ABSTRACT
This chapter deals with the application of artificial neural network (ANN) and expert system (ES) to voltage stability assessment. The use of artificial neural networks for voltage stability assessment and enhancement has been presented. The proposed scheme for ANN-based voltage stability assessment utilizes a multi-layer feed forward network employing back propagation algorithm for the training process. Details of constructing the network architecture, preparation of the training data, and testing process will be done. Voltage stability assessment requires identification of the collapse point based on load variation commonly employing a property such as singularity of the load flow Jacobian matrix at the collapse point. The ANN-based voltage stability enhancement is designed to predict the enhanced maximum demand at collapse and the reactive compensation needed to achieve the enhanced stability margin. The sensitivity of the accuracy of the predicted output from the ANN has been investigated with different ANN architectures.
