INVESTIGATION OF THE MOST SUITABLE POWER OUTPUT PREDICTION METHODS WITH ARTIFICIAL INTELLIGENCE IN A ROOFTOP PHOTOVOLTAIC POWER PLANT

Abstract

Installing photovoltaic (PV) systems in buildings effectively achieves sustainable energy targets and reduces carbon emissions. Energy demand is increasing day by day. Accessing solar energy is preferred, especially in urban areas, because it is easier and more economical than other renewable energy sources. It is important to calculate the losses that occur in the integration of PV systems into the interconnected system and to select the appropriate material for the system. In the feasibility reports prepared before the system is installed, the selection of appropriate materials for the system, system cost, energy production and consumption, and amortization periods are calculated by considering the environmental and physical conditions. The dataset used in this study was obtained from two rooftop PV systems (each 200 kW) installed on separate buildings of Yüksek İhtisas Hospital in Bursa, Turkey, with production and ambient temperature data collected at 15-minute intervals throughout 2024. This study investigates the use of artificial intelligence techniques—Decision Tree, Random Forest, LSTM, and Linear Regression—for predicting photovoltaic (PV) power output using real data from two 200 kW rooftop PV power plants located at Yüksek İhtisas Hospital in Bursa, Turkey. One-year production, irradiance, and ambient temperature data recorded at 15-minute intervals were used. The aim was to forecast the expected power output of a 440 kW PV system to be installed on the BTU G Block under similar environmental and technical conditions. The effects of environmental and physical conditions on one-year production data were examined using various artificial intelligence methods such as Random Forest, Decision Tree, Linear Regression, and LSTM. The aim was to predict the production data that would arise when a power plant with similar environmental and physical conditions is established. According to the analysis results, the Decision Tree method was determined to be the highest-performing technique, providing a 99.6% R² accuracy value.

Keywords

• Photovoltaics
• Power Prediction
• Artificial Intelligence
• Decision Tree
• LSTM

Ethical Statement

The author declare that this document does not require ethics committee approval or any special permission. This review does not cause any harm to the environment and does not involve the use of animal or human subjects.

Thanks

The authors thank to Associate Professor Dr. Mehmet Oğuzhan Ay, Chief Physician of Yüksek İhtisas Education and Research Hospital; Mr. İbrahim Bayoğlu, Director of Administrative and Financial Affairs; Mr. Yasin Erikligil, Director of Technical Services; and Mr. Mustafa Demircan, Technical Supervisor, for their invaluable support in providing the information and documents necessary for the completion of this article.

References

1. S. Bouckaert, A.F. Pales, C. McGlade, U.. Remme, B. Wanner, L. Varro ..& T. Spencer, Net zero by 2050: A roadmap for the global energy sector, (2021).
2. E. Gönültaş, "Güneş enerjisi santrallerinin tasarımı ve performans analizleri," Yüksek Lisans Tezi, Fen Bilimleri Enstitüsü, 2016.
3. A. Gupta, K. Gupta & S. Saroha, "Solar irradiation forecasting technologies: a review," Strategic Planning for Energy and the Environment, ss. 319-354, 2020.
4. H. Demolli, A. Dokuz, M. Gokcek & A. Ecemiş, "Makine Öğrenmesi Algoritmalarıyla Güneş Enerjisi Tahmini: Niğde İli Örneği," In International Turkic World Congress on Science and Engineering, ss. 748, 2019.
5. D. B. Unsal, A. Aksoz, S. Oyucu, J.M. Guerrero & M. Guler, "A Comparative Study of AI Methods on Renewable Energy Prediction for Smart Grids: Case of Turkey," Sustainability, c. 16, sy. 7, ss. 2894, 2024.
6. E.B. Ssekulima, M.B. Anvar, A. Al Hinai & M. S. El Moursi, "Wind speed and solar irradiance forecasting techniques for enhanced renewable energy integration with the grid: A review," IET Renewable Power Generation, c. 10, sy. 7, ss. 885-989, 2016.
7. C. Voyant, G. Notton, S. Kalogirou, M.L. Nivet, C. Paoli, F. Motte & A. Fouilloy, "Machine learning methods for solar irradiation forecasting: A review," Renewable Energy, c. 105, ss. 569-582, 2017.
8. A. Zafar, Y. Che, M. Faheem, M. Abubakar, S. Ali, S. & M.S. Bhutta, "Machine learning autoencoder-based parameters prediction for solar power generation systems in smart grid," IET Smart Grid, 2024.

9. Y. Chu, M. Li, C.F. Coimbra, D. Feng & H. Wang, "Intra-hour irradiance forecasting techniques for solar power integration: A review," Iscience, c. 24, sy. 10, 2021.
10. A. Chwilkowska-Kubala, K. Malewska & K. Mierzejewska, "The importance of resources in achieving the goals of energy companies," Engineering Management in Production and Services, c. 15, sy. 3, 2023.
11. S. Özbektaş, M. C. Şenel, B. Sungur, "Dünyada ve Türkiye’de Yenilenebilir Enerji Durumuve Kurum Malıyetleri," Mühendis ve Makina, c. 64, sy. 711, ss. 317-351, 2023.
12. S. Desai, N. Sabar, R. Alhadad, A. Mahmood, N. Chilamkurti, "Mitigating consumer privacy breach in smart grid using obfuscation-based generative adversarial network," Journal of Mitigating, 2022.
13. C.F. Mbey, F.G. Yem Soube, V.J. Foba Kakeu and A. T. Boum, "A Novel Deep Learning-Based Data Analysis Model for Solar Photovoltaic Power Generation and Electrical Consumption Forecasting in the Smart Power Grid," Applied Computational Intelligence and Soft Computing, c. 2024, ss. 9257508, 2024.
14. C. L. Stimmel, Big data analytics strategies for the smart grid. Boca Raton: CRC Press, 2015, ss. 155-169.
15. R. Sağ, Z.H. Tuğcu, "Akıllı Şebeke Uygulamalarında Derin Öğrenme Tekniklerinin Kullanımına İlişkin Kısa Bir İnceleme," EMO Bilimsel Dergi, c. 13, sy. 1, ss. 41-61, 2022.
16. A.U. Obiwole, N. Erusiafe, M.A. Olopade, S. C. Nwokolo, "Modelling and estimation of the optimal tilt angle, maximum incident solar radiation, and global radiation index of the photovoltaic system," Heliyon, c. 8, sy. 6, 2022.
17. N. M. Sezikli, "Makine öğrenmesi yöntemiyle yenilenebilir güneş enerjisi üretiminin meteorolojik veriler kullanılarak tahmin analizi," Yüksek Lisans Tezi, İstanbul Gelişim Üniversitesi Lisansüstü Eğitim Enstitüsü, 2023.
18. Ö. O. Dursun and S. Toraman, "Uzun kısa vadeli bellek yöntemi ile havayolu yolu tahmini," Journal of Aviation, c. 5, sy. 2, ss. 241-248, 2021.
19. A. Luque, A. Carrasco, A. Martin & A. de Les Heras, "The impact of class imbalance on classification performance metrics based on the binary confusion matrix," Pattern Recognition, c. 91, ss. 216-231, 2019.
20. AllSolaar. (n.d.). Crystalline Solar Panel Datasheet. [Online]. Available: https://www.allsolaar.com/pv/paneldata/sheet/crystalline/49071 (Accessed: March 30, 2025).
21. Global Solar Atlas. (n.d.). Global Solar Atlas Map. [Online]. Available: https://globalsolaratlas.info/map?c=40.18636,29.130042,11&s=40.18636,29.130042&m=site (Accessed: March 30, 2025).
22. Solartoday. (n.d.). XCS-545 Watt Monofacial Solar Panel. [Online]. Available: https://solartoday.com.tr/urunler/xcs-bos-solar-paneller/xcs-545-watt-monofacial-solar-panel/ (Accessed: March 30, 2025).
23. K. Başaran, M. T. Özdemir & G. Bayrak, "Sizing and Techno-Economic Analysis of Utility-Scale PV Systems with Energy Storage Systems in Factory Buildings: An Application Study," Applied Sciences, c. 15, sy. 7, ss. 3876, 2025, doi: 10.3390/app15073876.
24. R. Çakmak, G. Bayrak & M. Koç, "A Fuzzy Logic-Based Energy Management Approach for Fuel Cell and Photovoltaic Powered Electric Vehicle Charging Station in DC Microgrid Operations," IEEE Access, c. 13, ss. 49905–49921, 2025, doi: 10.1109/ACCESS.2025.3552253.
25. H. Tekin, H. Kılıç, C. Haydaroğlu, M.E. Asker, "Optimizing carbon emission reduction in hybrid microgrids: A case study integrating photovoltaics and hydrogen energy systems," Niğde Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi, c. 14, sy. 2, ss. 1–1, 2025, doi: 10.28948/nigdemuh.1567257.