Yapay Sinir Ağları ile Yenilenebilir Güneş Enerjisi Kaynağının Öngörüsü

Yıl 2025, Cilt: 12 Sayı: 27, 416 - 425, 24.12.2025

Ahmet Nur , Bayram Güre , Sabir Rüstemli , Özlem Bezek Güre

https://doi.org/10.54365/adyumbd.1705664

Öz

Elektrik enerjisi, ekonomik kalkınma ve teknolojik ilerlemenin temel unsurlarından biridir. Mevcut enerji alternatifleri arasında, özellikle güneş enerjisi gibi yenilenebilir enerji kaynakları, çevresel etkilerinin düşük olması nedeniyle öne çıkmakta ve küresel iklim değişikliğiyle mücadelede önemli rol oynamaktadır.Yenilenebilir kaynaklar arasında yer alan güneş enerjisi sistemlerinde enerji üretimi; güneşlenme şiddeti, ortam sıcaklığı, nem ve rüzgar hızı gibi birçok meteorolojik ve çevresel değişkenden etkilenmektedir.
Bu çalışmada, fotovoltaik bir sistemdeki enerji üretimini yüksek doğrulukla tahmin edebilmek amacıyla yapay sinir ağı (YSA) tabanlı bir model geliştirilmiştir. Modelin oluşturulması ve doğrulanması sürecinde, Kaggle veri tabanından elde edilen 4212 örnek ve 21 girdi değişkeninden oluşan açık kaynaklı bir veri seti kullanılmıştır. Veri seti %70 eğitim ve %30 test verisi olarak ayrılmıştır. Modelin performansı; Ortalama Kare Hata (MSE), Kök Ortalama Kare Hata (RMSE), Ortalama Mutlak Hata (MAE) ve Belirleme Katsayısı (R²) gibi istatistiksel hata kriterleri kullanılarak ölçülmüştür. Bu çalışma fotovoltaik sistem verimliliği üzerinde etkili olan güneş parametrelerinin önemini araştırıp değerlendirerek literatüre katkıda bulunmuştur.

Anahtar Kelimeler

Güneş enerjisi , Yapay sinir ağları , PV üretim , Kaggle verisi

Prediction of Renewable Solar Energy Source With Artificial Neural Networks

Öz

Electrical energy is one of the fundamental elements of economic development and technological progress. Among the existing energy alternatives, renewable energy sources, especially solar energy, stand out due to their low environmental impact and play an important role in combating global climate change. Energy production in solar energy systems, which are among the renewable resources, is affected by many meteorological and environmental variables such as insolation intensity, ambient temperature, humidity and wind speed.
In this study, an artificial neural network based model was developed to predict the energy production in a photovoltaic system with high accuracy. In the creation and validation process of the model, an open-source dataset consisting of 4212 samples and 21 input variables obtained from the Kaggle database was used. The dataset was divided into 70% training and 30% test data. The performance of the model was measured using statistical error criteria such as Mean Square Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE) and Coefficient of Determination (R²). This study has contributed to the literature by investigating and evaluating the importance of solar parameters that affect the efficiency of photovoltaic systems.

Anahtar Kelimeler

Solar energy , Artificial neural networks , PV production , Kaggle data

Kaynakça

• Şahin G, Levent I, Işık G, van Sark W, Rustemli S. Prediction and comparative analysis of rooftop PV solar energy efficiency considering indoor and outdoor parameters under real climate conditions factors with machine learning model. Computer Modeling in Engineering & Sciences 2025;143(1):1215–1248.
• Temiz D, Gökmen A. The importance of renewable energy sources in Turkey. International Journal of Economics and Finance Studies 2010;2(2):23–30.
• Kesler S, Kivrak S, Dinçer F, Rüstemli S, Karaaslan M, Ünal E, Erdiven U. The analysis of PV power potential and system installation in Manavgat Turkey: A case study in winter season. Renewable and Sustainable Energy Reviews 2014;31:671–680.
• Rani P, Taya R, Reddy VP. A review on solar energy and different electricity generations. 2023 International Conference on Power Energy, Environment & Intelligent Control (PEEIC) 2023;pp. 231–234.
• Vakulchuk R, Overland I, Scholten D. Renewable energy and geopolitics: A review. Renewable and Sustainable Energy Reviews 2020;122:109547.
• Rüstemli S, Dinçer F. Economic analysis and modeling process of photovoltaic power systems. Przegląd Elektrotech 2011;87(9a):243–247.
• Rüstemli S, Dinçer F. Modeling of photovoltaic panel and examining effects of temperature in Matlab Simulink. Electron Electr Eng 2011;109(3):35–40.
• Nourani V, Elkiran G, Abdullahi J, Tahsin A. Multi-region modeling of daily global solar radiation with artificial intelligence ensemble. Natural Resources Research 2019;28:1217–1238.
• Alboali J, Alsuwaid A, Aljafar M, Khalid M. Techno-economic assessment of different solar PV configurations for a typical house in Dhahran 4th International Symposium on Advanced Electrical and Communication Technologies (ISAECT) 2021;pp. 1–6.
• Alzain E, Al-Otaibi S, Aldhyani THH, Alshebami AS. Revolutionizing solar power production with artificial intelligence: A sustainable predictive model. Sustainability 2023;15(10):1–21.
• Shouman ERM. Solar power prediction with artificial intelligence. In: Advances in Solar Photovoltaic Energy Systems. Gizza (Egypt): IntechOpen; 2024. ch.2:1–28.
• Bouquet P, Jackson I, Nick M, Kaboli A. AI-based forecasting for optimised solar energy management and smart grid efficiency. International Journal of Production Research 2024;62(13):4623–4644.
• Chandel P, Roy L. Solar radiation prediction based on hybrid machine learning technique. In: 3rd International Conference on Technological Advancements in Computational Sciences (ICTACS). 2023;418–424.
• Hou Z, Zhang Y, Cheng X, Ye X. Photovoltaic power forecasting based on variational mode decomposition and long short-term memory neural network. Energies 2025;18:3572.
• Feng Z, Liu P, Niu W. Solar power generation prediction using radial basis function neural network with mode decomposition and cooperation search algorithm. Applied Soft Computing 2025;180.
• Serfa Juan RO, Kim J. Implementation of generalized regression neural network (GRNN) for solar panel power estimation. International Conference on Information and Communication Technology Convergence (ICTC) 2020;pp. 294–299.
• Rüstemli S, İlcihan Z, Şahin G, van Sark WG. A novel design and simulation of a mechanical coordinate based photovoltaic solar tracking system. AIMS Energy 2023;11(5):753–773.
• Künteş Ö, Güre ÖB. Investigation of work accidents occurring in the oil industry using artificial neural network. Journal of the Institute of Science and Technology 2024;14(3):1000–1012.
• Zhang GP. Neural networks for data mining. Data Min Knowl Disc Handb 2010;pp. 419–444.
• Aslan Y, Yaşar C, Nalbant A. Electrical peak load forecasting in Kütahya with artificial neural networks. Journal of Science and Technology of Dumlupınar University 2006;11:63–74.
• Güleç HG, Demirel H. Artificial neural network based prediction of intensity of insolation in the city of Kastamonu using meteorological data. NWSA 2017;12(3):114–121.
• Güre ÖB, Kayri M, Erdoğan F. Analysis of factors effecting PISA 2015 mathematics literacy via educational data mining. Education & Science 2020;45(202): 393-415.
• Yüzer EÖ, Bozkurt A. Evaluation of artificial neural network parameters in solar radiation prediction using meteorological data. KSU Journal of Engineering Sciences 2022;25(4):746–759.
• Premalatha M, Naveen C. Analysis of different combinations of meteorological parameters in predicting the horizontal global solar radiation with ANN approach: A case study. Renewable and Sustainable Energy Reviews 2018;91:248–258.
• Yadav AK, Chandel SS. Solar radiation prediction using artificial neural network techniques: A review. Renewable and Sustainable Energy Reviews 2014;33:772–781.
• Karaman ÖA, Ağır TT, Arsel I. Estimation of solar radiation using modern method. Alexandria Engineering Journal 2021;60(2):2447–2455.
• Akal D, Umut I. Using artificial intelligence methods for power estimation in photovoltaic panels. Journal of Tekirdag Faculty of Agriculture 2022;19(2):435–445.
• Saberian A, Hizam H, Radzi MA, Mirzaei M. Modelling and prediction of photovoltaic power output using artificial neural networks. International Journal of Photoenergy 2014;2014:1–10.
• Zhu HL, Li X, Sun Q, Nie L, Yao JX, Zhao G. A power prediction method for photovoltaic power plant based on wavelet decomposition and artificial neural networks. Energies 2016;9(1):11.
• Coşkun C, Koçyiğit N, Oktay Z. Estimation of PV module surface temperature using artificial neural networks. Mugla Journal of Science and Technology 2016;2(2):15–18.
• Sağaltıcı D, Alay F, Efil C, Ilhan N. Estimation of missing solar radiation values of meteorological data using data mining techniques. Harran University Journal of Engineering 2018;2:49–53.