Application of a novel quadratic polynomial discrete grey model to forecast energy consumption of China

Abstract

The discrete grey modelling technique is a novel methodology of grey predictionmodels, which is effective to improve the effectiveness and applicability of greymodels. In order to build a more general and effective univariate grey predictionmodel, the discrete grey modelling technique is utilised in this paper to builda quadratic polynomial discrete grey model, abbreviated as the QPDGM. Theproperties of the QPDGM model have been discussed, which indicate that thenew model can be regarded as an extension of the conventional discrete greymodel and nonhomogeneous grey model, and it is also coincidence with threeclasses of exponential sequences. The QPDGM model is finally applied to predictthe energy consumption of China, including the electric power, crude oil andnatural gas consumptions. The results have been compared to some commonlyused univariate grey prediction models, which indicates the QPDGM model isgenerally more accurate than other models.