Outlier detection-based real-time anti-power-theft monitoring method for power utilization information acquisition system

Abstract

The invention discloses an outlier detection-based real-time anti-power-theft monitoring method for a power utilization information acquisition system. The method comprises the steps of calculating line loss of each zone area according to acquired power data of each zone area, and preliminarily judging whether a zone area in an abnormal power utilization state exists or not; if the line loss of certain zone areas is abnormal, collecting power utilization data of the corresponding zone areas, wherein the power utilization data includes user real-time power utilization data and abnormal event data; selecting reasonable evaluation indexes and building a comprehensive power theft suspicion analysis model in combination with methods of outlier detection, data statistics and the like; and taking data collected by a main station as an input of the model, processing user data through the analysis model and obtaining a user power theft suspicion coefficient, thereby locating a suspected power theft user. According to the method, the deficiency of only manual analysis of massive data is overcome, and the efficiency of an algorithm and the reference value of a detection result are improved.

Description

Technical field [0001] The invention relates to the technical field of power system electricity consumption detection and analysis, and in particular relates to a real-time electricity theft prevention monitoring method for an electricity consumption information acquisition system based on outlier detection. Background technique [0002] Economic development is inseparable from the support of the power industry. Electricity has become a huge driving force for the development of the national economy. However, driven by interests, the means of stealing electricity are emerging one after another, and the increasingly serious phenomenon of stealing electricity has caused the line loss rate to increase year by year, which has a huge impact on the benefits of power supply companies, and also causes huge losses to the national economy. The benefits of normal users are also seriously affected. damage. [0003] In recent years, the research of anti-electricity stealing technology has been ...

AI Technical Summary

Problems solved by technology

However, for the increasingly specialized, high-tech, and concealed stealing behaviors, the existing anti-stealing measures still have certain shortcomings: large limitations, poor real-time performance, poor reliability, and high costs, etc.

[0007] Although the density-based outlier detection algorithm makes up for the shortcomings of other algorithms in identifying local outliers, it also faces the problem of high time complexity and is difficult to apply to large-scale data sets; Different indicators contribute differently to the suspicion of power theft, and the direct use of this algorithm cannot distinguish the importance of different indicators very well, which invisibly reduces the reference value of the detection results

Images