Dynamic equivalent of external power system and its parameter estimation through artificial neural networks

A multi-machine power network, external to a study system, has been replaced by one equivalent machine for dynamic studies. The back-propagation and radial-basis function neural networks have been employed to estimate unknown parameters of the dynamic equivalent. Transient stability indices like the peak overshoot, decay constant and frequency of oscillations of the study generator are used as input features to train the neural networks. While the back-propagation algorithm, generally, did not give very satisfactory estimates, the radial basis functions could be trained to predict the parameters of the equivalent with extreme precision. Estimating the dynamic equivalent from the transient stability indices is a novel approach.