PLoS ONE, Journal Year: 2024, Volume and Issue: 19(12), P. e0314391 - e0314391

Published: Dec. 20, 2024

In the contemporary context of a burgeoning energy crisis, accurate and dependable prediction Solar Radiation (SR) has emerged as an indispensable component within thermal systems to facilitate renewable generation. Machine Learning (ML) models have gained widespread recognition for their precision computational efficiency in addressing SR challenges. Consequently, this paper introduces innovative model, denoted Cheetah Optimizer-Random Forest (CO-RF) model. The CO plays pivotal role selecting most informative features hourly forecasting, subsequently serving inputs RF efficacy developed CO-RF model is rigorously assessed using two publicly available datasets. Evaluation metrics encompassing Mean Absolute Error (MAE), Squared (MSE), coefficient determination ( R 2 ) are employed validate its performance. Quantitative analysis demonstrates that surpasses other techniques, Logistic Regression (LR), Support Vector (SVM), Artificial Neural Network, standalone Random (RF), both training testing phases prediction. proposed outperforms others, achieving low MAE 0.0365, MSE 0.0074, 0.9251 on first dataset, 0.0469, 0.0032, 0.9868 second demonstrating significant error reduction.

Language: Английский