Modeling of Monthly Mean Solar Energy Potential using Artificial Neural Network

Year 2025, Volume: 30 Issue: 2, 512 - 523, 31.08.2025

Erdinç Timoçin

https://doi.org/10.53433/yyufbed.1665961

Abstract

The aim of this study is to develop an artificial neural network (ANN) model for accurately predicting monthly mean solar radiation and irradiance for Mersin (36.8o N, 34.6o E, Türkiye). The prediction of monthly mean solar radiation and irradiance was made by using two different ANN (NN-1 and NN-2) models with different input parameters and thus, a dual solution strategy for the monthly mean solar radiation and irradiance forecasts was presented. The ANN models were trained for the target parameters (monthly mean solar radiation and irradiance) at each month of the year. The training, testing and validating for both models were conducted using the data obtained for the period from 2004 to 2024. The performance results of these alternative models compared with each other. The accuracy of the models to predict the monthly mean solar radiation and irradiance are identified based on root mean square errors (RMSE) and cross-correlation coefficients (R). The NN-2 model has smaller RMSE values and has bigger R values. That is, the NN-2 model has higher prediction success with lower prediction error for both monthly mean solar radiation and irradiance intensity. The presence of two models may be advantageous for more precise forecasting situations and the NN-2 model can be chosen for such cases. In addition, the application of the NN-2 model proposed in this study can be extended to other locations.

Keywords

Artificial neural network , Modelling , Solar irradiance , Solar radiation

Yapay Sinir Ağı Kullanılarak Aylık Ortalama Güneş Enerjisi Potansiyelinin Modellenmesi

Abstract

Bu çalışmanın amacı, Mersin (36.8o N, 34.6o E, Türkiye) için aylık ortalama güneş radyasyonu ve ışınım şiddetini doğru bir şekilde tahmin etmek için bir yapay sinir ağı (YSA) modeli geliştirmektir. Aylık ortalama güneş radyasyonu ve ışınım şiddetinin tahmini, farklı giriş parametrelerine sahip iki farklı YSA (NN-1 ve NN-2) modeli kullanılarak yapılmış ve böylece aylık ortalama güneş radyasyonu ve ışınım şiddeti tahminleri için ikili bir çözüm stratejisi sunulmuştur. YSA modelleri, yılın her ayında hedef parametreler (aylık ortalama güneş radyasyonu ve ışınım şiddeti) için eğitilmiştir. Her iki model için eğitim, test ve doğrulama işlemleri 2004-2024 yılları arasında elde edilen veriler kullanılarak gerçekleştirilmiştir. Birbirine alternatif olan bu modellerin performans sonuçları birbirleriyle karşılaştırılmıştır. Aylık ortalama güneş radyasyonu ve ışınım şiddetini tahmin eden modellerin doğruluğu, kök ortalama karekök hatalarına (RMSE) ve çapraz korelasyon katsayılarına (R) dayanarak belirlenmiştir. NN-2 modeli daha küçük RMSE değerlerine ve daha büyük R değerlerine sahiptir. Yani, NN-2 modeli hem aylık ortalama güneş radyasyonu hem de ışınım yoğunluğu için daha düşük tahmin hatasıyla daha yüksek tahmin başarısına sahiptir. İki modelin varlığı daha hassas tahmin durumları için avantajlı olabilir ve bu gibi durumlar için NN-2 modeli seçilebilir. Ayrıca, bu çalışmada önerilen NN-2 modelinin uygulaması diğer konumlara genişletilebilir.

Keywords

Güneş ışınımı , Güneş radyasyonu , Modelleme , Yapay sinir ağı

References

• Arslan, G., & Bayhan, B. (2016). Solar energy potential in Mersin and a simple model to predict daily solar radiation. Muğla Journal of Science and Technology,1-4.
• Chaouachi, A., Kamel. R. M., & Nagasaka, K., (2009). Neural network ensemble-based solar power generation short-term forecasting. Journal of Advanced Computational Intelligence and Intelligent Informatics, 14(1), 69-75. https://doi:10.20965/jaciii.2010.p0069
• Demirgül, T., Demir, V., & Sevimli, M. F. (2024). Solar radiation estimation of Turkey with different machine learning approaches. Geomatik, 9(1), 106-122. https://doi.org/10.29128/geomatik.1374383
• Dupont, E., Koppelaar, R., & Jeanmart H. (2020). Global available solar energy under physical and energy return on investment constraints. Applied Energy, 257, 113968. https://doi.org/10.1016/j.apenergy.2019.113968
• Eşlik, A. H., Sen, O., & Serttaş, F. (2024). CNN-LSTM model for solar radiation prediction: Performance analysis. Gazi University Faculty of Engineering and Architecture Journal, 39(4), 2155-2162. https://doi.org/10.17341/gazimmfd.1243823
• Fadare, D. A., Irimisose, I., Oni, A. O., & Falana, A. (2010). Modeling of solar energy potential in Africa using an artificial neural network. American Journal of Scientific and Industrial Research, 1(2), 144-157. https://doi.org/10.5251/ajsir.2010.1.2.144.157
• Fletcher, R. (1990). Practical methods of optimization. Wiley, Chichester, New York.
• Hastie, T., Tibshirani, R., & Friedman, J. (2009). The elements of statistical learning: Data mining, inference, and prediction (2nd ed.). Springer.
• Haykin, S. (1999a). Neural networks. A comprehensive foundation. Prentice Hall, New Jersey.
• Haykin, S. (1999b). Neural networks and learning machines. Prentice Hall, New Jersey.
• Holechek, J. L., Geli, H. M. E., Sawalhah, M. N., & Valdez, R. (2022). A global assessment: Can renewable energy replace fossil fuels by 2050? Sustainability, 14(8), 4792. https://doi.org/10.3390/su14084792
• Jiang, Y. (2008). Prediction of monthly mean daily diffuse solar radiation using artificial neural networks and comparison with other empirical models. Energy Policy, 36(10), 3833-3837. https://doi.org/10.1016/j.enpol.2008.06.030
• Kaplan, Y. A. (2017). A new model for predicting the global solar radiation. Environmental Progress & Sustainable Energy, 37(2), 870-880. https://doi.org/10.1002/ep.12721
• Kaygusuz, K., & Sarı, A. (2003). Renewable energy potential and utilization in Turkey. Energy Conversion and Management, 44(3), 459-478. https://doi.org/10.1016/S0196-8904(02)00061-4
• Kılıç, B., & Kumaş, K. (2016). Prediction of solar radiation values of Burdur city using artificial neural networks (ANN). SDU Journal of Technical Sciences, 6(1), 38-44.
• Kulcu, R., Suslu, A., Cihanalp, C., & Yılmaz, D. (2017). Modeling of global solar radiation on horizontal surfaces for Mersin city. Journal of Clean Energy Technologies, 5(1), 77-80. https://doi.org/10.18178/JOCET.2017.5.1.348
• Menges, H. O., Ertekin, C., & Sonmete, M. H. (2006). Evaluation of global solar radiation models for Konya, Turkey. Energy Conversion and Management, 47(18-19), 3149-3173. https://doi.org/10.1016/j.enconman.2006.02.015
• Mohandes, M., Rehman, S., & Halawani, T. O. (1998). Estimation of global solar radiation using artificial neural networks. Renewable Energy, 14(1-4), 179-184. https://doi.org/10.1016/S0960-1481(98)00065-2
• Mubiru, J. (2011). Using artificial neural networks to predict direct solar irradiation. Advances in Artificial Neural Systems, 2011(1), 142054. https://doi.org/10.1155/2011/142054
• Mubiru, J., & Banda, E. J. K. B. (2008). Estimation of monthly average daily global solar irradiation using artificial neural networks. Solar Energy, 82(2), 181-187. https://doi.org/10.1016/j.solener.2007.06.003
• Nawab, F., Hamid, A. S. A., Ibrahim, A. Sopian, K., Fazlizan, A., & Fauzan, M. F. (2023). Solar irradiation prediction using empirical and artificial intelligence methods: A comparative review. Heliyon, 9(6). https://doi.org/10.1016/j.heliyon.2023.e17038
• Neelamegam, P., & Amirtham, V. A. (2016). Prediction of solar radiation for solar systems by using ANN models with different back propagation algorithms. Journal of Applied Research and Technology, 14(3), 206-214. https://doi.org/10.1016/j.jart.2016.05.001
• Priya, S. S., & Iqbal, M. H. (2015). Solar radiation prediction using artificial neural network. International Journal of Computer Applications, 116(16), 28-31. https://doi.org/10.5120/20422-2722
• Rehman, S., & Mohandes, M. (2008). Artificial neural network estimation of global solar radiation using air temperature and relative humidity. Energy Policy, 36(2), 571-576. https://doi.org/10.1016/j.enpol.2007.09.033
• Şenkal, O. (2016). Solar radiation modelling for Turkey using atmospheric parameters with artificial neural networks. Çukurova University Journal of the Faculty of Engineering and Architecture, 31(2), 179-185.
• SODA. (2025). Solar radiation data center. Access Date: 26.03.2025. http://www.soda-pro.com/tr/web services/radiation/nasa-sse/
• Solmaz, O., & Ozgoren, M. (2012). Prediction of hourly solar radiation in six provinces in Turkey by artificial neural networks. Journal of Energy Engineering, 138(4), 194-204. https://doi.org/10.1061/(ASCE)EY.1943-7897.0000080
• Sözen, A., Arcaklioğlu, E., & Özalp, M. (2004). Estimation of solar potential in Turkey by artificial neural networks using meteorological and geographical data. Energy Conversion and Management, 45(18-19), 3033-3052. https://doi.org/10.1016/j.enconman.2003.12.020
• Toğrul, İ. T., & Onat, E. (1999). A study for estimating solar radiation in Elazığ using geographical and meteorological data. Energy Conversion and Management, 40(14), 1577-1584. https://doi.org/10.1016/S0196-8904(99)00035-7
• Toğrul, İ. T., & Toğrul, H. (2002). Global solar radiation over Turkey: comparison of predicted and measured data. Renewable Energy, 25(1), 55-67. https://doi.org/10.1016/S0960-1481(00)00197-X
• Wackernagel, H. (1995). Direct and cross covariances. In: Multivariate geostatistics. Springer, Berlin, Heidelberg.
• Yang, K., & Koike, T. (2002). Estimating surface solar radiation from upper-air humidity. Solar Energy, 72(2), 177-186. https://doi.org/10.1016/S0038-092X(01)00084-6