Stochastic gradient identification algorithm for nonlinear system modeling in wind power curtailment prediction

摘要

This paper considered the parameter identification problem of Hammerstein finite impulse response models and a novel stochastic gradient identification algorithm is derived for the Hammerstein system modeling. By using the gradient search principle and minimizing the quadratic criterion functions, the presented stochastic gradient identification algorithm has a better computational efficiency. The given simulation validates that the proposed algorithm can identify the wind power characteristic curve accurately and contributes to calculate the wind power curtailment prediction.