Research and application of Power Consumers Behavior Based on K-means

Based on the data of power users in a certain city, this paper adopts K-means clustering algorithm to realize the clustering analysis of power users' monthly load data. According to the cluster of electricity users, the electricity users are roughly divided into different types, such as citizens, merchants, enterprises and factories. A measure standard is introduced to evaluate the reliability of the algorithm. Based on the clustering results of the monthly load curves of power users, it can be found out that the characteristics of power users in the corresponding month. According to these characteristics, this paper can play a guiding role in formulating the corresponding power service strategy for different types of power consumers in power supply companies.