An Optimized Adaptive Neural-Fuzzy Controller Based on an Indirect Vector Control of Doubly Fed Induction Generator for Wind Power Generation

Abstract

This paper proposes a genetic algorithm optimized adaptive neural-fuzzy controller based on an indirect vector control of Doubly Fed Induction Generator (DFIG) for wind power generation. The main goal of this paper is to improve and to optimize the performances of power system using a wind energy conversion system based on DFIG. In a first step vector control applied to the stator flux of DFIG is presented. In a second step, to ensure the real-time tracking of the optimum operating point and Maximum Power Point Track (MPPT) giving online a maximum production of electric power for different wind speeds, PI and fuzzy controllers are used for speed control. In the last step, in order to improve the dynamic performance of proposed system controller an Adaptive Neuro-Fuzzy Inference Systems (ANFIS) optimized by genetic algorithms is suggested for the speed regulation. The efficiency and validity of the proposed control strategy are illustrated by simulation results.