Power failure prediction method and device based on weighted extreme learning machine

Abstract

The invention relates to a power failure prediction method and device based on a weighted extreme learning machine, computer equipment and a storage medium. The method comprises the following steps: constructing a sample data set for model training according to fault detection feature data of a power system; traversing the sample data set to obtain a sample category of each sample in the sample data set, a total number of samples in the sample data set, a total number of positive samples in the sample data set and a total number of negative samples in the sample data set; distributing a sample weight corresponding to the sample category of each sample for each sample, and generating a weighting matrix according to the sample weight corresponding to the sample category of each sample; based on an improved weighted ELM model IWELM algorithm, performing training processing according to the weighted matrix and the sample data set to obtain a weighted extreme learning machine classification model; and predicting the power failure of the power system according to the weighted extreme learning machine classification model, and outputting a prediction result. By adopting the method, the identification effect and accuracy during power failure prediction can be improved.

Description

technical field [0001] The present application relates to the technical field of power failure detection, and in particular to a power failure prediction method, device, computer equipment and storage medium based on a weighted extreme learning machine. Background technique [0002] In recent years, big data has become a new type of productivity, and the power grid is the largest and most complex Internet of Things system, and various power detection data in the power grid have experienced massive growth. In the traditional technology, a training data set is generated according to the power detection data, and the existing extreme learning machine classification model for power fault prediction is constructed by using machine learning methods, so as to realize the prediction of power faults. However, the existing extreme learning machine classification model for power fault prediction has poor recognition effect and low accuracy in fault prediction, which makes it impossible...

AI Technical Summary

Problems solved by technology

However, the existing extreme learning machine classification model for power fault prediction has poor recognition effect and low accuracy in fault prediction, which makes it impossible to predict and deal with corresponding power faults in time

Images