Power utilization behavior electricity theft prevention diagnosis method and device based on dynamic grid outliers

Abstract

The invention discloses a power utilization behavior electricity theft prevention diagnosis method and device based on dynamic grid outliers. The method comprises the steps: obtaining the sampling information of three-phase voltage values (a, b, c) at a current moment from a metering device of a power utilization information collection system, building a data observation matrix based on the sampling information, and calculating the sampling information, an information variance actual measurement value, and an information variance theoretical value; building a first examination function based on residual examination and a second examination function based on the information variance examination according to the sampling information, the information variance actual measurement value and the information variance theoretical value, and respectively calculating a first detection value and a second detection value; and determining a power utilization abnormality of a user when the first detection value is greater than a first preset threshold value and the second detection value is greater than a second preset threshold value. The method solves technical problems in the prior art that the real-time performance is poor and the field inspection efficiency is low, which are caused by a method that a power monitoring department determines a suspected user with the electricity stealing behavior through the changes of a monthly power utilization quantity or the statistics of station line loss.

Description

technical field [0001] The invention relates to the field of data mining, in particular to a method and device for anti-stealing diagnosis of electricity consumption behavior based on dynamic grid outliers. Background technique [0002] Outlier data mining is the main method to solve the electricity stealing behavior diagnosis in the electricity market. Aiming at abnormal electricity stealing behaviors such as voltage or current over-limit and abnormality, flying away and sudden change, and power meter stop and go in the process of electricity consumption, obtain various loads, voltage, current, or electric energy indication value information of on-site acquisition devices, and use the outlier algorithm Abnormalities or faults can be quickly diagnosed. [0003] At present, the main methods based on outlier algorithm are five types of methods based on statistical distribution, based on depth, based on clustering, based on distance and based on density. Each method is applie...

AI Technical Summary

Problems solved by technology

[0006] Embodiments of the present invention provide a method and device for anti-stealing diagnosis of power consumption behavior based on outliers in dynamic grids, so as to at least solve the problem that power monitoring departments in the prior art rely on changes in monthly power consumption of users or statistics on line losses in station areas. The technical problems of poor real-time performance and low efficiency of on-site investigation brought about by methods such as identifying suspected users of electricity theft

Images