Optimal control for variable-speed wind generation systems using General Regression Neural Network

• An IG speed drive with the application of a optimal and a GRNN controller is introduced.
• The GRNN with AACO torque compensation is feed-forward to increase the robustness.
• The controller is designed to drive the turbine to extract maximum power from the wind.
• This technique can maintain the system stability and reach the desired performance.

An induction generator (IG) speed drive with the application of an optimal controller and a proposed General Regression Neural Network (GRNN) controller is introduced in this paper. Grid connected wind energy conversion system (WECS) present interesting control demands, due to the intrinsic nonlinear characteristic of wind mills and electric generators. The GRNN with adaptive ant colony optimization (AACO) torque compensation is feed-forward to increase the robustness of the wind driven induction generator system. An optimal control loop for the wind power system is designed. The optimality of the whole system is defined in relation with the trade-off between the wind energy conversion maximization and the minimization of the induction generator torque variation that is responsible for the frequency fluctuations. This is achieved by using a combined optimization criterion, resulting in a LQ tracking problem with an infinite horizon and a measurable exogenous variable (wind speed). The proposed controller is designed to drive the turbine speed to extract maximum power from the wind and adjust to the power regulation.