Facta universitatis - series: Electronics and Energetics
kako citirati ovaj članak
podeli ovaj članak


  • citati u SCIndeksu: 0
  • citati u CrossRef-u:0
  • citati u Google Scholaru:[]
  • posete u poslednjih 30 dana:1
  • preuzimanja u poslednjih 30 dana:0


članak: 1 od 1  
Mid-term load forecasting using recursive time series prediction strategy with support vector machines
(naslov ne postoji na srpskom)
aTechnical College of vocational studies, Nis
bUniverzitet u Nišu, Elektronski fakultet

e-adresamilos.stojanovic@vtsnis.edu.rs, milos1bozic@yahoo.com, milena.stankovic@elfak.ni.ac.rs
(ne postoji na srpskom)
Mediumterm load forecasting, using recursive time - series prediction strategy with Support Vector Machines (SVMs) is presented in this paper. The forecasting is performed for electrical maximum daily load for the period of one month. The data considered for forecasting consist of half hour daily loads and daily average temperatures for period of one year. An analysis of available data was performed and the most adequate set of features for our model are chosen. For evaluation of prediction accuracy we used data obtained from electricity load forecasting competition on the EUNITE network. Some drawn conclusions from the results are that the temperature significantly affects on load demand, but absence of future temperature information can be overcome with time - series concept. Also, it was shown that size and structure of the training set for SVM may significantly affect the accuracy of load forecasting.
Arroyo, D.O., Skov, M.K., Huynh, Q. (2005) Accurate electricity load forecasting with artificial neural networks. u: International Conference on Computational Intelligence for Modeling, Control and Automation, November, Vienna, Proceedings
Basak, D., Pal, S., Patranabis, D.C. Support vector regression. Neural Information Processing, vol. 11, br. 10, str. 203-224, Oct. 2010
Bunnoon, P., Chalermyanont, K., Limsakul, C. A computing model of artificial intelligent approaches to mid-term load forecasting: A state-of-the-art survey for the researcher. International Journal of Engineering Technology, vol. 2, br. 1, str. 94-101, Feb. 2010
Chang, C.C., Lin, C.J. (2005) LibSVM: A library for support vector machines. National Science Council of Taiwan
Chang, M.W., Chen, B.J., Lin, C.J. (2002) EUNITE network competition: Electricity load forecasting. Department of Computer Science and Information Engineering, National Taiwan University, Tech. Rep., http://neuron.tuke.sk/competition/index.php
Chen, B.J., Chang, M.W., Lin, C.J. (2002) Load forecasting using support vector machines: A study on EUNITE competition 2001. Taiwan: Department of Computer Science and Information Engineering, Tech. Rep
Cherkassky, V., Ma, Y. (2004) Practical selection of SVM parameters and noise estimation for SVM regression. Neural Networks, 17(1): 113
Crone, S.F., Pietsch, S. (2007) A naive support vector regression benchmark for the NN3 forecasting competition. u: International Joint Conference on Neural Networks, August, Orlando, Florida
Hao, J. (2005) Input selection using mutual information: Applications to time series prediction. Helsinki: Department of Computer Science and Engineering, Masters thesis
Hsu, C.W., Chang, C.C., Lin, C.J. (2003) A practical guide to support vector classification. Taiwan: Department of Computer Science
Jain, A., Satish, B. (2009) Clustering based short term load forecasting using support vector machines. u: Power Tech Conference, Bucharest, Romania, July
Lendasse, A., Wertz, V., Simon, G., Verleysen, M. (2004) Fast bootstrap applied to LSSVM for long term prediction of time series. u: International Joint Conference on Neural Networks, Budapest, Hungary, July, str. 705-710
Merino, M.M., Roman, J. (2006) Electricity load forecasting using self organizing maps. u: International Conference on Artificial Neural Networks, Athens: Springer, str. 709-716
Ruping, S. (2001) SVMkernels for time series analysis. u: LLWA 01, Dortmund, October, Germany, str. 43-50
Smola, A.J., Schölkopf, B. (2004) A tutorial on support vector regression. Statistics and Computing, 14(3): 199
Sorjamaa, A., Hao, J., Reyhani, N., Ji, Y., Lendasse, A. (2007) Methodology for long-term prediction of time series. Neurocomputing, 70(16-18): 2861-2869
Turker, N., Gunes, F. (2006) A competitive approach to neural device modeling: Support vector machines. u: International Conference on Artificial Neural Networks, September, Athens, Greece, Springer, str. 974-981
Vapnik, V.N. (1998) Statistical learning theory. New York: Wiley

O članku

jezik rada: engleski
vrsta rada: neklasifikovan
DOI: 10.2298/FUEE1003287S
objavljen u SCIndeksu: 28.12.2010.