Enhancing Solar Energy Prospects: Predicting Direct Normal Irradiance in Qinghai Province Using ALO-RF Modeling

Document Type : Original Article


1 College of Mechanical Design, Manufacturing, and Automation, China Three Gorges University, Hubei, China

2 Collage of Economics and Management, China Three Gorges University, Hubei China


One important aspect of solar radiation that has a direct impact on atmospheric processes, climatic conditions, and energy generation is direct normal irradiance. The integration of solar geometry, geographic location, and atmospheric characteristics is required for the prediction of Direct Normal Irradiance. Predicting Direct Normal Irradiance is essential for maximizing the efficiency of solar power plants in the field of renewable energy. Precise predictions facilitate the efficient assimilation of solar electricity into the electrical grid, augmenting energy production and maintaining system stability. This study uses the Genetic algorithm, Moth Flame Optimization, and Ant Lion Optimizer to optimize the Random Forest model. The basic approach for this study is provided as a novel hybrid method by combining Ant Lion Optimizer with Random Forest, which has the best performance outcome compared to other created models. The data used is from June 1, 2022, to July 30, 2023. In presenting this study, many aspects have been considered, including the coefficient of determination, root mean square error, mean absolute percentage error, and mean absolute error. The proposed model’s findings with the highest amount of R-squared have shown satisfactory performance.