24-h Ahead Wind Speed Prediction for the Optimum Operation of Hybrid Power Stations with the Use of Artificial Neural Networks

  • K. P. MoustrisEmail author
  • D. Zafirakis
  • D. H. Alamo
  • R. J. Nebot Medina
  • J. K. Kaldellis
Conference paper
Part of the Springer Atmospheric Sciences book series (SPRINGERATMO)


Remote areas are usually fed-in terms of electricity supply-from conventional generators that run on diesel. Recently, there is increasing interest on hybrid RES-based systems, including wind and solar power coupled with energy storage. To this end, optimum dispatching of such configurations is largely based on the capacity of prognostic tools employed in the respective energy management system. Acknowledging this, the aim of this work is the prediction of wind speed, 24-h ahead on an hourly basis, for the optimum operation of hybrid power stations (HPS) with the use of artificial neural networks (ANN). For this purpose, hourly data of wind speed have been used at a specific location (Tilos Island, Greece) where a HPS is going to be installed, including also a wind turbine of 800 kW. More specifically, an ANN which is fed with historical wind and air pressure data was developed in order to predict the wind speed at hub height on an hourly basis for the next 24 h. Results indicate that the proposed methodology gives an adequate forecast of wind speed in order to design an automated wind power information tool that could much facilitate the tasks of the energy management system.


Wind Speed Root Mean Square Error Artificial Neural Network Wind Turbine Artificial Neural Network Model 
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.



This work took place and was funded under the project TILOS (Horizon 2020 Low Carbon Energy Local/small-scale storage LCE-08-2014). This project has received funding from the European Union’s Horizon 2020 research and innovation programme under Grant Agreement No 646529. Open image in new window


  1. Brown BG, Katz RW, Murphy AH (1984) Time series models to simulate and forecast wind speed and wind power. J Clim Appl Meteorol 23:1184–1195CrossRefGoogle Scholar
  2. Cassola F, Burlando M (2012) Wind speed and wind energy forecast through Kalman filtering of numerical weather prediction model output. Appl Energ 99:154–166CrossRefGoogle Scholar
  3. Genton M, Hering A (2007) Blowing in the wind. Significance 4:11–14CrossRefGoogle Scholar
  4. Gneiting T, Larson K, Westrick K, Genton MG, Aldrich E (2006) Calibrated probabilistic forecasting at the stateline wind energy center: the regime-switching space-time method. J Am Stat Assoc 101:968–979CrossRefGoogle Scholar
  5. Hu Q, Zhang R, Zhou Y (2016) Transfer learning for short-term wind speed prediction with deep neural networks. Renew Energ 85:83–95CrossRefGoogle Scholar
  6. Kretzschmar R, Eckert P, Cattani D, Eggimann F (2004) Neural network classifiers for local wind prediction. J Appl Meteorol 43:727–738CrossRefGoogle Scholar
  7. Liu H, Tian H, Liang X, Li Y (2015) New wind speed forecasting approaches using fast ensemble empirical model decomposition, genetic algorithm, mind evolutionary algorithm and artificial neural networks. Renew Energ 83:1066–1075CrossRefGoogle Scholar
  8. Louka P, Galanis G, Siebert N, Kariniotakis G, Katsafados P, Kallos G, Pytharoulis I (2008) Improvements in wind speed forecasts for wind power prediction purposes using Kalman filtering. J Wind Eng Ind Aerod 96(12):2348–2362CrossRefGoogle Scholar
  9. McCulloh WS, Pitts W (1943) A logical calculus of ideas immanent in nervous activity. Bull Math Biophys B Math Biophys 5:115–133CrossRefGoogle Scholar
  10. Men Z, Yee E, Lien F-S, Wen D, Chen Y (2016) Short-term wind speed and power forecasting using an ensemble of mixture density neural networks. Renew Energ 87:203–211CrossRefGoogle Scholar
  11. Moustris KP, Ziomas IC, Paliatsos AG (2010) 3-day-ahead forecasting of regional pollution index for the pollutants NO2, CO, SO2, and O3 using artificial neural networks in Athens, Greece. Water Air Soil Poll 200:29–43CrossRefGoogle Scholar
  12. Nastos P, Moustris K, Larissi I, Paliatsos A (2011) Air quality and bioclimatic conditions within the greater athens area, Greece-development and applications of artificial neural networks. Adv Air Pollut, 557–584. InTech-Open Access (ISBN: 978-953-307-511-2)Google Scholar
  13. Nielsen TS, Madsen H, Nielsen HAa, Pinson P, Kariniotakis G, Siebert N, Marti I, Lange M, Focken U, Lueder V, Bremen LV, Louka P, Kallos G, Galanis G (2006) Short-term wind power forecasting using advanced statistical methods. In: The European wind energy conference, EWEC 2006, Athens, Greece, 9–17 Feb 2006Google Scholar
  14. Sloughter JM, Raftery AE, Gneiting T, Fraley C (2007) Probabilistic quantitative precipitation forecasting using Bayesian model averaging. Mon Weather Rev 135:3209–3220CrossRefGoogle Scholar
  15. Zhu X, Genton Marc G, Gu Y, Xie L (2014) Space-time wind speed forecasting for improved power system dispatch. TEST 23:1–25CrossRefGoogle Scholar
  16. Zjavka L (2015) Wind speed forecast correction models using polynomial neural networks. Renew Energ 83:998–1006CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2017

Authors and Affiliations

  • K. P. Moustris
    • 1
    Email author
  • D. Zafirakis
    • 2
  • D. H. Alamo
    • 3
  • R. J. Nebot Medina
    • 3
  • J. K. Kaldellis
    • 2
  1. 1.Laboratory of Fluid Mechanics, Mechanical Engineering DepartmentTechnological Education Institute of PiraeusAthensGreece
  2. 2.Soft Energy Applications and Environmental Protection Lab, Mechanical Engineering DepartmentTechnological Education Institute of PiraeusAthensGreece
  3. 3.Instituto Tecnológico de Canarias S.A.Las Palmas de GranSpain

Personalised recommendations