Selection method and device for key features of power system

Abstract

The invention provides a selection method and device for key features of a power system. The method comprises the steps that a dataset of samples is obtained according to a transient stable time-domain simulation result, and the dataset of the samples is discretized; the concepts of information entropy and mutual information are utilized to perform primary screening on the key features of the power system according to section features and considering a combination effect, and initial key features of the power system are obtained; and an encapsulation model based on a support vector machine (SVM) algorithm is utilized to perform further selection on the initial key features, and the key features of the power system are obtained. Through the method, information provided by different featurescan be quantified by aid of the information entropy tool, the key features capable of supplementing power flow section information are found, a feature subset containing the section features is screened out, therefore, the combination effect is fully considered to better find other features except the section features, and the reliability and accuracy of feature selection are improved.

Description

technical field [0001] The invention relates to the technical field of power system security and stability analysis, in particular to a method and device for selecting key features of a power system. Background technique [0002] At present, when using artificial methods to calculate the safe and stable operation rules of the power grid, the key sections are usually selected as the key control objects based on experience for research. The practice of power grid operation has proved that the power flow of these key sections has a certain causal relationship with the transient stability of the system under expected faults . [0003] In related technologies, in the process of solving the power grid security domain, the existing methods mainly combine the analytical method or the point-by-point method with the direct fitting method, and then screen the initial input features. Firstly, the screening depends on the meaning of each input feature for preliminary screening and dimen...

AI Technical Summary

Problems solved by technology

[0004] However, as the scale of the power grid becomes larger and the characteristics of the power grid become more and more complex, it is difficult to fully grasp the security characteristics and laws of the power grid only by manual experience, and it is easy to cause information omission, and it is difficult to find potential coupling relationships in the power grid. The selection method does not consider the synergistic effect between features, has poor reliability and low accuracy

Images