期刊文献+

中国工业化、城市化进程中的能源需求预测与分析 被引量:37

China Energy Demand Forecast and Analysis in the Process of Industrialization and Urbanization
下载PDF
导出
摘要 为了取得可靠的能源需求预测,本文引入工业化、城市化等重要因素,利用支持向量回归机在时间序列预测中的优势,确定了输入向量集合和输出向量集合,建立基于支持向量回归机能源需求预测模型。将我国1985-2009年能源需求相关数据进行模拟与仿真,并对中国2010-2020年能源需求量进行预测,并模拟解释变量不同增长率下能源需求的演变并给出政策选择。研究结果表明,中国高速的经济增长以及工业化和城市化的发展对能源需求影响很大,到2020年能源需求将达到45.3亿t标准煤,而且经济增长速度越快对能源需求就越大。变量模拟得出的结论是产业结构也是能源需求重要影响因素之一,工业结构的调整,即便是微调,也会对能源需求有很大的抑制作用;中国城市化进程以及城市化发展阶段所表现出的工业化特征,推动了能源需求快速增长,城市化率越高对能源需求越大,且对能源需求是刚性的,城市化也是能源需求重要影响因素之一。 In order to obtain reliable Chinese energy demand forecast,this paper introduces some important factors such as urbanization and industrialization,and makes use of the advantages of Support Vector Regression(SVR)in the prediction of time series,decides the set of input vectors,and output vectors,and then establishes the model of prediction of energy demand by SVR.This paper gives policy choice through modeling and simulating the related data of energy demand from 1985 to 2009,forecasting Chinese energy demand from 2010 to 2020 and simulating the evolution of energy demand under different growth of explanatory variables.The results show that the Chinese economy which is developing with a high speed,and the advancement of industrialization and urbanization have caused great impact on energy demand,and energy demand will be 4.53 billion tons of standard coal by 2020.And the greater the economic growth rate,the greater the energy demand.The result implication from the simulation shows that the industrial structure is also one of the important influencing factors of energy demand,and adjustment of industrial structure,even very small adjustment,would greatly impact energy demand.We find that the recent rapid growth of energy demand in China mainly comes from its accelerating process of urbanization and the industrial characteristics that required have appeared in a rapid urbanization process.The higher the rates of urbanization,the greater energy demand,and demand for energy is rigid.Urbanization is also one of the important influencing factors of energy demand.
作者 孙涵 成金华
出处 《中国人口·资源与环境》 CSSCI 北大核心 2011年第7期7-12,共6页 China Population,Resources and Environment
基金 中国地质大学(武汉)优秀青年教师特色学科团队项目(编号:CUG090113) 教育部人文社科青年项目(编号:10YJC790071)
关键词 能源需求 城市化 工业化 支持向量回归机 energy demand urbanization industrialization support vector regression
  • 相关文献

参考文献16

  • 1Capros P, Mantzos L. The European Energy Outlook to 2010 and 2030[ J ]. International Journal of Global Energy Issues, 2000, 14 (1-4): 137-154.
  • 2梁巧梅,魏一鸣,范英,Norio Okada.中国能源需求和能源强度预测的情景分析模型及其应用[J].管理学报,2004,1(1):62-66. 被引量:92
  • 3Bentzen J, Engsted T. Short and Long Run Elasticities in Energy Demand: A Cointegration Approach [J]. Energy Economics, 1993, 15:9 -16.
  • 4何晓萍,刘希颖,林艳苹.中国城市化进程中的电力需求预测[J].经济研究,2009,44(1):118-130. 被引量:146
  • 5林伯强,魏巍贤,李丕东.中国长期煤炭需求:影响与政策选择[J].经济研究,2007,42(2):48-58. 被引量:143
  • 6林伯强.中国重化工业之行的能源和环境约束[N/OL].2005,5.http://www.21page.net/html/2005—10—18/17393.htm.
  • 7林伯强.城市化是能源可持续问题的关键[N/OL].21世纪经济报道,2008,5.http://www.21cbh.corn/.
  • 8胡雪棉,赵国浩.基于Matlab的BP神经网络煤炭需求预测模型[J].中国管理科学,2008,16(S1):521-525. 被引量:42
  • 9Lawrence S, Giles C L, Tsoi A C. Lessons in Neural Network Training: Overfitting May Be Harder Than Expected [ C ]. Proceedings of the Fourteenth National Conference on Artificial Intelligence [ M ]. Mento Park, CA : AAA1 Press, 1997 : 540 - 545.
  • 10Moody J E. The Effective Number of Parameters: An Analysis of Generalization and Regularization in Nonlinear Learning Systems [ J ]. NIPS, 1992,4:847 - 854.

二级参考文献91

共引文献618

同被引文献391

引证文献37

二级引证文献275

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部