KETEP 세계에너지시장정보

1. A combinatorial method wind speed prediction model construction method, characterized in that it includes the following steps:S1: The original wind speed is decomposed to obtain the wind speed value after decomposition, and the decomposed wind speed value is predicted one step in advance by using the model, and the predicted value is combined, and the overall time series method based on wavelet decomposition is obtained.S2: EEMD decomposition is performed on the original wind speed, several eigenmode functions imf and residual information r are obtained, and the BP neural network optimized by genetic algorithm is used to predict the wind speed of each decomposition one step in advance to obtain the predicted values of each sub-sequence, and the predicted values are superimposed to obtain the overall wind speed prediction value;S3: The results of the above wavelet-time series prediction model and EEMD-GA-BP neural network prediction model are taken as the input vectors of the neural network; the prediction data of the wavelet-time series prediction model and the EEMD-GA-BP neural network prediction model are smoothed, that is, the average of the two prediction results is taken as the input vector of the combined prediction model; the prediction values are processed and the GA-BP neural network composite prediction model is established.