Nature Environment and Pollution Technology

Open Access Open Access  Restricted Access Subscription Access

Forecast and Control Study on Energy Consumption of China


Affiliations
1 College of International Economics and Trade, Jilin University of Finance and Economics, 130117, Changchun, China
 

Energy is an essential material for social development, as well as vital strategic material for a countries' economy. Therefore, the society pays more attention to it. This article builds a non-linear model to forecast the energy consumption amount of China during 2015 to 2017 based on supported vector. Meanwhile, principles such as grey correlation, genetic algorithms and principal component analysis are being manipulated to ensure the comprehensive, objective and authenticity for model processing operation. All these efforts enhance the accuracy and dynamic fitness of the model.

Keywords

Energy Consumption, Forecast, Genetic Algorithm.
User
Notifications
Font Size


  • Birol, F. and Keppler, J. H. 2000. Prices, technology development and the rebound effect. Energy Policy, 28: 457-469.

  • Garbaccio, R. F., Ho, M. S. and Jorgenson, D. W. 1999. Why has the energy-output ratio fallen in China? Energy Journal, 20(3): 63- 91.

  • Kraft, J. and Kraft, A. 1978. Relationship between energy and GNP. J. Energy Dev., 3(2): 401-403.

  • Liang, Na and Zhang, Jigang 2008. Forecast of energy consumption based on grey RBF network. Jiamusi University Journal (Natural Science Press), 2: 224-226.

  • Lin, Boqiang 2001. Econometric analysis of China energy demands. Statistical Research, 10: 34-39.

  • Lu, Erpo 2005. The Statistics and Decision of China’s energy demand forecasting model. 20: 29-31.

  • Mulder, Peter, Henri, L.F., de Gischolar_main, Marjan and W. Hofkes 2003. Explaining slow diffusion of energy-saving technologies; avintage model with returns to diversity and learning-by-using. Resource and Energy Economics, 25: 105-126.

  • Wang, Huogen and Shen, Lisheng 2008. Chinese economic growth and energy consumption research-panel data of empirical test for China’s 30 provinces. Statistics and Decision, 3: 126-128.

  • Wu, Guohua, Zhong, Yi and Mu, Jing 2011. Talk about the control of total energy consumption in China. Energy Technology and Management, 5: 10-12.

  • Xu, Guoxiang and Yang, Zhenjian 2011. Construction and application study of PCA-GA-SVM model-Empirical analysis of the Shanghai and Shenzhen 300 index forecast accuracy. Journal of Quantitative & Technical Economics, 2: 135-147.

  • Xing, Lu and Shan, Baoguo 2012. International experience and implications of the control of total energy consumption of China. China Energy, 34(9): 14-16, 45

  • Zhang, Yanzhi, Nie, Rui and Lv, Tao 2007. Nine type energy input-output model and prediction of energy demand. Technology Review, 5: 25-29.

  • Zhang, Yuejun, Zhou, Bin and Wang, Li 2013. The prediction study of energy demand in Beijing based on support vector machine. Beijing Institute of Technology Journal (Social Science Press), 15(3): 8-12.


Abstract Views: 203

PDF Views: 0




  • Forecast and Control Study on Energy Consumption of China

Abstract Views: 203  |  PDF Views: 0

Authors

Tian-Bao Guo
College of International Economics and Trade, Jilin University of Finance and Economics, 130117, Changchun, China
Yu-Ling Dong
College of International Economics and Trade, Jilin University of Finance and Economics, 130117, Changchun, China
Yun-Feng Wang
College of International Economics and Trade, Jilin University of Finance and Economics, 130117, Changchun, China

Abstract


Energy is an essential material for social development, as well as vital strategic material for a countries' economy. Therefore, the society pays more attention to it. This article builds a non-linear model to forecast the energy consumption amount of China during 2015 to 2017 based on supported vector. Meanwhile, principles such as grey correlation, genetic algorithms and principal component analysis are being manipulated to ensure the comprehensive, objective and authenticity for model processing operation. All these efforts enhance the accuracy and dynamic fitness of the model.

Keywords


Energy Consumption, Forecast, Genetic Algorithm.

References