Diagnosis method for abnormal line loss of distribution network based on contemporaneous characteristics and improved k-means clustering

Abstract

The invention discloses a method for diagnosing abnormal line loss of a distribution network based on synchronous characteristics and improved K-means clustering, including: 1. Collecting line loss data of a line in the distribution network; Key indicators: real-time line loss rate, average line loss rate and line loss distortion rate in the past 24 hours; step 2, classify the characteristics and causes of abnormal line loss, and initially establish an abnormal line loss diagnosis mode; step 3, adopt improved K-means clustering method to determine the number of clusters, and train the clustering model with a large amount of sample data to obtain the cluster centers; step 4, map the labels of the cluster centers to various abnormal causes; step 5, Finally, according to the clustering center, the real-time line loss data of a line in the newly collected distribution network is automatically diagnosed, and the cause of the abnormality is obtained. The invention can quickly and effectively perform automatic diagnosis on the cause of abnormal line loss in the area.

Description

technical field [0001] The invention belongs to the field of abnormal line loss diagnosis of electric power system, in particular to a method for diagnosing abnormal line loss of distribution network. Background technique [0002] Line loss index, as an important economic and technical index that comprehensively reflects the planning and design, production operation, and economic management of the power system, is the key management and assessment index of the power company. Moreover, this indicator is directly related to the net income and energy utilization rate of the power company, so the management and diagnosis of this indicator are of great significance. [0003] However, my country's current line loss index management and governance are still facing many problems. In terms of line loss management, the professional barriers between the various departments of the power company have not been completely dredged and integrated. There will still be a small number of inco...

AI Technical Summary

Problems solved by technology

[0006] Although the above studies have made great progress in the calculation and prediction of theoretical line loss, the analysis and repair of line loss management, there are few related studies that systematically diagnose and analyze the abnormal causes of line loss management

Images