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

Authors : Özgün UZ, Özge TÜZÜN ÖZMEN

Pages : 12-24

View : 10 | Download : 5

Publication Date : 2023-05-01

Article Type : Research Paper

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 insert ignore into journalissuearticles values(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