Next Article in Journal
A Single-Transmitter Multi-Receiver Wireless Power Transfer System with High Coil Misalignment Tolerance and Variable Power Allocation Ratios
Previous Article in Journal
Energy Efficiency Evaluation of Artificial Intelligence Algorithms
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

A Power Grid Topological Error Identification Method Based on Knowledge Graphs and Graph Convolutional Networks

1
College of Information Science and Engineering, Hohai Univercity, Changzhou 213200, China
2
National Electric Power Dispatching and Control Center of State Grid Corporation of China, Beijing 100032, China
3
State Grid Jiangsu Electric Power Co., Ltd., Nanjing 210024, China
4
State Grid Electric Power Research Institute, Nanjing 211106, China
5
State Grid Corporation of China East China Branch, Shanghai 200120, China
6
College of Computer Science and Software Engineering, Hohai University, Nanjing 211100, China
*
Author to whom correspondence should be addressed.
Electronics 2024, 13(19), 3837; https://doi.org/10.3390/electronics13193837 (registering DOI)
Submission received: 5 September 2024 / Revised: 21 September 2024 / Accepted: 25 September 2024 / Published: 28 September 2024

Abstract

Precise and comprehensive model development is essential for predicting power network balance and maintaining power system analysis and optimization. The development of big data technologies and measurement systems has introduced new challenges in power grid modeling, simulation, and fault prediction. In-depth analysis of grid data has become vital for maintaining steady and safe operations. Traditional knowledge graphs can structure data in graph form, but identifying topological errors remains a challenge. Meanwhile, Graph Convolutional Networks (GCNs) can be trained on graph data to detect connections between entities, facilitating the identification of potential topological errors. Therefore, this paper proposes a method for power grid topological error identification that combines knowledge graphs with GCNs. The proposed method first constructs a knowledge graph to organize grid data and introduces a new GCN model for deep training, significantly improving the accuracy and robustness of topological error identification compared to traditional GCNs. This method is tested on the IEEE 30-bus system, the IEEE 118-bus system, and a provincial power grid system. The results demonstrate the method’s effectiveness in identifying topological errors, even in scenarios involving branch disconnections and data loss.
Keywords: knowledge graph; graph convolutional network (GCN); power grid topological error identification knowledge graph; graph convolutional network (GCN); power grid topological error identification

Share and Cite

MDPI and ACS Style

Fei, S.; Wan, X.; Wu, H.; Shan, X.; Zhai, H.; Gao, H. A Power Grid Topological Error Identification Method Based on Knowledge Graphs and Graph Convolutional Networks. Electronics 2024, 13, 3837. https://doi.org/10.3390/electronics13193837

AMA Style

Fei S, Wan X, Wu H, Shan X, Zhai H, Gao H. A Power Grid Topological Error Identification Method Based on Knowledge Graphs and Graph Convolutional Networks. Electronics. 2024; 13(19):3837. https://doi.org/10.3390/electronics13193837

Chicago/Turabian Style

Fei, Shuyu, Xiong Wan, Haiwei Wu, Xin Shan, Haibao Zhai, and Hongmin Gao. 2024. "A Power Grid Topological Error Identification Method Based on Knowledge Graphs and Graph Convolutional Networks" Electronics 13, no. 19: 3837. https://doi.org/10.3390/electronics13193837

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Article metric data becomes available approximately 24 hours after publication online.
Back to TopTop