Towards a Greener Future: Machine Learning Applications in Solar Irradiance Forecasting for Renewable Energy Planning in Saudi Arabia

Abstract

Renewable energy planning is set to be transformed by the integration of advanced solar irradiance forecasting techniques. By harnessing the predictive power of Machine Learning (ML) algorithms, planners can gain more accurate insights into future solar irradiance levels. This study investigates the use of ML algorithms for solar irradiance forecasting, intending to enhance planning strategies for renewable energy sources (RES) in Saudi Arabia. Using datasets sourced from various regions in Saudi Arabia, several regression models are evaluated, including Gradient Boosting Regressor (GBR), Linear Regression (LR), Long Short-Term Memory (LSTM), Bidirectional Long Short-Term Memory (Bi-LSTM), and K-Nearest Neighbor (KNN). The analysis of this research reveals that ensemble techniques such as Random Forest Regression (RFR) and data-driven approaches like KNN exhibit superior performance compared to conventional regression models like LR, underscoring the significance of various ML methods in solar irradiance prediction When compared to Decision Tree Regressor (DTR) and RFR, models with high goodness of-fit metrics (R-squared, adjusted R-squared) and low error metrics (Mean Absolute Error (MAE), Root Mean Square Error (RMSE)) show better predictive power. The precision with which the proposed models forecast solar irradiance levels is further confirmed by comparison with previous studies. Planning for RES is advanced by this study’s identification of the best ML methods for predicting solar irradiation. The results highlight the potential of using ML approaches to optimize solar energy system integration and accelerate the shift to sustainable energy practices.