An Artificial Neural Network Controlled SVC for Dynamic Stability Enhancement of Power Transmission System

This paper reviews new approach in modern research using Artificial Neural Network. Voltage level of the system changes at the time of fault and the drop in the load voltage leads to an increased demand for the reactive power that, if not met by the power system leads to a further decline in the bus voltage. This decline eventually leads to a progressive rapid decline of voltage at that location, which may have a cascading effect on neighboring regions that causes voltage collapse. In this paper, In order to maintain system stability after faults, the transmission line is shunt compensated at its center by a 200-Mvar Static Var Compensator (SVC) in MATLAB / SIMULINK. SVC was used to maintain the voltage within the limits. SVC will either supply the reactive power or extract the reactive power. An Artificial Neural Network (ANN) is also developed with a systematic step-by-step procedure which optimizes a criterion commonly known as the learning rule. The input/output training data is fundamental for these networks as it conveys the information which is necessary to discover the optimal operating point. It is shown that trained Neural Network developed has excellent capabilities of forecasting which can be very useful in research.