Streaming dynamic mode decomposition for short‐term forecasting in wind farms
Abstract Forecasting in wind energy is a crucial task to perform adequate wind farm flow control or to participate in the energy market. While many power forecasting methods exist, it is notoriously difficult to capture both short‐ and long‐term variations in the wind farm system in real time. We de...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-04-01
|
| Series: | Wind Energy |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/we.2694 |
| _version_ | 1818356901566480384 |
|---|---|
| author | Jaime Liew Tuhfe Göçmen Wai Hou Lio Gunner Chr. Larsen |
| author_facet | Jaime Liew Tuhfe Göçmen Wai Hou Lio Gunner Chr. Larsen |
| author_sort | Jaime Liew |
| collection | DOAJ |
| description | Abstract Forecasting in wind energy is a crucial task to perform adequate wind farm flow control or to participate in the energy market. While many power forecasting methods exist, it is notoriously difficult to capture both short‐ and long‐term variations in the wind farm system in real time. We demonstrate a data‐driven real‐time system identification approach to forecasting based on streaming dynamic mode decomposition methodology (sDMD). The method is capable of characterizing nonlinear, time‐varying, multidimensional time series data in a computationally efficient manner. The algorithm is modified to work with data streams by adjusting the dynamic mode decomposition continuously as new data are made available. The method is applied to high‐frequency SCADA data from the Lillgrund offshore wind farm. A 23.31% improvement over persistence forecasting is found for 5‐min‐ahead forecasts of the power output of all turbines in the wind farm. sDMD is shown to be a suitable tool for capturing short‐term dynamics while adapting to long‐term changes in wind speed and direction and has potential applications in real‐time wind farm control. |
| first_indexed | 2024-12-13T20:04:35Z |
| format | Article |
| id | doaj.art-d73d238b0f5245c1b888f80eaf50f8a1 |
| institution | Directory Open Access Journal |
| issn | 1095-4244 1099-1824 |
| language | English |
| last_indexed | 2024-12-13T20:04:35Z |
| publishDate | 2022-04-01 |
| publisher | Wiley |
| record_format | Article |
| series | Wind Energy |
| spelling | doaj.art-d73d238b0f5245c1b888f80eaf50f8a12022-12-21T23:33:04ZengWileyWind Energy1095-42441099-18242022-04-0125471973410.1002/we.2694Streaming dynamic mode decomposition for short‐term forecasting in wind farmsJaime Liew0Tuhfe Göçmen1Wai Hou Lio2Gunner Chr. Larsen3Department of Wind Energy Technical University of Denmark Roskilde DenmarkDepartment of Wind Energy Technical University of Denmark Roskilde DenmarkDepartment of Wind Energy Technical University of Denmark Roskilde DenmarkDepartment of Wind Energy Technical University of Denmark Roskilde DenmarkAbstract Forecasting in wind energy is a crucial task to perform adequate wind farm flow control or to participate in the energy market. While many power forecasting methods exist, it is notoriously difficult to capture both short‐ and long‐term variations in the wind farm system in real time. We demonstrate a data‐driven real‐time system identification approach to forecasting based on streaming dynamic mode decomposition methodology (sDMD). The method is capable of characterizing nonlinear, time‐varying, multidimensional time series data in a computationally efficient manner. The algorithm is modified to work with data streams by adjusting the dynamic mode decomposition continuously as new data are made available. The method is applied to high‐frequency SCADA data from the Lillgrund offshore wind farm. A 23.31% improvement over persistence forecasting is found for 5‐min‐ahead forecasts of the power output of all turbines in the wind farm. sDMD is shown to be a suitable tool for capturing short‐term dynamics while adapting to long‐term changes in wind speed and direction and has potential applications in real‐time wind farm control.https://doi.org/10.1002/we.2694dynamic mode decompositionforecastingreal timewind energy |
| spellingShingle | Jaime Liew Tuhfe Göçmen Wai Hou Lio Gunner Chr. Larsen Streaming dynamic mode decomposition for short‐term forecasting in wind farms Wind Energy dynamic mode decomposition forecasting real time wind energy |
| title | Streaming dynamic mode decomposition for short‐term forecasting in wind farms |
| title_full | Streaming dynamic mode decomposition for short‐term forecasting in wind farms |
| title_fullStr | Streaming dynamic mode decomposition for short‐term forecasting in wind farms |
| title_full_unstemmed | Streaming dynamic mode decomposition for short‐term forecasting in wind farms |
| title_short | Streaming dynamic mode decomposition for short‐term forecasting in wind farms |
| title_sort | streaming dynamic mode decomposition for short term forecasting in wind farms |
| topic | dynamic mode decomposition forecasting real time wind energy |
| url | https://doi.org/10.1002/we.2694 |
| work_keys_str_mv | AT jaimeliew streamingdynamicmodedecompositionforshorttermforecastinginwindfarms AT tuhfegocmen streamingdynamicmodedecompositionforshorttermforecastinginwindfarms AT waihoulio streamingdynamicmodedecompositionforshorttermforecastinginwindfarms AT gunnerchrlarsen streamingdynamicmodedecompositionforshorttermforecastinginwindfarms |