Solar Irradiation Forecasting for PV Systems by Fully Tuned Minimal RBF Neural Networks

  • Lucio Ciabattoni
  • Gianluca Ippoliti
  • Sauro Longhi
  • Matteo Pirro
  • Matteo Cavalletti
Part of the Smart Innovation, Systems and Technologies book series (SIST, volume 19)

Abstract

An on-line prediction algorithm able to estimate, over a determined time horizon, the solar irradiation of a specific site is considered. The learning algorithm is based on Radial Basis Function (RBF) networks and combines the growing criterion and the pruning strategy of the minimal resource allocating network technique. An adaptive extended Kalman filter is used to update all the parameters of the Neural Network (NN). The on-line learning mechanism avoids the initial training of the NN with a large data set. The proposed solution has been experimentally tested on a 14 kWp PhotoVoltaic (PV) plant and results are compared to a classical RBF neural network.

Keywords

irradiation forecasting minimal resource allocating networks adaptive filtering self learning algorithm neural networks 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
  2. 2.
    Antonini, P., Ippoliti, G., Longhi, S.: Learning control of mobile robots using a multiprocessor system. Control Engineering Practice 14(11), 1279–1295 (2006)CrossRefGoogle Scholar
  3. 3.
    Ben Salah, C., Ben Mabrouk, A., Ouali, M.: Wavelet autoregressive forecasting of climatic parameters for photovoltaic systems. In: 2011 8th International Multi-Conference on Systems, Signals and Devices (SSD), pp. 1–6 (March 2011)Google Scholar
  4. 4.
    Cavalletti, M., Ippoliti, G., Longhi, S.: Lyapunov-based switching control using neural networks for a remotely operated vehicle. International Journal of Control 80(7), 1077–1091 (2007)MathSciNetMATHCrossRefGoogle Scholar
  5. 5.
    Cavalletti, M., Ippoliti, G., Longhi, S.: Intelligent control for a remotely operated vehicle. International Journal of Systems Science 40(11), 1099–1114 (2009)CrossRefGoogle Scholar
  6. 6.
    Chen, S., Cowan, C., Grant, P.: Orthogonal least squares learning algorithm for radial basis function networks. IEEE Transactions on Neural Networks 2(2), 302–309 (1991)CrossRefGoogle Scholar
  7. 7.
    Ciabattoni, L., Ippoliti, G., Longhi, S., Cavalletti, M., Rocchetti, M.: Solar irradiation forecasting using RBF networks for PV systems with storage. In: 2012 IEEE International Conference on Industrial Technology (ICIT), pp. 699–704 (March 2012)Google Scholar
  8. 8.
    Corradini, M., Ippoliti, G., Longhi, S., Marchei, D., Orlando, G.: A quasi-sliding mode observer-based controller for PMSM drives. Asian Journal of Control, 1–8 (2012), http://dx.doi.org/10.1002/asjc.555
  9. 9.
    Dorvlo, A.S., Jervase, J.A., Al-Lawati, A.: Solar radiation estimation using artificial neural networks. Applied Energy 71(4), 307–319 (2002)CrossRefGoogle Scholar
  10. 10.
    Giantomassi, A., Ippoliti, G., Longhi, S., Bertini, I., Pizzuti, S.: On-line steam production prediction for a municipal solid waste incinerator by fully tuned minimal RBF neural networks. Journal of Process Control 21(1), 164–172 (2011)Google Scholar
  11. 11.
    Hunt, K., Sbarbaro, D., Zbikowski, R., Gawthrop, P.: Neural networks for control systems – A survey. Automatica 28(6), 1083–1112 (1992)MathSciNetMATHCrossRefGoogle Scholar
  12. 12.
  13. 13.
    Jetto, L., Longhi, S., Venturini, G.: Development and experimental validation of an adaptive extended Kalman filter for the localization of mobile robots. IEEE Transactions on Robotics and Automation 15(2), 219–229 (1999)CrossRefGoogle Scholar
  14. 14.
    Karner, O.: ARIMA representation for daily solar irradiance and surface air temperature time series. Journal of Atmospheric and Solar-Terrestrial Physics 71(8-9), 841–847 (2009)CrossRefGoogle Scholar
  15. 15.
    Lange, M., Focken, U.: Physical approach to short term wind power prediction. Springer, New-York (2006)Google Scholar
  16. 16.
    Lorenz, E., Hurka, J., Heinemann, D., Beyer, H.: Irradiance forecasting for the power prediction of grid-connected photovoltaic systems. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2(1), 2–10 (2009)CrossRefGoogle Scholar
  17. 17.
    Palensky, P., Dietrich, D.: Demand side management: Demand response, intelligent energy systems, and smart loads. IEEE Transactions on Industrial Informatics 7(3), 381–388 (2011)CrossRefGoogle Scholar
  18. 18.
  19. 19.
  20. 20.
  21. 21.
  22. 22.
    Sundararajan, N., Saratchandran, P., Li, Y.: Fully tuned radial basis function neural networks for flight control. Kluver Academic, London (2002)MATHGoogle Scholar
  23. 23.
    Szabat, K., Orlowska-Kowalska, T.: Performance improvement of industrial drives with mechanical elasticity using nonlinear adaptive Kalman filter. IEEE Transactions on Industrial Electronics 55(3), 1075–1084 (2008)CrossRefGoogle Scholar
  24. 24.

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Lucio Ciabattoni
    • 1
  • Gianluca Ippoliti
    • 1
  • Sauro Longhi
    • 1
  • Matteo Pirro
    • 1
  • Matteo Cavalletti
    • 2
  1. 1.Dipartimento di Ingegneria dell’InformazioneUniversitá Politecnica delle MarcheAnconaItaly
  2. 2.Energy Resources S.p.A.JesiItaly

Personalised recommendations