Composite Model-free Adaptive Predictive Control for Wind Power Generation Based on Full Wind Speed

Aiming at the problem that the existing model-based control strategy cannot fully reflect stochastic fluctuations of wind power, this paper presents a model-free adaptive predictive controller (MFAPC) for variable pitch systems with speed disturbance suppression. First, an improved small-world neural network with topology optimization is used for 15-second-ahead forecasting of wind speed, whose rolling time is 1s, and the predicted value serves as a feedforward to obtain the early compensation variation of the pitch angle. Second, a function of the multi-objective optimization at full wind speed with optimal power point tracking and minimum control variation is constructed, and an advanced one-step adaptive predictive control algorithm for wind power is proposed based on the online estimation and prediction of the time-varying pseudo partial derivative (PPD). In addition, the compound MFAPC framework is synthetically obtained, whose closed-loop effectiveness is verified by a BP-built pitch system based on the SCADA data with all working conditions. Robustness of the schemes has been analyzed in terms of parametric uncertainties and different operating conditions, and a detailed comparison is finally presented. The results show that the proposed MFAPC can not only effectively suppress the random disturbance of wind speed, but also meet the stability of wind power and the security of grid-connections for all operating conditions.