Vertical wind speed extrapolation using regularized extreme learning machine
The cost of measuring wind speed (WS) increases significantly with mast heights. Therefore, it is required to have a method to estimate WS at hub height without the need to use measuring masts. This paper examines using the Regularized Extreme Learning Machine (RELM) to extrapolate WS at higher alti...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
University of Belgrade - Faculty of Mechanical Engineering, Belgrade
2022-01-01
|
| Series: | FME Transactions |
| Subjects: | |
| Online Access: | https://scindeks-clanci.ceon.rs/data/pdf/1451-2092/2022/1451-20922203412N.pdf |
| _version_ | 1828108183239917568 |
|---|---|
| author | Nuha H. Mohandes M. Rehman S. A-Shaikhi Ali |
| author_facet | Nuha H. Mohandes M. Rehman S. A-Shaikhi Ali |
| author_sort | Nuha H. |
| collection | DOAJ |
| description | The cost of measuring wind speed (WS) increases significantly with mast heights. Therefore, it is required to have a method to estimate WS at hub height without the need to use measuring masts. This paper examines using the Regularized Extreme Learning Machine (RELM) to extrapolate WS at higher altitudes based on measurements at lower heights. The RELM uses measured WS at heights 10-40 m to estimate WS at 50 m. The estimation results of 50 m are further used along with the measured WS at 10-40 to estimate WS at 60 m. This procedure continues until the estimation of 180 m. The RELM's performance is compared with the regression tree (RegTree) method and the standard 1/7 Power Law. The proposed algorithm provides an economical method to find wind speed at hub height and, consequently, the potential wind energy that can be generated from turbines installed at hub height based on measurements taken at much lower heights. Moreover, these methods' extrapolated values are compared with the actual measured values using the LiDAR system. The mean absolute percentage error (MAPE) between extrapolated and measured WS at the height of 180 m using measurements at the height of 10-40 m using RELM, RegTree, 1/7 Power Law, and Power Law with adaptive coefficients is 13.36%, 16.76%, 33.50%, and 15.73%, respectively. |
| first_indexed | 2024-04-11T10:42:23Z |
| format | Article |
| id | doaj.art-ab8a5f073ee547efa4b6c9e77e6584a5 |
| institution | Directory Open Access Journal |
| issn | 1451-2092 2406-128X |
| language | English |
| last_indexed | 2024-04-11T10:42:23Z |
| publishDate | 2022-01-01 |
| publisher | University of Belgrade - Faculty of Mechanical Engineering, Belgrade |
| record_format | Article |
| series | FME Transactions |
| spelling | doaj.art-ab8a5f073ee547efa4b6c9e77e6584a52022-12-22T04:29:09ZengUniversity of Belgrade - Faculty of Mechanical Engineering, BelgradeFME Transactions1451-20922406-128X2022-01-0150341242110.5937/fme2203412N1451-20922203412NVertical wind speed extrapolation using regularized extreme learning machineNuha H.0Mohandes M.1Rehman S.2A-Shaikhi Ali3School of Computing Telkom University, HUMIC, IndonesiaKing Fahd University of Petroleum & Minerals, EE Department and Interdisciplinary Research Center for Renewable Energy and Power Systems (IRC-REPS), Dhahran, Saudi ArabiaKing Fahd University of Petroleum & Minerals, Interdisciplinary Research Center for Renewable Energy and Power Systems (IRC-REPS), Dhahran, Saudi ArabiaKing Fahd University of Petroleum & Minerals, Department of Electrical Engineering, Dhahran, Saudi ArabiaThe cost of measuring wind speed (WS) increases significantly with mast heights. Therefore, it is required to have a method to estimate WS at hub height without the need to use measuring masts. This paper examines using the Regularized Extreme Learning Machine (RELM) to extrapolate WS at higher altitudes based on measurements at lower heights. The RELM uses measured WS at heights 10-40 m to estimate WS at 50 m. The estimation results of 50 m are further used along with the measured WS at 10-40 to estimate WS at 60 m. This procedure continues until the estimation of 180 m. The RELM's performance is compared with the regression tree (RegTree) method and the standard 1/7 Power Law. The proposed algorithm provides an economical method to find wind speed at hub height and, consequently, the potential wind energy that can be generated from turbines installed at hub height based on measurements taken at much lower heights. Moreover, these methods' extrapolated values are compared with the actual measured values using the LiDAR system. The mean absolute percentage error (MAPE) between extrapolated and measured WS at the height of 180 m using measurements at the height of 10-40 m using RELM, RegTree, 1/7 Power Law, and Power Law with adaptive coefficients is 13.36%, 16.76%, 33.50%, and 15.73%, respectively.https://scindeks-clanci.ceon.rs/data/pdf/1451-2092/2022/1451-20922203412N.pdfwind speedvertical extrapolationregularized extreme learning machineregression tree |
| spellingShingle | Nuha H. Mohandes M. Rehman S. A-Shaikhi Ali Vertical wind speed extrapolation using regularized extreme learning machine FME Transactions wind speed vertical extrapolation regularized extreme learning machine regression tree |
| title | Vertical wind speed extrapolation using regularized extreme learning machine |
| title_full | Vertical wind speed extrapolation using regularized extreme learning machine |
| title_fullStr | Vertical wind speed extrapolation using regularized extreme learning machine |
| title_full_unstemmed | Vertical wind speed extrapolation using regularized extreme learning machine |
| title_short | Vertical wind speed extrapolation using regularized extreme learning machine |
| title_sort | vertical wind speed extrapolation using regularized extreme learning machine |
| topic | wind speed vertical extrapolation regularized extreme learning machine regression tree |
| url | https://scindeks-clanci.ceon.rs/data/pdf/1451-2092/2022/1451-20922203412N.pdf |
| work_keys_str_mv | AT nuhah verticalwindspeedextrapolationusingregularizedextremelearningmachine AT mohandesm verticalwindspeedextrapolationusingregularizedextremelearningmachine AT rehmans verticalwindspeedextrapolationusingregularizedextremelearningmachine AT ashaikhiali verticalwindspeedextrapolationusingregularizedextremelearningmachine |