Effective wind speed estimation based maximum power point tracking control for variable-speed wind turbine

Abstract

With the rapid development of wind power generation technology, how to enhance the capture efficiency of wind turbines is still a challenging problem due to the stochastic characteristics of wind speed. In this paper, an effective wind speed estimation (EWSE) based Maximum Power Point Tracking (MPPT) controller for variable-speed wind turbines (VSWT) is presented. A wind speed estimation model is firstly developed via support vector regression (SVR), the training of which is conducted by utilizing data acquired through the existing supervisory control and data acquisition (SCADA) systems. After training, the estimate of effective wind speed is obtained from the SVR model in an online manner. A low-pass filter is utilized to remove the high-frequency components of the estimate signal, which can highly mitigate the incurred mechanical loads. Thereafter, a simple proportional-integral (PI) controller is designed to maneuver the rotor speed to its desired value by combining the EWSE module. Finally, the feasibility and performances of the proposed controller are validated and demonstrated with WP 1.5MW wind turbines on the platform of FAST (Fatigue, Aerodynamics, Structures, and Turbulence) code and Simulink.