Advertisement

Multimodel ensemble approach for hourly global solar irradiation forecasting

  • Nahed Zemouri
  • Hassen BouzgouEmail author
  • Christian A. Gueymard
Regular Article
  • 16 Downloads

Abstract.

This contribution proposes a novel solar time series forecasting approach based on multimodel statistical ensembles to predict global horizontal irradiance (GHI) in short-term horizons (up to 1 hour ahead). The goal of the proposed methodology is to exploit the diversity of a set of dissimilar predictors with the purpose of increasing the accuracy of the forecasting process. The performance of a specific multimodel ensemble forecast showing an improved forecast skill is demonstrated and compared to a variety of individual single models. The proposed system can be applied in two distinct ways. The first one incorporates the forecasts acquired from the different forecasting models constituting the ensemble via a linear combination (combination-based). The other one consists of a novel methodology that delivers as output the forecast provided by the specific model (involved in the ensemble) that delivers the maximum precision in the zone of the variable space connected with the considered GHI time series (selection-based approach). This forecasting model is issued from an appropriate division of the variable space. The efficiency of the proposed methodology has been evaluated using high-quality measurements carried out at 1min intervals at four radiometric sites representing widely different radiative climates (Arid, Temperate, Tropical, and High Albedo). The obtained results emphasize that, at all sites, the proposed multi-model ensemble is able to increase the accuracy of the forecasting process using the different combination approaches, with a significant performance improvement when using the classification strategy.

References

  1. 1.
    M. Diagne, M. David, P. Lauret, J. Boland, N. Schmutz, Renew. Sustain. Energy Rev. 27, 65 (2013)CrossRefGoogle Scholar
  2. 2.
    R.H. Inman, H.T.C. Pedro, C.F.M. Coimbra, Prog. Energy Combust. Sci. 39, 535 (2013)CrossRefGoogle Scholar
  3. 3.
    C. Voyant, G. Notton, S. Kalogirou, M.L. Nivet, C. Paoli, F. Motte, A. Fouilloy, Renew. Energy 105, 569 (2017)CrossRefGoogle Scholar
  4. 4.
    T. Khatib, A. Mohamed, K. Sopian, Renew. Sustain. Energy Rev. 16, 2864 (2012)CrossRefGoogle Scholar
  5. 5.
    A.K. Yadav, S.S. Chandel, Renew. Sustain. Energy Rev. 33, 772 (2014)CrossRefGoogle Scholar
  6. 6.
    D. Yang, J. Kleissl, C.A. Gueymard, H.T.C. Pedro, C.F.M. Coimbra, Sol. Energy 168, 60 (2018)CrossRefADSGoogle Scholar
  7. 7.
    A. Mellit, M. Benghanem, S.A. Kalogirou, Appl. Energy 83, 705 (2006)CrossRefGoogle Scholar
  8. 8.
    F.O. Hocaoglu, Ö.N. Gerek, M. Kurban, Sol. Energy 82, 714 (2008)CrossRefADSGoogle Scholar
  9. 9.
    J. Cao, X. Lin, Eng. Appl. Artif. Intell. 21, 1255 (2008)CrossRefGoogle Scholar
  10. 10.
    A. Mellit, A.M. Pavan, Sol. Energy 84, 807 (2010)CrossRefADSGoogle Scholar
  11. 11.
    L. Martín, L.F. Zarzalejo, J. Polo, A. Navarro, R. Marchante, M. Cony, Sol. Energy 84, 1772 (2010)CrossRefADSGoogle Scholar
  12. 12.
    K. Benmouiza, A. Cheknane, Energy Convers. Manag. 75, 561 (2013)CrossRefGoogle Scholar
  13. 13.
    S. Salcedo-Sanz, C. Casanova-Mateo, J. Munoz-Mari, G. Camps-Valls, IEEE Geosci. Remote Sens. Lett. 11, 1936 (2014)CrossRefADSGoogle Scholar
  14. 14.
    K. Benmouiza, A. Cheknane, Theor. Appl. Climatol. 124, 945 (2016)CrossRefADSGoogle Scholar
  15. 15.
    E. Akarslan, F.O. Hocaoglu, Renew. Energy 87, 628 (2016)CrossRefGoogle Scholar
  16. 16.
    S. Monjoly, M. Andre, R. Calif, T. Soubdhan, Energy 119, 288 (2017)CrossRefGoogle Scholar
  17. 17.
    H. Bouzgou, C.A. Gueymard, Sol. Energy 158, 595 (2017)CrossRefADSGoogle Scholar
  18. 18.
    H. Bouzgou, C.A. Gueymard, Renew. Energy 133, 1055 (2019)CrossRefGoogle Scholar
  19. 19.
    L. Cornejo-Bueno, C. Casanova-Mateo, J. Sanz-Justo, S. Salcedo-Sanz, Sol. Energy 183, 768 (2019)CrossRefADSGoogle Scholar
  20. 20.
    Y. Liu, X. Yao, Neural Netw. 12, 1399 (1999)CrossRefGoogle Scholar
  21. 21.
    Y. Ren, P.N. Suganthan, N. Srikanth, Renew. Sustain. Energy Rev. 50, 82 (2015)CrossRefGoogle Scholar
  22. 22.
    H. Bouzgou, Advanced Methods for the Processing and Analysis of Multidimensional Signals: Application to Wind Speed (University of Batna, 2012)Google Scholar
  23. 23.
    Y. Kemmoku, S. Orita, S. Nakagawa, T. Sakakibara, Sol. Energy 66, 193 (1999)CrossRefADSGoogle Scholar
  24. 24.
    S. Alessandrini, L. Delle Monache, S. Sperati, G. Cervone, Appl. Energy 157, 95 (2015)CrossRefGoogle Scholar
  25. 25.
    S. Sperati, S. Alessandrini, L. Delle Monache, Sol. Energy 133, 437 (2016)CrossRefADSGoogle Scholar
  26. 26.
    J. Hall, J. Hall, in Proceedings of the 40th ASES National Solar Conference 2011 (ASES, 2011)Google Scholar
  27. 27.
    A. Chaouachi, R. Kamel, K. Nagasaka, Jaciii 3, 41 (2010)Google Scholar
  28. 28.
    N. Zemouri, H. Bouzgou, in International Conference on Artificial Intelligence in Renewable Energy Systems, IC-AIRES2017 (2017) pp. 1--7Google Scholar
  29. 29.
    R.T. Clemen, Int. J. Forecast. 5, 559 (1989)CrossRefGoogle Scholar
  30. 30.
    Z.H. Zhou, Ensemble Methods: Foundations and Algorithms (2012)CrossRefGoogle Scholar
  31. 31.
    G.E.P. Box, G.M. Jenkins, G.C. Reinsel, in Time Series Analysis: Forecasting and Control (Prentice Hall, New Jersey, 1994)Google Scholar
  32. 32.
    S. Haykin, Neural Networks and Learning Machines (2008)Google Scholar
  33. 33.
    J. Park, I.W. Sandberg, Neural Comput. 3, 246 (1991)CrossRefGoogle Scholar
  34. 34.
    H. Bouzgou, N. Benoudjit, Appl. Energy 88, 2463 (2011)CrossRefGoogle Scholar
  35. 35.
    G.-B. Huang, Q.-Y. Zhu, C.-K. Siew, Neurocomputing 70, 489 (2006)CrossRefGoogle Scholar
  36. 36.
    H. Bouzgou, C.A. Gueymard, Sol. Energy 158, 595 (2017)CrossRefADSGoogle Scholar
  37. 37.
    V.N. Vapnik, Statistical Learning Theory (1998)Google Scholar
  38. 38.
    K.R. Müller, S. Mika, G. Rätsch, K. Tsuda, B. Schölkopf, IEEE Trans. Neural Networks 12, 181 (2001)CrossRefGoogle Scholar
  39. 39.
    L.I. Kuncheva, Combining Pattern Classifiers: Methods and Algorithms: Second Edition (2014)zbMATHGoogle Scholar
  40. 40.
    T.G. Dietterich, Neural Comput. 10, 1895 (1998)CrossRefGoogle Scholar
  41. 41.
    R.L. Winkler, Int. J. Forecast. 5, 605 (1989)CrossRefGoogle Scholar
  42. 42.
    J.S. Armstrong, in A Handbook of Human Resource Management Practice (2001) p. 849Google Scholar
  43. 43.
    C. Lemke, B. Gabrys, Neurocomputing 73, 2006 (2010)CrossRefGoogle Scholar
  44. 44.
    L. Bruzzone, F. Melgani, IEEE Trans. Geosci. Remote Sens. 43, 159 (2005)CrossRefADSGoogle Scholar
  45. 45.
    C.A. Gueymard, J.A. Ruiz-Arias, Sol. Energy 128, 1 (2016)CrossRefADSGoogle Scholar
  46. 46.
    A. Ohmura, E.G. Dutton, B. Forgan, C. Fröhlich, H. Gilgen, H. Hegner, A. Heimo, G. König-Langlo, B. McArthur, G. Müller, R. Philipona, R. Pinker, C.H. Whitlock, K. Dehne, M. Wild, Bull. Am. Meteorol. Soc. 79, 2115 (1998)CrossRefADSGoogle Scholar
  47. 47.
    C.F.M. Coimbra, J. Kleissl, R. Marquez, in Solar Energy Forecasting and Resource Assessment (Academic Press, 2013) pp. 171--194Google Scholar
  48. 48.
    C.A. Gueymard, Renew. Sustain. Energy Rev. 39, 1024 (2014)CrossRefGoogle Scholar
  49. 49.
    C.M. Bishop, in Neural Networks Pattern Recognition (1996)Google Scholar
  50. 50.
    R. Perez, P. Ineichen, K. Moore, M. Kmiecik, C. Chain, R. George, F. Vignola, Sol. Energy 73, 307 (2002)CrossRefADSGoogle Scholar
  51. 51.
    K.E. Taylor, J. Geophys. Res. Atmos. 106, 7183 (2001)CrossRefADSGoogle Scholar
  52. 52.
    T.W. Anderson, Biometrics 41, 815 (1985)CrossRefGoogle Scholar

Copyright information

© Società Italiana di Fisica and Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Department of Electronics, Faculty of TechnologyUniversity of M’silaM’silaAlgeria
  2. 2.Department of Industrial Engineering, Faculty of TechnologyUniversity of Batna 2 (Mostefa Ben Boulaïd)BatnaAlgeria
  3. 3.Solar Consulting ServicesColebrookUSA

Personalised recommendations