Evaluation of the Performance of a Loss Minimization Method using ANN Based UPFC

Due to the shortcomings of conventional schemes, such as the tap changer and regulating transformer, and associated controller in the minimization of transmission system losses, this study proposed the use of artificial neural network (ANN) based UPFC for transmission network loss minimization. The overall effect of power losses on the system is a reduction in the quantity of power available to the consumers. Power loss leads to high cost of power generation, transmission and distribution. Unlike exiting up change and regulating transformer techniques for loss reduction, FACTS devices have fast switching capability and can be subjected to very free control algorithms for more optimal performance in loss reduction application in power systems. In the modeling of the neural network, controller for the UPFC carried out in this work, the input parameters of the neural controller includes power system variables that relates to the control of ohmic and corona losses on transmission lines. The neural network was modeled to output the firing angle to enable the FACTS device effectively control the adsorption and injection of reactive power for transmission loss reduction. The Nigerian 330KV power grid was used as a case study for the evaluation of the proposed power loss reduction system A digital model of the case study power system with the proposed neural network controlled UPFC integrated was created in the MATLAB/SIMULINK programming environment. The simulation and evaluation were carried out under two scenarios: (i) with the UPFC installed and (ii) without the UPFC installed. With each variation of the load at the bus, load flow is run to determine total system loss either with the UPFC installed or without the UPFC installed. Results obtained showed that the proposed system achieved an average active power loss reduction of 14.40% and an average reactive power loss reduction of 24.6%