Artificial neural network based early detection of real-time transient instability for initiation of emergency control through wide-area synchrophasor measurements

This paper proposes an approach for early detection of transient instability of power system for initiating the emergency control in time. The synchrophasor measurements are used for real-time monitoring of the system. The Artificial Neural Network (ANN) is used as classifier for predicting the transient instability status of the system with rotor angles and speeds (frequency) of generator as inputs at different consecutive cycle lengths after fault clearing. The stability status obtained from ANN can be utilized for initiating the emergency control actions within few cycles from fault clearing. The proposed scheme is able to successfully predict the transient stability status of the system for unseen operating conditions with varying topology. The proposed method is investigated on IEEE-39 New England system for its real-time applications and results obtained reflect the effectiveness of the proposed methodology.