The ELM Model to Estimate Energy Demand of China

DOI

10.2991/iccte-16.2016.236How to use a DOI?

Keywords

Energy Demand; Projection; ELM; Scenario Analysis

Abstract

Energy demand is closely bound up with the problem of global climate change, environmental pollution and carbon emissions, which is always a hot issue that the world is paying attention to, especially the energy demand scale is the focus of social attention. Therefore, it is highly urgent to forecast the energy demand accurately. Firstly, this paper summarizes six main factors of energy demand; Then, constructs the prediction model based on ELM, trains and tests the model based on historical sample data of energy demand and its factors; Finally, forecasts evolution rule of China's energy demand as its factors from 2014 to 2035 through setting three scenarios. Conclusions show that: 1) The error rate of ELM model in training phase and testing phase is only 1.35% and 0.18% respectively, and the prediction results of energy demand in this paper with the method of ELM model is relatively close to the predicted results of EIA and BP; 2) China's energy demand in future will present a gradual increment trend, which will reach 5.29, 6.61 and 6.92 billion tons of standard coal respectively in 2020, 2030 and 2035 under the baseline scenario, and the energy supply system and carbon emissions system in future will still be under grater pressure; 3) China's energy demand will still experience a rigid growth stage with a high speed, but the growth rate of energy demand will tend to slow down gradually.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Shuai Wei
PY  - 2016/01
DA  - 2016/01
TI  - The ELM Model to Estimate Energy Demand of China
BT  - Proceedings of the 2016 International Conference on Civil, Transportation and Environment
PB  - Atlantis Press
SP  - 1343
EP  - 1350
SN  - 2352-5401
UR  - https://doi.org/10.2991/iccte-16.2016.236
DO  - 10.2991/iccte-16.2016.236
ID  - Wei2016/01
ER  -