Forecasting coal demand in key coal consuming industries based on the data-characteristic-driven decomposition ensemble model

Delu Wang, Cuicui Tian, Jinqi Mao and Fan Chen

Energy, 2023, vol. 282, issue C

Abstract: Accurately predicting the coal demand in China's key coal-consuming industries is crucial for coal exit path planning. This paper selects the chemical, building materials, steel and thermal power industries as research objects, organically integrates data-characteristic-driven and decomposition-ensemble ideas to construct combination forecasting models for coal demand in each industry, and empirically analyzes the influencing factors and evolutionary trends of coal demand in these industries. The results show that: First, the prediction accuracy and stability of models constructed in this paper based on data characteristics are significantly superior to other traditional combination models and single models. Second, the coal demand of all four industries is influenced by industrial policies and economic fluctuations, additionally, that of thermal power industry is increasingly influenced by energy-saving and emission reduction policies. Third, during 2021–2025, the overall coal demand in four industries will fall and then rise, reaching 2.88 billion tons by 2025; different industries will exhibit significant heterogeneity in coal demand trends, among which coal demand of thermal power industry will decrease and then rise, that of building materials industry will remain stable, while that of chemical and steel industries will show a fluctuating downward trend and the speed of decline: steel > chemical.

Keywords: Key coal consuming industries; Coal demand forecasting; Data-characteristic-driven (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544223022351
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:282:y:2023:i:c:s0360544223022351

DOI: 10.1016/j.energy.2023.128841

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().