Fast Prediction of Angle Stability Using Support Vector Machine and Fault Duration Data

Abstract

This paper deals with the prediction of the transient stability of power systems using only pre-fault and fault duration data measured by Wide Area Measurement System (WAMS). In the proposed method, the time-synchronized values of voltage and current generated by synchronous generators (SGs) are measured by Phasor Measurement Units (PMUs) installed at generator buses, and given as input to the proposed algorithm in order to extract a proper feature set. Then, the proposed feature set is applied to Support Vector Machine (SVM) classifier to predict the transient stability status after fault occurrence and before fault clearance. The robustness and accuracy of the proposed method has been extensively examined under both unbalanced and balanced fault conditions as well as under different operating conditions. The results of simulation performed on an IEEE 14-bus test system using DIgSILENT PowerFactory software show that the proposed method can accurately predict the transient stability status against different contingencies using only pre-disturbance and fault duration data. © 2019 IEEE.