Correction method of wind speed prediction system using predicted wind speed fluctuation

This paper describes a prediction of a wind speed fluctuation by using hierarchical neural network to improve the wind speed prediction. The future wind speed fluctuation (increase or decrease) is predicted with discrete value (1 or -1). The timing of the wind speed changes after 10 minutes is predicted. Time delay is confirmed during the predicted and observed values. Therefore, the timing of wind speed change is focused. Besides, the correction system of the wind speed prediction by using the fluctuation prediction result is proposed where two types of correction methods are applied. The wind speed prediction by applying RMSE method in the existence/absence of correction is evaluated. Finally, the application limit of correction when using fluctuation prediction result and effectiveness of predicting the wind speed fluctuation also will be considered.