Forecasting Energy Demand Based on Empirical Mode Decomposition and Grey-periodic Extensional Combinatorial Model

Energy is an important material basis for the economic development and social progress. Whether the energy supplies could support the sustainable economic growth of a country in the future is becoming an important problem in the world. The empirical mode decomposition (EMD) is a technique for decomposing a time series into a finite number of components referred to as intrinsic mode functions. This paper puts forward the EMD-GPM model integrating EMD and GPM for energy demand forecasting. In particular we use the increase of energy demand as the input of EMD. Different characteristics information of increase time series can be shown on different scales by EMD. Considering that grey system prediction model can reflect the general trends of change visually, and periodic extensional prediction model mainly reflects the periodic fluctuation, the grey-periodic extensional combinatorial model is adopted to predict the IMFs containing specific information. So, the EMD-GPM model considers both the development trends and periodic fluctuation of the energy demand.