Research on Accurate Audit of Defaulting Power Consumption Based on K-Means Multidimensional Overrun Judgment

With the rapid economic growth and the development of science and technology, the power supply is becoming increasingly tight. Some users use electricity in various ways in order to pay less electricity. The sudden increase of load not only increases the pressure of power enterprises to ensure power supply, but also disrupts the normal social order of power supply and consumption, and seriously damages the legitimate rights and interests of power supply enterprises. The traditional method of electricity default investigation has the disadvantages of difficult to check completely and accurately. To solve this problem, this paper based on $\mathbf{K}$ -Means clustering method to cluster analysis of daily frozen electricity data, combined with active power, load current and maximum demand data, to find out the abnormal points of electricity consumption, to form a multidimensional criterion, in order to realize the accurate inspection of the user's defaulted electricity consumption.