Abstract
The development of wind power has a higher requirement for the accurate prediction of wind. In this paper, a trustworthy and practical approach, Multidimensional Support Vector Regression (MSVR) with Data-Dependent Kernel(DDK), is proposed. In the prediction model, we applied the longitudinal component and lateral component of the wind speed, changed from original wind speed and direction, as the input of this model. Then the Data-Dependent kernel is instead of classic kernels. In order to prove this model, actual wind data from NCEP/NCAR is used to test. MSVR with DDK model has higher accuracy comparing with MSVR without DDK, single SVR, Neural Networks.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Negnevitsky, M., Potter, C.W.: Innovative short-term wind generation prediction techniques. In: Power Engineer in Society General Meeting, pp. 60-65. IEEE Press, Montreal (2006)
Han, S., Yang, Y.P., Liu, Y.Q.: Application study of three methods in wind speed prediction. J. North China Electric Power Univ. 35(3), 57–61 (2008)
Firat, U., Engin, S.N., Saralcar, M., Ertuzun, A.B.: Wind speed forecasting based on second order blind identification and autoregressive model. In: International Conference on Machine Learning and Applications (ICMLA), pp. 686-691 (2010)
Babazadeh, H., Gao, W.Z., Lin, C., Jin, L.: An hour ahead wind speed prediction by Kalman filter. In: Power Electronics and Machines in Wind Applications (PEMWA), pp. 1-6 (2012)
Huang, C.Y., Liu, Y.W., TZENG W.C., Wang, P.Y.: Short term wind speed predictions by using the grey prediction model based forecast method. In: Green Technologies Conference (IEEE-Green), pp. 1-5 (2011)
Ghanbarzadeh, A., Noghrehabadi, A.R., Behrang, M.A., Assareh, E.: Wind speed prediction based on simple meteorological data using artificial neural network. In: IEEE International Conference on Industrial Informatics, pp. 664-667 (2009)
Peng, H.W., Yang, X.F., Liu, F.R.: Short-term wind speed forecasting of wind farm based on SVM method. Power Syst. Clean Energy 07, 48–52 (2009)
Wang, D.C., Ni, Y.J., Chen, B.J., Cao, Z.L.: A wind speed forecasting model based on support vector regression with data dependent kernel. J. Nanjing Normal Univ. (Nat. Sci. Edn.) 37(3), 15–20 (2014)
Bin, G., Victor, S.: Feasibility and finite convergence analysis for accurate on-line v-support vector machine. IEEE Trans. Neural Netw. Learn. Syst. 24(8), 1304–1315 (2013)
Crotes, C., Vapnik, V.: Support vector networks. Mach. Learn. 20, 273–297 (1995)
Wu, I., Amari, S.: Conformal transformation of kernel functions: a data-dependent way to improve support vector machine classifiers. Neural Process. Lett. 15(1), 59–67 (2002)
Acknowledgments
This work was supported in full by the Natural Science Foundation of JiangSu Province No. BK2012858, and supported in part by the National Natural Science Foundation of China under grant numbers 61103141.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Wang, D., Ni, Y., Chen, B., Cao, Z., Tian, Y., Zhao, Y. (2015). Wind Speed and Direction Predictions Based on Multidimensional Support Vector Regression with Data-Dependent Kernel. In: Huang, Z., Sun, X., Luo, J., Wang, J. (eds) Cloud Computing and Security. ICCCS 2015. Lecture Notes in Computer Science(), vol 9483. Springer, Cham. https://doi.org/10.1007/978-3-319-27051-7_36
Download citation
DOI: https://doi.org/10.1007/978-3-319-27051-7_36
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-27050-0
Online ISBN: 978-3-319-27051-7
eBook Packages: Computer ScienceComputer Science (R0)