High-resolution photovoltaic power forecasting using machine learning models under seasonal and stress conditions
Hany S. E. Mansour, Amira S. Mohamed, Hassan M. Hussein Farh, AL-Wesabi Ibrahim, Abdullah M. Al-Shaalan, Abdullahi Bala Kunya, Hany S. Elnashar · 2026
Read High-resolution photovoltaic power forecasting using machine learning models under seasonal and stress conditions by Hany S. E. Mansour, Amira S. Mohamed, Hassan M. Hussein Farh, AL-Wesabi Ibrahim, Abdullah M. Al-Shaalan, Abdullahi Bala Kunya, Hany S. Elnashar (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13280394.txt.
Description
Hany S. E. Mansour and colleagues present a 2026 study of high resolution solar power forecasting with machine learning. Accurate short term photovoltaic forecasts, at sub hourly scale, keep grids stable as solar grows. The team benchmarked six machine learning models against a persistence baseline, which just repeats the last value. Data came from the Yulara Solar System, resampled at five, ten and fifteen minute steps. A full preprocessing frame built time, lag and rolling features and filtered outliers.
Models held XGBoost, Decision Tree, Linear Regression, Ridge, Lasso and Elastic Net. Five error metrics scored them across train, validation and test sets, plus seasonal and stress subsets. Stress scenes held night time and wild irradiance swings. Tree based models beat linear regressors by a lot in both accuracy and robustness. The Decision Tree took the best overall performance in their tests. Fine grain forecasts can smooth solar grid work.
Catalog record
| CREATOR | Hany S. E. Mansour, Amira S. Mohamed, Hassan M. Hussein Farh, AL-Wesabi Ibrahim, Abdullah M. Al-Shaalan, Abdullahi Bala Kunya, Hany S. Elnashar |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 128930 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |