AI-Based Solar Irradiance Prediction for Efficient Photovoltaic Energy Management
International Journal of Drug Delivery Technology · 30.04.2026 · 16 (23s)
DOI: 10.25258/ijddt.16.23s.8 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Drug Delivery Technology, online erschienen am 30.04.2026. Verfasst von Shahab Uddin Baqar und 4 weiteren Autor:innen.
Abstract (Originalsprache)
Accurate forecasting of solar irradiance is a pivotal requirement for maximising the operational efficiency of photovoltaic (PV) energy systems. Inherent variability in solar resource availability, driven by atmospheric dynamics, cloud cover, aerosol loading, and seasonal cycles, introduces substantial uncertainty into power grid planning and real-time energy dispatch. This study proposes a hybrid ensemble framework that integrates Long Short-Term Memory (LSTM) networks, Extreme Gradient Boosting (XGBoost), and Random Forest (RF) models through a stacked meta-learning layer for one-hour-ahead global horizontal irradiance (GHI) prediction. A six-year observational dataset (2018–2023) comprising meteorological variables, satellite-derived cloud indices, and aerosol optical depth measurements was used for training and evaluation. Temporal cross-validation was employed to prevent data leakage. The ensemble achieved a Root Mean Squared Error (RMSE) of 38.9 W/m², a Mean Absolute Error (MAE) of 31.4 W/m², and an R² of 0.960, outperforming all single-model baselines. Seasonal analysis revealed that the proposed framework maintains robust performance even under variable winter and monsoon-influenced sky conditions. The practical implications for real-time PV dispatch scheduling, storage sizing, and grid-balancing operations are discussed.
Zitieren
APA
Baqar, S. U., Kumar, C., Ranjan, A., Kumar, V., & Priyadarshini, P. (2026). AI-Based Solar Irradiance Prediction for Efficient Photovoltaic Energy Management. International Journal of Drug Delivery Technology, 16(23s). https://doi.org/10.25258/ijddt.16.23s.8
Vancouver
Baqar SU, Kumar C, Ranjan A, Kumar V, Priyadarshini P. AI-Based Solar Irradiance Prediction for Efficient Photovoltaic Energy Management. International Journal of Drug Delivery Technology. 2026;16(23s). doi:10.25258/ijddt.16.23s.8
BibTeX
@article{Baqar2026,
author = {Baqar, Shahab Uddin and Kumar, Chandrabhanu and Ranjan, Anand and Kumar, Varun and Priyadarshini, Priyadarshini},
title = {AI-Based Solar Irradiance Prediction for Efficient Photovoltaic Energy Management},
journal = {International Journal of Drug Delivery Technology},
year = {2026},
volume = {16},
number = {23s},
doi = {10.25258/ijddt.16.23s.8}
}
EUVIMED