neuro-fuzzy based algorithm for online dynamic voltage stability status prediction using wide-area phasor measurements

in this paper, a novel neuro-fuzzy based method combined with a feature selection technique is proposed for online dynamic voltage stability status prediction of power system. this technique uses synchronized phasors measured by phasor measurement units (pmus) in a wide-area measurement system. in order to minimize the number of neuro-fuzzy inputs, training time and complication of neuro-fuzzy system, the pearson feature selection technique is exploited to select set of input variables that have the strongest correlation with the output. study on the network features such as phase angle and voltage amplitude has shown that among two interesting features, phase angle has maximum information about the performance of the network and solely can be used for training purposes. this is extra advantage of the proposed method that minimum data is needed to predict dynamic voltage stability status the efficiency of the proposed dynamic voltage stability prediction method is verified by simulation results of new england 39-bus and ieee 68-bus test systems. simulation results show that the proposed algorithm is accurate, computationally very fast and reliable. moreover, it requires minimum data and so it is desirable for wide area monitoring system (wams).