Forecasting fuel combustion-related CO$_2$ emissions by a novel continuous fractional nonlinear grey Bernoulli model with Grey Wolf Optimizer
Abstract
Foresight of CO emissions from fuel combustion is essential for policy-makers to identify ready targets for effective reduction plans and further to improve energy policies and plans. For the purpose of accurately forecasting the future development of China's CO emissions from fuel combustion, a novel continuous fractional nonlinear grey Bernoulli model is developed in this paper. The fractional nonlinear grey Bernoulli model already in place is known that has a fixed first-order derivative that impairs the predictive performance to some extent. To address this problem, in the newly proposed model, a flexible variable is introduced into the order of derivative, freeing it from integer-order accumulation. In order to further improve the performance of the newly proposed model, a meta-heuristic algorithm, namely Grey Wolf Optimizer (GWO), is determined to the emerging coefficients. To demonstrate the effectiveness, two real examples and China's fuel combustion-related CO emissions are used for model validation by comparing with other benchmark models, the results show the proposed model outperforms competitors. Thus, the future development trend of fuel combustion-related CO emissions by 2023 are predicted, accounting for 10039.80 Million tons (Mt). In accordance with the forecasts, several suggestions are provided to curb carbon dioxide emissions.
Keywords
Cite
@article{arxiv.2012.03241,
title = {Forecasting fuel combustion-related CO$_2$ emissions by a novel continuous fractional nonlinear grey Bernoulli model with Grey Wolf Optimizer},
author = {Wanli Xie and Wen-Ze Wu and Chong Liu and Tao Zhang and Zijie Dong},
journal= {arXiv preprint arXiv:2012.03241},
year = {2020}
}