HOURLY GLOBAL SOLAR RADIATION ESTIMATION BASED ON MACHINE LEARNING METHODS IN ESKISEHIR
Abstract
Due to the increasing importance of knowing the global solar radiation (GSR) amount incident on solar panels; short term data, such as hourly global solar radiation (HGSR), is essentially required to obtain more accurate and reliable power generation prediction. Nowadays, Machine Learning (ML) methods are becoming a huge trend for data forecasting. Therefore, in this paper, a comparison between Collares-Pereira & Rabl empirical model modified by Gueymard (CPRG) and ML methods for HGSR estimation in Eskişehir city in Turkey is conducted. Artificial Neural Network (ANN), Regression Tree (RT) and Support Vector Regression (SVR) are ML methods that are used to predict HGSR. Besides, hourly metrological and geographical parameters for the year 2014 are taken as inputs in the training models. The inputs are solar time, solar hour angle, Julian day number, daily GSR, altitude, longitude, latitude, hourly average humidity, hourly temperature and hourly pressure. To demonstrate these techniques, a comparison is implemented using MATLAB software with the help of existing toolboxes. Finally, this study proved that ML methods outperform the CPRG model and not to mention that they have far more accurate results. Although almost all ML models gave similar results, SVR was the best among them with a correlation coefficient of 0.979532 for the training set and 0.978244 for the testing set. In a nutshell, ML are successful methods that should be to be taken into consideration to perfectly estimate HGSR now and in the future in the field of solar renewable energy estimation.
Keywords
References
- [1] Başaran Filik Ü, Filik T and Gerek Ö, New Electric Transmission Systems: Experiences, in Handbook of Clean Energy Systems, Wiley, 2015.
- [2] Shaddel M, Javan DS and Baghernia P. Estimation of hourly global solar irradiation on tilted absorbers from horizontal one using Artificial Neural Network for case study of Mashhad, vol. 53, Elsevier Ltd, 2016, pp. 59-67.
- [3] Khosravi A, Koury RN, Machado L and Pabon JJ. Prediction of hourly solar radiation in Abu Musa Island using machine learning algorithms, Journal of Cleaner Production, vol. 176, pp. 63-75, 2018.
- [4] Voyant C, Notton G, Kalogirou S, et al. Machine learning methods for solar radiation forecasting: A review, vol. 105, Elsevier Ltd, 2017, pp. 569-582.
- [5] Kaba K, Sarıgül M, Avcı M, et al. Estimation of daily global solar radiation using deep learning model, Energy, vol. 162, pp. 126-135, 2018.
- [6] Sözen A, Arcaklioğlu E and Özalp M. Estimation of solar potential in Turkey by artificial neural networks using meteorological and geographical data, Energy Conversion and Management, vol. 45, no. 18-19, pp. 3033-3052, 2004.
- [7] Elminir HK, Areed FF and Elsayed TS. Estimation of solar radiation components incident on Helwan site using neural networks, Solar Energy, 2005; vol. 79, no. 3, pp. 270-279.
- [8] Angela K, Taddeo S and James M. Predicting Global Solar Radiation Using an Artificial Neural Network Single-Parameter Model, Advances in Artificial Neural Systems, vol. 2011, pp. 1-7.
- [9] Salem H, Pharma H, Abdelhafez E, et al. Prediction of Hourly Solar Radiation in Amman Jordan by Using Artificial Neural Networks, Int. J. of Thermal & Environmental Engineering, 2017; vol. 14, no. 2, pp. 103-108.
- [10] Troncoso A, Salcedo-Sanz S, Casanova-Mateo C, et al. Local models-based regression trees for very short-term wind speed prediction, Renewable Energy, 2015; vol. 81, pp. 589-598.