Yapay Sinir Ağları ve Angström-Prescott Denklemleri Kullanılarak Gaziantep, Antakya ve Kahramanmaraş İçin Global Güneş Radyasyonu Tahmini

Abstract

Bu çalışmada, Akdeniz bölgesinin doğusundan seçilen Gaziantep (37°.06K, 37°.35D, 750m), Antakya (36°.15K, 36°.08D, 100m) ve Kahramanmaraş (37°.35K, 36°.55D, 572m) bölgeleri için yatay bir yüzeydeki aylık olarak ortalama global güneş ışınımını tahmin etmek için yapay sinir ağı (YSA) modeli ve güneşlenme süresine bağlı Angström-Prescott tipi eşitlikler kullanılmıştır. Bu amaçla, ölçülen veriler kullanılarak YSA modeli ve güneşlenme saatlerine ilişkin Angström-Prescott tipi denklemler uygulanmıştır. İlk olarak, modelleme için en iyi YSA modeli için transfer fonksiyonu olarak Hyperbolic Tangent Sigmoidli (tansig) iki gizli katmanı ve lineer transfer fonksiyonu kullanan bir çıkış katmanlı ileri beslemeli geri yayılımlı bir modeli kullanılmıştır. Levenberg-Marquardt geri yayılım eğitim algoritması (trainlm) YSA modelinde eğitim algoritması olarak seçilmiştir. Devlet Meteoroloji Genel Müdürlüğü'nden alınan on beş yıllık (1993-2007) ölçülmüş meteorolojik veriler ağın eğitilmesi (on bir yıl) ve test edilmesi (dört yıl) için kullanılmıştır. İkinci olarak, aylık ortalama güneşlenme süresi (saat), aylık ortalama sıcaklık (°C), bağıl nem ve güneş deklinasyon açısı () gibi parametreler kullanılarak aylık olarak yıllık global güneş radyasyonunun tahmin edilmesi için beş farklı Angström-Prescott tipi regresyon modeli (M1-5) de geliştirilmiştir. YSA’dan ve Angström-Prescott tipi denklemlerden tahmin edilen veriler ile ölçülen veriler R², RMSE, MAPE ve MSE gibi dört farklı istatistiksel yöntem kullanılarak karşılaştırılmıştır. YSA modeli için R², RMSE, MAPE ve MSE istatistiksel göstergeleri sırasıyla Gaziantep için 0.990, 0.586, 4.105 ve 0.343, Antakya için 0.997, 0.287, 2.584, ve 0.083 ve Kahramanmaraş için 0.997, 0.414, 2.445 ve 0.171 olarak bulunmuştur. Beş farklı Angström-Prescott modeli (M1-M5) modeli için R², RMSE ve MSE performans göstergelerine göre, Gaziantep ve Kahramanmaraş için M3 modeli, Antakya için ise M5 modeli en iyi performansı göstermiştir. İstatistiksel hata sonuçlarından görülebileceği gibi, ANN ve Angström-Prescott tipi modellerden tahmini global güneş radyasyon verileri, ölçülen meteorolojik değerlerle iyi bir uyum içindedir. Geliştirilen YSA ve Angström-Prescott tip modellerin diğer yerleşim yerleri için de tahmin etmede kullanılabileceğini önermekteyiz.

Keywords

• Global güneş ışınımı
• Güneş ışınım tahmin modelleri
• Yapay sinir ağları
• Güneşlenme süresi
• Açıklık indeksi
• Angström-Prescott eşitliği
• Korelasyon modelleri

Estimation of Solar Radiation for Gaziantep, Antakya and Kahramanmaraş Using Artificial Neural Network and Angström-Prescott Equations

Abstract

In this study, we estimated monthly average global solar radiation on a horizontal surface for selected regions of Gaziantep (37°.06N, 37°.35E, 750m), Antakya (36°.15N, 36°.08E, 100m), and Kahramanmaraş (37°.35N, 36°.55E, 572m) from the east of the Mediterranean region. For this purpose, an artificial neural network (ANN) model and Angström-Prescott type equations related to sunshine hosurs were applied using the data measured. Firstly, a multi-layer feed-forward back-propagation model containing two hidden layers with tangent sigmoid (tansig) as the transfer function and one output layer with utilized a linear transfer function for the best ANN model was used for the modelling. Levenberg-Marquardt back propagation training algorithm (trainlm) was chosen as the training algorithm in the ANN model. A period of fifteen years (1993-2007) meteorological data taken from the Turkish State Meteorological Service were used for training (eleven years) and testing (four years) the network. Secondly, five Angström-Prescott type regression models (M1-5) were also used for estimating the monthly annual global solar radiation using parameters such as monthly average sunshine duration (hour), monthly average temperature (°C), relative humidity and solar declination angle (). Estimated data from ANN and Angström-Prescott type equations were compared with measured data using four different statistical methods such as R², RMSE, MAPE and MSE. For the ANN model, R², RMSE, MAPE and MSE statically indicators were found to be 0.990, 0.586, 4.105 and 0.343 for Gaziantep, 0.997, 0.287, 2.584, and 0.083 for Antakya, and 0.997, 0.414, 2.445 and 0.171 for Kahramanmaraş, respectively. For five different Angström-Prescott models (M1-M5) models, M3 model is the best performance for Gaziantep and Kahramanmaraş, while M5 model is the best performing for Antakya, according R², RMSE and MSE MSE performance indicators. As can be seen from the statistical error results, the estimated global solar radiation data from both ANN and Angström-Prescott type models are in reasonable agreement with the actual meteorological values. We suggest that the developed both ANN and Angström-Prescott type models can also be used to predict solar radiation another location.

Keywords

• Global solar radiation
• Solar radiation estimation models
• Artificial neural network
• Sunshine hours
• Clearness index
• Angström-Prescott equation
• Correlation models

References

1. [1] M. A. AbdulAzeez, “Artificial neural network estimation of global solar radiation using meteorological parameters in Gusau, Nigeria,” Archives of Applied Science Research, 3 (2), 586-595, 2011.
2. [2] E.A. Ahmed and M. El-Nouby Adam, “Estimate of global solar radiation by using artificial neural network in Qena, Upper Egypt,” Journal of Clean Energy Technologies, 1, 2, 2013.
3. [3] O. Şenkal and T. Kuleli, “Estimation of solar radiation over Turkey using artificial neural network and satellite data,” Applied Energy, 86, 1222–1228, 2009.
4. [4] O. Şenkal “Modeling of solar radiation using remote sensing and artificial neural network in Turkey,” Energy, 35 (12), 4795-4801, 2010.
5. [5] M. Şahan ve Y. Okur, “Akdeniz Bölgesine ait meteorolojik veriler kullanılarak yapay sinir ağları yardımıyla güneş enerjisinin tahmini,” Süleyman Demirel Üniversitesi Fen Edebiyat Fakültesi Fen Dergisi, 11 (1), 61-71, 2016.
6. [6] A. Angström, “Solar and terrestrial radiation,” Quarterly Journal of the Royal Meteorological Society, 50 (210), 121-126, 1924.
7. [7] J. A. Prescott, “Evaporation from a water surface in relation to solar radiation,” Transactions of the Royal Society of South Australia, 64, 114-148, 1940.
8. [8] M. R. Rietveld, “A new method for estimating the regression coefficients in the formula relating solar radiation to sunshine,” Agricult. Meteorol., 19, 243–252, 1978.

9. [9] H. Ogelman, A. Ecevit, and E. Tasdemiroglu, “A new method for estimating solar radiation from bright sunshine data,” Solar Energy, 33, 619–625, 1984.
10. [10] K. L. Bristow and G. S. Campbell, “On the relationship between incoming solar radiation and daily maximum and minimum temperature,” Agric. For. Meteorol., 31, 159–166, 1984.
11. [11] B. G. Akınoglu and A. Ecevit, “A further comparison and discussion of sunshine based models to estimate global solar radiation,” Solar Energy, 15, 865–872, 1990.
12. [12] R. De Jong and D. W. Stewart, “Estimating global solar radiation from common meteorological observations in western Canada,” Can. J. Plant. Sci. 73, 509–518, 1993.
13. [13] B. T.Nguyen and T. L. Pryor, “The relationship between global solar radiation and sunshine duration in Vietnam,” Renewable Energy, 11, 47-60, 1997.
14. [14] I. T. Togrul, H. Togrul, and D. Evin, “Estimation of global solar radiation under clear sky radiation in Turkey,” Renewable Energy, 21, 271-287, 2000.
15. [15] S. A. Khalil and A. M. Fathy, “An empirical method for estimating global solar radiation over Egypt,” Acta Polytechnica, 48 (5), 48-53, 2008.
16. [16] S. Edalati, M. Ameri, and M. Iranmanesha, “Estimating and modeling monthly mean daily global solar radiation on horizontal surfaces using artificial neural networks in South East of Iran,” Journal of Renewable Energy and Environment (JREE), 2 (1), 36-42, 2015.
17. [17] I. A. Basheera and M. Hajmeer, “Artificial neural networks: fundamentals, computing, design, and application,” Journal of Microbiological Methods, 43, 3-31, 2000.
18. [18] F. S. Marzano, E. Fionda, and P. Ciotti, “Neural-network approach to ground-based passive microwave estimation of precipitation ıntensity and extinction,” Journal of Hydrology, 328, 121-131, 2005.
19. [19] D. Graupe, Principles of Artificial Neural Networks. (2nd Edition), Advanced series on circuits and systems, volume 6, World Scientific Publishing Co. Pte. Ltd., 2007.
20. [20] C. Gershenson, “Artificial neural networks for beginners, formal computational skills teaching package,” COGS, University of Sussex, Brighton, UK, 2001.
21. [21] J. K. Page, “The estimation of monthly ea values of daily total short wave radiation on vertical and inclined surfaces from sunshine records for latitudes 40°N -40°S,” Proceedings of the UN Conference on New Sources of Energy, Paper No. 598, 378-390, 1964.
22. [22] S. Klein, “Calculation of monthly average insolation on tilted surfaces,” Solar Energy, 19 (4), 1977, 325-329, 1977.
23. [23] M. Iqbal, An Introduction to Solar Radiation. London: Academic Press, 1983.
24. [24] J. A. Duffie and W. A. Beckman, Solar Engineering of Thermal Processes. (4th ed.), John Wiley and Sons, Inc., New York, 2013.
25. [25] J. R. Howell, R. B. Bannerot, and G. C. Vliet, Solar-Thermal Energy Systems Analysis and Design. McGraw-Hill, Inc., New York, 1982.
26. [26] M. Despotovic, V. Nedic, D. Despotovic, and S. Cvetanovic, “Review and statistical analysis of different global solar radiation sunshine models,” Renewable and Sustainable Energy Reviews, 52, 1869-1880, 2015.