Active power line conditioner with a neural network control

Abstract

Harmonics in a power system can lead to communication interference, transformer heating or solid-state device malfunctions. Active power line conditioners (APLC) are one important method of achieving harmonic reduction. The purpose of this paper is to propose a novel voltage-type APLC which cancels harmonic currents by injecting a compensation current. The proposed APLC consists of a variable DC voltage source, an inverter and a neural network controller that is trained with the genetic algorithm and backpropagation. Computer simulations for two load current test cases show that the neural net can provide switch control signals for the proposed APLC to generate compensation currents that reduce line current THD significantly.