Intelligent substation communication network fault location method based on dynamic spatiotemporal graph association perception

Ligang Ye; Wenzhang Li; Jing Zhao; Yuanyuan Liu

doi:10.4108/ew.10423

Authors

Ligang Ye State Grid Inner Mongolia Eastern Power Co., LTD
Wenzhang Li State Grid Inner Mongolia Eastern Power Co., LTD
Jing Zhao State Grid Inner Mongolia Eastern Power Co., LTD
Yuanyuan Liu State Grid Information and Telecommunication Group Co., LTD

DOI:

https://doi.org/10.4108/ew.10423

Keywords:

Intelligent Substation, Communication Network, Fault Location, Dynamic Graph Neural Network, Spatiotemporal Modeling

Abstract

INTRODUCTION: Accurately locating faults in intelligent substation communication networks is crucial for power grid safety. Existing methods fail to fully capture dynamic fault characteristic evolution and complex dependencies within network topologies

OBJECTIVES: This paper aims to (1) model spatiotemporal fault features in communication networks, (2) enhance fault pattern capture through multi-view learning, and (3) improve fault location accuracy.

METHODS: We propose a multi-view spatiotemporal dynamic graph network. First, a multi-view graph neural network models spatial dependencies via cross-view comparative learning using topological and attribute data. Second, a gated recurrent unit with dynamic time windows extracts temporal evolution trends, focusing on local fault patterns and short-term dependencies.

RESULTS: Evaluations on a 220kV substation communication network show our method achieves higher fault location accuracy versus baselines, effectively capturing spatiotemporal fault characteristics.

CONCLUSION: The proposed framework addresses dynamic fault evolution and topological dependencies, providing a robust solution for intelligent substation fault diagnosis.

Downloads

Download data is not yet available.

References

[1] Li H, Zhang X, Pan H, et al. Research on the reliability of communication networks in intelligent substations. Power Syst Prot Control. 2021;49(9):165-171.

[2] Wang Y, Zhang W, Wang C, et al. Numerical simulation research on electromagnetic response of grounding grid in intelligent substation based on multiple grid division technology. Electr Meas Instrum. 2024;61(12):97-103.

[3] Zhou H, Huang J, Zhang C, et al. GOOSE loop fault diagnosis in intelligent substations based on Petri nets. South Power Syst Technol. 2017;11(6):8-16.

[4] Zhang Y, Cai Z, Long P, et al. Real-time fault diagnosis model and method for communication networks in intelligent substations. Power Syst Technol. 2016;40(6):7-14.

[5] Yang W, Yin K, Bao Y, et al. Power grid fault type identification based on deep belief networks. Electr Power Eng Technol. 2021;40(2):169-177.

[6] Zhou L, Zhou Y, Shen W, et al. Reactive power and voltage optimization control for new power systems based on deep reinforcement learning. Electr Meas Instrum. 2024;61(9):182-189.

[7] Ren B, Li J, Zheng Y, et al. Research on fault location of process-level communication networks in smart substations based on deep neural networks. IEEE Access. 2020;8:109707-109718.

[8] Zhang C, Zheng Y, Lu J, et al. Research on fault location of secondary circuits in intelligent substations based on graph neural networks. Power Syst Prot Control. 2022;50(11):10-20.

[9] Lin Y, Chen N, Cai J. Security control technology for distribution network dispatching data based on multi-source information fusion. Electr Meas Instrum. 2024;61(6):118-132.

[10] Zou D, Hong Z, Dai W, et al. Transformer short-circuit current calculation method based on graph neural networks. J Glob Energy Interconnect. 2024;7(3):303-311.

[11] Wu Z, Pan S, Chen F, et al. A comprehensive survey on graph neural networks. IEEE Trans Neural Netw Learn Syst. 2020;32(1):4-24.

[12] Feng X, Feng X, Zhang Z, et al. Measurement error detection method for intelligent electricity meters based on maximum likelihood method and decision tree. Electr Meas Instrum. 2024;61(12):205-211.

[13] Qi F, Yao W, Zhang C, et al. Fault diagnosis of power communication networks based on convolutional neural networks. Inf Technol. 2023;(6):119-128.

[14] Chen D, Lin Y, Li W, et al. Measuring and relieving the over-smoothing problem for graph neural networks from the topological view. Proc AAAI Conf Artif Intell. 2020;34(4):3438-3445.

[15] Wang H, Chen P, Li N, et al. Bi-level optimal operation of virtual power plants considering multi-type reserve of source-load. Electr Meas Instrum. 2024;61(11):31-39.

[16] Tang H, Liang X, Guo Y, et al. Diffuse and Smooth: Beyond Truncated Receptive Field for Scalable and Adaptive Graph Representation Learning. ACM Trans Knowl Discov Data. 2023;17(5):1-25.

[17] Zhang Q. Research on fault point location method for wired communication networks based on verification twin neural networks. Yangtze Inf Commun. 2024;37(8):169-171.

[18] Lin S, Zhou P, Hu Z, et al. Prototypical graph contrastive learning. IEEE Trans Neural Netw Learn Syst. 2022;35(2):2747-2758.

[19] Xu D, Cheng W, Luo D, et al. Infogcl: Information-aware graph contrastive learning. Adv Neural Inf Process Syst. 2021;34:30414-30425.

[20] Zhu W, Hu Y, Nie Y, et al. Research on power grid false data intrusion detection method based on deep machine learning. Electr Meas Instrum. 2022;61(10):67-73.

[21] Zhou H, Qin Q, Hou J, et al. Deep global semantic structure-preserving hashing via corrective triplet loss for remote sensing image retrieval. Expert Syst Appl. 2024;238:122105.

[22] Aimit A, Bai X, Jiang D, et al. Research on power communication network fault identification and location technology based on Beidou and two-stage. Artif Intell Sci Eng. 2024;(3):75-83.

[23] Cai L, Chen Z, Luo C, et al. Structural temporal graph neural networks for anomaly detection in dynamic graphs. Proc 30th ACM Int Conf Inf Knowl Manag. 2021:3747-3756.

[24] Zhu W, Jiang W, Zhou Z, et al. Research on network security situation awareness method based on power grid dispatching system. Electr Meas Instrum. 2024;61(7):21-27.

[25] Liu Y, Pan S, Wang Y, et al. Anomaly detection in dynamic graphs via transformer. IEEE Trans Knowl Data Eng. 2021;35(12):12081-12094.