Voltage stability is one of the major concerns in competitive electricity market. In this paper, two new neural network based approaches are presented in order to predict the static voltage stability index and to rank the critical line outage contingencies. These algorithms speedup the neural network training process by reducing the dimensions of neural network training vectors. Based on the weak buses identification method, the first developed algorithm introduces a new feature extraction technique. The second algorithm is based on Principal Component Analysis algorithm which is a statistical method. A clustering method is applied to reduce the number of neural network training vectors. The proposed algorithms have been tested on the IEEE 30 bus test system. Fast performance, accurate evaluation and good prediction accuracy for voltage stability index and contingency ranking have been obtained.

Keywords