Self-encoding network, training method thereof, and method and system for detecting abnormal power consumption

Abstract

The invention discloses a self-coding network and a training method thereof, and a method and a system for detecting abnormal power consumption, wherein the training method comprises the following steps: splicing the sample power data by a sliding window to obtain a training sample set, and marking the training sample set containing the surveyed user to obtain a labeled sample, wherein the unlabeled training sample is a non-labeled sample; carrying out unsupervised training on the self-coding network by unlabeled samples, and obtaining the initialization parameters of the self-coding network,then taking the discrete class tags obtained from the coding layer of the coding network as classifiers, carrying out supervised training on the classifiers by the labeled samples, and updating the parameters of the coding layer to obtain the trained self-coding network; then, utilizing the trained self-coding network to detect the power data of the user to be measured, and judging whether the user to be measured abnormally uses power. The invention can mine abnormal information in low-density electric power data, avoid noise data interference, and improve abnormal detection accuracy.

Description

technical field [0001] The invention belongs to the technical field of electricity consumption behavior analysis, and more specifically relates to an autoencoder network and its training method, a method and a system for detecting abnormal electricity consumption. Background technique [0002] Abnormal power consumption detection is an important support for the safe power consumption of the power grid. In the operation of the power grid, regardless of the failure of the metering device or the theft of electricity by the user, the real electricity consumption data of the user cannot be collected. These electricity consumption data are called abnormal electricity consumption data. Abnormal power consumption data will affect the dispatch and management of the power grid, as well as the security of power supply, and cause the power sector to suffer huge losses. Therefore, the detection of abnormal electricity consumption is of great significance. By proactively discovering abno...

AI Technical Summary

Problems solved by technology

[0008] Aiming at the above defects or improvement needs of the prior art, the present invention provides an autoencoder network and its training method, a method and a system for detecting abnormal power consumption, thereby solving the difficulties in the training of existing models in the prior art and the detection efficiency. Too low, technical problems with a large number of misjudgments

Images