Power distribution network fault section positioning method and device based on graph convolutional neural network

Abstract

The invention provides a power distribution network fault section positioning method and device based on a graph convolutional neural network, and relates to the technical field of power grid fault positioning, and the method comprises the steps: obtaining a power distribution network feature model G = (V, E), and constructing a power distribution network positioning network model which comprises an input layer, a hidden layer and an output layer, in the power distribution network characteristic model G = (V, E), V is mainly a load node and a distributed power supply node, and E is a power distribution line and a switch; obtaining a power distribution network node V based on a power distribution network feature model G = (V, E), converting feature data of adjacent edges E of all the nodes V, and merging the converted feature data to a feature vector Nv of the nodes V to obtain node feature data; transmitting the node feature data to a hidden layer; carrying out aggregation in the hidden layer by adopting a GraphSAGE algorithm, and outputting an edge feature vector; the output layer obtains an edge feature vector and extracts an output vector. According to the invention, the application effect of the data with the topological graph structure in the power distribution network can be improved.

Description

technical field [0001] The present invention relates to the technical field of power grid fault location, in particular to a method and device for locating a distribution network fault section based on a graph convolutional neural network. Background technique [0002] Although the proportion of investment in distribution network automation equipment has gradually increased in recent years, a large amount of distribution network operation data has not been effectively utilized due to the lack of effective analysis methods. And due to the rise of new energy, many distributed power sources have been added to the distribution network. After the distribution network fails, the fault location cannot be determined simply according to the traditional fault current direction. The actual fault situation is more complicated and changeable, which increases the fault location. difficulty. Researchers have conducted systematic research on distribution network fault location and accumula...

AI Technical Summary

Problems solved by technology

[0004] The existing traditional fault section location algorithms are all applied to the distribution network with few branches, and it is easy to make mistakes when facing the complex distribution network with many branches. greater impact, and the fact that some faults are located at branch nodes increases the difficulty of section location, and the use of traditional fault section location algorithms is subject to certain restrictions

Artificial intelligence deep learning has shown powerful capabilities in various fields, but it is only suitable for regular image data in Euclidean space, and the application effect for data with topological structure in distribution network is poor

Images