Deriving a transient stability index by neural networks for power-system security assessment

This paper proposes an approach for establishing a transient stability classifier and derives a continuous transient stability index, using a three-layer feed-forward artificial neural network (ANN), for on-line security assessment in large power systems. With the derived stability index, a never classification scheme creating an 'indeterminate' class, is introduced to minimize misclassifications and to improve the reliability of the classification results. Several post-fault abstract attributes about the system generators' acceleration rates and kinetic energies provide the basis for the stability classification. In order to derive the transient stability index, a semi-supervised backpropagation (BP) learning algorithm, making use of a specially defined error function, is developed. The proposed approach can not only distinguish whether a power system is stable or unstable, on the basis of the specific post-fault attributes, but can also provide a relative stability quantifier. Furthermore, as the number of the selected abstract attributes is independent of the system size, the methodology of the proposed approach can realistically be applied to large power systems. The 10-unit 39-bus New England power system is employed to demonstrate the proposed approach. The numerical results show that the ANN-based classifier can assess the transient stability reasonably well. (C) 1998 Elsevier Science Ltd. All rights reserved.