Adaptive fractional backstepping intelligent controller for maximum power extraction of a wind turbine system

Controlling wind power plants is a challenging issue, however. This is due to its highly nonlinear dynamics, unknown disturbances, parameter uncertainties, and quick variations in the wind speed profiles. So robust controllers are needed to overcome these challenges. This paper suggests two novel control approaches for doubly fed induction generator-based wind turbines. Its key objective is to regulate the generator speed and rotor currents. A radial basis function (RBF) neural network disturbance observer based fractional order backstepping sliding mode control (SMC) is presented to control the rotor currents. This RBF neural network-based disturbance observer estimates unknown disturbances. Also, a new adaptive fractional order terminal SMC is suggested for the control of the generator speed. This robust chattering-free controller that does not require any information about the bound of uncertainties fractional calculus is adopted in the SMC design to eliminate undesired chattering phenomena. The controller parameters are optimally tuned utilizing the ant colony optimization algorithm. The proposed approach was validated using a simulation study entailing various conditions. Its performance was also compared to that of the conventional backstepping and conventional backstepping sliding mode controller. The simulations results verified the approach's ability to maximize power extraction from the wind and properly regulate the rotor currents. The proposed method has about 20% less tracking error than the other two methods, which means 20% higher efficiency.