Time Series Forecasting

  • Marius Paulescu
  • Eugenia Paulescu
  • Paul Gravila
  • Viorel Badescu
Part of the Green Energy and Technology book series (GREEN)


Nowcasting global solar irradiance on very short time horizons is the principal topic discussed in this chapter. Various ARIMA models for nowcasting clearness index are inferred and assessed. Radiometric data measured at 15 s lag during June 2010 in Timisoara (Romania) are used for setting up and testing the models. First-order differencing ARIMA models have proven suitable for nowcasting instantaneous values of the clearness index components, beam and global. The model performance is studied as a function of forecasting time horizon and season. The model’s accuracy goes down with increased time horizon. It is shown that the model’s accuracy increases with the stability of the solar radiative regime. The second subject discussed in this chapter is forecasting daily global solar irradiation for the next day, also using ARIMA models.


Solar Irradiance ARIMA Model Autocorrelation Coefficient Global Solar Irradiation Radiative Regime 
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. Box GEP, Jenkins GM (1970) Time series analysis. Forecasting and control. Holden-Day, San FranciscoMATHGoogle Scholar
  2. Box GEP, Tiao GC (1992) Bayesian Inference in Statistical Analysis (Wiley Classics Library) Wiley-InterscienceGoogle Scholar
  3. Brockwell PJ, Davis RA (2002) Introduction to time series and forecasting. Springer, New YorkMATHCrossRefGoogle Scholar
  4. Chen D, Peace KE (2010) Clinical trial data analysis using R. CRC Press, Boca RatonCrossRefGoogle Scholar
  5. De Gooijer JG, Hyndman RJ (2006) 25 years of time series forecasting. Int J Forecast 22:443–473CrossRefGoogle Scholar
  6. Gallego AJ, Camacho EF (2012) Estimation of effective solar irradiation using an unscented Kalman filter in a parabolic-trough field. Sol Energy (in press, corrected proofs). doi:  10.1016/j.solener.2011.11.012
  7. Gillespie DT (1991) Markov processes: An introduction for physical scientists. Academic Press, LondonGoogle Scholar
  8. Gottman JM (1982) Time-series analysis: a comprehensive introduction for social scientists. Cambridge University Press, CambridgeGoogle Scholar
  9. Iizumi T, Nishimori M, Yokozawa M, Kotera A, Duy Khang N (2012) Statistical downscaling with bayesian inference: estimating global solar radiation from reanalysis and limited observed data. Int J Climatol 32:464–480CrossRefGoogle Scholar
  10. Kalman R (1960) A new approach to linear filtering and prediction problems. J Basic Eng 82:35–45CrossRefGoogle Scholar
  11. Palit AK, Popovic D (2005) Computational intelligence in time series forecasting: theory and engineering applications. Springer, BerlinMATHGoogle Scholar
  12. Paoli C, Voyant C, Muselli M, Nivet M-L (2010) Forecasting of preprocessed daily solar radiation time series using neural networks. Sol Energy 84(12):2146–2160CrossRefGoogle Scholar
  13. Pankratz A (1983) Forecasting with univariate Box-Jenkins models. Concepts and cases. Wiley, New YorkGoogle Scholar
  14. Poggi P, Notton G, Muselli M, Louche A (2000) Stochastic study of hourly total solar radiation in Corsica using a markov model. Int J Climatol 20:1843–1860CrossRefGoogle Scholar
  15. PTC (2012)—MathCAD—Engineering calculations software.
  16. Sprott JC (2003) Chaos and time-series analysis. Oxford University Press, OxfordMATHGoogle Scholar
  17. Statgrafics (2012) Statgraphics centurion

Copyright information

© Springer-Verlag London 2013

Authors and Affiliations

  • Marius Paulescu
    • 1
  • Eugenia Paulescu
    • 1
  • Paul Gravila
    • 1
  • Viorel Badescu
    • 2
    • 3
  1. 1.Physics DepartmentWest University of TimisoraTimisoraRomania
  2. 2.Candida Oancea InstitutePolytechnic University of BucharestBucharestRomania
  3. 3.Romanian AcademyBucharestRomania

Personalised recommendations