VOLTAGE COMPENSATION USING ARTIFICIAL NEURAL NETWORK: A CASE STUDY OF RUMUOLA DISTRIBUTION NETWORK
A study of hourly voltage log taken over a period of six months from Rumuola Distribution network Port Harcourt, Rivers State indicates that power quality problems prevalent in the Network are undervoltage/voltage sags and overvoltage/voltage swells. This paper aims at addressing these power quality problems in the distribution network using artificial neural network (ANN) controller based dynamic voltage restorer (DVR). The artificial neural networks controller engaged to controlling the dynamic voltage restorer were trained with input and output data of proportional integral (PI) controller and of unit amplitude generator obtained during simulation. All simulations and modeling were carried out in MathLab/Simulink. Proposed dynamic voltage restorer was tested with replicated model of Rumuola substation by simulating with sample of average voltage for Omerelu, Waterlines, Rumuola, Shell Industrial and Barracks feeders. Simulation results showed that DVR is effective in compensating for under-voltage and over-voltage in Rumuola Distribution network Port Harcourt, Rivers State.