with the collaboration of Iranian Society of Mechanical Engineers (ISME)

Document Type : Research Article

Authors

1 Faculty of Agriculture, Shahrood University of Technology, Shahrood, Iran

2 Department of Agricultural Machinery, Faculty of Agricultural Engineering and Technology, University College of Agriculture and Natural Resources, University of Tehran, Karaj, Iran

Abstract

Introduction
Global solar radiation is the sum of direct, diffuse, and reflected solar radiation. Weather forecasts, agricultural practices, and solar equipment development are three major fields that need proper information about solar radiation. Furthermore, sun in regarded as a huge source of renewable and clean energy which can be used in numerous applications to get rid of environmental impacts of non-renewable fossil fuels. Therefore, easy and fast estimation of daily global solar radiation would play an effective role is these affairs.
Materials and Methods
This study aimed at predicting the daily global solar radiation by means of artificial neural network (ANN) method, based on easy-to-gain weather data i.e. daily mean, minimum and maximum temperatures. Having a variety of climates with long-term valid weather data, Washington State, located at the northwestern part of USA was chosen for this purpose. It has a total number of 19 weather stations to cover all the State climates. First, a station with the largest number of valid historical weather data (Lind) was chosen to develop, validate, and test different ANN models. Three training algorithms i.e. Levenberg – Marquardt (LM), Scaled Conjugate Gradient (SCG), and Bayesian regularization (BR) were tested in one and two hidden layer networks each with up to 20 neurons to derive six best architectures. R, RMSE, MAPE, and scatter plots were considered to evaluate each network in all steps. In order to investigate the generalizability of the best six models, they were tested in other Washington State weather stations. The most accurate and general models was evaluated in an Iran sample weather station which was chosen to be Mashhad.
Results and Discussion
The variation of MSE for the three training functions in one hidden layer models for Lind station indicated that SCG converged weights and biases in shorter time than LM, and LM did that faster than BR. It means that SCG provided the fastest performance. However, the story for accuracies was different i.e. the BR, LM, and SCG algorithms provided the most accurate performances, respectively, both among one or two hidden layers. According to the evaluation criteria, six most accurate derived models out of 1260 tested ones for Lind station was 3-14-1 and 3-11-19-1 with LM, 3-20-1 and 3-20-19-1 with BR, and 3-9-1 and 3-20-17-1 with SCG training algorithm, and 3-20-19-1 topology with BR showed the best performance out of all architectures. Results of the evaluation of the six accurate models in the remaining 18 stations of Washington State proved that regardless of the climate, in each weather station, BR with its inherent automatic regularization, provided the most accurate models (0.87 67.41 %), and then SCG (0.90>R>0.83, 3.91>RMSEMAPE > 77.28 %). Therefore, the Bayesian neural networks, which showed the best performance among all Washington State weather stations, were evaluated for Mashhad station, as an Iran sample climate. The results proved the ability of the said networks for this climate (R=0.82, RMSE=3.92‌ MJm-2, MAPE=79.92%).

Conclusion
The results indicated that the Bayesian neural networks are capable of predicting global solar radiation with minimum inputs in different climates. This was concluded both in Washington State weather stations, which has a variety of climates, and also in Mashhad as an Iran sample weather station. These models would eliminate the need for complex climate-dependent mathematical relations or other models which are mostly dependent on many inputs. So, this algorithm would be a good means first in weather forecast practices, also in the design and development of solar assisted equipment, as well as in managerial practices in agriculture when monitoring crop solar-dependent processes like photosynthesis and evapotranspiration.

Keywords

1. Ahmad, E. A., and E. N. Adam. 2013. Estimate of global solar radiation by using artificial neural network in Qena, Upper Egypt. Journal of Clean Energy Technologies 1: 148-150.
2. Aksoy, B., S. Ener Rusen, and B. Akinoglu. 2011. A Simple correlation to estimate global solar irradiation on a horizontal surface using METEOSTAT sattellite images. Turkish Journal of Engineering and Environmental Sciences 35 (2): 125-137.
3. Allen, R. G. 1997. Self-calibrating method for estimating solar radiation from air temperature. Journal of Hydrologic Engineering 2 (2): 56-67.
4. Almorox, J., M. Bocco, and E. Willington. 2013. Estimation of daily global solar radiation from measured temperatures at Canada de Lugue, Cordoba, Argentina. Renewable Energy 60: 382-387.
5. Anjavi Arsanjani, M., M. Yaghoubi, and K. JafarPour, 2014. Evaluation of solar energy potential in some climatical zones of Iran using artificial neural nework. The first International Solar Energy Conference and Exhibition, Tehran, Iran. (In Farsi).
6. Anonymous. 2017. I.R. of Iran Meteorological Organization. from: http://www.razavimet.ir/node/114. Accessed 7 March 2017.
7. Anonymous. 2015. Pacific Northwest Region. from: https://www.usbr.gov/pn/agrimet/. Accessed 10 April 2016.
8. Behboudian, J. 2015. Introductory Probability and Statistics. Emam Reza publication. (In Farsi).
9. Bindi, M., and F. Miglietta. 1991. Estimating daily global radiation from air temperature and rainfall measurements. Climate Research 1 (2): 117-124.
10. Bristow, K. L. and G. S. Campbell. 1984. On the relationship between incoming solar radiation and daily maximum and minimum temperature. Agricultural and Forest Meteorology 31: 159-166.
11. Burden, F., and D. Winkler. 2008. Bayesian regularization of neural networks. Methods in Molecular Biology 458: 25-44.
12. Cornaro, C. F. 2013. Solar radiation forecast using neural networks for the prediction of grid connected PV plants energy production (DSP). Proceedings of 28th European Photovoltaic Solar Energy Conference and Exhibition. Paris, France.
13. Dehghani, R., M. Ghorbani, M. Teshnehlab, A. Rikhtehgar Gheasi, and E. Asadi, 2015. Comparison and evalution of bayesian neural network, gene gramming, support vector machine and multiple expression proLinear regression in river discharge estimation (Case Study: Sufi Chay Basin). Journal of Irrigation and Water Engineering 20: 66-85. (In Farsi).
14. Faraji Mahyari, K., Z. Faraji Mahyari, and M. Khanali. 2015a. Modeling daily solar radiation temperature-based in four climate regions of Iran. 9th National Congress on Agricultural Machinery Engineering (Mechanics of Biosystems) and Mechanization, Tehran, Iran. (In Farsi).
15. Faraji Mahyari, Z., K. Faraji Mahyari, and M. Khanali. 2015b. Evaluation of performance of empirical sunshine-based models for predicting the daily global solar radiation (Case Study: Bandar Abbas Station). 9th National Congress on Agricultural Machinery Engineering (Mechanics of Biosystems) and Mechanization, Tehran, Iran. (In Farsi).
16. Forsee, F., and M. Hagan. 1997. Gauss-Newton approximation to bayesian learning. In 1997 IEEE international conference on neural networks, 1-4, pp. 1930-1935.
17. Gadiwala , M., A. Usman, M. Akhtar, and K. Jamil. 2013. Empirical models for the estimation of global solar radiation with sunshine hours on horizontal surface in various cities of Pakistan. Pakistan Journal of Meteorology 9 (18): 43-49.
18. Ghahreman, N., and B. Bakhtiari. 2009. Solar radiation estimation from rainfall and temerature data in arid and semi-arid climates of Iran. Desert 14: 141-150.
19. Hargreaves, G. L., G. H. Hargreaves, and J. P. Riley. 1985. Irrigation water requirements for Senegal River basin. Journal of Irrigation and Drainage Engineering, ASCE, 111 (3): 265-275.
20. Hunt, L. A., L.Kuchar, and C. J. Swanton. 1998. Estimation of solar radiation for use in crop modeling. Agric. Forest. Meteorol. 91: 293-300.
21. Kia, M. 2010. Soft Computing in MATLAB. Kian Rayaneh Sabz. (In Farsi).
22. Kim, K. H., J. C. Baltazar, and J. S. Haberl. 2014. Evaluation of meteorological base models for estimating hourly global solar radiation in Texas. Energy Procedia 57: 1189-1198.
23. Layeghi, M. 2015. Solar energy, technologies and applications. Jahad daneshgahi publication. (In Farsi).
24. Li, H., F. Cao, X. Wang, and W. Ma. 2014. A temperature-based model for estimating monthly average daily global solar radiation in China. The Scientific World Journal. 2014, 9 pages.
25. Li, M. F., L. Fan, H. B.Liu, P. T.Guo, and W. Wu. 2013a. A general model for estimation of daily global solar radiation using air temperature and site parameters in Southwest China. Journal of Atmospheric and Solar-Terrestrial Physics 92: 145-150.
26. Li, M. F., X. P. Tang, W. Wu, and H. B. Liu. 2013b. General models for estimating daily global solar radiation for different solar radiation zones in Mainlan China. Energy Conversion and Management 70: 139-148.
27. Liu, X., M. Xurong, Y. Li, Q. Wang, J. Raunso Jensen, Y. Zhang, and J. R. Porter. 2009. Evaluation of temperature-based global solar radiatin models in China. Agricultural and Forest Meteorology 149: 1433-1446.
28. Mackay, D. J. 1992. A practical bayesian framework for backpropagation networks. Neural Computation 4: 448-472.
29. Mirzaee ghale, E., M. Omid, A. Keyhani, and S. Behzadi Pour. 2014. The use of solar energy for a model heating poultry house. Fifth International Conference on heating, cooling and ventilation Systems. Tehran, Iran. (In Farsi).
30. Motamed-Shariati, H. R., H. Mobli, M. Sharifi, and H. Ahmadi. 2016. Prediction of solar radiation by ordinary weather data for Mashhad climate. Iranian Journal of Biosystem Engineering 47 (1): 185-196. (In Farsi).
31. Mousazadeh, H. K. 2010. Optimal power and energy modeling and range evaluation of a solar assist plug-in hybrid electric tractor (SAPHT). Transaction on ASABE, 53 (4): 1-11.
32. Mubiru, J. 2011. Using artificial neural network to predict direct solar irradiation. Advances in Artificial Neural Systems. 2011, 6 pages.
33. Namrata, K., S. Sharma, and S. Saksena. 2013. Comparison of different models for estimation of global solar radiation in Jharkhand (India) Region. Smart Grid and Renewable Energy 4: 384-352.
34. Paoli, C., C. Voyant, M. Muselli, and M. L. Nivet. 2009. Solar radiation forcasting using ad-hoc time series preprocessing and neural network. Emerging Intelligent Computing Technology and Applications 5th International Conference on Intelligent Computing.Ulsan, South Korea.
35. Razafiarison, I., L. Andriazafimahazo, B. Ramamonjisoa, and B. Zeghmati. 2011. Using mutilayered neural networks for determining global solar radiation upon tilted surface in Fianarantsoa Madagascar. Reveu des Energies Renouvelables 14: 329-342.
36. Rivington, M., G. Bellocchi, K. B. Matthews, and K. Buchan. 2005. Evaluation of three model estimation of solar radiation at 24 UK stations. Agricultureal and Forest Meteorology 132: 228-243.
37. Rohani, A., S. Saedi, H. Gerailu, and M. H. Aghkhani. 2015. Prediction of lateral surface, volume and sphericity of pomegranate using MLP artificial neural network. Journal of Agricultural Machinery 5: 292-301. (In Farsi).
38. Sabziparvar, A. A. 2008. A Simple formula for estimation global solar radiation in central arid deserts of Iran. Renewable Energy 33: 1002-1010.
39. Samani, Z. 2000. Estimating solar radiation and evapotranspiration using minimum climatological data. Journal of Irrigation and Drainage Engineering 126 (4): 265-275.
40. Ticknor, J. L. 2013. A bayesian regularized artificial neural network for stock market forcasting. Expert Systems with Applications 40: 5501-5506.
41. Wang, F., Z. Mi, S. Su, and H. Zhao. 2012. Short term solar irradiance forcasting model based on artificial neural network using statistical feature parameters. Energies 5: 1355-1370.
42. Yano, A. O. 2014. Prototype semi-transparent photovoltaic modules for greenhouse roof application. Biosystems Engineering, 122: 62-73.
CAPTCHA Image