Line loss multi-source diagnosis method and system based on correlation analysis

Abstract

The invention provides a line loss multi-source diagnosis method and system based on correlation analysis. The method comprises following steps of according to acquired basic device information, acquisition information and connection information of a power grid, analyzing key factors influencing line losses so as to obtain a multi-factor clustering analysis result; inputting a multi-data source set, carrying out source end system long link transmission, by use of a preset diagnosis rule, carrying out multi-source connection diagnosis and outing a multi-source connection diagnosis result; setting a line loss rate index abnormal threshold, and using a correlation coefficient method to carry out dynamic diagnosis on wiring and line loss index abnormities in courts; and according to the multi-factor clustering analysis result and the multi-source connection diagnosis result, by combining a physical solid-state factor and a dynamic statistical factor influencing the line losses, carrying out correlation analysis composite diagnosis on the line losses of the power grid. According to the invention, line loss management efficiency of source end service departments of the power grid can beeffectively improved.

Description

technical field [0001] The invention relates to the technical field of comprehensive diagnosis of power grid line loss, in particular to a multi-source diagnosis method and system for line loss based on correlation analysis. Background technique [0002] Cluster analysis refers to the analytical process of grouping a collection of physical or abstract objects into multiple classes consisting of similar objects. Clustering originates from many fields and collects data to classify on the basis of similarity. These technical methods are used to describe data, measure the similarity between different data sources, and classify data sources into different clusters. The correlation coefficient is a statistical indicator used to reflect the closeness of the correlation between variables. The correlation coefficient is calculated by the product difference method, which is also based on the deviation of the two variables from their respective average values, and the degree of correl...

AI Technical Summary

Problems solved by technology

However, in the field of electric power, there are many factors that affect power grid line loss. Currently, the diagnosis method for power grid line loss is relatively simple, and it cannot be combined with physical solid-state factors and dynamic statistical factors for comprehensive diagnosis of power grid line loss. Therefore, the power grid source business department The efficiency of line loss management is low, that is, the level of line loss management is not high

Images