Global solar radiation prediction: Application of novel hybrid data-driven model

One of the significant prerequisites for harvesting solar energy is precise global solar radiation (GHI) forecasts. However, variability and uncertainty are inherent characteristics of solar radiation. It is challenging to show better generalization using current data analysis approaches. Thus, this research presents a new intelligence framework by hybridizing Support Vector Regression (SVR) with the Grasshopper Optimization Algorithm (GOA) and the Boruta-based feature selection algorithm (BA) for forecasting GHI values at different sites of Saudi Arabia. Interestingly, the most significant distinction that differentiates this proposed prediction model (SVR-GOA-BAK) from other models is that the GOA is automatically employed to search for optimal SVR's hyperparameters. In contrast, these hyperparameters are chosen randomly and manually in conventional models. Consequently, the contribution helps save time, reduce cost, and avoid the possibility of models' overfitting or underfitting caused by random and manual selection. A diversity of statistical measures has justified the proposed model's effectiveness and superiority. In terms of mean absolute percentage error (MAPE), the proposed model outperformed the standalone SVR models by 32.15-39.69% at different study sites. In tuning the SVR's parameters, GOA outperforms popular optimization algorithms. All the simulation test results demonstrate the superiority of the proposed model. Hence, the proposed approach provides a foundation for precise solar radiation forecasting, which can aid in the growth of renewable-energy-based technologies. (c) 2021 Elsevier B.V. All rights reserved.

Automated summary

This study presents a new intelligent framework combining Support Vector Regression, Grasshopper Optimization Algorithm, and feature selection algorithm for forecasting solar radiation values at different sites in Saudi Arabia. By automatically searching for optimal hyperparameters, saving time, and reducing costs, the proposed model outperformed traditional models in accuracy at different study sites.