Artificial Neural Network Based Methodologies for the Estimation of Wind Speed

  • Despina Deligiorgi
  • Kostas Philippopoulos
  • Georgios Kouroupetroglou
Chapter
Part of the Green Energy and Technology book series (GREEN, volume 129)

Abstract

Recent advances in artificial neural networks (ANN) propose an alternative promising methodological approach to the problem of time series assessment as well as point spatial interpolation of irregularly and gridded data. In the field of wind power sustainable energy systems ANNs can be used as function approximators to estimate both the time and spatial wind speed distributions based on observational data. The first part of this work reviews the theoretical background, the mathematical formulation, the relative advantages, and limitations of ANN methodologies applicable to the field of wind speed time series and spatial modeling. The second part focuses on implementation issues and on evaluating the accuracy of the aforementioned methodologies using a set of metrics in the case of a specific region with complex terrain. A number of alternative feedforward ANN topologies have been applied in order to assess the spatial and time series wind speed prediction capabilities in different time scales. For the temporal forecasting of wind speed ANNs were trained using the Levenberg–Marquardt backpropagation algorithm with the optimum architecture being the one that minimizes the Mean Absolute Error on the validation set. For the spatial estimation of wind speed the nonlinear Radial basis function Artificial Neural Networks are compared versus the linear Multiple Linear Regression scheme.

References

  1. Barbounis TG, Theocharis JB (2007) Locally recurrent neural networks for wind speed prediction using spatial correlation. Inform Sci 177(24):5775–5797. doi:10.1016/j.ins.2007.05.024 CrossRefGoogle Scholar
  2. Beyer H, Degner T, Hausmann J, Hoffmann M, Rujan P (1994) Short term prediction of wind speed and power output of a wind turbine with neural networks. In: Proceedings of the 5th European wind energy association conference and exhibition. Thessaloniki, Greece, pp 349–352Google Scholar
  3. Bilgili M, Sahin B, Yasar A (2007) Application of artificial neural networks for the wind speed prediction of target station using reference stations data. Renew Energ 32:2350–2360. doi:10.1016/j.renene.2006.12.001 CrossRefGoogle Scholar
  4. Bishop CM (1995) Neural networks for pattern recognition. Oxford University Press, CambridgeGoogle Scholar
  5. Bouzgou H, Benoudjit N (2011) Multiple architecture system for wind speed prediction. Appl Energ 88:2463–2471. doi:10.1016/j.apenergy.2011.01.037 CrossRefGoogle Scholar
  6. Cadenas E, Rivera W (2007) Wind speed forecasting in the South coast of Oaxaca, Mexico. Renew Energ 32:2116–2128. doi:10.1016/j.renene.2006.10.005 CrossRefGoogle Scholar
  7. Cellura M, Cirrincione G, Marvuglia A, Miraoui A (2008) Wind speed spatial estimation for energy planning in Sicily: Introduction and statistical analysis. Renew Energ 33:1237–1250. doi:10.1016/j.renene.2007.08.012 CrossRefGoogle Scholar
  8. Costa A, Crespo A, Navarro J, Lizcano G, Madsen H, Feitosa E (2008) A review on the young history of the wind power short-term prediction. Renew Sust Energ Rev 12(6):1725–1744. doi:10.1016/j.rser.2007.01.015 CrossRefGoogle Scholar
  9. Cybenco G (1989) Approximation by superposition of a sigmoidal function. Math Control Signal 2:303–314. doi:10.1007/BF02551274 CrossRefGoogle Scholar
  10. Deligiorgi D, Philippopoulos K (2011) Spatial interpolation methodologies in urban air pollution modeling: application for the greater area of metropolitan Athens, Greece. In Nejadkoorki F (ed) Advanced air pollution, InTech Publishers, doi: 10.5772/17734
  11. Deligiorgi D, Kolokotsa D, Papakostas T, Mantou E (2007) Analysis of the wind field at the broader area of Chania, Crete. In: Proceedings of the 3rd IASME/WSEAS International Conference on Energy, Environment and Sustainable Development, pp 270–275Google Scholar
  12. Fadare DA (2010) The application of artificial neural networks to mapping of wind speed profile for energy application in Nigeria. Appl Energ 87(3):934–942. doi:10.1016/j.apenergy.2009.09.005 CrossRefGoogle Scholar
  13. Fausett LV (1994) Fundamentals neural networks: architecture, algorithms, and applications. Prentice-Hall, Inc., Englewood CliffsGoogle Scholar
  14. Fox DG (1981) Judging air quality model performance. B Am Meteorol Soc 62:599–609. doi: 10.1175/1520-0477(1981)062<0599:JAQMP>2.0.CO;2
  15. Gardner MW, Dorling SR (1998) Artificial neural networks (the multilayer perceptron)-A review of applications in the atmospheric sciences. Atmos Environ 32:2627–2636. doi:10.1016/S1352-2310(97)00447-0 CrossRefGoogle Scholar
  16. Heaton J (2005) Introduction to neural networks with Java. Heaton Research Inc., ChesterfieldGoogle Scholar
  17. Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2:359–366. doi:10.1016/0893-6080(89)90020-8 CrossRefGoogle Scholar
  18. Jain A, Mao J, Mohiuddin KM (1996) Artificial neural networks: a tutorial. Computer 29(3):31–44CrossRefGoogle Scholar
  19. Kalogirou SA (2001) Artificial neural networks in renewable energy systems applications: a review. Renew Sust Energ Rev 5:273–401. doi: 10.1016/S1364-0321(01)00006-5 Google Scholar
  20. Kamal L, Jafri ZY (1997) Time series models to simulate and forecast hourly averaged wind speed in Quetta, Pakistan. Sol Energ 61(1):23–32. doi: 10.1016/S0038-092X(97)00037-6
  21. Kariniotakis G, Stavrakakis GS, Nogaret EF (1996) Wind power forecasting using advanced neural network models. IEEE T Energ Conver 11(4):762–7. doi: 10.1109/60.556376
  22. Koletsis I, Lagouvardos K, Kotroni V, Bartzokas A (2009) The interaction of northern wind flow with the complex topography of Crete island-part 1: observational study. Nat Hazards Earth Syst Sci 9:1845–1855. doi: 10.5194/nhess-9-1845-2009
  23. Koletsis I, Lagouvardos K, Kotroni V, Bartzokas A (2010) The interaction of northern wind flow with the complex topography of Crete island-part 2: numerical study. Nat Hazards Earth Syst Sci 10:1115–1127. doi: 10.5194/nhess-10-1115-2010
  24. Kotroni V, Lagouvardos K, Lalas D (2001) The effect of the island of Crete on the etesian winds over the Aegean sea. Q J R Meteorol Soc 127:1917–1937. doi: 10.1002/qj.49712757604 Google Scholar
  25. Lei M, Shiyan L, Chuanwen J, Hongling L, Yan Z (2009) A review on the forecasting of wind speed and generated power. Renew Sust Energ Rev 13:915–920. doi: 10.1016/j.rser.2008.02.002 Google Scholar
  26. Li G, Shi J (2010) On comparing three artificial neural networks for wind speed forecasting. Appl Energ 87:2313–20. doi: 10.1016/j.apenergy.2009.12.013 Google Scholar
  27. Luo W, Taylor CM, Parker RS (2008) A comparison of spatial interpolation methods to estimate continuous wind speed surfaces using irregularly distributed data from England and Wales. Int J Climatol 28:947-959. doi: 10.1002/joc.1583 Google Scholar
  28. Mohandes M, Rehman S, Halawani TO (1998) A neural networks approach for wind speed prediction. Renew Energ 13(3):345–354. doi: 10.1016/S0960-1481(98)00001-9 Google Scholar
  29. More A, Deo MC (2003) Forecasting wind with neural networks. Mar Struct 16(1):35–49. doi: 10.1016/S0951-8339(02)00053-9 Google Scholar
  30. Oztopal A (2006) Artificial neural network approach to spatial estimation of wind velocity. Energ Convers Manage 47:395–406. doi: 10.1016/j.enconman.2005.05.009
  31. Philippopoulos K, Deligiorgi D (2012) Application of artificial neural networks for the spatial estimation of wind speed in a coastal region with complex topography. Renew Energ 38(1):75–82CrossRefGoogle Scholar
  32. Poggi P, Muselli M, Notton G, Cristofari C, Louche A (2003) Forecasting and simulating wind speed in Corsica by using an autoregressive model. Energ Convers Manage 44:3177–3196CrossRefGoogle Scholar
  33. Powell MJD (1987) Radial basis functions for multivariable interpolation: a review. In: Mason JC, Cox MG (eds) Algorithms for approximation. Clarendon Press, OxfordGoogle Scholar
  34. Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations by back-propagating errors. Nature 323:533–536CrossRefGoogle Scholar
  35. Soman SS, Zareipour H, Malik O, Mandal P (2010) A review of wind power and wind speed forecasting methods with different time horizons. North American Power Symposium (NAPS), doi: 10.1109/NAPS.2010.5619586
  36. Torres LJ, Garcia A, De Blas M, De Francisco A (2005) Forecast of hourly average wind speed with ARMA models in Navarre (Spain). Sol Energ 79:65–77. doi:10.1016/j.solener.2004.09.013 CrossRefGoogle Scholar
  37. Velazquez S, Carta AJ, Matias JM (2011) Comparison between ANNs and linear MCP algorithms in the long-term estimation of the cost per kWh produced by a wind turbine at a candidate site: a case study in the Canary Islands. Appl Energ 88:3869–3881. doi:10.1016/j.apenergy.2011.05.007 CrossRefGoogle Scholar
  38. Willmott CJ (1982) Some comments on the evaluation of model performance. B Am Meteorol Soc 63:1309–1313. doi: 10.1175/1520-0477(1982)063<1309:SCOTEO>2.0.CO;2
  39. Willmott CJ, Matsuura K (2005) Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Clim Res 30:79–82. doi: 10.3354/cr030079 Google Scholar
  40. Willmott CJ, Ackleson SG, Davis RE, Feddema JJ, Klink KM, Legates DR, O’Donnell J, Rowe CM (1985) Statistics for the evaluation and comparison of models. J Geophys Res 90:8995–9005. doi: 10.1029/JC090iC05p08995 Google Scholar
  41. Yu H, Wilamowski BM (2011) Levenberg–Marquardt training. In: Wilamowski BM, Irwin JD (eds) Industrial electronics handbook, 2nd edn. CRC Press, Boca RatonGoogle Scholar
  42. Zhang GP, Patuwo E, Hu M (1998) Forecasting with artificial neural networks: the state of the art. Int J Forecasting 14(1):35–62. doi: 10.1016/S0169-2070(97)00044-7 Google Scholar

Copyright information

© Springer-Verlag London 2013

Authors and Affiliations

  • Despina Deligiorgi
    • 1
  • Kostas Philippopoulos
    • 3
  • Georgios Kouroupetroglou
    • 2
  1. 1.Department of Physics Division of Environmental Physics and MeteorologyUniversity of AthensAthensGreece
  2. 2.Department of Informatics and Telecommunications, Division of Signal Processing and CommunicationUniversity of AthensAthensGreece
  3. 3.Division of Environmental Physics-Meteorology, Department of PhysicsUniversity of AthensAthensGreece

Personalised recommendations