Method and system for identifying abnormal industry users and abnormal power utilization behaviors of power system

Abstract

The invention provides a method and a system for identifying abnormal industry users and abnormal power utilization behaviors of a power system. The method comprises the following steps: acquiring power consumption data of each industry; establishing power utilization characteristic index items capable of accurately describing industry characteristics based on the industry characteristics; whereinthe power utilization characteristic index items comprise peak time periods, namely a valley period, valley period power consumption and peak period power consumption; determining user characteristicindex valley and peak load ratios through the power utilization characteristic index items; according to the method, on the basis of establishing power utilization characteristic index items, adopting an AP clustering algorithm to carry out clustering analysis on power utilization behaviors according to industries, and abnormal users with wrong power utilization industry attribute identificationand abnormal power utilization behavior users in the industries are identified through clustering results. According to the method and the system, the number of user clusters is remarkably reduced, the difficulty of electricity consumption abnormity detection and the false alarm rate of electricity stealing detection are correspondingly reduced, and the operation benefit of a power supply enterprise is effectively improved.

Description

technical field [0001] The present invention relates to the field of electric power analysis, and more specifically, relates to a method and system for identifying abnormal industry users and abnormal power consumption behaviors of a power system. Background technique [0002] Under the condition of market economy, in order to seek huge profits, some unscrupulous operators steal electric energy by all means, which disrupts the normal order of power supply and consumption, and directly causes the loss of income of power supply enterprises. Traditionally, electricity theft detection mainly relies on manual screening. The application of smart energy meters has significantly enriched the electricity consumption information of users. In recent years, in engineering applications, it is mainly based on the rules summed up by the experience of the inspectors to monitor the meters' loss of current, undervoltage and other indicators to identify electricity theft. This kind of method ...

AI Technical Summary

Problems solved by technology

In engineering practice, a large number of interference factors can lead to sudden changes in power consumption and load. Taking the sudden change in power consumption as a key indicator to conduct cluster analysis to identify abnormal power consumption behaviors often has the problem of low accuracy and difficulty in meeting application requirements.

Images