Electricity consumption abnormity detection method, device and equipment and readable storage medium

Abstract

The invention discloses an electricity consumption abnormity detection method, an abnormity detection device, an abnormity detection device and a computer readable storage medium. the electricity consumption abnormity detection method comprises the steps: collecting sequence characteristic values of each target time point from a plurality of power consumption time sequences according to a preset time interval, so as to generate a characteristic data sequence corresponding to each power consumption time sequence; Calculating abnormal scores of all the characteristic data sequences according toan isolated forest algorithm; If the abnormal score is greater than an abnormal warning value, confirming the feature data sequence as a normal sequence; And if the abnormal score is smaller than or equal to an abnormal warning value, determining the feature data sequence as an abnormal sequence. The accuracy of power consumption abnormity detection is improved, the interference of abnormal valuesis eliminated, the calculation complexity is reduced, and the detection efficiency is improved.

Description

technical field [0001] The present invention relates to the technical field of abnormality detection, in particular to a method for detecting abnormality in electricity consumption, an abnormality detecting device, an abnormality detecting device and a computer-readable storage medium. Background technique [0002] At present, the anomaly detection of electricity consumption time series is mostly from the perspective of electricity consumption time series (such as year-on-year difference, ring-to-month difference, moving average, ARIMA forecast, etc.) and distance difference (such as comparing the sequence in a certain time window with other sequences Euclidean distance), the disadvantages of starting from the perspective of electricity consumption time series are: 1. The consideration of year-on-year difference and ring-to-month difference is too one-sided, which may cause misjudgment; A sequence after the abnormal value is also judged as abnormal; the disadvantage of start...

AI Technical Summary

Problems solved by technology

[0003] The main purpose of the present invention is to provide a method for detecting abnormal electricity consumption, an abnormal detecting device, an abnormal detecting device, and a computer-readable storage medium, aiming at solving the problem that the traditional method for detecting abnormal electricity consumption is not accurate enough and is easily detected by abnormal values. Interference, complex calculations, and low detection efficiency

Images