article · Next Energy
Predicting day-ahead renewable energy generation is difficult because wind and solar outputs depend directly on unpredictable weather conditions. An artificial intelligence framework evaluated one-day-ahead renewable power generation under two distinct conditions using hourly NASA POWER meteorological data. The first condition relied strictly on historical operational data, whereas the second incorporated day-ahead meteorological predictors as weather-forecast proxies. Machine learning models, including least-squares boosting, random forest bagging, neural network regression, and weighted ensembles, were tested. Historical data alone proved inadequate, delivering a low determination coefficient and high prediction errors. Introducing meteorological inputs dramatically improved performance, with least-squares boosting reaching near-perfect accuracy. However, this weather-informed outcome represents an idealised upper-bound benchmark rather than an immediately operational tool, because generation values were synthetically modelled from identical weather inputs. The comparative framework establishes practical lower and upper boundaries for renewable power estimation.
Energy operators need reliable forecasts to balance electricity grids, plan storage, and schedule microgrids effectively. Demonstrating the stark performance gap between purely historical models and weather-informed predictions highlights the fundamental role of meteorological data. This benchmarking framework helps system planners recognise the limits of historical telemetry and quantify the theoretical best-case accuracy achievable when integrating weather predictions into energy management systems.
The framework addresses applications in microgrid scheduling, energy planning, and battery-aware renewable power management for grid operators and energy planners. However, the technology is at an early, benchmark-setting stage of research. It cannot be directly deployed commercially because the high-accuracy results depend on synthetic generation profiles and actual realised weather observations rather than real-world numerical weather forecasts.
AI-generated from the published abstract. Always read the original work before citing.
Accurate day-ahead renewable energy forecasting remains one of the most challenging problems in modern energy systems because photovoltaic and wind generation are not controlled by the operator, but by uncertain atmospheric forcing. This paper develops a complete NASA POWER-driven artificial intelligence framework for one-day-ahead renewable power forecasting under two sharply different operational assumptions. The first scenario is a strict blind forecast , where only historical information is available. The second is a weather-informed forecast , where day-ahead meteorological predictors at the target hour are introduced as proxy weather-forecast inputs. Hourly solar irradiance, wind speed, temperature, and humidity from NASA POWER are used to construct photovoltaic production, wind turbine generation, battery state of charge, persistence baselines, lagged features, residual-correction forecasts, daily-energy forecasts, and learning-based predictions. Three machine learning models, least-squares boosting, random forest bagging, and neural network regression, are compared with weighted ensemble variants. The obtained results show that historical information alone is insufficient for accurate hourly 24-hour-ahead prediction, with the best strict blind model achieving R 2 = 0.3551 and RMSE=445.50 kW. However, when day-ahead weather predictors are introduced, the LSBoost model reaches RMSE=2.29 kW and R 2 = 0.99998. This weather-informed result is interpreted as an idealized upper-bound experiment rather than as a directly deployable operational forecast, because the target renewable generation is synthetically constructed from the same meteorological variables and because realized target-hour NASA POWER variables are used instead of numerical weather prediction forecasts. This contrast does not merely improve accuracy; it exposes the physical reason behind renewable forecastability. Meteorological information is therefore a central driver of one-day-ahead renewable-power prediction. The proposed dual-scenario strategy therefore provides both a lower-bound historical evaluation and an upper-bound weather-informed benchmark for energy planning, microgrid scheduling, and battery-aware renewable management.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1016/j.nxener.2026.100922
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
