A multivariate grey prediction model based on energy logistic equation and its application in energy prediction in China

The energy consumption problem is an important issue in the development process of various countries, and scientific methods for predicting energy consumption can assist governments in making decisions. The energy consumption trend usually shows a saturated S-shaped curve, and the mathematical model of the Logistic function can be used to fit this trend. Based on the Energy Logistic equation, a novel multivariable grey prediction model of energy consumption is proposed in this paper. The least square method is used to estimate the parameters of the model, and the approximate time response formula of the model is obtained. The degree of correlation between several energy consumptions is calculated by the grey correlation analysis. Then, from the angle of the three main energy sources to establish the energy consumption prediction model respectively, and the validity of the model is verified by selecting the data of three typical coal, crude oil and natural gas consumption provinces in China (Shandong Province, Heilongjiang Province and Guangdong Province). Compared with the other six multivariate grey models, the results show that the new model is superior to the other models according to five test indexes. Finally, based on the modelling of three provinces in China, the model predicts the consumption of three kinds of energy in the next five years, and a correlation analysis is performed according to the prediction results. (c) 2021 Elsevier Ltd. All rights reserved.

Automated summary

A novel multivariable grey prediction model of energy consumption is proposed in this paper, which calculates the correlation between energy consumption using grey correlation analysis. The model is validated using data from three provinces in China, showing superior performance compared to other models according to five test indexes.