Fault location method for distribution networks based on multi-head graph attention networks

被引:0
|
作者
Liang, Lingyu [1 ]
Zhang, Huanming [1 ]
Cao, Shang [1 ]
Zhao, Xiangyu [1 ]
Li, Hanju [1 ]
Chen, Zhiwei [2 ]
机构
[1] China Southern Power Grid Artificial Intelligence, China Southern Power Grid, Digital Grid Res Inst, Guangzhou, Peoples R China
[2] South China Univ Technol, Sch Elect Power Engn, Guangzhou, Peoples R China
来源
关键词
fault location; distribution networks; graph attention networks; graph convolutional networks; smart grids;
D O I
10.3389/fenrg.2024.1395737
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
The precise fault localization holds significant importance in reducing power outage duration and frequency in power systems. The widespread application of synchrophasor measurement technology (PMU) has laid the foundation for achieving accurate fault localization in distribution networks. However, fault localization methods based on PMU often suffer from a significant decrease in accuracy due to topological reconstruction and inaccurate parameters. To address these challenges, this paper proposes a fault location method for distribution networks based on Multi-head Graph Attention Networks (GATs). The proposed method begins by modeling the distribution network as a graph, where nodes represent network components and edges represent the connections between these components. GATs have been employed to learn the underlying relationships between topological structure and electrical characteristics of the distribution network. The results demonstrate that our approach outperforms traditional fault location methods in terms of accuracy and speed. The proposed method achieves high precision which reducing the time required for fault location and enabling faster response times for network maintenance personnel.
引用
收藏
页数:12
相关论文
共 50 条
  • [1] Hybrid graph convolutional networks with multi-head attention for location recommendation
    Zhong, Ting
    Zhang, Shengming
    Zhou, Fan
    Zhang, Kunpeng
    Trajcevski, Goce
    Wu, Jin
    [J]. WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS, 2020, 23 (06): : 3125 - 3151
  • [2] Hybrid graph convolutional networks with multi-head attention for location recommendation
    Ting Zhong
    Shengming Zhang
    Fan Zhou
    Kunpeng Zhang
    Goce Trajcevski
    Jin Wu
    [J]. World Wide Web, 2020, 23 : 3125 - 3151
  • [3] Multi-head multi-order graph attention networks
    Ben, Jie
    Sun, Qiguo
    Liu, Keyu
    Yang, Xibei
    Zhang, Fengjun
    [J]. APPLIED INTELLIGENCE, 2024, 54 (17-18) : 8092 - 8107
  • [4] Bearing fault diagnosis method based on a multi-head graph attention network
    Jiang, Li
    Li, Xingjie
    Wu, Lin
    Li, Yibing
    [J]. MEASUREMENT SCIENCE AND TECHNOLOGY, 2022, 33 (07)
  • [5] Combining Multi-Head Attention and Sparse Multi-Head Attention Networks for Session-Based Recommendation
    Zhao, Zhiwei
    Wang, Xiaoye
    Xiao, Yingyuan
    [J]. 2023 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, IJCNN, 2023,
  • [6] Improving Multi-head Attention with Capsule Networks
    Gu, Shuhao
    Feng, Yang
    [J]. NATURAL LANGUAGE PROCESSING AND CHINESE COMPUTING (NLPCC 2019), PT I, 2019, 11838 : 314 - 326
  • [7] Construction safety predictions with multi-head attention graph and sparse accident networks
    Mostofi, Fatemeh
    Togan, Vedat
    [J]. AUTOMATION IN CONSTRUCTION, 2023, 156
  • [8] Attention-Enhanced Graph Convolutional Networks for Aspect-Based Sentiment Classification with Multi-Head Attention
    Xu, Guangtao
    Liu, Peiyu
    Zhu, Zhenfang
    Liu, Jie
    Xu, Fuyong
    [J]. APPLIED SCIENCES-BASEL, 2021, 11 (08):
  • [9] Research Method for Ship Engine Fault Diagnosis Based on Multi-Head Graph Attention Feature Fusion
    Ai, Zeren
    Cao, Hui
    Wang, Jihui
    Cui, Zhichao
    Wang, Longde
    Jiang, Kuo
    [J]. APPLIED SCIENCES-BASEL, 2023, 13 (22):
  • [10] Multi-head collaborative learning for graph neural networks
    Xu, Haiyun
    Jiang, Bo
    Huang, Lili
    Tang, Jin
    Zhang, Shaojie
    [J]. NEUROCOMPUTING, 2022, 499 : 47 - 53