A comparison of machine learning algorithms for forecasting solar irradiance in Eskişehir, Turkey

This work compares the efficiency of 45 different machine learning (ML) algorithms to provide a comprehensive and most accurate model for global horizontal solar irradiance (GHSI) prediction in Eskişehir, Turkey. The dataset is provided by NASA Prediction of Worldwide Energy Resource (POWER) as satellite data that involves some characteristic weather condition variables such as temperature, precipitation, humidity etc. over 35 years. Some ML algorithms such as Extra Trees, LightGBM, HistGB, Random Forest (RF), Bagging and Decision Tree exhibit better performance among the others with commonly used statistical evaluation metrics in literature such as coefficient of determination (R²), root mean squared error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE). In addition, Extra Tress regression slightly outperformed the rest of ensemble learning methods with R² of 0.99, RMSE of 8.05, MAE of 5.67, MAPE of 4%. Finally, the outcome demonstrates that the ML algorithms belonging to ensemble learning family achieved great results in GHSI prediction at specific location.

Keywords:

Solar irradiance prediction, Machine learning Satellite data, Ensemble learning.,

PDF

___

P. Kumari, D. Toshniwal, Extreme gradient boosting and deep neural network based ensemble learning approach to forecast hourly solar irradiance, Journal of Cleaner Production 279 (2021) 123285.
G. ARSLAN, B. BAYHAN, K. YAMAN, Mersin/Türkiye için Ölçülen Global Güneş Işınımının Yapay Sinir Ağları ile Tahmin Edilmesi ve Yaygın Işınım Modelleri ile Karşılaştırılması, Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji 7(1) (2019) 80-96.
M. Öztürk, N. Özek, B. Berkama, Comparison of Some Existing Models for Estimating Monthly Average Daily Global Solar Radiation for Isparta, Pamukkale University Journal of Engineering Sciences 18(1) (2012) 13-27.
S. Aggarwal, L. Saini, Solar energy prediction using linear and non-linear regularization models: A study on AMS (American Meteorological Society) 2013–14 Solar Energy Prediction Contest, Energy 78 (2014) 247-256.
B. Brahma, R. Wadhvani, Solar irradiance forecasting based on deep learning methodologies and multi-site data, Symmetry 12(11) (2020) 1830.
Y.S. GÜÇLÜ, Ş. Zekâi, Güneş Işınımı Tahmini için Yeni Bir Yaklaşım: OrtLin Modeli, İklim Değişikliği ve Çevre 5(1) (2020) 26-31.
N. ARSLANOĞLU, KOCAELİ İÇİN MEVCUT GLOBAL GÜNEŞ IŞINIMI TAHMİN MODELLERİNİN UYGULANABİLİRLİĞİNİN DEĞERLENDİRİLMESİ, Uludağ University Journal of The Faculty of Engineering 21(1) (2016) 217-226.
H. Karakaya, A.S. AVCI, U. Ercan, M.A. Kallioğlu, Şanlıurfa ilinde yatay yüzeye gelen anlık global güneş ışınımının modellenmesi, Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi 10(1) (2019) 147-155.
H.O. Menges, C. Ertekin, M.H. Sonmete, Evaluation of global solar radiation models for Konya, Turkey, Energy Conversion and Management 47(18-19) (2006) 3149-3173.
H.T. Pedro, C.F. Coimbra, M. David, P. Lauret, Assessment of machine learning techniques for deterministic and probabilistic intra-hour solar forecasts, Renewable Energy 123 (2018) 191-203.
M. ALSAFADI, Ü.B. FİLİK, HOURLY GLOBAL SOLAR RADIATION ESTIMATION BASED ON MACHINE LEARNING METHODS IN ESKISEHIR, Eskişehir Technical University Journal of Science and Technology A-Applied Sciences and Engineering 21(2) 294-313.
G. Muhammet, E. Çelik, ANFIS kullanılarak Tunceli ili için global güneş radyasyonu tahmini, Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi 8(4) (2017) 891-899.
S. Aliyu, A.S. Zakari, M. Ismail, M.A. Ahmed, An Artificial Neural Network Model for Estimating Daily Solar Radiation in Northwest Nigeria, FUOYE Journal of Engineering and Technology 5(2) (2020).
Y. Yu, J. Cao, J. Zhu, An LSTM short-term solar irradiance forecasting under complicated weather conditions, IEEE Access 7 (2019) 145651-145666.
K. Ahmet, Uzun-Kısa Süreli Bellek Ağı Kullanarak Global Güneş Işınımı Zaman Serileri Tahmini, Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji 7(4) (2019) 882-892.
M. QASEM, Ü. BAŞARAN FİLİK, Solar radiation forecasting by using deep neural networks in Eskişehir, Sigma: Journal of Engineering & Natural Sciences/Mühendislik ve Fen Bilimleri Dergisi 39(2) (2021).
S.S. Moustafa, M.S. Abdalzaher, M.H. Yassien, T. Wang, M. Elwekeil, H.E.A. Hafiez, Development of an optimized regression model to predict blast-driven ground vibrations, IEEE Access 9 (2021) 31826-31841.