Electricity stealing behavior detection method and device

Abstract

The embodiment of the invention provides an electricity stealing behavior detection method and device. The method is applied to power utilization data monitoring equipment, a detection classifier model corresponding to at least one user account is stored in the equipment, and the detection classifier model is obtained through training on the basis of a power utilization characteristic parameter set corresponding to historical power utilization data of the user account. According to the method, electricity stealing behavior detection is carried out on electricity utilization data of a user account by using the detection classifier model corresponding to the user account; the precision and the efficiency of electricity stealing behavior detection are ensured; the operation cost of a smart power grid is not increased. In the training process of the detection classifier model, the electricity utilization characteristic parameters of the electricity utilization data are adopted for training, it can be guaranteed that the training time of the classifier model is short enough, meanwhile, the complexity of the classifier model is reduced, and it is guaranteed that the classifier model canrapidly achieve the electricity stealing behavior detection function.

Description

technical field [0001] The present application relates to the technical field of smart grid, in particular, to a method and device for detecting electricity theft. Background technique [0002] With the continuous development of science and technology, the application of smart grid system is more and more extensive. For the smart grid system, detecting whether there is electricity theft in the user's electricity consumption behavior is an extremely important aspect in the process of monitoring the electricity consumption behavior of the smart grid system. [0003] At present, the mainstream of the industry usually directly uses the user's power consumption data to train the neural network model, so as to detect the electricity theft behavior of the user's power consumption mode through the trained neural network model, or install additional measurement for the smart grid system. equipment to realize the detection of stealing behavior. Among them, in the former method, it i...

AI Technical Summary

Problems solved by technology

Among them, in the former method, it is impossible to distinguish whether the change of the power consumption pattern is caused by the randomness of the user's power consumption or the user's electricity stealing behavior, and the overall detection accuracy of the electricity stealing behavior is not high, and at the same time It also takes a lot of time to train the neural network model, and because of the complexity of the neural network model, it is impossible to quickly detect electricity stealing behavior

In the latter way, there are great difficulties in equipment deployment, and it will increase the operating cost of the smart grid

Images