Wide area transient stability prediction using on-line Artificial Neural Networks

This paper proposes a real-time wide area protection system which incorporates artificial neural networks (ANN) for transient stability prediction. The ANN makes use of the advent of phasor measurements units (PMU) for real-time prediction. Rate of change of bus voltages and angles for six cycles after fault tripping and/or clearing is used to train a two layers ANN. Coherent groups of generators which swing together is identified through an algorithm based on PMU measurements. A remedial action scheme (RAS) is applied to counteract the system instability by splitting the system into islands and initiate under-frequency load shedding actions. The potential of the proposed approach is tested using New England 39-bus system.