Application of an ANN based voltage stability assessment tool to restructured power systems

This paper presents an ANN based method for assessing the effect of various transactions on the voltage stability margins at the most vulnerable load buses in a restructured power system operated in a combined pool and bilateral transaction modes regime. The most vulnerable load buses of the system from voltage stability point of view are first identified by a 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 of each generator-vulnerable load bus pair with the electrical distance between the corresponding 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. A comprehensive set of input patterns for the ANN's covering all the pertinent loading conditions that may lead to voltage instability in the system, including both the pool operation and the bilateral transactions, are generated. 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 a modified CIGRE 32 bus test system. The trained ANN's are utilized to assess the effect of the individual bilateral transactions on the distance to voltage collapse at the vulnerable load buses, so that appropriate corrective actions, like limiting of bilateral transactions or mobilizing of suitable reactive power resources to ensure voltage stability, could be taken.