Estimation of missing transmission line reactance data using multiple linear regression

Abstract

This paper explores the use of Multiple Linear Regression techniques in order to estimate sections of missing line reactance data sometimes found in the data received from synchrophasor measurement units. The high correlation between transmission line reactance and the system frequency is used to predict these estimates. Dynamic predictor coefficients are used to improve accuracy of the estimations and analysis is done to determine the most appropriate parameters to use in the regression model. All model building, analysis and testing is done using multiple sections of real PMU data.