Öz

ama mutlak hata 0,0142 ve ortalama mutlak ölçekli hata 0,0047 ile en yüksek doğruluğa ulaşmıştır.

Machine learning-based prediction of solar radiation in the Southeastern Anatolia Region of Türkiye

Öz

Solar energy systems play a vital role in alleviating the potential environmental risks that arise from using conventional energy sources. Since the performance of these systems relies heavily on solar radiation, it is crucial to develop reliable tools for accurate solar radiation forecasting. This study investigates the utilization of supervised machine learning models for predicting solar radiation in the Southern Anatolian Region in Türkiye. Nine different models were used to predict both instantaneous and daily solar radiation in the study area, based on 18 years (2005–2022) of weather data obtained from the NSRDB database. The results showed that the tree-based models had better performance than other models evaluated. Moreover, the extra trees model was found to have the best performance, with R2 scores above 0.999 for daily global horizontal irradiation, 0.975 for daily direct normal irradiation, 0.955 for instantaneous global horizontal irradiation, and 0.945 for instantaneous direct normal irradiation. Moreover, the extra trees model achieved its highest accuracy when predicting the daily global horizontal irradiation, with a station-wise average R2 score of 0.9999, root mean squared error of 0.0244, mean absolute error of 0.0142, and mean absolute scaled error of 0.0047.

Anahtar Kelimeler

• Solar radiation
• Machine learning
• Weather forecasting

Kaynakça

1. [1] Obiora CN, Ali A, Hassan AN. Predicting Hourly Solar Irradiance Using Machine Learning Methods. 2020 11th International Renewable Energy Congress (IREC)2020. pp. 1-6.
2. [2] Guher AB, Tasdemir S, Yaniktepe B. Effective Estimation of Hourly Global Solar Radiation Using Machine Learning Algorithms. International Journal of Photoenergy. 2020;2020:8843620. https://doi.org/10.1155/2020/8843620.
3. [3] Allal Z, Noura HN, Chahine K. Machine Learning Algorithms for Solar Irradiance Prediction: A Recent Comparative Study. e-Prime - Advances in Electrical Engineering, Electronics and Energy. 2024;7:100453. https://doi.org/10.1016/j.prime.2024.100453.
4. [4] Zhou Y, Liu Y, Wang D, Liu X, Wang Y. A review on global solar radiation prediction with machine learning models in a comprehensive perspective. Energy Conversion and Management. 2021;235:113960. https://doi.org/10.1016/j.enconman.2021.113960.
5. [5] Voyant C, Notton G, Kalogirou S, Nivet M-L, Paoli C, Motte F, Fouilloy A. Machine learning methods for solar radiation forecasting: A review. Renewable Energy. 2017;105:569-82. https://doi.org/10.1016/j.renene.2016.12.095.
6. [6] Nematchoua MK, Orosa JA, Afaifia M. Prediction of daily global solar radiation and air temperature using six machine learning algorithms; a case of 27 European countries. Ecological Informatics. 2022;69:101643. https://doi.org/10.1016/j.ecoinf.2022.101643.
7. [7] Ercan U, Kocer A. Prediction of solar irradiance with machine learning methods using satellite data. International Journal of Green Energy. 2024;21:1174-83. 10.1080/15435075.2024.2305857.
8. [8] Ağbulut Ü, Gürel AE, Biçen Y. Prediction of daily global solar radiation using different machine learning algorithms: Evaluation and comparison. Renewable and Sustainable Energy Reviews. 2021;135:110114. https://doi.org/10.1016/j.rser.2020.110114.

9. [9] Hacioğlu R. Prediction of solar radiation based on machine learning methods. The journal of cognitive systems. 2017;2:16-20.
10. [10] Demir V, Demirgül T, Sevimli MF. Model-Ağacı (M5-tree) yaklaşımı ile HELIOSAT tabanlı güneş radyasyonu tahmini. Geomatik. 2023;8:124-35. 10.29128/geomatik.1137687.
11. [11] Demir V, Citakoglu H. Forecasting of solar radiation using different machine learning approaches. Neural Computing and Applications. 2023;35:887-906. 10.1007/s00521-022-07841-x.
12. [12] Demirgül T, Demir V, Sevimli MF. Farklı makine öğrenmesi yaklaşımları ile Türkiye'nin solar radyasyon tahmini. Geomatik. 2024;9:106-22. 10.29128/geomatik.1374383.
13. [13] Mendyl A, Demir V, Omar N, Orhan O, Weidinger T. Enhancing Solar Radiation Forecasting in Diverse Moroccan Climate Zones: A Comparative Study of Machine Learning Models with Sugeno Integral Aggregation. Atmosphere. 2024;15:103.
14. [14] Toylan H. SOLAR IRRADIANCE PREDICTION USING BAGGING DECISION TREE-BASED MACHINE LEARNING. Kirklareli University Journal of Engineering and Science. 2022;8:15-24. 10.34186/klujes.1106357.
15. [15] Tercha W, Tadjer SA, Chekired F, Canale L. Machine Learning-Based Forecasting of Temperature and Solar Irradiance for Photovoltaic Systems. Energies. 2024;17:1124.
16. [16] Ahmad MW, Mourshed M, Rezgui Y. Tree-based ensemble methods for predicting PV power generation and their comparison with support vector regression. Energy. 2018;164:465-74. https://doi.org/10.1016/j.energy.2018.08.207.
17. [17] Hassan MA, Khalil A, Kaseb S, Kassem MA. Exploring the potential of tree-based ensemble methods in solar radiation modeling. Applied Energy. 2017;203:897-916. https://doi.org/10.1016/j.apenergy.2017.06.104.
18. [18] Ahmad MW, Reynolds J, Rezgui Y. Predictive modelling for solar thermal energy systems: A comparison of support vector regression, random forest, extra trees and regression trees. Journal of Cleaner Production. 2018;203:810-21. https://doi.org/10.1016/j.jclepro.2018.08.207.
19. [19] SolarGIS. Solar resource maps & GIS data (Turkey), https://solargis.com/resources/free-maps-and-gis-data?locality=turkey; 2024 [accessed 15 November 2024].
20. [20] Kaygusuz K. Prospect of concentrating solar power in Turkey: The sustainable future. Renewable and Sustainable Energy Reviews. 2011;15:808-14. https://doi.org/10.1016/j.rser.2010.09.042.
21. [21] Bulut M. Integrated solar power project based on CSP and PV technologies for Southeast of Turkey. International Journal of Green Energy. 2022;19:603-13. 10.1080/15435075.2021.1954006.
22. [22] Güngör-Demirci G. Spatial analysis of renewable energy potential and use in Turkey. Journal of Renewable and Sustainable Energy. 2015;7:10.1063/1.4907921.
23. [23] NREL. NSRDB: National Solar Radiation Database, https://nsrdb.nrel.gov/; 2024 [accessed 29 December 2024].
24. [24] Buster G, Bannister M, Habte A, Hettinger D, Maclaurin G, Rossol M, et al. Physics-guided machine learning for improved accuracy of the National Solar Radiation Database. Solar Energy. 2022;232:483-92. https://doi.org/10.1016/j.solener.2022.01.004.
25. [25] Sengupta M, Xie Y, Lopez A, Habte A, Maclaurin G, Shelby J. The National Solar Radiation Data Base (NSRDB). Renewable and Sustainable Energy Reviews. 2018;89:51-60. https://doi.org/10.1016/j.rser.2018.03.003.
26. [26] Mukherjee A, Ain A, Dasgupta P. Solar Irradiance Prediction from Historical Trends Using Deep Neural Networks. 2018 IEEE International Conference on Smart Energy Grid Engineering (SEGE)2018. pp. 356-61.
27. [27] Narvaez G, Giraldo LF, Bressan M, Pantoja A. Machine learning for site-adaptation and solar radiation forecasting. Renewable Energy. 2021;167:333-42. https://doi.org/10.1016/j.renene.2020.11.089.
28. [28] Hinkelman L, Sengupta M. Relating Solar Resource Variability to Cloud Type. AGU Fall Meeting Abstracts2012. pp. A31F-0086.
29. [29] NREL. High-Performance Computing: National Solar Radiation Database, https://www.nrel.gov/hpc/nsrdb-dataset.html; 2024 [accessed 30 December 2024].
30. [30] Kalogirou SA. Chapter two - Environmental Characteristics. in: S.A. Kalogirou, (Ed.). Solar Energy Engineering. Academic Press, Boston, 2009. pp. 49-762.
31. [31] Poslavskaya E, Korolev A. Encoding categorical data: Is there yet anything 'hotter' than one-hot encoding? arXiv preprint arXiv:231216930. 2023;
32. [32] Duffie JA, Beckman WA. Solar Engineering of Thermal Processes. ed. Wiley; 2013.
33. [33] Atiea MA, Shaheen AM, Alassaf A, Alsaleh I. Enhanced Solar Power Prediction Models With Integrating Meteorological Data Toward Sustainable Energy Forecasting. International Journal of Energy Research. 2024;2024:8022398. https://doi.org/10.1155/er/8022398.
34. [34] Natekin A, Knoll A. Gradient boosting machines, a tutorial. Frontiers in Neurorobotics. 2013;7:10.3389/fnbot.2013.00021.
35. [35] Chaibi M, Benghoulam EM, Tarik L, Berrada M, Hmaidi AE. An Interpretable Machine Learning Model for Daily Global Solar Radiation Prediction. Energies. 2021;14:7367.
36. [36] Song Z, Cao S, Yang H. An interpretable framework for modeling global solar radiation using tree-based ensemble machine learning and Shapley additive explanations methods. Applied Energy. 2024;364:123238. https://doi.org/10.1016/j.apenergy.2024.123238.
37. [37] Plevris V, Solorzano G, Bakas NP, Ben Seghier MEA. Investigation of performance metrics in regression analysis and machine learning-based prediction models. 8th European Congress on Computational Methods in Applied Sciences and Engineering (ECCOMAS Congress 2022). European Community on Computational Methods in Applied Sciences2022.
38. [38] Hyndman RJ, Athanasopoulos G. Forecasting: Principles and Practice. ed. OTexts; 2014.
39. [39] Hyndman RJ, Koehler AB. Another look at measures of forecast accuracy. International Journal of Forecasting. 2006;22:679-88. https://doi.org/10.1016/j.ijforecast.2006.03.001.
40. [40] Di Bucchianico A. Coefficient of Determination (2). Encyclopedia of Statistics in Quality and Reliability2007.
41. [41] Zhang S. Challenges in KNN Classification. IEEE Transactions on Knowledge and Data Engineering. 2022;34:4663-75. 10.1109/TKDE.2021.3049250.