Energy metering data feature reduction method and device based on weighted entropy FCM

Abstract

The invention provides an energy metering data feature reduction method and device based on weighted entropy FCM, relates to the technical field of power system automation, and is technically characterized by comprising the following steps: step 1, acquiring to-be-processed data; 2, performing feature extraction on the data information of the to-be-processed data by adopting a Gaussian mixture model; 3, performing reduction processing on the features extracted in the step 2 based on an FCM function; 4, under the condition that data reduction convergence is determined, completing feature reduction, and quitting execution logic; and under the condition that it is determined that number reduction is not convergent, adopting a weight updating method to remove small features, then executing thestep 3 again, and carrying out reduction processing. According to the method and device, accurate and real-time screening of the feature data is facilitated.

Description

technical field [0001] The invention relates to the technical field of power system automation, in particular to a data feature reduction method and device based on feature weighted entropy FCM. Background technique [0002] The power industry is in the era of digital information, and the amount of information is growing explosively. The era of big data in the power industry is coming. While enjoying the information and convenience brought by informatization, people are also faced with such a huge amount of information. The great challenge to come - the availability of information. Power big data has 4 "V" characteristics, that is, large volume, rapid growth (Velocity), many categories (Variety), and low value (Value). According to the 4 "V" characteristics of electric power big data, in order to obtain decision-making information beneficial to power grid operation from these rapidly generated, multi-source, heterogeneous, and value-thin mass data, it is necessary to proces...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the deficiencies of the prior art, and propose a method and device for reducing energy metering data features based on weighted entropy FCM with high accuracy and good real-time performance, so as to solve the problem that existing data processing methods cannot effectively screen out Technical issues with feature data

Images