A Power Oscillation Type Discrimination Method Based on Multidimensional Features of Power System

Abstract

The invention discloses a method for discriminating power oscillation types based on multi-dimensional characteristics of a power system, by calculating time-domain indicators, frequency-domain indicators, energy indicators, cross-correlation indicators, autocorrelation indicators, sample entropy indicators and modal indicators for low-frequency oscillation signals , a relatively complete index set is established, which can describe the characteristic information of power system oscillation more completely. The present invention uses a mutual information feature selection method. Compared with the widely used Fisher discriminant method, the mutual information feature selection can measure the nonlinear relationship between variables. Using the features obtained by the mutual information feature selection method for model training can help improve the generalization ability of the training model and reduce the complexity of the training model, thereby effectively preventing over-fitting. The invention uses a machine learning classifier to identify the power system power oscillation event type, and compared with the traditional classification method, it can effectively improve the classification accuracy and the generalization ability of the training model.

Description

A Power Oscillation Type Discrimination Method Based on Multidimensional Features of Power System technical field The present invention relates to the technical field of power system analysis, in particular to a power system based on multidimensional features of the power system. Rate oscillation type discrimination method. Background technique [0002] With the continuous expansion of the scale of my country's power system, the risk of low frequency oscillation is increasing, and it shows Many new features. There are mainly two types of low-frequency oscillations in the power system, one is caused by insufficient system damping The negatively damped oscillation of , and the forced power oscillation due to periodic power disturbances. In a real power system, the negative Different suppression measures are required for damped oscillation and forced power oscillation due to different generation mechanisms. But the two oscillating waves They are similar in shape and ...

AI Technical Summary

Problems solved by technology

Moreover, 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, which is likely 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