Global horizontal irradiance prediction for renewable energy system in Najran and Riyadh

• Published in: AIP advances Vol. 14; no. 3; pp. 035137 - 035137-15
• Main Authors: Irfan, Muhammad, Shaf, Ahmad, Ali, Tariq, Zafar, Maryam, AlThobiani, Faisal, Almas, Majid A., Attar, H. M., Alqhatani, Abdulmajeed, Rahman, Saifur, Almawgani, Abdulkarem H. M.
• Format: Journal Article
• Language: English
• Published: Melville American Institute of Physics 01-03-2024; AIP Publishing LLC
• Subjects: Alternative energy sources; Atmospheric models; Decision trees; Irradiance; Rainfall; Regression; Relative humidity; Solar energy; Solar energy conversion; Weather; Wind direction; Wind speed; Saudi Arabia; Riyadh Saudi Arabia
• ISSN: 2158-3226; 2158-3226
• DOI: 10.1063/5.0191676

Producing and supplying energy efficiently are important for many countries. Using models to predict energy production can help reduce costs, improve efficiency, and make energy systems work better. This research predicts solar electricity production in the Najran and Riyadh regions of Saudi Arabia by analyzing 14 weather factors. The weather factors that were considered in the study include date, time, Global Horizontal Irradiance (GHI), clear sky, top of atmosphere, code, temperature, relative humidity, pressure, wind speed, wind direction, rainfall, snowfall, and snow depth. GHI is the most important factor because it determines how much solar energy a system can produce. Therefore, it is important to be able to predict GHI accurately. This study used a variety of data-driven models to predict GHI, including the elastic net regression, linear regression, random forest, k-nearest neighbor, gradient boosting regressor, light gradient boosting regressor, extreme gradient boosting regressor, and decision tree regressor. The models were evaluated using a set of metrics, including the mean absolute error, mean squared error, root mean square error, coefficient of determination (R2), and adjusted coefficient of determination. This study found that the decision tree regression, Random Forest (RF), and Extreme Gradient Boosting (XGB) models performed better in the Riyadh region than in the Najran region. The R2 values for the Riyadh region were 99%, 99%, and 98%, while the R2 values for the Najran region were 89%, 94%, and 94%. This suggests that the Riyadh region is a more suitable location for solar energy conversion systems. These findings are important for policymakers and investors who are considering the development of solar energy projects in Saudi Arabia.