Modeling and prediction of Turkey’s electricity consumption using Support Vector Regression
DOI: 10.1016/J.APENERGY.2010.07.021
关键词: Electricity 、 Variable (computer science) 、 Engineering 、 Consumption (economics) 、 Support vector machine 、 Energy modeling 、 Econometrics 、 Hyperparameter optimization 、 Population 、 Mean squared error
摘要: Abstract Support Vector Regression (SVR) methodology is used to model and predict Turkey’s electricity consumption. Among various SVR formalisms, e-SVR method was since the training pattern set relatively small. Electricity consumption modeled as a function of socio-economic indicators such population, Gross National Product, imports exports. In order facilitate future predictions consumption, separate created for each input variables using their current past values; these models were combined yield prediction values. A grid search parameters performed find best variable based on Root Mean Square Error. Turkey predicted until 2026 data from 1975 2006. The results show that can be
elsevier.com
sci-hub.se 参考文章(26)
Vladimir Naumovich Vapnik, Estimation of Dependences Based on Empirical Data ,(2010)
Obas John Ebohon, Energy, economic growth and causality in developing countries: A case study of Tanzania and Nigeria Energy Policy. ,vol. 24, pp. 447- 453 ,(1996) , 10.1016/0301-4215(96)00027-4
Eden S.H. Yu, Been-Kwei Hwang, The relationship between energy and GNP Energy Economics. ,vol. 6, pp. 186- 190 ,(1984) , 10.1016/0140-9883(84)90015-X
Torsten Soderstrom, Discrete-Time Stochastic Systems: Estimation and Control Springer-Verlag New York, Inc.. ,(1995)
Alex J. Smola, Bernhard Schölkopf, A tutorial on support vector regression Statistics and Computing. ,vol. 14, pp. 199- 222 ,(2004) , 10.1023/B:STCO.0000035301.49549.88
M. Duran Toksarı, Ant colony optimization approach to estimate energy demand of Turkey Energy Policy. ,vol. 35, pp. 3984- 3990 ,(2007) , 10.1016/J.ENPOL.2007.01.028
Igor Beliaev, Robert Kozma, Time series prediction using chaotic neural networks on the CATS benchmark Neurocomputing. ,vol. 70, pp. 2426- 2439 ,(2007) , 10.1016/J.NEUCOM.2006.09.013
Yetis Sazi Murat, Halim Ceylan, Use of artificial neural networks for transport energy demand modeling Energy Policy. ,vol. 34, pp. 3165- 3172 ,(2006) , 10.1016/J.ENPOL.2005.02.010
Volkan Ş. Ediger, Hüseyin Tatlıdil, Forecasting the primary energy demand in Turkey and analysis of cyclic patterns Energy Conversion and Management. ,vol. 43, pp. 473- 487 ,(2002) , 10.1016/S0196-8904(01)00033-4
Coşkun Hamzaçebi, Forecasting of Turkey's net electricity energy consumption on sectoral bases Energy Policy. ,vol. 35, pp. 2009- 2016 ,(2007) , 10.1016/J.ENPOL.2006.03.014