Voltage collapse prediction based on minimum singular value using Artificial Neural Network (ANN)

Voltage stability is an important factor which needs to be taken into consideration during the planning and operation of power systems in order to avoid voltage collapse and subsequently partial or full blackout. This thesis presents the voltage collapse prediction based on minimum singular value using artificial neural network (ANN). The aim of the study is to predict the voltage collapse in a power system. These data were generated at several loading conditions. The generated data are consequently divided into training and testing data. These data were generated from the experiments performed on the IEEE 30-Bus Reliability Test System. In this study, data were generated based on repetitive load flow studies taking Minimum Singular Value (MSV) as the indicator. The Minimum Singular Value must higher than unity that will indicate a stable system.