A data storage method and device for power load classification application

Abstract

The invention provides a data storage method and device oriented to the application of electric load classification. The method includes selecting a wavelet basis function to perform multi-resolution decomposition on the preprocessed electric load data to obtain a set of candidate feature wavelet coefficients, and the preprocessed Add label information to the electric load data; select the characteristic wavelet coefficients from the candidate feature wavelet coefficient set, and establish the characteristic model of electric load data; use the characteristic model of electric load data to characterize the electric load data; store the characteristic The processed user charge data. The present invention applies the advantages of wavelet transform to the feature extraction of electric load data, and maintains the original information while compressing and storing the data, which can bring strong support to subsequent applications such as electric load classification; The number of characteristic wavelet coefficients is adjusted, and the optimal and minimum characteristic wavelet coefficients are selected, which improves the efficiency of characterization of electric load data.

Description

technical field [0001] The invention relates to a data characterization technology, in particular to a data storage method and device for application of electric load classification. Background technique [0002] With the advent of the era of big data, organizations and enterprises from all walks of life regard data as an important resource for future development, and invest heavily in the research and development of data collection, transmission and storage technologies. For power grid enterprises, the large amount of data, various types, and high value have become the basic elements to promote the development of companies and society. [0003] Electricity load data are all numerical records, but the amount of data records is large, the records are intensive, the data redundancy is large, and the storage space is high. Its handling, storage, analysis and processing require large-capacity storage and high-performance computing platform support. Therefore, it is necessary to...

AI Technical Summary

Problems solved by technology

[0003] The electricity load data are all numerical records, but the amount of data records is large, the records are intensive, the data redundancy is large, and the storage space is high. Its handling, storage, analysis and processing require large-capacity storage and high-performance computing platform support

Images