SPEED DEVIATION AND MULTILAYER PERCEPTRON NEURAL NETWORK BASED TRANSIENT STABILITY STATUS PREDICTION SCHEME

Abstract

In this paper, a rotor speed deviation and multilayer perceptron neural network (MPLNN) based transient stability prediction scheme is presented. The scheme uses the sum of the maximum rotor speed deviations (MSDs) of the individual generators in a power system as inputs to an MPLNN. The proposed scheme predicts transient stability one cycle after the tripping of a bus or line following a disturbance. The trained MLPNN responded to 61 transient unstable cases with 100% accuracy. The response to 34 transient stable cases was also 100% accurate. The IEEE 39-bus test system was used for the study.