Short-term forecasting optimization algorithms for wind speed along Qinghai-Tibet railway based on different intelligent modeling theories

Abstract

To protect trains against strong cross-wind along Qinghai-Tibet railway, a strong wind speed monitoring and warning system was developed. And to obtain high-precision wind speed short-term forecasting values for the system to make more accurate scheduling decision, two optimization algorithms were proposed. Using them to make calculative examples for actual wind speed time series from the 18th meteorological station, the results show that: the optimization algorithm based on wavelet analysis method and improved time series analysis method can attain high-precision multi-step forecasting values, the mean relative errors of one-step, three-step, five-step and ten-step forecasting are only 0.30%, 0.75%, 1.15% and 1.65%, respectively. The optimization algorithm based on wavelet analysis method and Kalman time series analysis method can obtain high-precision one-step forecasting values, the mean relative error of one-step forecasting is reduced by 61.67% to 0.115%. The two optimization algorithms both maintain the modeling simple character, and can attain prediction explicit equations after modeling calculation.

Keywords

train safety / wind speed forecasting / wavelet analysis / time series analysis / Kalman filter / optimization algorithm

References

[1] TianH.-q., MiaoX.-j., GaoG.-jun.. Aerodynamic performance of sidewall shape of boxcar under strong crosswind [J]. Journal of Traffic and Transportation Engineering, 2006, 6(3): 5-8

[2] ZhouD., TianH.-q., YangM.-z., LuZ.-jun.. Comparison of aerodynamic performance of different kinds of wagons running on embankment of the Qinghai-Tibet Railway under strong cross-wind [J]. Journal of the China Railway Society, 2007, 29(5): 32-36

[3] TianH.-qi.. Study evolvement of train aerodynamics in China [J]. Journal of Traffic and Transportation Engineering, 2006, 6(1): 1-9

[4] GaoG.-j., TianH.-q., YaoS., LiuT.-h., BiG.-hong.. Effect of strong cross-wind on the stability of trains running on the Lanzhou-Xinjiang railway line [J]. Journal of the China Railway Society, 2004, 26(4): 36-40

[5] LiY.-f., LiangX.-f., GaoG.-j., LiuT.-hong.. Influence of cross-wind on aerodynamic performances of high-speed container flat car running on embankment [J]. Journal of Railway Science and Engineering, 2007, 4(5): 78-82

[6] SuzukiM., TanemotoK., MaedaT.. Aerodynamic characteristics of train/vehicles under cross winds [J]. Journal of Wind Engineering and Industrial Aerodynamics, 2003, 91(1): 209-218

[7] BarcalaM., MeseguerJ.. An experimental study of the influence of parapets on the aerodynamic loads under cross wind on a two-dimensional model of a railway vehicle on a bridge [J]. Journal of Rail and Rapid Transit, 2007, 221(4): 487-494

[8] HoppmannU., KoenigS., TielkesT., MatschkeG.. A short-term strong wind prediction model for railway application: Design and verification [J]. Journal of Wind Engineering and Industrial Aerodynamics, 2002, 90(10): 1127-1134

[9] ImaiT., FujiiT., TanemotoK., ShimamuraT., MaedaT., IshidaH., HibinoY.. New train regulation method based on wind direction and velocity of natural wind against strong winds [J]. Journal of Wind Engineering and Industrial Aerodynamics, 2002, 90(12/15): 1601-1610

[10] AnderssonE., HaggstromJ., SimaM., StichelS.. Assessment of train-overturning risk due to strong cross-winds [J]. Journal of Rail and Rapid Transit, 2004, 218(3): 213-223

[11] PanD.-f., LiuH., LiY.-fei.. A wind forecasting optimization model for wind farms based on time series analysis and Kalman filter algorithm [J]. Power System Technology, 2008, 32(7): 82-86

[12] SanzS., PerezA., OrtizE., PortillaA., PrietoL., ParedesD., CorreosoF.. Short-term wind speed prediction by hybridizing global and mesoscale forecasting models with artificial neural networks [C]. Proceedings of the 8th International Conference on Hybrid Intelligent Systems, 2008, Piscataway, Institute of Electrical and Electronics Engineers Computer Society: 608-612

[13] TorresJ., GarciaA., DeblasM., DefranciscoA.. Forecast of hourly average wind speed with ARMA models in Navarre (Spain) [J]. Solar Energy, 2005, 71(1): 65-77

[14] LoukaP., GalanisG., SiebertN., KariniotakisG., KatsafadosP., PytharoulisI., KallosG.. Improvements in wind speed forecasts for wind power prediction purposes using Kalman filtering [J]. Journal of Wind Engineering and Industrial Aerodynamics, 2008, 96(12): 2348-2362

[15] ErasmoC., WilfridoR.. Short term wind speed forecasting in La Venta, Oaxaca, Mexico, using artificial neural networks [J]. Renewable Energy, 2008, 34(1): 274-278

[16] FerreiraA., LudermirT., AquinoD., RonaldoR., LiraM., NetoN.. Investigating the use of reservoir computing for forecasting the hourly wind speed in short-term [C]. Proceedings of the International Joint Conference on Neural Networks, 2008, Piscataway, Institute of Electrical and Electronics Engineers Inc: 1649-1656

[17] CostaaA., CresopbA., NavarroaJ., LizcanocG., MadsendH., FeitosaeE.. A review on the young history of the wind power short-term prediction [J]. Renewable and Sustainable Energy Reviews, 2008, 12(6): 1725-1744

[18] MarciukaitisM., KatinasV., KavaliauskasA.. Wind power usage and prediction prospects in Lithuania [J]. Renewable and Sustainable Energy Reviews, 2008, 12(1): 265-277

[19] CastronetoM., JeongY. S., JeongM. K., HanL. D.. Online-SVR for short-term traffic flow prediction under typical and atypical traffic conditions [J]. Expert Systems with Applications, 2009, 36(3): 6164-6173

[20] XueJ.-n., ShiZ.-ke.. Short-time traffic flow prediction based on chaos time series theory [J]. Journal of Transportation Systems Engineering and Information Technology, 2008, 8(5): 68-72