Research on the combined forecasting method of wind speed

Wind speed forecasting is very important for the operation of wind power plants and power system. Combined forecasting method is proposed based on the BP neural network and RBF neural network in this paper. The predictive effect indicators are also given. Finally, the wind speed of a certain coastal city in north China is forecasted in 2012. We take two-parameter Weibull distribution to fit actual wind speed data and adopt maximum likelihood method to get relevant parameters. The results show that mean absolute error and root mean square error are reduced by combined forecasting method which takes into account the error precision of BP neural network and RBF neural network. Therefore, we can gain an ideal forecasting effect for wind speed by combined forecasting method.