Wind speed forecasting is a prerequisite and a guarantee for the efficient operation of wind farms. Estimation of the non-stationary property and prediction of the future moving average of wind speed are challenging because of various environmental factors. In this paper, a new model is proposed for wind speed forecasting. The proposed model consists of three main stages: preprocessing, regression, and aggregation. In the first stage, the original wind speed time series is decomposed into different subseries by using the variational mode decomposition technique. These subseries are then used to construct training patterns and forecasted outputs. In the second stage, support vector regression is applied to fit and forecast the wind speed for each subseries. Eventually, the final forecasted wind speed is calculated by summing all the forecasting values of each subseries. The performance of the proposed model is evaluated using real data collected from a wind farm in China, and the experimental results confirm the superiority of the proposed model to the existing models with respect to accurate forecasting and stability.
SkittidesC. and FruhW.G., Wind forecasting using principalcomponent analysis, Renewable Energy69 (2014), 365–374.
2.
HuangN.T., YuanC., CaiG.W. and XingE.K., Hybrid short term windspeed forecasting using variational mode decomposition and aweighted regularized extreme learning machine, Energies19(2) (2016), 989.
3.
LiG. and ShiJ., Application of Bayesian model averaging inmodeling long-term wind speed distributions, Renewable Energy35(6) (2010), 1192–1202.
4.
JungJ. and BroadwaterR.P., Current status and future advances forwind speed and power forecasting, Renewable and SustainableEnergy Reviews31 (2014), 762–777.
YeR., SuganthanP.N. and SrikanthN., A comparative study ofempirical mode decomposition-based short-term wind speed forecastingmethods, IEEE Transactions on Sustainable Energy6(1) (2015), 236–244.
7.
PichelliE., FerrettiR., CiminiD., PanegrossiG., PerissinD.PierdiccaN., RoccaF. and RommenB., InSAR water vapor dataassimilation into mesoscale model MM5: Technique and pilot study, IEEE Journal of Selected Topics in Applied Earth Observationsand Remote Sensing8(8) (2015), 3859–3875.
8.
WagenbrennerN.S.ForthoferJ.M, LambB.K, ShannonK.S and ButlerB.W, Downscaling surface wind predictions from numerical weatherprediction models in complex terrain with WindNinja, Atmospheric Chemistrya and Physics16(8) (2016), 5229–5241.
9.
CadenasE. and RiveraW., Wind speed forecasting in three different regions of Mexico, using a hybrid ARIMA-ANN model, Renewable Energy35 (2010), 2732–2738.
10.
MaL., LuanS.Y., JiangC.W., LiuH.L. and ZhangY., A review on theforecasting of wind speed and generated power, Renewable and Sustainable Energy Reviews13 (2009), 915–920.
11.
ZuluagaC.D., ÁlvarezM.A. and GiraldoE., Short-term wind speedprediction based on robust Kalman filtering: An experimentalcomon, Applied Energy156(15) (2015), 321–330.
12.
CadenasE., JaramilloO.A. and RiveraW., Analysis and forecastingof wind velocity in chetumal, quintana roo, using the singleexponential smoothing method, Renewable Energy35 (2010), 925–930.
13.
GaoY.Y., QuC. and ZhangK.Q., A hybrid method based on singularanalysis, firefly algorithm, and BP neural network forshort-term wind speed forecasting, Energies9(10) (2016), 757–785spectrum.
14.
ChangG.W., LuH.J., ChangY.R. and LeeY.D., An improved neuralnetwork-based approach for short-term wind speed and power forecast, Renewable Energy105 (2017), 301–311.
15.
KongX.B., NiuX.J., ShiR.F. and LeeK.Y., Wind speed predictionusing reduced support vector machines with feature selection, Neurocomputing169 (2015), 449–456.
16.
WangJ.Z., QinS.S., ZhouQ.P. and JiangH.Y., Medium-term windspeeds forecasting utilizing hybrid models for three different sitesin Xinjiang, China, Renewable Energy76 (2015), 91–101.
17.
HuJ.M., WangJ.Z. and ZengG.W., A hybrid forecasting approachapplied to wind speed time series, Renewable Energy60 (2013), 185–194.
18.
HuQ.H., ZhangS.G., XieZ.X., MiJ.S. and WanJ., Noise model basedν-support vector regression with its application to short-termwind speed forecasting, Neural Networks57 (2014), 1–11.
19.
LiC., SanchezR.V., ZuritaG., CerradaM., CabreraD. and VásquezR.E., Multimodal deep support vector classification withhomologous features and its application to gearbox fault diagnosis, Neurocomputing168 (2015), 119–127.
20.
Santamaría-BonfilG., Reyes-BallesterosA. and GershensonWindC., speed forecasting for wind farms: A method based on supportvector regression, Renewable Energy85 (2016), 790–809.
21.
BaiY., SunZ.Z., ZengB., DengJ. and LiC., A multi-pattern deepfusion model for short-term bus passenger flow forecasting., Applied Soft Computing58 (2017), 669–680.
22.
WangJ.J, ZhangW.Y., LiY.N., WangJ.Z. and DangZ.L., Forecastingwind speed using empirical mode decomposition and Elman neuralnetwork, Applied Soft Computing23 (2014), 452–459.
23.
AbdoosA.A., A new intelligent method based on combination of VMD and ELM for short term wind power forecasting, Neurocomputing203 (2016), 111–120.
24.
LiuD., NiuD.X., WangH. and FanL.L., Short-term wind speedforecasting using wavelet transform and support vector machinesoptimized by genetic algorithm, Renewable Energy62 (2014), 592–597.
25.
WangS.X., ZhangN.WuL. and WangY.M., Wind speed forecastingbased on the hybrid enble empirical mode decomposition and GA-BPneural network method, Renewable Energy94 (2016), 629–636sem.
26.
MaX.J., JinY. and DongQ.L., A generalized dynamic fuzzy neuralnetwork based on singular analysis optimized by brain stormoptimization for short-term wind speed forecasting, AppliedSoft Computing54 (2017), 296–312spectrum.
27.
LiuH., TianH., LiangX. and LiY., Wind speed forecasting approachusing secondary decomposition algorithm and Elman neural networks, Applied Energy157 (2015), 183–194.
28.
LiC., OliveiraJ.V.D., SanchezR.V., CerradaM., ZuritaG. and CabreraD., Fuzzy determination of informative frequency band forbearing fault detection, Journal of Intelligent & FuzzySystems30 (2016), 3513–3525.
29.
LiC., LedoL., DelgadoM., CerradaM., PachecoF., CabreraD.SánchezR.V. and OliveiraJ.V.D., A Bayesian approach to consequentparameter estimation in probabilistic fuzzy systems and itsapplication to bearing fault classification., Knowledge- Based Systems129 (2017), 39–60.
30.
DragomiretskiyK. and ZossoD., Variational mode decomposition, IEEE Transactions on Signal Processing62(3) (2014), 531–544.
31.
LiuY.Y., YangG.L., LiM. and YinH.L., Variational modedecomposition denoising combined the detrended fluctuation analysis, Signal Processing125 (2016), 349–364.
32.
AbdoosA.A., MianaeiP.K. and GhadikolaeiM.R., Combined VMD-SVM based feature selection method for classification of power qualityevents, Applied Soft Computing38 (2016), 637–646.
33.
ZhangY.C., LiuK.P., QinL. and AnX.L., Deterministic andprobabilistic interval prediction for short-term wind powergeneration based on variational mode decomposition and machinelearning methods, Energy Converdion & Management112 (2016), 208–219.
34.
SuyKensJ.A.K. and VanJ., dewalle, Least squares support vectormachine classifiers, Neural Processing Letters9 (1999), 293–300.
35.
LiX.J., ChengZ.Q., YuQ.B., BaiY. and LiC., Water-qualityprediction using multimodal support vector re-gression: Case studyof Jialing River, China, Journal of Environmental Engineering143(10) (2017), 04017070.
36.
PUDN, wind farm data, online website, upload on February 16, 2014–http://www.pudn.com/downloads604/sourcecode/windows/system/detail2463000.html.
