Short-term Wind Speed Combination Prediction Model of Neural Network and Time Series

This paper uses neural network combined with time series to establish rolling neural network model to predict short-term wind speed in the wind farm. In order to improve wind speed prediction accuracy, this paper analyzes effects of wind direction on wind speed by grey correlation analysis and obtains the correlation coefficient between wind speed at next moment and current wind direction is the largest by calculating. Then historical wind speed values and residuals determined by time series and wind direction at current moment are used as input variables to establish wind prediction model with rolling BP neural network. The simulation results show that neural network combined with time series which considers wind direction can improve the prediction accuracy when wind speed fluctuation is large.