LS-SVM model for electrical load prediction based on incremental training set update

• Autorzy: Stojanović M. , Božić M. , Stajić Z. , Milošević M.

Warianty tytułu

PL

Model LS-SVM w predykcji obciążenia elektrycznego – przyrostowa metoda uczenia

• Języki publikacji: EN

Abstrakty

EN

In this paper a forecasting model based on an incremental update scheme is proposed for the hourly load demand of the next day, using least square support vector machines (LS-SVM). The model is based on historical daily load demands in combination with calendar and climate features. The presented model was tested on real-life load data and the results show that the proposed approach can, by catching the evolving nature of the load pattern and dynamically updating the training set with new instances, lead to significant improvements in the accuracy of load forecasts.

PL

W artykule opisano opracowany model przyrostowy do przewidywania godzinowego zapotrzebowania na energię elektryczną na dzień następny, w którym wykorzystano maszynę wektorów pomocniczych LS-SVM. Proponowany model bazuje na wcześniejszych danych, dotyczących zapotrzebowania dziennego w połączeniu z analizą kalendarza i warunków klimatycznych. Badania eksperymentalne na rzeczywistych danych pozwala na skuteczne przewidywanie obciążenia energetycznego.

Słowa kluczowe

EN

load forecasting; LS-SVM model; incremental model

PL

przewidywanie obciążenia; model LS-SVM; model przyrostu niezawodności

• Wydawca: Wydawnictwo SIGMA-NOT
• Czasopismo: Przegląd Elektrotechniczny
• Rocznik: 2013
• Tom: R. 89, nr 4
• Strony: 194--198
• Opis fizyczny: Bibliogr. 16 poz., rys., wykr.

Twórcy

autor

Stojanović M.

• School of Higher Technical Professional Education Niš

autor

Božić M.

• Faculty of Electronic Engineering, University of Niš

autor

Stajić Z.

• School of Higher Technical Professional Education Niš

autor

Milošević M.

• R&D Center Alfatec

Bibliografia

• [1] Papalexopoulos A.D., Hesterberg T.C., A regression-based approach to short-term load forecasting, IEEE Transactions on Power System, 5 (1990), No. 4 1535–1550.
• [2] Christiaanse W.R., Short term load forecasting using general exponential smoothing, IEEE Transactions on Power Apparatus and Systems, 90 (1971), 900–911.
• [3] Huang S.J., Shih K.R., Short-term load forecasting via ARMA model identification including non Gaussian process considerations, IEEE Transactions on Power System, 18 (2003), No. 2, 673–679.
• [4] Irisarri G.D., Widergren S.E., Yehsakul P.D., On-line load forecasting for energy control center application, IEEE Transactions on Power Apparatus and Systems, 101 (1982), 71–78.
• [5] Hippert H.S., Pedreira C.E., Castro R., Neural networks for short term load forecasting: A review and evaluation, IEEE Transactions on Power System, 16 (2001), No. 1, 44–55.
• [6] Rahman S., Bhatnagar R., An expert system based algorithm for short term load forecast, IEEE Transactions on Power System, 3 (1998), No. 2, 392–399.
• [7] Mori H., Kobayashi H., Optimal fuzzy inference for short-term load forecasting, IEEE Transactions on Power System, 11 (1996), 390–396.
• [8] Chen B., Chang M., Lin C., Load forecasting using support vector machines: A study on EUNITE competition 2001, IEEE Transactions on Power System, 19 (2004), No. 4, 1821–1830.
• [9] Božić M., Stojanović M., Stajić Z., Short - term electric load forecasting using Least squares support vector machines, Facta Universitatis Automatic Control and Robotics, 9 (2010), No. 1, 141-150.
• [10] Wang L., Liu Z., RVM with wavelet kernel combined with PSO for short-term load forecasting in electric power systems, Przegląd Elektrotechniczny, 88 (2012), nr 1b, 146-149.
• [11] Amjady N., Short-term bus load forecasting of power systems by a new hybrid method, IEEE Transactions on Power System, 22 (2007), No. 1, 333–341.
• [12] Huang C.M., Huang C.J, Wang M.L., A particle swarm optimization to identifying the ARMAX model for short-term load forecasting, IEEE Transactions on Power System, 20 (2005), No. 2, 1126–1133.
• [13] Asrari A., Javan D.S., Javidi M.H., Monfared M., Application of Gray-Fuzzy-Markov Chain Method for Day-Ahead Electric Load Forecasting, Przegląd Elektrotechniczny, 88 (2012), nr 3b, 228-237.
• [14] Dudek G., Neuro-fuzzy approach to the next day load curve forecasting, Przegląd Elektrotechniczny, 87 (2011), nr 2, 61-64.
• [15] Dudek G., Artificial Immune Clustering Algorithm to Forecasting Seasonal Time Series, Computational Collective Intelligence. Technologies and Applications, vol. 6922, Springer, pp 468 - 477, 2011.
• [16] Suykens K., Gestel T., Brabanter J., Moor B, Vandewalle J., Least Squares Support Vector Machines, World Scientific, Singapore, 2002.