Open AccessEnergy consumption forecasting using improved non-homogeneous exponential grey model
Author(s) -
Zhao Zi
Publication year - 2021
Publication title -
iop conference series. earth and environmental science
Language(s) - English
Resource type - Journals
eISSN - 1755-1307
pISSN - 1755-1315
DOI - 10.1088/1755-1315/675/1/012120
Subject(s) - homogeneous , exponential function , consumption (sociology) , energy consumption , mathematics , exponential growth , mathematical optimization , value (mathematics) , computer science , statistics , econometrics , engineering , mathematical analysis , social science , combinatorics , sociology , electrical engineering
The classical non-homogeneous exponential grey model is a valid tool for accurate prediction with small samples. But the classical non-homogeneous exponential grey model needs to be improved for higher accuracy. In this paper, a new discrete non-homogeneous exponential grey model is proposed, and the background value of the new model is given by Simpson numerical integration formula. Further, the electricity consumption is given to validate the accuracy of the new model and the result illustrates the new model provides accurate prediction. In the example, the mean absolute percentage error is 2.14%. Finally, the new model is used to forecast the consumption of energy for China in 2025 and the result is 1076.08 million tons of standard coal. It is of great significance to make scientific decisions and plans on energy development.