Machine learning–based piecewise affine model of wind turbines during maximum power point tracking
Abstract In this paper, a discrete‐time piecewise affine (PWA) model of a wind turbine during Maximum Power Point Tracking (MPPT) region is identified. A clustering‐based identification method is utilized to create PWA maps for nonlinear aerodynamic torque and thrust force functions. This method exp...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-02-01
|
| Series: | Wind Energy |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/we.2440 |
| _version_ | 1818522507538333696 |
|---|---|
| author | Peyman Sindareh‐Esfahani Jeff Pieper |
| author_facet | Peyman Sindareh‐Esfahani Jeff Pieper |
| author_sort | Peyman Sindareh‐Esfahani |
| collection | DOAJ |
| description | Abstract In this paper, a discrete‐time piecewise affine (PWA) model of a wind turbine during Maximum Power Point Tracking (MPPT) region is identified. A clustering‐based identification method is utilized to create PWA maps for nonlinear aerodynamic torque and thrust force functions. This method exploits the combined use of clustering, pattern recognition, and parameter identification techniques. The well‐known K‐means clustering method is employed along with a perceptron‐based multiclassifier for pattern recognition and the least squared technique for parameter estimation. The identified maps are approximated the nonlinear static functions of the dynamic model of the wind turbine. Characteristics of a 5‐MW wind turbine are considered and the resulting model, which consists of 25 subregions is compared with the nonlinear dynamic model. Two test cases are studied in order to validate the presented model. Simulation results demonstrate the effectiveness and accuracy of the PWA model such that the response of the identified PWA model is fitted well to the nonlinear one. The PWA model identified in this paper can be widely used for advanced control systems design and long‐term performance and security assessment of the power grid. |
| first_indexed | 2024-12-11T05:34:09Z |
| format | Article |
| id | doaj.art-5fd148555e6440fca5b31bdae8aec652 |
| institution | Directory Open Access Journal |
| issn | 1095-4244 1099-1824 |
| language | English |
| last_indexed | 2024-12-11T05:34:09Z |
| publishDate | 2020-02-01 |
| publisher | Wiley |
| record_format | Article |
| series | Wind Energy |
| spelling | doaj.art-5fd148555e6440fca5b31bdae8aec6522022-12-22T01:19:20ZengWileyWind Energy1095-42441099-18242020-02-0123240442210.1002/we.2440Machine learning–based piecewise affine model of wind turbines during maximum power point trackingPeyman Sindareh‐Esfahani0Jeff Pieper1Department of Mechanical and Manufacturing Engineering, Schulich School of Engineering University of Calgary Calgary Alberta CanadaDepartment of Mechanical and Manufacturing Engineering, Schulich School of Engineering University of Calgary Calgary Alberta CanadaAbstract In this paper, a discrete‐time piecewise affine (PWA) model of a wind turbine during Maximum Power Point Tracking (MPPT) region is identified. A clustering‐based identification method is utilized to create PWA maps for nonlinear aerodynamic torque and thrust force functions. This method exploits the combined use of clustering, pattern recognition, and parameter identification techniques. The well‐known K‐means clustering method is employed along with a perceptron‐based multiclassifier for pattern recognition and the least squared technique for parameter estimation. The identified maps are approximated the nonlinear static functions of the dynamic model of the wind turbine. Characteristics of a 5‐MW wind turbine are considered and the resulting model, which consists of 25 subregions is compared with the nonlinear dynamic model. Two test cases are studied in order to validate the presented model. Simulation results demonstrate the effectiveness and accuracy of the PWA model such that the response of the identified PWA model is fitted well to the nonlinear one. The PWA model identified in this paper can be widely used for advanced control systems design and long‐term performance and security assessment of the power grid.https://doi.org/10.1002/we.2440classificationclustering‐based identificationmachine learningpiecewise affine modelregressionsystem identification |
| spellingShingle | Peyman Sindareh‐Esfahani Jeff Pieper Machine learning–based piecewise affine model of wind turbines during maximum power point tracking Wind Energy classification clustering‐based identification machine learning piecewise affine model regression system identification |
| title | Machine learning–based piecewise affine model of wind turbines during maximum power point tracking |
| title_full | Machine learning–based piecewise affine model of wind turbines during maximum power point tracking |
| title_fullStr | Machine learning–based piecewise affine model of wind turbines during maximum power point tracking |
| title_full_unstemmed | Machine learning–based piecewise affine model of wind turbines during maximum power point tracking |
| title_short | Machine learning–based piecewise affine model of wind turbines during maximum power point tracking |
| title_sort | machine learning based piecewise affine model of wind turbines during maximum power point tracking |
| topic | classification clustering‐based identification machine learning piecewise affine model regression system identification |
| url | https://doi.org/10.1002/we.2440 |
| work_keys_str_mv | AT peymansindarehesfahani machinelearningbasedpiecewiseaffinemodelofwindturbinesduringmaximumpowerpointtracking AT jeffpieper machinelearningbasedpiecewiseaffinemodelofwindturbinesduringmaximumpowerpointtracking |