Novel Compositional Data's Grey Model for Structurally Forecasting Arctic Crude Oil Import

11/03/2020 ∙ by Pan Qilong, et al. ∙ 0

The reserve of crude oil in the Arctic area is abundant. Ice melting is making it possible to have intermediate access to the Arctic crude oil and its transportation. A novel compositional data's grey model is proposed in this paper to structurally forecast Arctic crude oil import. Firstly, the general accumulative operation sequence of multivariate compositional data is defined according to Aitchison geometry, then obtaining the novel model with the form of the compositional data vectors. Secondly, this paper studies the least square parameter estimation of the model. The novel model is deduced and selected as the time-response expression of the solution. Thirdly, this paper infuses the novel model with traditional grey model to improve its robustness. Differential Evolution algorithm is introduced to determine the optimal value of the general matrix. Lastly, two validation examples are provided for confirming the effectiveness of the novel model by comparing it with other existing models, before being employed to forecast the crude oil import structure in China. The results show that the novel model provides better performance in all crude oil cases in short-term forecasting. Therefore, by using the new model, China's development parameter is 0.5214 and Determination Factor of the novel model is 0.5999, which means that the crude oil import structure of China is being changed. Specifically, the amount of crude oil imported from the Arctic area is obviously increasing in the next 6 years, showing sufficient proof of the edge owned by the Arctic area: abundant crude oil reserves and shortening transportation distance.



There are no comments yet.


page 1

page 11

page 13

page 22

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.