The Establishment And Application Of Combination Forecasting Model

With the application of the grey system theory and the BP neural network in the field of forecasting, the forecasting technology has obtained the great development. The grey forecast model has the very strong fusion strength and penetrability to the general model, so it can be combined with other models to improve the forecasting precision. Therefore, analysis and research of the grey model with other model's combination are carried, the combination forecasting models are established and the energy consumption of China is forecasted. The primary research content and results are obtained as followes:1. Based on the grey forecast model GM(1,1), the triangle model and the ARMA model, the combination forecast model TGMA(1,1) has been proposed. GM(1,1) is used to fit the tendency item of the data series, meanwhile, the triangle model and ARMA(p,q) model capture system's residual sequence.2. The grey-neural network combination model has been built. Three improved grey models (the grey optimization model GOM(1,1), the agonic grey forecast model and the improved metabolism forecast model) are combined through the theory of the neural network model.3. The further improvement of the grey-nerual network combination model has been made. The grey relation analysis method is adopted to find the main influencing factors of the energy consumption and time series data of the factors are used as an input of BP neural network. So, the energy consumption system's influencing factors are also considered comprehensively, thus, the forecast precision is improved further.