Use of Empirical Regression and Artificial Neural Network Models for Estimation of Global Solar Radiation in Dubai, UAE

  • Hassan A. N. HejaseEmail author
  • Ali H. Assi
  • Maitha H. Al Shamisi


The geographical location of the United Arab Emirates (UAE) (latitude between 26° and 32° North and longitude between 51° and 56° East) favors the development and utilization of solar energy. This chapter presents estimation models for the global solar radiation (GSR) in Dubai, UAE. It compares between six empirical regression models and the best of 11 different configurations of artificial neural network (ANN) models. The models have been developed using measured average daily GSR data for 7 years (2002–2008) while the measured data for the years 2009–2010 are used for testing the models. Results of monthly average daily GSR data of all the empirical models for the test period 2009–2010 yield low statistical error parameters and coefficients of determination (R2) better than 96 %. Comparison with ANN models and Solar Radiation (SoDa) Web site data shows that the optimal multilayer perceptron (MLP) ANN model is the best with R2 = 98 %, and with the lowest statistical error parameters. The results also confirm that a simple linear regression model provides a very good estimation for monthly and daily average GSR data.


Global solar radiation Empirical regression Artificial neural networks 



Inputs of ANN


Weights of ANN


Outputs of ANN


Activation function


Total weighted sum of input signals to neuron j


Target output for neuron j


Center of the radial basis function

Greek Symbols


Summation function


Mean sunrise hour angle in radians


Latitude in radians


Declination angle in radians


Learning rate


A factor that depends on whether neuron j is an output/hidden neuron


Momentum coefficient


Hidden layer output (activation function) for RBF ANN



Artificial Neural Network


Extraterrestrial solar radiation on a horizontal surface (kWh/m2)


Geographical Information System


Mean daily Global Solar Radiation (kWh/m2)


Mean Absolute Bias Error (kWh/m2)


Mean Absolute Percent Error


Mean Bias Error (kWh/m2)


Multilayer Perceptron


National Aeronautics and Space Administration


Coefficient of Determination


Radial Basis Function


Clearness coefficient


Relative Humidity ( % )


Root-Mean-Square Error (kWh/m2)


Sunshine duration ratio


Renewable energy Resource EXplorer


Theoretical maximum sunshine hours


Solar radiation Data


Solar meteorology and Solar Energy


Mean daily Sunshine Hours


Solar and Wind Energy Resource Assessment


Maximum air Temperature (degrees Celsius)


United Arab Emirates


Average Wind Speed (knots)



The authors would like to thank the National Center for Meteorology and Seismology (NCMS), Abu Dhabi for providing the weather data.


  1. 1.
    International Energy Agency (IEA Statistics © OECD/IEA,, Energy Statistics and Balances of Non-OECD Countries and Energy Statistics of OECD Countries (
  2. 2.
    Rahman S (2012) UAE power capacity outpaces demand., August 31
  3. 3.
    Assi A, Jama M (2010) Estimating global solar radiation on horizontal from sunshine hours in Abu Dhabi—UAE. In: Proceedings of the 4th International conference on renewable energy sources (RES’10), 101–108, Sousse, Tunisia, 03–06 May 2010Google Scholar
  4. 4.
    Assi A, Jama M, Al-Shamisi M (2012) Prediction of Global Solar Radiation in Abu Dhabi. ISRN Renew Energy, 2012: 10, doi: 10.5402/2012/328237
  5. 5.
    Hejase HAN, Assi AH (2011) MATLAB-assisted regression modeling of mean daily global solar radiation in Al-Ain, UAE. In: Assi AH (ed) Engineering education and research using MATLAB. Intech, New York, pp 195–218Google Scholar
  6. 6.
    Al-Shamisi MH, Assi AH, Hejase HAN (2011) Using MATLAB to develop artificial neural network models for predicting global solar radiation in Al Ain City—UAE. In: Assi AH (ed) Engineering education and research using MATLAB. Intech, New York, pp 219–238Google Scholar
  7. 7.
    Assi A, Al-Shamisi M (2010) Prediction of monthly average daily global solar radiation in Al Ain City–UAE using artificial neural networks. In: Proceedings of the 25th European photovoltaic solar energy conference, 508–512, Valencia, Spain, 06–10 September 2010Google Scholar
  8. 8.
    Assi A, Al-Shamisi M, Jama M (2010) Prediction of monthly average daily global solar radiation in Al Ain City–UAE using artificial neural networks. In: Proceedings of the 4th International conference on renewable energy sources (RES’10), 109–113, Sousse, Tunisia, 03–06 May 2010Google Scholar
  9. 9.
    Hejase HAN, Assi AH (2012) Time-series regression model for prediction of mean daily global solar radiation in Al-Ain, UAE. ISRN Renew Energy, 2012:11 2012. doi: 10.5402/2012/412471
  10. 10.
    Al Shamisi MH, Assi AH, Hejase HAN (2012) Artificial Neural Network Modeling of Global Solar Radiation. Accepted for publication, Int J Green Energy, Taylor and Francis publisher, posted online Feb, 22, 2012. doi: 10.1080/15435075.2011.641187
  11. 11.
    Abdalla YAG, Feregh GM (1988) Contribution to the study of solar radiation in Abu Dhabi. Energy Convers Manag 28(1):63–67CrossRefGoogle Scholar
  12. 12.
    Akinoglu BG, Ecevit A (1990) A further comparison and discussion of sunshine based models to estimate global solar radiation. Energy 15:865–872CrossRefGoogle Scholar
  13. 13.
    Al Mahdi N, Al Baharna NS, Zaki FF (1992) Assessment of solar radiation models for Gulf Arabian countries. Renew Energy 2(1):65–71CrossRefGoogle Scholar
  14. 14.
    Ampratwum DB, Dorvlo ASS (1999) Estimation of solar radiation from the number of sunshine hours. Appl Energy 63:161–167CrossRefGoogle Scholar
  15. 15.
    Elagib N, Mansell MG (2000) New approaches for estimating global solar radiation across Sudan. Energy Convers Manag 41:419–434CrossRefGoogle Scholar
  16. 16.
    Falayi EO, Adepitan JO, Rabiu AB (2008) Empirical models for the correlation of global solar radiation with meteorological data for Iseyin, Nigeria. Int J Phys Sci 3:210–216Google Scholar
  17. 17.
    Fortin J, Anctil F, Parent L, Bolinder M (2008) Comparison of empirical daily surface incoming solar radiation models. Agric For Meteorol 148:1332–1340CrossRefGoogle Scholar
  18. 18.
    Khalil A, Alnajjar A (1995) Experimental and theoretical investigation of global and diffuse solar radiation in the United Arab Emirates. Renew Energy 6(5–6):537–543CrossRefGoogle Scholar
  19. 19.
    Menges HO, Ertekin C, Sonmete MH (2006) Evaluation of solar radiation models for Konya, Turkey. Energy Convers Manag 47:3149–3173CrossRefGoogle Scholar
  20. 20.
    Newland FJ (1988) A study of solar radiation models for the coastal region of south China. Sol Energy 31:227–235Google Scholar
  21. 21.
    Podestá G, Núñez L, Villanueva C, Skanski M (2004) Estimating daily solar radiation in the Argentine Pampas. Agric For Meteorol 123:41–53CrossRefGoogle Scholar
  22. 22.
    Şahin AD (2007) A new formulation for solar irradiation and sunshine duration estimation. Int J Energy Res 31:109–118CrossRefGoogle Scholar
  23. 23.
    Samuel T (1991) Estimation of solar radiation for Sri Lanka. Sol Energy 47:333–337CrossRefGoogle Scholar
  24. 24.
    Ulgen K, Hepbasli A (2002) Comparison of solar radiation correlations for Izmir, Turkey. Int J Energy Res 26:413–430CrossRefGoogle Scholar
  25. 25.
    Al-Alawi S, Al-Hinai H (1998) An ANN-based Approach for Predicting Global Solar Radiation in Locations with no Measurements. Renew Energy 14:199–204CrossRefGoogle Scholar
  26. 26.
    Behrang MA, Assareh E, Ghanbarzadeh A, Noghrehabadi AR (2010) The potential of different artificial neural network (ANN) techniques in daily global solar radiation modeling based on meteorological data. Sol Energy 84:1468–1480CrossRefGoogle Scholar
  27. 27.
    Benghanem M, Mellit A, Alamri SN (2009) ANN-based modeling and estimation of daily global solar radiation data: a case study. Energy Convers Manag 50:1644–1655CrossRefGoogle Scholar
  28. 28.
    Boccol M, Willington E, Arias M (2010) Comparison of regression and neural networks models to estimate solar radiation. Chilean J Agri Res 70:428–435Google Scholar
  29. 29.
    Elminir H, Areed F, Elsayed T (2005) Estimation of solar radiation components incident on Helwan site using neural networks. Sol Energy 79:270–279CrossRefGoogle Scholar
  30. 30.
    Kassem AS, Aboukarima AM, El Ashmawy NM (2009) Development of neural network model to estimate hourly total and diffuse solar radiation on horizontal surface at Alexandria city (Egypt). J Appl Sci Res 5:2006–2015Google Scholar
  31. 31.
    Krishnaiah T, Srinivasa S, Madhumurthy K, Reddy KS (2007) A neural network approach for modelling global solar radiation. J Appl Sci Res 3(10):1105–1111Google Scholar
  32. 32.
    Mohandes M, Balghonaim A, Kassas M, Rehman S, Halawani TO (2000) Use of radial basis functions for estimating monthly mean daily solar radiation. Sol Energy 68(2):161–168CrossRefGoogle Scholar
  33. 33.
    Mohandes M, Rehman S, Halawani TO (1998) Estimation of global solar radiation using artificial neural networks. Renew Energy 14:179–184CrossRefGoogle Scholar
  34. 34.
    Rehman S, Mohandes M (2008) Artificial neural network estimation of global solar radiation using air temperature and relative humidity. Energy Policy 36:571–576CrossRefGoogle Scholar
  35. 35.
    Lam JC, Wan KKW, Liu Y (2008) Solar radiation modeling using ANNs for different climates in China. Energy Convers Manag 49:1080–1090CrossRefGoogle Scholar
  36. 36.
    Mubiru J (2008) Predicting total solar irradiation values using artificial neural networks. Renew Energy 33(10):2329–2332CrossRefGoogle Scholar
  37. 37.
    SoDa: a Web service on solar radiation, Accessed 10 June 2012
  38. 38.
    Haykin S (2009) Neural networks and learning machines. Pearson Education, Inc., New JerseyGoogle Scholar
  39. 39.
    Yang J, Rivard H, Zmeureanu R (2005) Building Energy Predication with Adaptive Artificial Neural Networks. Ninth International IBPSA Conference Montréal 15–18Google Scholar
  40. 40.
    Chantasut N, Charoenjit C, Tanprasert C (2004) Predictive mining of rainfall predictions using artificial neural networks for Chao Phraya River. In: 4th International conference of the asian federation of information technology in agriculture and the 2nd world congress on computers in agriculture and natural resources 9–12.Google Scholar
  41. 41.
    Jain A, Mao J, Mohiuddin K (1996) Artificial neural networks: a tutorial. Computer 29(3):31–44CrossRefGoogle Scholar
  42. 42.
    Jayawardena AW, Fernando DAK (1998) Use of radial basis function type artificial neural networks for runoff simulation. Computer-Aided Civil Infrastruct Eng 13:91–99. doi: 10.1111/0885-9507.00089 CrossRefGoogle Scholar
  43. 43.
    Assi AH, Al-Shamisi MH, Hejase HAN (2012) Solar radiation in UAE—a comparison between ground station measurements and satellite estimation. In: Proceedings of the global conference on global warming 2012 (GCGW-2012), CD-ROM, Istanbul, Turkey, July 8–12Google Scholar
  44. 44.
    Surface meteorology and Solar Energy (SSE) Release 6.0, Accessed on 13 Oct 2012
  45. 45.
    Solar and Wind Energy Resource Assessment (SWERA)—A United Nations environment programme facilitated effort. Accessed 10 June 2012
  46. 46.
  47. 47.
  48. 48.
    MATLAB (2010), version (R 2010 a). The MathWorks Inc.Google Scholar
  49. 49.
    IBM SPSS Statistics for Windows (2010), Version 19.0.0, SPSS Inc.Google Scholar
  50. 50.
    Al-Shamisi MH, Assi AH, Hejase HAN (2012) Using artificial neural networks to predict global solar radiation in Dubai City (UAE). In: Proceedings of the 2nd International conference on renewable energy: generation and applications (ICREGA 2012), CD-ROM, Al-Ain, UAE, March 4–7Google Scholar

Copyright information

© Springer Science+Business Media New York 2013

Authors and Affiliations

  • Hassan A. N. Hejase
    • 1
    Email author
  • Ali H. Assi
    • 2
  • Maitha H. Al Shamisi
    • 1
  1. 1.College of EngineeringUnited Arab Emirates UniversityAl-AinUAE
  2. 2.Department of Electrical and Electronic EngineeringLebanese International UniversityBeirutLebanon

Personalised recommendations