Multi-source data error correction processing method and system based on arbitrary division of power grid

Abstract

The invention discloses a multi-source data error correction processing method and system based on the arbitrary division of the power grid. The method includes: processing the line loss data of the same period based on the big data Kettle tool to obtain data at each level; automatic layout based on the grid Algorithm and orthogonal automatic layout algorithm to complete automatic graphing; on the basis of theoretical line loss calculation of the power grid, segment the power grid; according to the cluster analysis method, determine the clustering factor set that affects the line loss rate; use positive and negative correlation The analysis method analyzes the data of the power grid to determine the abnormal data; locates the abnormal data of the power grid and divides them, and uses the multi-source data error correction method in the arbitrary division of the power grid, combined with the power flow calculation method, to correct the abnormal data of the power grid; according to the data correction results, Record the abnormal data correction process of the power grid, and provide abnormal data error correction processing work orders. The invention improves the data quality by utilizing the multi-source data error correction method of any divided area.

Description

technical field [0001] The present application relates to the technical field of data processing, and in particular to a method and system for error correction and processing of multi-source data based on arbitrarily divided areas of the power grid. Background technique [0002] At present, the traditional power data restoration methods mainly include missing data processing and inconsistent data processing. Among them, missing data processing includes single filling method and multiple filling method. The single filling method is to fill the missing value with a single substitute value. Common methods include average or median filling method, regression filling method, maximum expectation filling method, etc. However, the single-value imputation method often cannot reflect the uncertainty of the original data set, which may cause large deviations. The multiple imputation method is to use multiple values ​​to fill, and then analyze them with the method for the complete data...

AI Technical Summary

Problems solved by technology

[0003] It can be seen from this that using traditional data repair methods, whether it is missing data processing methods or inconsistent data processing methods, cannot achieve accurate data governance, and even requires manual intervention. For massive power grid data, roughly Data governance methods can no longer meet the requirements of power grid lean management analysis

In addition, using the traditional data repair method, it is impossible to artificially select the area of ​​interest for data error correction management, and only for designated areas or specific voltage levels.

Images