Application of ARMA Model in Ultra-short Term Prediction of Wind Power

The randomness of the wind velocity causes the fluctuation of wind power. Therefore, It is necessary to forecast the wind power in a certain time. In this paper, the ultra-short term predication of wind power has been carried out based on the Auto-Regressive-and-Moving-Average (ARMA) model. The wind power was predicted by prediction steps of ARMA in section II. According to the corresponding national standard, the predicted results were evaluated in TABLE I and II, simultaneously, compared with the predicted results of BP neural network in subsection C of section III. Finally, it is found that the ARMA model is more suitable for ultra-short term prediction of wind power.