Transformer area classification method based on multiple thresholds and KNN

Abstract

The invention provides a transformer area classification method based on multiple thresholds and a KNN, and the method comprises the following steps: A, obtaining transformer area related data which comprises the corresponding relation between a 10kV line and a transformer area, a transformer area name, a transformer area address code, and transformer area outlet voltage data; b, based on the distribution transformer outlet voltage data obtained in the step A, calculating a first classification index of the transformer area by adopting a multi-threshold method; c, according to the first classification index of the transformer area calculated in the step B, performing preliminary classification on the transformer area; d, calculating a second classification index of the transformer area byadopting a KNN algorithm according to the transformer area classification result in the step C; and E, completing court classification according to the court second classification index calculated inthe step D. According to the classification method based on the multiple thresholds and the KNN, the transformer area classification accuracy can be improved, and erroneous judgment and missing judgment are reduced.

Description

technical field [0001] The invention relates to the technical field of distribution station area operation, in particular to a station area classification method based on multi-threshold and KNN. Background technique [0002] The line-change relationship of the distribution network is very important basic data. When the line-change relationship is wrong, it will directly affect the line loss calculation, power outage management and operation and maintenance of the distribution network line. In order to verify the correctness of the line-change relationship, manual methods are traditionally used, but the cost Time-consuming and difficult to guarantee real-time. Distribution network operation will generate a large amount of operation data, which can be used to carry out automatic verification of distribution network line change relationship through analysis and mining of these data. [0003] A very important link in the verification of the distribution network line-change rel...

AI Technical Summary

Problems solved by technology

[0005] Although the above-mentioned patents involve the classification of the station area, they are mainly aimed at the classification of the load and line loss of the station area, and none of them involve the classification of the station area in terms of the correctness of the line change relationship.

Images