Knowledge and Information Systems

, Volume 52, Issue 1, pp 255–265 | Cite as

Wind speed parameters sensitivity analysis based on fractals and neuro-fuzzy selection technique

  • Vlastimir Nikolić
  • Vojislav V. Mitić
  • Ljubiša Kocić
  • Dalibor Petković
Regular Paper

Abstract

Fluctuation of wind speed affects wind energy systems since the potential wind power is proportional the cube of wind speed. Hence precise prediction of wind speed is very important to improve the performances of the systems. Due to unstable behavior of the wind speed above different terrains, in this study fractal characteristics of the wind speed series were analyzed. According to the self-similarity characteristic and the scale invariance, the fractal extrapolate interpolation prediction can be performed by extending the fractal characteristic from internal interval to external interval. Afterward neuro-fuzzy technique was applied to the fractal data because of high nonlinearity of the data. The neuro-fuzzy approach was used to detect the most important variables which affect the wind speed according to the fractal dimensions. The main goal was to investigate the influence of terrain roughness length and different heights of the wind speed on the wind speed prediction.

Keywords

Wind speed Neuro-fuzzy Variable selection Fractal interpolation 

References

  1. 1.
    Abdi DS, Bitsuamlak GT (2014) Wind flow simulations on idealized and real complex terrain using various turbulence models. Adv Eng Softw 75:30–41CrossRefGoogle Scholar
  2. 2.
    Andersson FO, Åberg M, Jacobsson SP (2000) Algorithmic approaches for studies of variable influence, contribution and selection in neural networks. Chemometr Intell Lab Syst 51(1):61–72CrossRefGoogle Scholar
  3. 3.
    Barszcz T, Bielecka M, Bielecki A, Wójcik M (2012) Wind speed modelling using Weierstrass function fitted by a genetic algorithm. J Wind Eng Ind Aerodyn 109:68–78CrossRefGoogle Scholar
  4. 4.
    Barnsley MF (2014) Fractals everywhere. Academic press, MassachusettsMATHGoogle Scholar
  5. 5.
    Calif R, Emilion R, Soubdhan T (2011) Classification of wind speed distributions using a mixture of Dirichlet distributions. Renew Energy 36(11):3091–3097CrossRefGoogle Scholar
  6. 6.
    Calif R (2012) PDF models and synthetic model for the wind speed fluctuations based on the resolution of Langevin equation. Appl Energy 99:173–182CrossRefGoogle Scholar
  7. 7.
    Chang TP, Ko HH, Liu FJ, Chen PH, Chang YP, Liang YH, Chen YH (2012) Fractal dimension of wind speed time series. Appl Energy 93:742–749CrossRefGoogle Scholar
  8. 8.
    Castellano G, Fanelli AM (2000) Variable selection using neural-network models. Neurocomputing 31(1):1–13CrossRefGoogle Scholar
  9. 9.
    Chan KY, Ling SH, Dillon TS, Nguyen HT (2011) Diagnosis of hypoglycemic episodes using a neural network based rule discovery system. Expert Syst Appl 38(8):9799–9808CrossRefGoogle Scholar
  10. 10.
    Cibas T, Soulié FF, Gallinari P, Raudys S (1996) Variable selection with neural networks. Neurocomputing 12(2):223–248CrossRefMATHGoogle Scholar
  11. 11.
    Dieterle F, Busche S, Gauglitz G (2003) Growing neural networks for a multivariate calibration and variable selection of time-resolved measurements. Anal Chim Acta 490(1):71–83CrossRefGoogle Scholar
  12. 12.
    Fractals MBLO (1975) Forme, Hasard et Dimension. Flammarion, Paris, p 192Google Scholar
  13. 13.
    Giovannini L, Antonacci G, Zardi D, Laiti L, Panziera L (2014) Sensitivity of simulated wind speed to spatial resolution over complex terrain. Energy Proc 59:323–329CrossRefGoogle Scholar
  14. 14.
    Huang GB, Chen L, Siew CK (2006) Universal approximation using incremental constructive feedforward networks with random hidden nodes. IEEE Trans Neural Netw 17(4):879–892CrossRefGoogle Scholar
  15. 15.
    He YC, Chan PW, Li QS (2014) Standardization of raw wind speed data under complex terrain conditions: a data-driven scheme. J Wind Eng Ind Aerodyn 131:12–30CrossRefGoogle Scholar
  16. 16.
    He YC, Chan PW, Li QS (2013) Wind characteristics over different terrains. J Wind Eng Ind Aerodyn 120:51–69CrossRefGoogle Scholar
  17. 17.
    Jang JS (1993) ANFIS: adaptive-network-based fuzzy inference system. IEEE Trans Syst Man Cybern 23(3):665–685CrossRefGoogle Scholar
  18. 18.
    Kwong CK, Wong TC, Chan KY (2009) A methodology of generating customer satisfaction models for new product development using a neuro-fuzzy approach. Exp Syst Appl 36(8):11262–11270CrossRefGoogle Scholar
  19. 19.
    Lopez P, Velo R, Maseda F (2008) Effect of direction on wind speed estimation in complex terrain using neural networks. Renew Energy 33(10):2266–2272CrossRefGoogle Scholar
  20. 20.
    Liang NY, Huang GB, Saratchandran P, Sundararajan N (2006) A fast and accurate online sequential learning algorithm for feedforward networks. IEEE Trans Neural Netw 17(6):1411–1423CrossRefGoogle Scholar
  21. 21.
    Lubitz WD, White BR (2007) Wind-tunnel and field investigation of the effect of local wind direction on speed-up over hills. J Wind Eng Ind Aerodyn 95(8):639–661CrossRefGoogle Scholar
  22. 22.
    Mandelbrot BB (1983) The fractal geometry of nature, vol 173. Macmillan, LondonGoogle Scholar
  23. 23.
    Mitchell SJ, Lanquaye-Opoku N, Modzelewski H, Shen Y, Stull R, Jackson P, Ruel JC (2008) Comparison of wind speeds obtained using numerical weather prediction models and topographic exposure indices for predicting windthrow in mountainous terrain. For Ecol Manag 254(2):193–204CrossRefGoogle Scholar
  24. 24.
    Makridis A, Chick J (2013) Validation of a CFD model of wind turbine wakes with terrain effects. J Wind Eng Ind Aerodyn 123:12–29CrossRefGoogle Scholar
  25. 25.
    Miller CA, Davenport AG (1998) Guidelines for the calculation of wind speed-ups in complex terrain. J Wind Eng Ind Aerodyn 74:189–197CrossRefGoogle Scholar
  26. 26.
    Mitić VV, Kocić LM, Mitrović I, Ristić MM (1997). Models of \(BaTiO_3\) ceramics grains contact surfaces. In: The 4th IUMRS international conference in Asia OVTA Makuhari, Chiba, JapanGoogle Scholar
  27. 27.
    Mitić VV, Kocić LM, Miljković M, Petković I (1998) Fractals and \(BaTiO_3\)-ceramic microstructure analysis. In: Love G, Nicholson WAP, Armigliato A (eds) Modern developments and applications in microbeam analysis. Springer Vienna, pp 365–369. doi:10.1007/978-3-7091-7506-4_48
  28. 28.
    Mitić VV, Kocić L, Paunović V, Pavlović V (2014a) Fractal corrections of \(BaTiO_3\)-ceramic sintering parameters. Sci Sinter 46(2):149–156Google Scholar
  29. 29.
    Mitić VV, Paunović V, Kocić L (2014b) Dielectric Properties of \(BaTiO_3\) Ceramics and Curie-Weiss and Modified Curie-Weiss Affected by Fractal Morphology. In: Advanced Processing and Manufacturing Technologies for Nanostructured and Multifunctional Materials: A Collection of Papers Presented at the 38th International Conference on Advanced Ceramics and Composites January 27–31, 2014 Daytona Beach, Florida (pp. 123–133). John Wiley & Sons, IncGoogle Scholar
  30. 30.
    Mitic VV, Paunovic V, Kocic L (2015a) Fractal approach to Ba\(TiO_3\)-ceramics micro-impedances. Ceram Int 41(5):6566–6574CrossRefGoogle Scholar
  31. 31.
    Mitić VV, Kocić L (2015) Fractal nature structure, grains and pores, reconstruction analysis method and application in advance designed microstructure properties prognosis function, Patent, Application number 2015/0152. Intellectual Property Office, SerbiaGoogle Scholar
  32. 32.
    Mitic VV, Kocic L, Paunovic V, Bastic F, Sirmic D (2015c) The Fractal Nature Materials Microstructure Influence on Electrochemical Energy Sources. Sci Sinter 47(2):195CrossRefGoogle Scholar
  33. 33.
    Obukhov AM (1988) Turbulentnost’ i dinamika atmosfery. Gidrometeoizdat, LeningradGoogle Scholar
  34. 34.
    Robertson A (1994) Directionality, fractals and chaos in wind-shaped forests. Agric For Meteorol 72(1):133–166CrossRefGoogle Scholar
  35. 35.
    Sharples JJ, McRae RHD, Weber RO (2010) Wind characteristics over complex terrain with implications for bushfire risk management. Environ Model Softw 25(10):1099–1120CrossRefGoogle Scholar
  36. 36.
    Serpa C, Buescu J (2015) Explicitly defined fractal interpolation functions with variable parameters. Chaos Solitons Fractals 75:76–83MathSciNetCrossRefMATHGoogle Scholar
  37. 37.
    Sofge D (2002) Using Genetic Algorithm Based Variable Selection to Improve Neural Network Models for Real-World Systems. In: ICMLA (pp. 16–19)Google Scholar
  38. 38.
    Xiu C, Wang T, Tian M, Li Y, Cheng Y (2014) Short-term prediction method of wind speed series based on fractal interpolation. Chaos Solitons Fractals 68:89–97CrossRefMATHGoogle Scholar
  39. 39.
    Vapnik VN, Vapnik V (1998) Statistical learning theory, vol 1. Wiley, New YorkMATHGoogle Scholar

Copyright information

© Springer-Verlag London 2016

Authors and Affiliations

  • Vlastimir Nikolić
    • 1
  • Vojislav V. Mitić
    • 2
  • Ljubiša Kocić
    • 3
  • Dalibor Petković
    • 4
  1. 1.University of Niš, Faculty of Mechanical EngineeringNišSerbia
  2. 2.Institute of Technical SciencesSerbian Academy of Science and ArtBelgradeSerbia
  3. 3.University of Niš, Faculty of Electronic EngineeringNišSerbia
  4. 4.University of Niš, Pedagogical Faculty in VranjeVranjeSerbia

Personalised recommendations