A user identification and discrimination method in station area based on supervised learning

Abstract

The invention relates to the field of data analysis, in particular to a method for identifying and discriminating users in a station area based on a supervised learning method. Including: establishing a training set, a verification set and a test set according to the station area to which the user belongs and the corresponding labels of the user data, which are determined by means of cross-validation; using the trained training model to identify the voltage data of the user to be identified; Establish a quantitative evaluation index for the reliability of the user identification results in the station area, and calculate the reliability of the initial identification result of the user in the station area. The invention realizes the conversion from unsupervised learning to supervised learning, reduces hardware and labor costs, and makes the identification results more reliable; meanwhile, it establishes a quantitative evaluation index for the identification results of the user-to-user relationship in the station area, and realizes the accurate identification of "disputed users" , so as to accurately and effectively identify the user's station area and difference, completely solve the problem of cross-station user attribution, and lay a foundation for comprehensively guiding the work in various fields such as operation, maintenance, emergency repair, technical transformation, and planning of low-voltage station areas.

Description

technical field [0001] The invention relates to the field of data analysis, in particular to a method for identifying and discriminating station area users based on an optimization-based supervised learning method. Background technique [0002] Accurate basic station area files are an important basis for a series of advanced applications such as line loss rate analysis, distribution network fault location, emergency repair work order issuance, and three-phase unbalance analysis. However, due to the late start of my country's power system and the imperfect initial development plan, the distribution of distribution transformers in my country at this stage is scattered and the distribution lines are intricate. At the same time, due to the loss of information records, untimely updates, and incomplete information of the power grid company during the years of operation, the archives of the station area are often inaccurate, that is, a small number of end users have a real connecti...

AI Technical Summary

Problems solved by technology

When the data quality is low, the accuracy of identification is low and the identification result is unreliable

[0007] 3. Although some of the existing technologies can identify the relationship between users more accurately, there are still two major problems: first, there is no quantitative evaluation index for the identification results, so it is not known which users' identification results are reliable and which ones are reliable. The identification results of the users are controversial; secondly, for the "disputed users" whose identification results are not reliable enough, no further strategy is adopted to distinguish the station area and phase they belong to

Images