New Study on Renewable Energy Reveals Insights into Photovoltaic Module Temperature Prediction
Researchers at the Universidad Pontificia Bolivariana have made a significant breakthrough in the field of renewable energy by developing a new modeling methodology for predicting the temperature of photovoltaic (PV) modules in large-scale power plants. The study, published in the International Journal of Renewable Energy Development, focuses on the thermal behavior of single-axis tracked bifacial PV modules in tropical regions under high irradiation and temperature conditions.
Key Takeaways:
- The developed modeling methodology uses symbolic regression (SR) with genetic algorithms (GA) to create an explicit, interpretable equation for predicting PV module temperature.
- The study collected one year of data from a 19.9 MW PV plant in San Marcos, Colombia, featuring measurements of solar radiation, ambient temperature, wind speed, and module temperature.
- The constructed SR GA model achieved a satisfactory prediction accuracy compared to classic models, with a root mean square error (RMSE) of 4.14 °C and an R² of 0.91 on the test data set.
- The results compare favorably with the standard industry NOCT model (RMSE = 8.59 °C, R² = 0.60) and the Skoplaki I model (RMSE = 5.92 °C, R² = 0.81).
- The study found that the maximum temperature of the bifacial module is reached around 14:00h, likely due to the accumulation of temperature caused by solar tracking.
- The research demonstrated the potential of symbolic regression with a genetic algorithm kernel for producing accurate, interpretable, and computationally economical models for advanced photovoltaic systems.
Statistics:
- RMSE of 4.14 °C and R² of 0.91 on the test data set for the constructed SR GA model.
- 19.9 MW PV power plant used in the study.
- 1-year data collection period featuring measurements at 5-minute intervals.
- 14:00h identified as the time of maximum temperature of the bifacial module.
Sources:
- "Thermal analysis of bifacial photovoltaic modules with single-axis trackers in a large power plant: Modeling by symbolic equations in tropical climates." International Journal of Renewable Energy Development, 2025,14(6):1160-1170.
- Universidad Pontificia Bolivariana.
- Diponegoro University.