A novel approach to capture the maximum power from variable speed wind turbines using PI controller, RBF neural network and GSA evolutionary algorithm

Abstract

This paper presents a hybrid method for generator torque control in wind turbines. The generator torque control is usually used in lower wind speeds in order to capture the maximum power. In the proposed method, the wind turbine generator torque is regulated using a proportional and integral (PI) controller. In order to tune the PI gains, a radial basis function (RBF) neural network is used. The optimal dataset to train this neural network is provided by the Gravitational Search Algorithm (GSA). A 5MW wind turbine model based on FAST (Fatigue, Aero-dynamics, Structures and Turbulence) software code developed at the US National Renewable Energy Laboratory (NREL) is used to simulate and verify the results. The simulation results show that the proposed method has a good performance.