A Hybrid Wind Speed Forecasting Framework Based on Downscaled Multi-Model Forecasts and Machine Learning for Day-Ahead Wind Power Applications.
Saved in:
| Title: | A Hybrid Wind Speed Forecasting Framework Based on Downscaled Multi-Model Forecasts and Machine Learning for Day-Ahead Wind Power Applications. |
|---|---|
| Authors: | Oh, Donggun1 (AUTHOR), Lee, Minkyu1,2 (AUTHOR), Oh, Myeongchan1 (AUTHOR), Kim, Chang Ki1,2 (AUTHOR), Kim, Jin-Young1 (AUTHOR) jinyoung.kim@kier.re.kr |
| Source: | Energies (19961073). Jun2026, Vol. 19 Issue 12, p2928. 26p. |
| Subject Terms: | *Wind forecasting, *Machine learning, *Numerical weather forecasting, *Downscaling (Climatology), *Renewable energy sources, *Wind power, *Forecasting |
| Geographic Terms: | Jeju Island (Korea) |
| Abstract: | Accurate day-ahead wind speed forecasting is essential for wind power forecasting and electricity market participation under increasing renewable energy penetration. This study proposes a hybrid forecasting framework that combines raw global forecasts from GFS and IFS, the KMA KIM-RDAPS regional forecast, and dynamically downscaled GFS/IFS forecasts generated with alternative boundary-layer physics. Seven forecast members were synthesized using arithmetic averaging, performance-weighted averaging, and LightGBM-based machine learning (ML) regression. The framework was evaluated over Jeju Island, Republic of Korea, using 10 m Automatic Weather Station observations from 2023 to 2024 and 80 m meteorological mast observations from 2023. For the AWS evaluation, 2023 was used for training and validation, and 2024 was reserved for independent testing. The site-specific LightGBM synthesis achieved the most consistent improvement, reducing the median site-wise MAE across 31 AWS sites to 0.90 m s−1, corresponding to a 39.2% improvement relative to the best non-downscaled member and 47.2% relative to the unweighted multi-model mean. In the 80 m mast-based diagnostic assessment, the same approach reduced derived normalized power MAE to 11.4%. These results indicate that ML synthesis of multi-source NWP forecasts can improve day-ahead wind speed and power-oriented forecast information over complex island terrain. [ABSTRACT FROM AUTHOR] |
| Database: | Energy & Power Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | Accurate day-ahead wind speed forecasting is essential for wind power forecasting and electricity market participation under increasing renewable energy penetration. This study proposes a hybrid forecasting framework that combines raw global forecasts from GFS and IFS, the KMA KIM-RDAPS regional forecast, and dynamically downscaled GFS/IFS forecasts generated with alternative boundary-layer physics. Seven forecast members were synthesized using arithmetic averaging, performance-weighted averaging, and LightGBM-based machine learning (ML) regression. The framework was evaluated over Jeju Island, Republic of Korea, using 10 m Automatic Weather Station observations from 2023 to 2024 and 80 m meteorological mast observations from 2023. For the AWS evaluation, 2023 was used for training and validation, and 2024 was reserved for independent testing. The site-specific LightGBM synthesis achieved the most consistent improvement, reducing the median site-wise MAE across 31 AWS sites to 0.90 m s−1, corresponding to a 39.2% improvement relative to the best non-downscaled member and 47.2% relative to the unweighted multi-model mean. In the 80 m mast-based diagnostic assessment, the same approach reduced derived normalized power MAE to 11.4%. These results indicate that ML synthesis of multi-source NWP forecasts can improve day-ahead wind speed and power-oriented forecast information over complex island terrain. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 19961073 |
| DOI: | 10.3390/en19122928 |
