A Novel ANN Based Method for Online Voltage Stability Assessment

This paper presents an ANN based method for online voltage stability assessment of power systems. The most vulnerable load buses of the system from voltage stability point of view have been identified by Modal analysis. A separate feed forward type of ANN is trained for each vulnerable load bus. For each of these ANN's, some novel inputs, comprising of the moments obtained by multiplying the real power and reactive power contributions with the electrical distance between each generator-vulnerable load bus pair and the reactive power margins available at the generators, are used in addition to the usually used inputs viz. the real and reactive power loads and the voltage magnitude at the vulnerable load bus. 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 (Contour Program) incorporating the Q limits of the generators. The proposed method has been applied to the IEEE 30 bus test system. The distances to voltage collapse obtained by the ANN and by the analytical method are found to be closely matching with each other.