Voltage Stability Margin Assessment Using Multilayer Feed Forward Neural Network

With the deregulation of electricity markets, the system operation strategies have changed in recent years. The systems are operated with smaller margins. How to maintain the voltage stability of the power systems have become an important issue.This paper presents an Artificial Feed Forward Neural Network (FFNN) approach for the assessment of power system voltage stability. This paper uses some input feature sets using real power, reactive power, voltage magnitude and phase angle to train the neural network (NN). The target output for each input pattern is obtained by computing the distance to voltage collapse from the current system operating point using a continuation power flow type algorithm. This paper compared different input feature sets and showed that reactive power and the phase angle are the best predictors of voltage stability margin. Further, the paper shows that the proposed ANN based method can successfully estimate the voltage stability margin not only under normal operation but also under N-1 contingency situations. The proposed method has been applied to the IEEE 14 and IEEE 30 bus test system. The continuation power flow technique run with PSAT and the proposed method is implemented in MATLAB.