Abstract
Improving the proportion of natural gas consumption of the manufacturing industry would make significant contributions to the low-carbon and sustainable development of China, which is one of the largest manufacturers in the world. However, it is very difficult to catch the trend of natural gas consumption of the concerning manufacturing industry as not enough trustable data can be collected. To fill this gap, a novel time-delayed fractional grey model is developed to forecast the natural gas consumption concerning time-delayed effect. Theoretical analysis shows it has more general formulation, unbiasedness and higher flexibility than the existing similar model. Being optimized by the Particle Swarm Optimization algorithm, the proposed model presents higher accuracy in four validation cases. Finally, it is used to forecast the natural gas consumption of the manufacturing industry of China, and the results show that the proposed model significantly outperforms the other seven existing grey models.
Original language | English |
---|---|
Article number | 263 |
Number of pages | 30 |
Journal | Journal of Computational and Applied Mathematics |
Volume | 39 |
DOIs | |
Publication status | Published - 4 Sept 2020 |
Externally published | Yes |
Bibliographical note
AcknowledgementsThis work received the support of the National Natural Science Foundation of China (71901184), Humanities and Social Science Fund of Ministry of Education of China (19YJCZH119), National Statistical Scientific Research Project (2018LY42).