Akademik Veri Yönetim Sistemi
Mühendislik bilimleri ve araştırmaları dergisi (Online), cilt.6, sa.1, ss.24-34, 2024 (Hakemli Dergi)
The efficiency of solar energy systems requires a complicated forecasting process due to the variability of sunlight and environmental conditions. Among environmental factors, cloud coverage (% range), temperature (0C), wind speed (Mph), and humidity (%) variables were taken into account in this study. Neural networks (NN), which are machine learning (ML) algorithms with a flexible structure that can define complex relationships and process large amounts of data for solar energy prediction, were used in this study. The NN algorithm showed a high performance, with mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE), and R-squared (R2) values calculated as 0.019, 0.139, 0.053, and 0.977, respectively. This study emphasized that solar energy predictions made with the NN algorithm, considering environmental factors, are an essential tool that helps use solar energy systems more efficiently and sustainably.