PERFORMANCE INVESTIGATION OF A CSI BASED POWER LINE CONDITIONER WITH ANN CONTROL

Abstract

Solid state control of ac power using thyristors and other semiconductor switches is widely employed to feed controlled electric power to electrical loads. These nonlinear devices inject harmonic currents in the AC system and increase overall reactive power demanded by the equivalent load. The increased severity of harmonic pollution in power networks has attracted the attention of power electronics and power system engineers to develop dynamic and adjustable solutions to the power quality problems. Such equipment, generally known as active power filters (APF's), are also called active power line conditioners (APLC's). The simulation models of different implementation techniques for current source active power filters are developed in MATLAB Simulink and the results are presented. The hysteresis PWM control is simple, but its average switching frequency is very high and varies with load conditions so that switching patterns are uneven and random. The space vector modulation (SVM) technique, with some modifications, is implemented for Current Source APF. The Artificial Neural Network is used to customize the conventional SVM approach. The technique reduces software complexity, and computation time, and increases the accuracy of the positioning of the switching instants.