An Online Identification Method of Power System State Sensitivity Based on Target Regularization

Abstract

The invention discloses an on-line identification method of power system state sensitivity based on target regularization, which comprises the following steps: collecting system parameters and system observations, performing spatial regularization on the collected data, and obtaining a regression model; calculating other operating points of the system parameters and the current Run point Euclidean distance, after sorting, select a batch of samples with smaller Euclidean distance to calculate the weight value, and then stretch the weight space to obtain the regression model variant, and calculate the sensitivity vector based on the cost function, regression model and regression model variant ; The present invention collects system parameters and system observations, and performs data space regularization, distance calculation, sample selection, weight value calculation, weight space stretching, and regression calculation to obtain sensitivity vectors, and solves the occurrence of matrix inversion under collinear conditions The error problem caused by pathological conditions can describe the system characteristics of power systems in different regions, the numerical value is stable, and the accuracy of online identification of sensitivity can be improved, which can be widely used.

Description

technical field [0001] The invention relates to the research field of the intersection of power system identification and data processing, in particular to an on-line identification method of power system state sensitivity based on target regularization. Background technique [0002] The state sensitivity of the power system (hereinafter referred to as the sensitivity) refers to the sensitivity between the state variables of the power system, which is usually expressed as the first-order partial derivative relationship between the observed quantity of the power system and the system parameters. The observed quantity can be the eigenvalue damping ratio of the system. , bus voltage and other variables, and the system parameters can be variables such as the injected power of each bus. [0003] Traditionally, the calculation and analysis method of sensitivity needs to rely on the offline mathematical model of the system. Under the condition of strong uncertainty in the future po...

AI Technical Summary

Problems solved by technology

Data collinearity makes the distribution of samples in the high-dimensional data space concentrated in local areas, which cannot fully describe the system characteristics, resulting in the matrix X of the existing locally weighted linear regression method T Numerical instability problems such as WX inverse ill-conditioning, which directly limit the accuracy and application value of online sensitivity identification

Images