View in EDS HTML Full Text PDF Full Text

A Hybrid Wind Speed Forecasting Framework Based on Downscaled Multi-Model Forecasts and Machine Learning for Day-Ahead Wind Power Applications.

Saved in:
Bibliographic Details
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.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: enr
DbLabel: Energy & Power Source
An: 194909377
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: A Hybrid Wind Speed Forecasting Framework Based on Downscaled Multi-Model Forecasts and Machine Learning for Day-Ahead Wind Power Applications.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Oh%2C+Donggun%22">Oh, Donggun</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Lee%2C+Minkyu%22">Lee, Minkyu</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Oh%2C+Myeongchan%22">Oh, Myeongchan</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Kim%2C+Chang+Ki%22">Kim, Chang Ki</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Kim%2C+Jin-Young%22">Kim, Jin-Young</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> jinyoung.kim@kier.re.kr</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Energies+%2819961073%29%22">Energies (19961073)</searchLink>. Jun2026, Vol. 19 Issue 12, p2928. 26p.
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: *<searchLink fieldCode="DE" term="%22Wind+forecasting%22">Wind forecasting</searchLink><br />*<searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br />*<searchLink fieldCode="DE" term="%22Numerical+weather+forecasting%22">Numerical weather forecasting</searchLink><br />*<searchLink fieldCode="DE" term="%22Downscaling+%28Climatology%29%22">Downscaling (Climatology)</searchLink><br />*<searchLink fieldCode="DE" term="%22Renewable+energy+sources%22">Renewable energy sources</searchLink><br />*<searchLink fieldCode="DE" term="%22Wind+power%22">Wind power</searchLink><br />*<searchLink fieldCode="DE" term="%22Forecasting%22">Forecasting</searchLink>
– Name: SubjectGeographic
  Label: Geographic Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Jeju+Island+%28Korea%29%22">Jeju Island (Korea)</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: 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]
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=enr&AN=194909377
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3390/en19122928
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 26
        StartPage: 2928
    Subjects:
      – SubjectFull: Wind forecasting
        Type: general
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Numerical weather forecasting
        Type: general
      – SubjectFull: Downscaling (Climatology)
        Type: general
      – SubjectFull: Renewable energy sources
        Type: general
      – SubjectFull: Wind power
        Type: general
      – SubjectFull: Forecasting
        Type: general
      – SubjectFull: Jeju Island (Korea)
        Type: general
    Titles:
      – TitleFull: A Hybrid Wind Speed Forecasting Framework Based on Downscaled Multi-Model Forecasts and Machine Learning for Day-Ahead Wind Power Applications.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Oh, Donggun
      – PersonEntity:
          Name:
            NameFull: Lee, Minkyu
      – PersonEntity:
          Name:
            NameFull: Oh, Myeongchan
      – PersonEntity:
          Name:
            NameFull: Kim, Chang Ki
      – PersonEntity:
          Name:
            NameFull: Kim, Jin-Young
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 15
              M: 06
              Text: Jun2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 19961073
          Numbering:
            – Type: volume
              Value: 19
            – Type: issue
              Value: 12
          Titles:
            – TitleFull: Energies (19961073)
              Type: main
ResultId 1