Voltage stability indicators (VSI) play a significant role in determining the voltage stability of the power system. In order to forecast the voltage instability of the system using voltage stability indicators, this paper presents an implementation of an artificial neural network (ANN) based on the Levenberg Marquardt (LM) technique. In this context, the performance of three voltage stability indicators—the line voltage stability index (LVSI), the line stability index (Lmn), and the fast voltage stability indicator (FVSI) are compared. Based on the maximum active power loadability of load buses of the IEEE-14 and IEEE-118 bus systems, these indicators are used to assess their vulnerability. The LVSI, Lmn, and FVSI indices obtained from the Newton-Raphson method of the most severe buses of both test systems are compared with the forecasted values by the ANN method under base load to critical loading conditions. The real and reactive power losses of the lines associated with the most severe bus of the systems and totally real and reactive power losses of the systems are forecasted by the MATLAB NN toolbox under wide variations in active power loading. The Static Synchronous Compensator (STATCOM) is used to enhance the voltage of the most severe bus of the systems. The outcomes show that the methods for assessing voltage stability using ANN under the variation of the real power demand of the critical bus is highly précised and technically feasible.
Gupta et al. (Tue,) studied this question.