Comparison of Success Rates of Artificial Intelligence and Classical Methods in Estimation of Photovoltaic Energy Production: Study of İzmir Bakırçay University

Abstract

Global solar energy has become a popular investment choice for investors, with installed power reaching 940GW according to 2021 data. Investors are interested in profit margin estimations based on energy production, which are provided through feasibility studies conducted before building solar power plants (SPP). While classical mathematical algorithms are typically used to calculate energy production, advances in technology offer opportunities to achieve better results. In our energy production estimation studies conducted at İzmir Bakırçay University SPP, we achieved a 70.24% success rate using classical estimation algorithms based on past production and meteorological data. However, by developing an artificial neural network, we achieved a 98.23% success rate, making it a more beneficial option for investors. Our aim was to create a reliable feasibility environment.

Keywords

• photovoltaic energy
• energy estimation methods
• artificial neural networks

Thanks

We would like to express our endless thanks to the late Assoc.Prof.Dr. Selçuk ÖZMEN, who was of great help in obtaining the meteorological data used in this study and passed away during the studies. Rest in peace.

References

1. [1] Mohtasham, J. (2015). Review Article-Renewable Energies. Energy Procedia, 74, pp.1289–1297.
2. [2] Li, L., Lin, J., Wu, N., Xie, S., Meng, C., Zheng, Y., Zhao, Y., (2020). Review and Outlook on the International Renewable Energy Development. Energy and Built Environment, 3(2), pp.139-157.
3. [3] Panwar, N. L., Kaushik, S. C., & Kothari, S., (2011). Role of renewable energy sources in environmental protection: A review. Renewable and Sustainable Energy Reviews, 15(3), pp. 1513–1524.
4. [4] Marques Lameirinhas, Ricardo A., João Paulo N. Torres, and João P. de Melo Cunha. (2022). "A photovoltaic technology review: history, fundamentals and applications" Energies, 15(5), pp.1823-1867.
5. [5] Kumar Sahu, B. (2015). A study on global solar PV energy developments and policies with special focus on the top ten solar PV power producing countries. Renewable and Sustainable Energy Reviews, 43, 621-634.
6. [6] Kassem, Y.; Çamur, H.; Alhuoti, S.M.A., (2020). Solar Energy technology for Northern Cyprus: assessment, statistical analysis, and feasibility study. Energies, 13(4), pp. 940-969.
7. [7] Beltran, H., Perez, E., Aparicio, N., & Rodriguez, P. (2013). Daily solar energy estimation for minimizing energy storage requirements in pv power plants. IEEE Transactions on Sustainable Energy, 4(2), pp. 474-481.
8. [8] Sharma, R., & Gidwani, L. (2017). Grid connected solar PV system design and calculation by using PV*SOL premium simulation tool for campus hostels of RTU Kota. 2017 International Conference on Circuit,Power and Computing Technologies (ICCPCT) 20-21 April 2017, Kollam, India. doi:10.1109/iccpct.2017.8074315

9. [9] Kaczorowska, D., Leonowicz, Z., Rezmer, J., & Janik, P. (2017). Long term performance of a PV system with monocrystalline PV cells — a case study. 2017 IEEE International Conference on Environment and Electrical Engineering and 2017 IEEE Industrial and Commercial Power Systems Europe (EEEIC / I&CPS Europe). Milan, Italy. doi:10.1109/eeeic.2017.7977838
10. [10] Milosavljević, Dragana D., Kevkić, Tijana S. and Jovanović, Slavica J. (2022). Review and validation of photovoltaic solar simulation tools/software based on case study. Open Physics, 20(1), pp. 431-451.
11. [11] Villarrubia, G., De Paz, J. F., Chamoso, P., & la Prieta, F. D. (2018). Artificial neural networks used in optimization problems. Neurocomputing, 272, 10–16.
12. [12] URL-1 Izmir Governorship [Accessed 12 February 2023]
13. [13] URL-2 The World Bank Global Solar Atlas Data [Accessed 12 February 2023]
14. [14] Bakirci, K. (2012). General models for optimum tilt angles of solar panels: Turkey case study. Renewable and Sustainable Energy Reviews, 16(8), pp. 6149–6159.
15. [15] Aksu, G., Güzeller, C. O. & Eser, M. T. (2019). The effect of the normalization method used in different sample sizes on the success of artificial neural network model, International Journal of Assessment Tools in Education, 6 (2), pp.170-192.
16. [16] URL-3 2. Regional Meteorology Directorate - İzmir. [Accessed 12 February 2023]
17. [17] Sazlı, M.H., 2006. A brief review of feed-forward neural networks. Communications Faculty of Science University of Ankara, 50(1), pp.11-17.