Improved Generation Quality of an Isolated Wind Driven Induction Generator Using Artificial Neural Network

Abstract

This paper presents the improvement of generation quality for a wind energy conversion scheme using artificial neural network (ANN). High generation quality means that, the induction generator generate voltages and frequency at nominal specified values, under all operating conditions, determined by various wind speeds and loads. The scheme consists of a three-phase induction generator driven by a horizontal axis wind turbine and interfaced to an isolated load. A static VAR compensator (SVC) is connected at the induction generator terminals to regulate its voltage. The mechanical power input is controlled by regulating the blade pitch-angle. Both blade pitch-angle and firing angle are adjusted using an ANN to improve the generation quality for a wind energy conversion scheme. The proposed ANN training is based on suitable values of SVC firing angles and blade pitch-angles of the wind turbine, for achieving a high generation quality at different operating conditions. The training data is obtained by using Newton-Raphson method to generate voltages and frequency at nominal specified values. The simulation results prove that, the wind energy conversion scheme, with the proposed ANN, gives good power generation quality over wide range of wind speeds and loads.