Electricity stealing user identification method and device combining cloud end and side end

Abstract

The invention discloses an electricity larceny user identification method and device combining a cloud end and a side end, and the method comprises the steps: responding to the historical electricity utilization data of a user at the side end and the electricity larceny record of a terminal device, extracting an electricity larceny identification evaluation index and an electricity larceny label, and enabling a training data set to be formed; training a combined classification model based on the training data set, wherein the combined classification model is a combined model based on a LightGBM sub-model and a neural network sub-model; and inputting real-time power consumption data of a certain user into the combined classification model, and outputting an electricity stealing suspicion coefficient of the certain user, so that an electricity stealing suspicion user is determined. According to the technical scheme of the invention, the side end server preprocesses the data and generates the electricity larceny identification label, the calculation burden of the cloud server is reduced, the calculation efficiency and the detection efficiency are improved, and a combined model of the LightGBM model and the BP neural network is adopted, so that the calculation speed is increased, and the classification accuracy is improved.

Description

technical field [0001] The invention belongs to the technical field of power grid anti-stealing, and in particular relates to a method and device for identifying electricity-stealing users combining cloud and edge terminals. Background technique [0002] With the acceleration of my country's modernization, the country's energy consumption is also increasing, especially the demand for electricity is increasing year by year. In this context, some criminals steal power resources by destroying metering devices and connecting lines privately, thereby reducing electricity costs. Stealing electricity not only seriously affects the normal order of power supply and consumption, but also brings large economic losses to power grid enterprises, and also causes electric shock accidents and electrical fire accidents, endangering personal and power grid safety. [0003] At present, most of the identification methods for users suspected of stealing electricity are worker inspections and re...

AI Technical Summary

Problems solved by technology

Stealing electricity not only seriously affects the normal order of power supply and consumption, but also brings large economic losses to power grid enterprises, and also causes electric shock accidents and electrical fire accidents, endangering personal and power grid safety

[0003] At present, most of the identification methods for users suspected of stealing electricity are worker inspections and regular house-to-house inspections. However, this method is inefficient and consumes a lot of manpower and material resources. At the same time, it is difficult to accurately identify some concealed methods of stealing electricity.

Images