Identification of voltage weak buses/areas using neural network based classifier

This paper presents a neural network-based method for voltage weak buses/areas identification. By the use of a power flow analysis and singular value decomposition method, a self-organizing Kohonen neural network, is trained to cluster buses with the similar features in terms of voltage stability. The generalization capability of the self-organizing network can cope with vagarious operating conditions which have not been encountered during the training phase and hence a give correct classification result. The effectiveness of the proposed network has been demonstrated on the IEEE 30-bus test system.