Solar trackers maximize solar radiation collection but are less commonly used due to their high cost, maintenance requirements, and the additional expenses associated with monthly angle adjustments. This paper proposes optimizing solar energy absorption by determining the optimal tilt for fixed-site solar panels in Turkey. It introduces an equation developed with artificial neural networks to forecast the ideal angle based on five location-specific features. Input variables, training procedures, and network design significantly impact the accuracy of Neural Network models' predictions. MATLAB software created three distinct ANN models for this investigation, each employing unique training setups and procedures. Matlab graphs guided the selection of algorithms and models based on minimizing MAE and RMSE while maximizing the linear correlation coefficient (R). The RMSE value obtained according to the calculations was 3.5881e^(-6), and the R value was 0.99998. The network's estimated data was compared to the training and testing cosθ data, yielding an RMSE error of 0.43% and an R2 value of 0.99978, indicating high accuracy. The average annual optimum inclination angles for the studied cities are as follows: Ankara (35.18°), Antalya (34.29°), Ağrı (34.91°), İstanbul (34.50°), Sivas (34.96°), İzmir (35.19°), Sinop (35.06°), and Gaziantep (34.97°).
Solar trackers maximize solar radiation collection but are less commonly used due to their high cost, maintenance requirements, and the additional expenses associated with monthly angle adjustments. This paper proposes optimizing solar energy absorption by determining the optimal tilt for fixed-site solar panels in Turkey. It introduces an equation developed with artificial neural networks to forecast the ideal angle based on five location-specific features. Input variables, training procedures, and network design significantly impact the accuracy of Neural Network models' predictions. MATLAB software created three distinct ANN models for this investigation, each employing unique training setups and procedures. Matlab graphs guided the selection of algorithms and models based on minimizing MAE and RMSE while maximizing the linear correlation coefficient (R). The RMSE value obtained according to the calculations was 3.5881e^(-6), and the R value was 0.99998. The network's estimated data was compared to the training and testing cosθ data, yielding an RMSE error of 0.43% and an R2 value of 0.99978, indicating high accuracy. The average annual optimum inclination angles for the studied cities are as follows: Ankara (35.18°), Antalya (34.29°), Ağrı (34.91°), İstanbul (34.50°), Sivas (34.96°), İzmir (35.19°), Sinop (35.06°), and Gaziantep (34.97°).
Primary Language | English |
---|---|
Subjects | Engineering |
Journal Section | Research Article |
Authors | |
Early Pub Date | November 10, 2023 |
Publication Date | |
Submission Date | May 18, 2023 |
Published in Issue | Year 2024 Volume: 27 Issue: 5 |
This work is licensed under Creative Commons Attribution-ShareAlike 4.0 International.