. Lu, Y.L. Li, et al. A spatiotemporal directed graph convolution network for ultra-short-term wind power prediction. IEEE Transactions on Sustainable Energy, 2022, 14(1), 39-54. DOI: 10.1109/TSTE.2022.3198816
X.H. Zhan, L. Kou, M.T. Xue, J.L. Zhang, L. Zhou. Reliable long-term energy load trend prediction model for smart grid using hierarchical decomposition self-attention network. IEEE Transactions on Reliability, 2022, 72(2), 609-621. DOI: 10.1109/TR.2022.3174093
A. Ahmadi, M.C. Smith, E.R. Collins, V. Dargahi, S. Jin. Fast Newton-Raphson power flow analysis based on sparse techniques and parallel processing. IEEE Transactions on Power Systems, 2021, 37(3), 1695-1705. DOI: 10.1109/TPWRS.2021.3116182
J.Y. Huang, L. Guan, Y.S. Su, H.C. Yao, M.X. Guo, Z. Zhong. System-scale-free transient contingency screening scheme based on steady-state information: A pooling-ensemble multi-graph learning approach. IEEE Transactions on Power Systems, 2021, 37(1), 294-305. DOI: 10.1109/TPWRS.2021.3097331
J. Kwon, J. Kong, A. Munir. Sparse convolutional neural network acceleration with lossless input feature map compression for resource‐constrained systems. IET Computers & Digital Techniques, 2022, 16(1), 29-43. DOI: 10.1049/cdt2.12038
B. Najafi, S. Parsaeefard, A. Leon-Garcia. Entropy-aware time-varying graph neural networks with generalized temporal hawkes process: Dynamic link prediction in the presence of node addition and deletion. Machine Learning and Knowledge Extraction, 2023, 5(4), 1359-1381. DOI: 10.3390/make5040069
H.H. Alhelou, N. Nagpal, H. Nagpal, P. Siano, M. AL-Numay. Dynamic state estimation for improving observation and resiliency of interconnected power systems. IEEE Transactions on Industry Applications, 2023, 60(2), 2366-2380. DOI: 10.1109/TIA.2023.3341060
H.B. Zhang, W. Xiang, W.X. Lin, J.Y. Wen. Grid forming converters in renewable energy sources dominated power grid: Control strategy, stability, application, and challenges. Journal of Modern Power Systems and Clean Energy, 2021, 9(6), 1239-1256. DOI: 10.35833/MPCE.2021.000257
M. Mansourlakouraj, H. Hosseinpour, H. Livani, M. Benidris. Waveform measurement unit-based fault location in distribution feeders via short-time matrix pencil method and graph neural network. IEEE Transactions on Industry Applications, 2022, 59(2), 2661-2670. DOI: 10.1109/TIA.2022.3231586
X. Chen, G.N. Qu, Y.J. Tang, S. Low, N. Li. Reinforcement learning for selective key applications in power systems: Recent advances and future challenges. IEEE Transactions on Smart Grid, 2022, 13(4), 2935-2958. DOI: 10.1109/TSG.2022.3154718
R.I. Hamilton, P.N. Papadopoulos. Using SHAP values and machine learning to understand trends in the transient stability limit. IEEE Transactions on Power Systems, 2023, 39(1), 1384-1397. DOI: 10.1109/TPWRS.2023.3248941
A. Aligholian, H. Mohsenian-Rad. GraphPMU: Event clustering via graph representation learning using locationally-scarce distribution-level fundamental and harmonic PMU measurements. IEEE Transactions on Smart Grid, 2022, 14(4), 2960-2972. DOI: 10.1109/TSG.2022.3225373
W.Y. Guo, S.J. Liu, L.G. Weng, X.Y. Liang. Power Grid Load Forecasting Using a CNN-LSTM Network Based on a Multi-Modal Attention Mechanism. Applied Sciences, 2025, 15(5). DOI: 10.3390/app15052435
X.X. Yu, Z.G. Zhang, B.P. Tang, M.H. Zhao. A multi-head self-attention autoencoder network for fault detection of wind turbine gearboxes under random loads. Measurement Science and Technology, 2024, 35(8), 086137. DOI: 10.1088/1361-6501/ad4dd4
H.C. Shu, H.M. Liu, Y.T. Tang, X. Su, Y.M. Han, Y. Dai. Fault Identification Method for Measured Travelling Wave of Transmission Line Based on CSCRFAM-Transformer. Protection and Control of Modern Power Systems, 2025, 10(2), 69-82. DOI: 10.23919/PCMP.2023.000322
J. Luo, J.Y. Huang, J.C. Ma, S.Y. Liu. Application of self-attention conditional deep convolutional generative adversarial networks in the fault diagnosis of planetary gearboxes. Proceedings of the Institution of Mechanical Engineers, Part O: Journal of Risk and Reliability, 2024, 238(2), 260-273. DOI: 10.1177/1748006X221147784
M.A. Hasnat, M. Rahnamay‐Naeini. Detecting and locating cyber and physical stresses in smart grids using the k‐nearest neighbour analysis of instantaneous correlation of states. IET Smart Grid, 2021, 4(3), 307-320. DOI: 10.1049/stg2.12030
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Zhengning Pang, Guoyu Zhu, Yang Liang (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
