Electric power data leakage point completion method, apparatus and device, and readable storage medium

Abstract

The invention discloses an electric power data leakage point completion method, which comprises the following steps: traversing to-be-completed electric power data, and querying a position where leakage point data exists; selecting historical power data in a plurality of historical data windows from a historical power database according to a preset window size; performing similarity operation on the historical power data in each historical data window and adjacent data corresponding to the leakage point data, and obtaining the historical data window corresponding to the highest similarity; and according to the historical power data in the historical data window corresponding to the highest similarity, complementing the power data at the position corresponding to the leakage point data. The leakage point data determined according to the approximate historical power data is more accurate and effective, so that the accuracy and the reliability of power information analysis according to the completed power data can be ensured, and the reliable operation of the smart power grid is promoted. The invention further provides an electric power data leakage point complementing apparatus and device and a computer readable storage medium, which have the above beneficial effects.

Description

technical field [0001] The present invention relates to the technical field of power data processing, in particular to a method, device, equipment and computer-readable storage medium for complementing power data leakage points. Background technique [0002] With the full development of my country's smart grid construction, electric power big data has emerged as the times require, and has become an indispensable part of the process of grid intelligence. The basis for supporting the reliable operation of the smart grid is the grid panorama real-time data collection, transmission and storage, as well as the analysis of accumulated massive multi-source power data. In the face of various types and large volumes of structured, semi-structured and unstructured power data, it is inevitable that there will be gaps in varying degrees. Only stable and reliable power data can support upper-level applications based on measurement big data. The existence of data not only affects the ana...

AI Technical Summary

Problems solved by technology

[0003] At present, the commonly used missing data completion method is the interpolation method. The interpolation method includes simple filling, mean filling, random filling, regression model filling, nearest neighbor filling, random forest filling method, etc.; but no matter what kind of filling is used to fill missing data There are more or less limitations in these methods, which lead to poor reliability of the completed power data and affect the reliable operation of the smart grid.

Images