An anomaly detection method for power dispatching monitoring data based on dynamic integration of reversed information entropy

Abstract

The embodiment of the present invention proposes a power dispatching monitoring data anomaly detection method based on the dynamic integration of inversion information entropy, including: dividing the power dispatching monitoring historical data into a training set and a verification set, and using the training set to train a certain number of base classifiers , the output of the base classifier is the probability that the input data belongs to the normal class; use the abnormal class labeling method to mark a part of the historical data in the verification set as an abnormal class; use the KNN algorithm to select historical data with a small Euclidean distance from the verification set and the data to be detected as Validation subset; use the base classifier evaluation method based on inverse information entropy to calculate the score of the base classifier on the data in the validation subset; use the base classifier selection method based on non-parametric statistical hypothesis testing to select the base classifier based on the score, The output of the selected base classifiers is averaged as the detection result of the data to be detected. The technical solutions provided by the embodiments of the present invention can reduce the false positive rate of abnormal detection of power dispatch monitoring data.

Description

【Technical field】 [0001] The invention relates to an abnormal detection method of power dispatch monitoring data, in particular to an abnormal detection method of power dispatch monitoring data based on dynamic integration of inversion information entropy. 【Background technique】 [0002] Unified Strong Smart Grid is a new type of grid formed by highly integrating modern advanced sensing and measurement technology, communication technology, information technology, computer technology and control technology with the physical grid based on the physical grid, which includes power generation, transmission, and transformation. , power distribution, power consumption and dispatching links. In the actual work of the power system, dispatching undertakes the functions of commanding, supervising and managing the power production and operation, which is an important guarantee for the safe operation of the power system. With the increasing scale of the power grid, the requirements for t...

AI Technical Summary

Problems solved by technology

The current semi-supervised anomaly detection method based on dynamic integration algorithm does not take into account the data characteristics of the lack of sufficient amount of historical anomaly data, resulting in the problem of greatly increasing the false negative rate in order to reduce the false positive rate

Images