Fault Location Technology of DC Control and Protection System Based on Deep Learning

EasyChair Preprint 15067

Abstract

Power systems sometimes experience various types of faults, and fault location in power systems has become increasingly complex with the growing complexity of distribution networks and the diversity of measurement data. This paper proposes a fault location method for power systems based on a Graph Convolutional Neural Network (GCN) and incorporates an attention mechanism to further improve the accuracy and stability of fault location. 

By collecting real power grid data, fault data is simulated for model training and testing. Measurement points are treated as nodes in the graph, and node connections are constructed based on the power grid structure. The GNN is used to interact node information, while a Transformer model with an attention mechanism aggregates and predicts the information. Additionally, the paper compares the proposed model with several existing methods, demonstrating the accuracy and stability of the model for fault location in power systems.

Keyphrases: GCN, deep learning, fault location, power system, transformer

@booklet{EasyChair:15067,
  author    = {Xintong Mao and Zhihan Liu and Yumeng Wang and Huilong Zhao and Yong Lu and Xu Yuan and Rui Jing},
  title     = {Fault Location Technology of DC Control and Protection System Based on Deep Learning},
  howpublished = {EasyChair Preprint 15067},
  year      = {EasyChair, 2024}}