Distribution network topology verification method based on k-nearest neighbor classification algorithm

Abstract

The invention discloses a distribution network topology verification method based on the k-nearest neighbor classification algorithm, which includes the following steps: (1) Obtain other users in the station area where the verification user is located and all users in its adjacent station areas to form a verification user Training sample set; (2) Extract the voltage curve data of the verification user and all users of the training sample set in the most recent period; (3) Calculate the similarity of the voltage curve between the verification user and each user of the training sample set; (4 ) Select the k nearest neighbors of the verification user based on the similarity, calculate the correct station type of the verification user, and then judge whether the distribution network topology of the verification user is correct. The invention can effectively verify the correctness of the topological structure data of the power distribution network in the GIS platform of the power grid, and has low material and labor costs, high accuracy and good operability.

Description

technical field [0001] The invention relates to the field of distribution network topology verification methods, in particular to a distribution network topology verification method based on a k-nearest neighbor classification algorithm. Background technique [0002] Power grid companies usually use the grid GIS platform to maintain the topological structure data of distribution network equipment, mainly including the connection relationship between power users and transformers in the station area, and the connection relationship between transformers in the station area and feeders. The topological structure of the distribution network plays an important role in 95598 customer repair and positioning, distribution network fault research and judgment, and power outage plan optimization management. At present, there are a large number of errors or deletions in the distribution network topology data of the power grid GIS platform, which is inconsistent with the actual topology s...

AI Technical Summary

Problems solved by technology

[0005] In view of this, the purpose of the present invention is to address the deficiencies of the prior art and provide a distribution network topology verification method based on the k-nearest neighbor classification algorithm to solve the problem of high labor costs and insufficient accuracy of the existing verification methods , the problem of poor operability

Images