Voltage stability evaluation of power system with FACTS devices using fuzzy neural network

Voltage stability has been a major concern for power system utilities because of several events of voltage collapses in the recent past. With the developments of flexible ac transmission system (FACTS) devices, power system performance has improved. This paper proposes an approach based on fuzzy neural network to calculate loadability margin of the power system with static synchronous compensator (STATCOM). A multi-input, single output fuzzy neural network is developed. Kohonen self-organizing map is employed to cluster the real and reactive loads at all the buses to reduce the input features, thus limiting the size of the network and reducing computational burden. Uncertainties of real and reactive loads, real and reactive generations, bus voltages and STATCOM parameters are taken into account by transforming them into fuzzy domains using combination of different nonlinear membership functions. A three-layered feed-forward neural network with fuzzy input variables is developed to evaluate the loadability margin. All ac limits are considered. The proposed methodology is applied to IEEE-30 bus and IEEE-118 bus systems. The proposed methodology is fast and accurate as compared to the conventional techniques. This method can also be used for online calculation of the voltage stability of the large power systems.