Makine Öğrenmesi Teknikleri ile Meteorolojik Verilere Dayalı Güneş Işınımı Tahmini: Isparta Örneği

Year 2023, Volume: 15 Issue: 2, 704 - 713, 14.07.2023

Buğra Güzel , Onur Sevli , Ersan Okatan

https://doi.org/10.29137/umagd.1268055

Cited By: 1

Abstract

Yenilenebilir enerji kaynaklarından olan güneş enerji sistemleri her geçen gün daha fazla ilgi görmekte ve kullanımı yaygınlaşmaktadır. Diğer birçok yenilenebilir enerji kaynaklarında olduğu gibi güneş enerji sistemlerindeki önemli bir sorun sistemin sağlayacağı enerjinin sürekli olmamasıdır. Elde edilecek enerjinin tahmin edilebilmesi bu bakımdan oldukça önemlidir. Bu çalışmada Meteoroloji Genel Müdürlüğü’nden Isparta ili için alınan meteorolojik veriler kullanılarak güneş ışınımı tahmini yapılmıştır. Tahmin işlemi için Rastgele Orman (RF), k-EYK (k-En Yakın Komşu), YSA (Yapay Sinir Ağları) ve Derin Öğrenme yöntemleri kullanılmıştır. Ayrıca zaman verileri için kukla değişken kullanımının bu farklı metotlar ile oluşturduğu sonuçlar incelenmiştir. Elde edilen bulgulara göre kukla değişken kullanımının YSA ve Derin Öğrenme yöntemlerinde performansı arttırdığı, Rastgele orman ve k-EYK yöntemlerinde ise performansı düşürdüğü görülmüştür. YSA ve derin öğrenme ile güneş ışınımı tahmininde en iyi sonuçlar elde edilmiştir.

Keywords

derin öğrenme, kukla değişken, rastgele orman, güneş ışınımı tahmini, yapay sinir ağları

Thanks

Meteoroloji Genel Müdürlüğü

Forecasting Solar Radiation Based on Meteorological Data Using Machine Learning Techniques: A Case Study of Isparta

Abstract

Solar energy systems which is one of renewable energy sources takes more interest and gains prevalence day by day. As in other many renewable energy sources, a significant problem in solar energy systems is the unstability of the energy that the system will provide. Prediction of the energy to be obtained is very important in this respect. In this study, solar radiation is predicted using meteorological data taken from the General Directorate of Meteorology for Isparta. For predictions, the random forest (RF), KNN (k-Nearest Neighbor), ANN (Artificial Neural Networks) and Deep Learning (DL) methods are used. In addition, the results of dummy variable usage for time data are examined with these different methods. According to the findings obtained, it is seen that the dummy variable usage increases performance for ANN and DL methods but decreases performance for random forest and KNN methods. Best results are obtained for the prediction of the solar radiation with ANN and DL.

Keywords

Artificial neural networks, deep learning, dummy variable, random forest, solar radiation prediction

References

• Alomari, M. H., Adeeb, J., & Younis, O. (2018). Solar Photovoltaic Power Forecasting in Jordan using Artificial Neural Networks. International Journal of Electrical and Computer Engineering (IJECE), 8(1), 497. https://doi.org/10.11591/ijece.v8i1.pp497-504
• Al-Rousan, N., Al-Najjar, H., & Alomari, O. (2021). Assessment of predicting hourly global solar radiation in Jordan based on Rules, Trees, Meta, Lazy and Function prediction methods. Sustainable Energy Technologies and Assessments, 44, 100923. https://doi.org/10.1016/j.seta.2020.100923
• Al-Sbou, Y. A., & Alawasa, K. M. (2017). Nonlinear Autoregressive Recurrent Neural Network Model For Solar Radiation Prediction. 12(14), 10.
• Anonymus. (2021). “Renewable capacity highlights”, International Renewable Energy Agency (IRENA).
• Arslan, G., Bayhan, B., & Yaman, K. (2019). 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), 80–96. https://doi.org/10.29109/gujsc.419473
• Ayko, O. & Bozkurt Keser, S. (2021). A comparison of machine learning algorithms for forecasting solar irradiance in Eskişehir, Turkey . International Journal of Applied Mathematics Electronics and Computers , 9 (4) , 103-109. https://doi.org/10.18100/ijamec.995506
• Bamisile, O., Oluwasanmi, A., Ejiyi, C., Yimen, N., Obiora, S., & Huang, Q. (2022). Comparison of machine learning and deep learning algorithms for hourly global/diffuse solar radiation predictions. International Journal of Energy Research, 46(8), 10052–10073. https://doi.org/10.1002/er.6529
• Benali, L., Notton, G., Fouilloy, A., Voyant, C., & Dizene, R. (2019). Solar radiation forecasting using artificial neural network and random forest methods: Application to normal beam, horizontal diffuse and global components. Renewable Energy, 132, 871–884. https://doi.org/10.1016/j.renene.2018.08.044
• Demirtas, M., Yesilbudak, M., Sagiroglu, S., & Colak, I. (2012). Prediction of solar radiation using meteorological data. 2012 International Conference on Renewable Energy Research and Applications (ICRERA), 1–4. https://doi.org/10.1109/ICRERA.2012.6477329
• Demolli, H., Ecemiş, A., Dokuz, A. Ş., & Gökçek, M. (2019). Makine Öğrenmesi Algoritmalarıyla Güneş Enerjisi Tahmini: Niğde İli Örneği.
• Döş, M. E., & Uysal, M. (2019). Uzaktan algılama verilerinin derin öğrenme algoritmaları ile sınıflandırılması. Türkiye Uzaktan Algılama Dergisi, 1(1), 28-34.
• Elsheikh, A. H., Sharshir, S. W., Abd Elaziz, M., Kabeel, A. E., Guilan, W., & Haiou, Z. (2019). Modeling of solar energy systems using artificial neural network: A comprehensive review. Solar Energy, 180, 622–639. https://doi.org/10.1016/j.solener.2019.01.037
• Erten, M. Y. & Aydilek, H. (2022). Solar Power Prediction using Regression Models . International Journal of Engineering Research and Development , Special Issue 2022 , 333-342. https://doi.org/10.29137/umagd.1100957
• Gullu, M., Yilmaz, M., & Yilmaz, I. (2011). Application of back propagation artificial neural network for modelling local GPS/levelling geoid undulations: A comparative study. In FIG Working Week (pp. 18-22).
• Hamdan, M. A., Abdelhafez, E., & Ghnaimat, O. (2017). Prediction of Hourly Solar Radiation in Amman-Jordan by Using Artificial Neural Networks. Int. J. of Thermal & Environmental Engineering, 14(2), 103-108.
• Hong, T., Gui, M., Baran, M. E., & Willis, H. L. (2010, July). Modeling and forecasting hourly electric load by multiple linear regression with interactions. In Ieee pes general meeting (pp. 1-8). IEEE.
• Ibrahim, I. A., & Khatib, T. (2017). A novel hybrid model for hourly global solar radiation prediction using random forests technique and firefly algorithm. Energy Conversion and Management, 138, 413–425.
• Jolly, S., & Gupta, N. (2021). Understanding and implementing machine learning models with dummy variables with low variance. In International Conference on Innovative Computing and Communications: Proceedings of ICICC 2020, Volume 1 (pp. 477-487). Springer Singapore.
• Kara, A. (2019). Uzun-Kısa Süreli Bellek Ağı Kullanarak Global Güneş Işınımı Zaman Serileri Tahmini . Gazi University Journal of Science Part C: Design and Technology , 7 (4) , 882-892 . https://doi.org/10.29109/gujsc.571831
• KAYCI, B. (2021). Güneş Panellerinin Dört Rotorlu İha Kullanilarak Termografi Yöntemiyle Derin Öğrenme Tabanli Hata Tespit ve Teşhisi (Doctoral dissertation).
• Korkmaz, D., Çelik, H. E., & Kapar, M. (2018). Sınıflandırma ve Regresyon Ağaçları ile Rastgele Orman Algoritması Kullanarak Botnet Tespiti: Van Yüzüncü Yıl Üniversitesi Örneği.
• Kraus, M., Feuerriegel, S., & Oztekin, A. (2020). Deep learning in business analytics and operations research: Models, applications and managerial implications. European Journal of Operational Research, 281(3), 628–641. https://doi.org/10.1016/j.ejor.2019.09.018
• Marzouq, M., El Fadili, H., Lakhliai, Z., Mechaqrane, A., & Zenkouar, K. (2019). New distance weighted k Nearest Neighbor model for hourly global solar irradiation estimation. 2019 International Conference on Wireless Technologies, Embedded and Intelligent Systems (WITS), 1–5. https://doi.org/10.1109/WITS.2019.8723697
• Mohammed, L. B., Hamdan, M. A., Abdelhafez, E. A., & Shaheen, W. (2013). Hourly Solar Radiation Prediction Based on Nonlinear Autoregressive Exogenous (Narx) Neural Network. 7(1), 8.
• Ozoegwu, C. G. (2019). Artificial neural network forecast of monthly mean daily global solar radiation of selected locations based on time series and month number. Journal of Cleaner Production, 216, 1–13. https://doi.org/10.1016/j.jclepro.2019.01.096
• Pardo, A., Meneu, V., & Valor, E. (2002). Temperature and seasonality influences on Spanish electricity load. Energy Economics, 24(1), 55-70.
• Sanders, S., Barrick, C., Maier, F., & Rasheed, K. (2017). Solar Radiation Prediction Improvement Using Weather Forecasts. 2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA), 499–504. https://doi.org/10.1109/ICMLA.2017.0-112
• Sun, H., Gui, D., Yan, B., Liu, Y., Liao, W., Zhu, Y., Lu, C., & Zhao, N. (2016). Assessing the potential of random forest method for estimating solar radiation using air pollution index. Energy Conversion and Management, 119, 121–129. https://doi.org/10.1016/j.enconman.2016.04.051
• Şahin, M. (2013). Comparison of modelling ANN and ELM to estimate solar radiation over Turkey using NOAA satellite data. International Journal of Remote Sensing, 34(21), 7508–7533. https://doi.org/10.1080/01431161.2013.822597
• Şeker, M. (2021). Yapay Sinir Ağı (YSA) Kullanılarak Meteorolojik Verilere Dayalı Solar Radyasyon Tahmini Estimation of Solar Radiation Based on Meteorological Data Using Artificial Neural Network (ANN). 13.
• Torres-Barrán, A., Alonso, Á., & Dorronsoro, J. R. (2019). Regression tree ensembles for wind energy and solar radiation prediction. Neurocomputing, 326–327, 151–160. https://doi.org/10.1016/j.neucom.2017.05.104
• Uğuz, S. , Oral, O. & Çağlayan, N. (2019). PV Güç Santrallerinden Elde Edilecek Enerjinin Makine Öğrenmesi Metotları Kullanılarak Tahmin Edilmesi . International Journal of Engineering Research and Development , Aralık 2019-Özel Sayı , 769-779 . https://doi.org/10.29137/umagd.514933
• Yadav, A. K., Malik, H., & Chandel, S. S. (2015). Application of rapid miner in ANN based prediction of solar radiation for assessment of solar energy resource potential of 76 sites in Northwestern India. Renewable and Sustainable Energy Reviews, 52, 1093–1106. https://doi.org/10.1016/j.rser.2015.07.156
• Yesilbudak, M., & Ozcan, A. (2022). k-NN Classifier Applications in Wind and Solar Energy Systems. 2022 11th International Conference on Renewable Energy Research and Application (ICRERA), 480–484. https://doi.org/10.1109/ICRERA55966.2022.9922701
• Zeng, Z., Wang, Z., Gui, K., Yan, X., Gao, M., Luo, M., Geng, H., Liao, T., Li, X., An, J., Liu, H., He, C., Ning, G., & Yang, Y. (2020). Daily Global Solar Radiation in China Estimated From High-Density Meteorological Observations: A Random Forest Model Framework. Earth and Space Science, 7(2), e2019EA001058. https://doi.org/10.1029/2019EA001058
• Zhou, Y., Liu, Y., Wang, D., Liu, X., & Wang, Y. (2021). A review on global solar radiation prediction with machine learning models in a comprehensive perspective. Energy Conversion and Management, 235, 113960. https://doi.org/10.1016/j.enconman.2021.11396