Phase identification method based on clustering algorithm and network search

Abstract

The embodiment of the invention discloses a phase recognition method based on a clustering algorithm and network search, and the method comprises the steps: S1, carrying out the data collection, and carrying out the data collection of data of a phase recognition model; s2, performing data processing, processing missing data in the sample data in a data deleting or complementing manner, and removing abnormal values from abnormal data by adopting a 3 sigma criterion; s3, establishing a phase recognition model, judging the connectivity between the samples from the perspective of sample density based on a density-based clustering algorithm DBSCAN, and forming a clustering cluster based on the connectable samples to obtain a final cluster; and S4, performing model evaluation and prediction, performing cross validation on the data set for phase identification model evaluation, finding out optimal parameters of the model, and adding a new data set into the model to perform model prediction. According to the invention, the problems of three-phase imbalance and inaccurate line loss calculation of the existing electric energy meter are solved.

Description

technical field [0001] The embodiment of the present invention relates to the technical field of electric power measurement, in particular to a phase identification method based on clustering algorithm and network search. Background technique [0002] The inaccurate phase of the energy meter makes the distribution load not evenly distributed to each phase, resulting in three-phase imbalance, which reduces the utilization rate of the distribution transformer and makes the line loss remain high. The line loss in the station area is a measure of the line power supply. In order to ensure the accuracy of line loss calculation, the important basic data of efficiency and control of power theft, in the area management, accurate energy meter phase is required as data support. Due to the untimely update of the information of the low-voltage station area, there are problems of inaccurate file phase records and three-phase imbalance in the management of the station area. This situation ...

AI Technical Summary

Problems solved by technology

[0004] For this reason, the embodiment of the present invention provides a phase identification method based on clustering algorithm and network search to solve the problems of three-phase unbalance and inaccurate calculation of line loss in existing electric energy meters

Images