Power grid data quality improvement method based on data correlation

Abstract

The invention provides a power grid data quality improvement method based on data correlation. The power grid data quality improvement method comprises the steps of S1, obtaining a data flow; S2, preprocessing the data; S3, judging whether the data has continuity in time, if yes, skipping to S4, and if not, skipping to S5; S4, judging whether the data has time regularity, if yes, skipping to S6, and if not, skipping to S7; S5, judging whether the missing data scale of the data exceeds a preset threshold value, if yes, skipping to S8, and if not, skipping to S9; S6, complementing the missing data by using the previous corresponding data by using the time correlation; S7, performing interpolation completion on the missing data by utilizing peripheral data of the missing data; S8, directly abandoning the group of data; and S9, carrying out zero setting processing on the missing data. According to the power grid data quality improvement method based on data correlation, the quality of dataacquired by the data sensing equipment of the power Internet-of-things terminal layer can be improved, so that the stability and controllability of data service are ensured.

Description

technical field [0001] The invention relates to the technical field of power grid data quality improvement methods, in particular to a data correlation-based power grid data quality improvement method. Background technique [0002] With the continuous development of ubiquitous power Internet of Things and smart grid technology, the scale of data in the power industry continues to expand, and big data technology has been more widely used in the power field. The popularity of power big data has led to more accurate and intelligent power services in the ubiquitous power Internet of Things environment. At the same time, the big data environment has also brought some problems. Traditional power data has a low dimension and a small amount of data. Daily operation and maintenance and troubleshooting can be achieved by manual work or some simple algorithms. However, the current mass power data is huge in scale and high in dimension. At the same time, due to the increasingly complex...

AI Technical Summary

Problems solved by technology

At the same time, the big data environment has also brought some problems. Traditional power data has a low dimension and a small amount of data. Daily operation and maintenance and troubleshooting can be achieved by manual work or some simple algorithms.

However, the current mass power data is huge in scale and high in dimension. At the same time, due to the increasingly complex power system, abnormal frequency of data collection and network transmission, the quality of power sensing data is difficult to guarantee, and various problems in it are difficult to troubleshoot.