Nonstationarity in correlation matrices for wind turbine SCADA‐data
Abstract Modern utility‐scale wind turbines are equipped with a Supervisory Control And Data Acquisition (SCADA) system gathering vast amounts of operational data that can be used for analysis to improve operation and maintenance of turbines. We analyze high‐frequency SCADA‐data from the Thanet offs...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-08-01
|
| Series: | Wind Energy |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/we.2843 |
| _version_ | 1797782106604044288 |
|---|---|
| author | Henrik M. Bette Edgar Jungblut Thomas Guhr |
| author_facet | Henrik M. Bette Edgar Jungblut Thomas Guhr |
| author_sort | Henrik M. Bette |
| collection | DOAJ |
| description | Abstract Modern utility‐scale wind turbines are equipped with a Supervisory Control And Data Acquisition (SCADA) system gathering vast amounts of operational data that can be used for analysis to improve operation and maintenance of turbines. We analyze high‐frequency SCADA‐data from the Thanet offshore wind farm in the United Kindom and evaluate Pearson correlation matrices for a variety of observables with a moving time window. This renders possible a quantitative assessment of nonstationarity in mutual dependencies of different types of data. We show that a clustering algorithm applied to the correlation matrices reveals distinct correlation structures for different states. Looking first at only one and then at multiple turbines, the main dependence of these states is shown to be on wind speed. This is in accordance with known turbine control systems, which change the behavior of the turbine depending on the available wind speed. We model the boundary wind speeds separating the states based on the clustering solution. Our analysis shows that for high‐frequency data, the control mechanisms of a turbine lead to detectable nonstationarity in the correlation matrix. The presented methodology allows accounting for this with an automated preprocessing by sorting new data based on wind speed and comparing it to the respective operational state, thereby taking the nonstationarity into account for an analysis. |
| first_indexed | 2024-03-13T00:06:22Z |
| format | Article |
| id | doaj.art-fa02b138688347b5b37dbb119cb05765 |
| institution | Directory Open Access Journal |
| issn | 1095-4244 1099-1824 |
| language | English |
| last_indexed | 2024-03-13T00:06:22Z |
| publishDate | 2023-08-01 |
| publisher | Wiley |
| record_format | Article |
| series | Wind Energy |
| spelling | doaj.art-fa02b138688347b5b37dbb119cb057652023-07-13T03:36:01ZengWileyWind Energy1095-42441099-18242023-08-0126882684910.1002/we.2843Nonstationarity in correlation matrices for wind turbine SCADA‐dataHenrik M. Bette0Edgar Jungblut1Thomas Guhr2Faculty of Physics University of Duisburg‐Essen Duisburg GermanyFaculty of Physics University of Duisburg‐Essen Duisburg GermanyFaculty of Physics University of Duisburg‐Essen Duisburg GermanyAbstract Modern utility‐scale wind turbines are equipped with a Supervisory Control And Data Acquisition (SCADA) system gathering vast amounts of operational data that can be used for analysis to improve operation and maintenance of turbines. We analyze high‐frequency SCADA‐data from the Thanet offshore wind farm in the United Kindom and evaluate Pearson correlation matrices for a variety of observables with a moving time window. This renders possible a quantitative assessment of nonstationarity in mutual dependencies of different types of data. We show that a clustering algorithm applied to the correlation matrices reveals distinct correlation structures for different states. Looking first at only one and then at multiple turbines, the main dependence of these states is shown to be on wind speed. This is in accordance with known turbine control systems, which change the behavior of the turbine depending on the available wind speed. We model the boundary wind speeds separating the states based on the clustering solution. Our analysis shows that for high‐frequency data, the control mechanisms of a turbine lead to detectable nonstationarity in the correlation matrix. The presented methodology allows accounting for this with an automated preprocessing by sorting new data based on wind speed and comparing it to the respective operational state, thereby taking the nonstationarity into account for an analysis.https://doi.org/10.1002/we.2843clusteringcorrelation matrixnonstationaritySCADA‐datawind turbine |
| spellingShingle | Henrik M. Bette Edgar Jungblut Thomas Guhr Nonstationarity in correlation matrices for wind turbine SCADA‐data Wind Energy clustering correlation matrix nonstationarity SCADA‐data wind turbine |
| title | Nonstationarity in correlation matrices for wind turbine SCADA‐data |
| title_full | Nonstationarity in correlation matrices for wind turbine SCADA‐data |
| title_fullStr | Nonstationarity in correlation matrices for wind turbine SCADA‐data |
| title_full_unstemmed | Nonstationarity in correlation matrices for wind turbine SCADA‐data |
| title_short | Nonstationarity in correlation matrices for wind turbine SCADA‐data |
| title_sort | nonstationarity in correlation matrices for wind turbine scada data |
| topic | clustering correlation matrix nonstationarity SCADA‐data wind turbine |
| url | https://doi.org/10.1002/we.2843 |
| work_keys_str_mv | AT henrikmbette nonstationarityincorrelationmatricesforwindturbinescadadata AT edgarjungblut nonstationarityincorrelationmatricesforwindturbinescadadata AT thomasguhr nonstationarityincorrelationmatricesforwindturbinescadadata |