Power consumption behavior pattern classification method based on secondary clustering

Abstract

The invention relates to a power consumption behavior pattern classification method based on secondary clustering. The method mainly comprises three parts. The method comprises the following steps: firstly, identifying and processing abnormal numbers in a large amount of load data by adopting three methods of transverse processing, longitudinal processing and temperature processing; processing data through a moving average method, and reducing noise; and solving the problems of large dimension difference and the like by adopting range normalization processing and weighting processing; secondly, providing the clustering tree and the clustering center of the optimal clustering method for a fuzzy C clustering method for clustering, carrying out effectiveness analysis, and determining the category number; and finally, enabling the clustering analysis to mainly comprise the steps of repeatedly clustering according to the obtained clustering number, restoring data and outputting a clusteringresult. The method is used for solving the problem of classification of the power consumption behavior patterns with a large number of samples and a large number of feature vector dimensions, the sensitivity of a fuzzy C-means clustering method to initial parameters can be avoided, and the clustering effect of accurate and objective classification can be achieved.

Description

technical field [0001] The invention relates to the technical field of cluster analysis of electricity consumption characteristics, in particular to a method for classifying electricity consumption behavior patterns based on secondary clustering. Background technique [0002] With the rapid development of social economy, my country's electricity demand has increased sharply, and the power supply is often in a relatively tense state. At peak load, the contradiction between supply and demand becomes more acute. Blindly increasing the power supply capacity not only requires a lot of investment, but also the asset utilization rate is not high when the load is low. With the advancement of information collection and processing technology, it is of great significance to collect user electricity consumption data, analyze load data based on a large amount of data, classify users with the same electricity consumption characteristics, and analyze their electricity consumption behavior...

AI Technical Summary

Problems solved by technology

[0003] However, the power users are numerous and complex, and it is difficult to analyze each user in detail, and the power consumption behavior of a single user is relatively random

Images