Wind Energy Production Forecasting

  • G. Atsalakis
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 28)


This paper presents a forecasting system of short-term wind energy production. The system is a feedforward neural network that uses genetic algorithm as a learning method of forecasting the wind energy production of the following day. The data concerns four different wind power plants. The neural network forecasts are compared with the predictions made by a neural network that uses Quasi-Newton learning algorithm and are evaluated based on the four common statistical measures. Both models perform satisfactorily as far as the prediction of the following day’s wind energy production is concerned.


Genetic Algorithm Root Mean Square Error Wind Power Wind Energy Mean Absolute Percentage Error 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Abdel-Aal RE, Al-Garni AZ, Al-Nassar YN (1997) Modeling and forecasting monthly electric energy consumption in Eastern Saudi Arabia using adductive networks. Energy 22:911–921CrossRefGoogle Scholar
  2. 2.
    Atsalakis G, Ucenic C (2006) Electric load forecasting by Neuro-fuzzy approach. In: WSEAS International Conference on Energy and Environmental Systems, Evia, GreeceGoogle Scholar
  3. 3.
    Atsalakis G, Ucenic C (2006) Forecasting the electricity demand using a Neuro-fuzzy approach versus traditions methods. J WSEAS Trans Bus Econ 3:9–17Google Scholar
  4. 4.
    Atsalakis G, Ucenic C (2006) Forecasting the wind energy production using a Neuro-fuzzy model. J WSEAS Trans Environ Dev 2:6 823–829Google Scholar
  5. 5.
    Atsalakis G, Ucenic C, Plokamakis G (2005) Forecasting of electricity demand using Neuro-fuzzy (ANFIS) approach. In: International Conference on NHIBE, Corfu, GreeceGoogle Scholar
  6. 6.
    Azoff E (1994) Neural network time series forecasting of financial markets. Wiley, New YorkGoogle Scholar
  7. 7.
    Brown BG, Katz RW, Murphy AH (1984) Time series models to simulate and forecast wind speed and wind power. J Climate Appl Meteorol 23:1184–1195CrossRefGoogle Scholar
  8. 8.
    Chedid R, Mezher T, Jarrouche C (1999) A fuzzy programming approach to energy resource allocation. Int J Energ Res 23:303–317CrossRefGoogle Scholar
  9. 9.
    Czernichow T, Germond A, Dorizzi B, Caire P (1995) Improving recurrent network load forecasting. In: Proceedings IEEE International Conference ICNN’95 Perth (Western Australia), 2:899–904Google Scholar
  10. 10.
    Datta D, Tassou SA (1997) Energy management in supermarkets through electrical load prediction. In: Proceedings 1st International Conference on Energy and Environment, Limassol (Cyprus), 2:493–587Google Scholar
  11. 11.
    Davis L (1991) Handbook of genetic algorithms. Van Nostrand Reinhold, New YorkGoogle Scholar
  12. 12.
    Giebel G (2003) The state-of-the-art in short-term prediction of wind power, Deliverable Report D1.1, Project Anemos, Available online at modules.php?name= Downloads& dop=viewdownload&cid=3Google Scholar
  13. 13.
    Goldberg DE (1989) Genetic algorithms in search optimization and machine learning. Addison-Wesley, Reading MAMATHGoogle Scholar
  14. 14.
    Hagan MT, Demuth HB, Beale M (1996) Neural network design. PWS Publishing Company, BostonGoogle Scholar
  15. 15.
    Holland JH (1975) Adaptation in natural and artificial systems. University of Michigan Press, Ann ArborGoogle Scholar
  16. 16.
    Hornik K, Stinchombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Networks 2:359–366CrossRefGoogle Scholar
  17. 17.
    Javeed Nizami S, Al-Garni AG (1995) Forecasting electric energy consumption using neural networks. Energ Policy 23:1097–1104CrossRefGoogle Scholar
  18. 18.
    Kalogirou SA (2000) Applications of artificial neural networks for energy systems. Appl Energ 67:17–35CrossRefGoogle Scholar
  19. 19.
    Khotanzad A, Hwang RC, Maratukulam D (1993) Hourly load forecasting by Neural networks. Proceedings of the IEEE PES Winter Meeting, OhioGoogle Scholar
  20. 20.
    Kingdon J (1997) Intelligent systems and financial forecasting. Springer-Verlag, BerlinGoogle Scholar
  21. 21.
    Kretzschmar R, Eckert P, Cattani D, Eggimann F (2004) Neural network classifiers for local wind prediction. J Appl Meteorol 43:727–738CrossRefGoogle Scholar
  22. 22.
    Maier HR, Dandy GC (2000) Neural networks for prediction and forecasting of water re- resources variables: a review of modeling issue and applications. Environ Model Source Softw 15:101–124CrossRefGoogle Scholar
  23. 23.
    Makridakis S, Weelwright SE, McGee VE (1983) Forecasting: methods and applications. Wiley, New YorkGoogle Scholar
  24. 24.
    Mandal JK, Sinha AK, Parthasarathy G (1995) Application of recurrent neural network for short term load forecasting in electric power system. In: Proceedings IEEE International Conference ICNN’95, Perth (Western Australia), 5:2694–2698Google Scholar
  25. 25.
    McNelis DP (2005) Neural networks in finance: gaining predictive edge in the market. Elsevier Academic Press, San Diego, CAGoogle Scholar
  26. 26.
    Metaxiotis K, Kagiannas A, Ashounis D, Psarras J (2003) Artificial intelligence in short term electric load forecasting: a state-of-the-art survey for the researcher. Energ Convers Manage 44:1525–1534CrossRefGoogle Scholar
  27. 27.
    Michalik G, Khan ME, Bonwick WJ, Mielczarski W (1997) Structural modeling of energy demand in the residential sector: the use of linguistic variables to include uncertainty of customer’s behavior. Energy 22:949–958CrossRefGoogle Scholar
  28. 28.
    Mohandes AM, Rehman S, Halawani TO (1998) A neural network approach for wind speed prediction. Renew Energ 13:345–354CrossRefGoogle Scholar
  29. 29.
    Papalexopoulos AD, Shangyou H, Peng TM (1994) An implementation of neural network based load forecasting models for the EMS. IEEE Trans Power Syst 9(4)Google Scholar
  30. 30.
    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
  31. 31.
    Rosenblatt F (1958) The perceptron: a probabilistic model for information storage and organization in the brain. Psychol Rev 65:386–408CrossRefMathSciNetGoogle Scholar
  32. 32.
    Rummeihart DE, Hinton BE, Williams RJ (1986) Learning internal representations by error propagation. In: Rumelhart DE, McClelland JL (eds) Parallel distributed processing: explorations in the microstructures of cognition.MIT Press, Cambridge, MAGoogle Scholar
  33. 33.
    Sanders I, Batty WJ, Hagino K (1993) Supply of and demand for a resource: fuzzy logistical optimization technique. Appl Energ 46:285–302CrossRefGoogle Scholar
  34. 34.
    Sfetsos A (2000) A comparison of various forecasting techniques applied to mean hourly wind speed time series. Renew Energ 21:23–35CrossRefGoogle Scholar
  35. 35.
    Weisser D (2003) A wind energy analysis of Grenada: an estimation using the ‘Weibull’ density function. Renew Energ 28:1803–1812CrossRefGoogle Scholar
  36. 36.
    Youcef Ettoumi F, Sauvageot H, Adane AEH (2003) Statistical bivariate modeling of wind using first-order Markov chain and Weibull distribution. Renew Energ 28:1787–1802CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2009

Authors and Affiliations

  1. 1.Department of Production Engineering and ManagementTechnical University of CreteChaniaGreece

Personalised recommendations