Evaluation of artificial neural network and support vector machine methods in estimating total solar radiation at Kerman and Yazd

Document Type : Review Article

Authors

1 M. Sc. Student in Water Resources Engineering, Water Engineering Department, Faculty of Agriculture, Shahid Bahonar University of Kerman and member of Young Researchers Society, Kerman, Iran

2 Associate Professor, Department of Water Engineering, Faculty of Agriculture, Shahid Bahonar University of Kerman, Kerman, Iran

Abstract

The value of radiation energy is considered to be the main component of the design of clean energy devices. Due to the fact that this amount is not measured or in some cases the radiation station may not be available in Iran, so it is necessary to estimate this component. In this study, Kerman and Yazd were selected as the regions with the maximum potential of solar energy. Then Artificial Neural Network (ANN) and Support Vector Machine (SVM) capabilities were evaluated in solar energy estimation. For this purpose, the daily data of 25 years (1992-2017) including maximum temperature, mean temperature, relative humidity, sunshine hours and solar radiation were collected at the synoptic stations of these regions. To evaluate the performance of models, common evaluation statistics were used. The results showed that at the Yazd station, in the ANN method, the lowest values of RMSE, MAE and the highest values of IA and R2 were 2.381, 1.760, 0.869, and 0.962 , respectively. These values at Kerman Station are equal to 2.708, 2.050, 0.945 and 0.810 , respectively.In the SVM method, the lowest values of RMSE, MAE and the highest values of IA and R2 at the Yazd station were 2.028, 1.540, 0.901 and 0.973, respectively, and at Kerman station were 2.407 , 1.896, 0.956 and 0.846 , resp ectively. Overall, the efficiency of the SVM method in both regions was more accurate than the ANN method.

Keywords

References

[1]    K. E. N’Tsoukpoe, K. Y. Azoumah, E. Ramde, A.K. Fiagbe, P. Neveu, X. Py, M. Gaye, A. Jourdan, Integrated design and construction of a micro-central tower power plant, Energy for Sustainable Development, Vol. 31, pp. 1-13, 2016.
[2]       A. Qazi, H. Fayaz, A. Wadi, R. G. Raj, N. A. Rahim, W. A. Khan, The artificial neural network for solar radiation prediction and designing solar systems: a systematic literature review. Journal of cleaner production, Vol. 104, PP. 1-12, 2015.
[3]       J. Jang, S. Roger, ANFIS: Adaptive-network-based fuzzy inference systems, IEEE transactions on systems, man, and cybernetics, Vol. 23, pp. 665-685, 2003.
[4]     X. Yan, D. Abbes, B. Francois, Solar radiation forecasting using Artificial Neural Network for local power reserve, International Conference on Electrical Sciences and Technologies in Maghreb, (CISTEM), Tunis, Tunisia, PP. 1-6, 2014.
[8]    Z. Ramedani, M. Omid, A. Keyhani, Modeling solar energy potential          in a Tehran province using artificial neural networks, International Journal of Green Energy, Vol. 10, pp. 427-441, 2013.
[9]       J. Piri, S. Shamshirband, D. Petković, C. W. Tong, M. H. ur  Rehman, Prediction of the solar radiation on the Earth using support vector regression technique, Infrared Phys. Infrared Physics and Technol, Vol. 68, pp. 179–185, 2015.
[10]     K. Mohammadi, S. Shamshirband, A. S. Danesh, M. S. Abdullah, M. Zamani, Temperature-based estimation of global solar radiation using soft computing methodologies, Theoretical and Applied Climatology, Vol. 125, pp. 101-112, 2015.
[11]     N. KUMAR, S. P. Sharma, U. K. Sinha, Y. K. Nayak, Prediction of solar energy based on intelligent ANN modeling. International Journal of Renewable Energy Research (IJRER), Vol. 6, No. 1, pp. 183-188, 2016.
[12]    H. C. Bayrakçı, C. Demircan, A. Keçebaş, The development of empirical models for estimating global solar radiation on horizontal surface: a case study, Renewable and Sustainable Energy Reviews, Vol. 81, pp. 2771–2782, 2018.
[13]    V. Z. Antonopoulos, D. M. Papamichail, V. G. Aschonitis, A. V. Antonopoulos, Solar radiation estimation methods using ANN and empirical models. Computers and Electronics in Agriculture, Vol. 160, pp. 160-167, 2019.
[14]     J. L. Chen, G. S. Li, Evaluation of support vector machine for estimation of solar radiation from measured meteorological variables, Theoretical and Applied Climatology, Vol. 115, pp. 627–638, 2014.
[15]     O. Şenkal, Solar radiation and precipitable water modeling for Turkey using artificial neural networks. Meteorology and Atmospheric Physics, Vol. 127, pp. 481-488, 2015.
[16]     L. Olatomiwa, S. Mekhilef, S. Shamshirband, K. Mohammadi, D. Petković, C. Sudheer, A support vector machine–firefly algorithm-based model for global solar radiation prediction, Solar Energy, Vol. 115, pp. 632-644, 2015.
[17]    C. M. dos Santos, J. F. Escobedo, E. T. Teramoto, S. H. M. G. da Silva, Assessment of ANN and SVM models for estimating normal direct irradiation (Hb). Energy conversion and management, Vol. 126, pp. 826-836, 2016.
[18]     V. H. Quej, J. Almorox, J. A. Arnaldo, L. Saito, L. ANFIS, SVM and ANN soft-computing techniques to estimate daily global solar radiation in a warm sub-humid environment. Journal of Atmospheric and Solar-Terrestrial Physics, Vol. 155, pp. 62-70, 2017.
[19]    J. Rahimi, M. Ebrahimpour, A. Khalili, Spatial changes of extended De Martonne climatic zones affected by climate change in Iran. Theoretical and applied climatology, Vol. 112, pp. 409-418, 2013.
[20]     I. Moradi, Quality control of global solar radiation using sunshine duration hours. Energy, Vol. 34, No. 1, pp. 1-6, 2009.
[21]   H. DehghaniSanij, T. Yamamoto, V. Rasiah, Assessment of evapotranspiration estimation models for use in semi-arid environments. Agricultural water management, Vol. 64, No. 2, pp. 91-106, 2004.
[22]     M. Turhan, Neural networks and computation of neural network weights and biases by the generalized delta rule and backpropagation of errors, Rock SolidImages Press, 1995.
[25]    S. Haykin, Neural networks and learning machines, Three Eddition, Pearson Education, New York: Prentice Hall, 2006.
[26]     R. Hecht-Nielsen, (1987). Kolmogorov's mapping neural network existence theorem. In Proceedings of the International Conference on Neural Networks, IEEE Press, Vol. 3, pp. 11-14, 1987.
[27]      P. F. Pai, W.C. Hong, A recurrent support vector regression model in rainfall forecasting, HydrologicalProcess, Vol. 21, No. 6, pp. 819-827, 2007.
[28]     V. N. Vapnik, Statistical Learning Theory, First Edittion, pp. 156-160, New York: Wilay, 1998.
[29]    L. Hamel, Knowledge Discovery with Support Vector Machines, First Edittion, Hoboken: John Wiley, 2009.
[30]     O. Kisi, M. Cimen, Evapotranspiration modelling using support vector machines, Hydrological Sciences.Vol. 54, No. 5, pp. 918-928, 2010.
[32]    P. S. Yu, S. T. Chen, I. F. Chang, Support vector regression for real-time flood stage forecasting, Journal of Hydrology,Vol. 328, pp. 704-716, 2006.
[34]  C. J. Willmott, Some comments on the evaluation of model performance, Bulletin of the American Meteorological Society, Vol. 63, No. 11, pp. 1309-1313, 1982.
[35]     R. Meenal, A. I. Selvakumar, Assessment of SVM, empirical and ANN based solar radiation prediction models with most influencing input parameters. Renewable Energy, Vol. 121, pp. 324-343, 2018.
[36]    S. A. Ahmad, M. Y. Hassan, M. P. Abdullah, H. A. Rahman, F. Hussin, H. Abdullah, R. Saidur, A review on applications of ANN and SVM for building electrical energy consumption forecasting, Renewable and Sustainable Energy Reviews, Vol. 33, No. 1, pp. 102-109, 2014.
Journal of Renewable and New Energy
Volume 7, Issue 2 - Serial Number 14
September 2020
Pages 19-28

Files

History

  • Receive Date: 25 May 2019
  • Revise Date: 08 September 2019
  • Accept Date: 10 December 2019

Share

How to cite

Statistics