Machine Learning Prediction of Large Area Photovoltaic Energy Production

  • Ángela FernándezEmail author
  • Yvonne Gala
  • José R. Dorronsoro
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8817)


In this work we first explore the use of Support Vector Regression to forecast day-ahead daily and 3-hourly aggregated photovoltaic (PV) energy production on Spain using as inputs Numerical Weather Prediction forecasts of global horizontal radiation and total cloud cover. We then introduce an empirical “clear sky” PV energy curve that we use to disaggregate these predictions into hourly day-ahead PV forecasts. Finally, we use Ridge Regression to refine these day-ahead forecasts to obtain same-day hourly PV production updates that for a given hour \(h\) use PV energy readings up to that hour to derive updated PV forecasts for hours \(h+1, h+2, \ldots \). While simple from a Machine Learning point of view, these methods yield encouraging first results and also suggest ways to further improve them.


Photovoltaic energy Numerical weather prediction Support vector regression Ridge regression 



With partial support from Spain’s grants TIN2010-21575-C02-01 and TIN2013-42351-P, and the UAM–ADIC Chair for Machine Learning. We thank Red Elctrica de Espaa for useful discussions and making available PV energy data.


  1. 1.
    Benghanem, M., Mellit, A., Alamri, S.: Ann-based modelling and estimation of daily global solar radiation data: a case study. Energy Convers. Manage. 50(7), 1644–1655 (2009)CrossRefGoogle Scholar
  2. 2.
    Chang, C., Lin, C.: LIBSVM a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2, 27:1–27:27 (2011).
  3. 3.
    Chu, W., Keerthi, S.S., Ong, C.J.: Bayesian support vector regression using a unified loss function. IEEE Trans. Neural Netw. 15(1), 29–44 (2004)CrossRefGoogle Scholar
  4. 4.
    ECMWF: European Center for Medium-range Weather Forecasts (2005).
  5. 5.
    GFS: NOAA Global Forecast System (2014).
  6. 6.
    Hastie, T., Tibshirani, R., Friedman, J.: The Elements of Statistical Learning. Springer, Heidelberg (2001)CrossRefzbMATHGoogle Scholar
  7. 7.
    Kleissl, J.: Solar Energy Forecasting and Resource Assessment. Academic Press, New York (2013)Google Scholar
  8. 8.
    Lin, C.J., Weng, R.C.: Simple probabilistic predictions for support vector regression. Technical report, Department of Computer Science, National Taiwan University (2003)Google Scholar
  9. 9.
    Mellit, A., Kalogirou, S.A.: Artificial intelligence techniques for photovoltaic applications: a review. Prog. Energy Combust. Sci. 34(5), 574–632 (2008)CrossRefGoogle Scholar
  10. 10.
    Myers, D.R.: Solar radiation modeling and measurements for renewable energy applications: data and model quality. Energy 30(9), 1517–1531 (2005)CrossRefGoogle Scholar
  11. 11.
    Pedro, H., Coimbra, C.: Assessment of forecasting techniques for solar power output with no exogenous inputs. Sol. Energy 86, 2017–2028 (2012)CrossRefGoogle Scholar
  12. 12.
    Pedro, H., Coimbra, C.: Stochastic learning methods. In: Kleissl, J. (ed.) Solar Energy Forecasting and Resource Assessment, pp. 383–407. Academic Press, New York (2013)Google Scholar
  13. 13.
    Scholkopf, B., Smola, A.: Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond. MIT Press, Cambridge (2001)Google Scholar
  14. 14.
    Ulbricht, R., Fischer, U., Lehner, W., Donker, H.: First steps towards a systematical optimized strategy for solar energy supply forecasting. In: Proceedings of the DARE 2013, Data Analytics for Renewable Energy Integration Workshop, pp. 14–25 (2013)Google Scholar
  15. 15.
    Wolff, B., Lorenz, E., Kramer, O.: Statistical learning for short-term photovoltaic power predictions. In: Proceedings of the DARE 2013, Data Analytics for Renewable Energy Integration Workshop, pp. 2–13 (2013)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Ángela Fernández
    • 1
    Email author
  • Yvonne Gala
    • 1
  • José R. Dorronsoro
    • 1
  1. 1.Dpto. Ing. InformáticaUniversidad Autónoma de MadridMadridSpain

Personalised recommendations