Investigation of the Features Influencing the Accuracy of Wind Turbine Power Calculation at Short-Term Intervals

The accurate prediction of wind power generation, as well as the development of a digital twin of a wind turbine, require estimation of the power curve. Actual measurements of generated power, especially over short-term intervals, show that in many cases the power generated differs from the calculat...

Full description

Saved in:
Bibliographic Details
Main Authors: Pavel V. Matrenin, Dmitry A. Harlashkin, Marina V. Mazunina, Alexandra I. Khalyasmaa
Format: Article
Language:English
Published: MDPI AG 2024-10-01
Series:Applied System Innovation
Subjects:
Online Access:https://www.mdpi.com/2571-5577/7/6/105
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846105910468935680
author Pavel V. Matrenin
Dmitry A. Harlashkin
Marina V. Mazunina
Alexandra I. Khalyasmaa
author_facet Pavel V. Matrenin
Dmitry A. Harlashkin
Marina V. Mazunina
Alexandra I. Khalyasmaa
author_sort Pavel V. Matrenin
collection DOAJ
description The accurate prediction of wind power generation, as well as the development of a digital twin of a wind turbine, require estimation of the power curve. Actual measurements of generated power, especially over short-term intervals, show that in many cases the power generated differs from the calculated power, which considers only the wind speed and the technical parameters of the wind turbine. Some of these measurements are erroneous, while others are influenced by additional factors affecting generation beyond wind speed alone. This study presents an investigation of the features influencing the accuracy of calculations of wind turbine power at short-term intervals. The open dataset of SCADA-system measurements from a real wind turbine is used. It is discovered that using ensemble machine learning models and additional features, including the actual power from the previous time step, enhances the accuracy of the wind power calculation. The root-mean-square error achieved is 113 kW, with the nominal capacity of the wind turbine under consideration being 3.6 MW. Consequently, the ratio of the root-mean-square error to the nominal capacity is 3%.
format Article
id doaj-art-39df7cfbc0a24968a154c29052bbfe80
institution Kabale University
issn 2571-5577
language English
publishDate 2024-10-01
publisher MDPI AG
record_format Article
series Applied System Innovation
spelling doaj-art-39df7cfbc0a24968a154c29052bbfe802024-12-27T14:09:31ZengMDPI AGApplied System Innovation2571-55772024-10-017610510.3390/asi7060105Investigation of the Features Influencing the Accuracy of Wind Turbine Power Calculation at Short-Term IntervalsPavel V. Matrenin0Dmitry A. Harlashkin1Marina V. Mazunina2Alexandra I. Khalyasmaa3Ural Power Engineering Institute, Ural Federal University Named After the First President of Russia B.N. Yeltsin, Ekaterinburg 620062, RussiaUral Power Engineering Institute, Ural Federal University Named After the First President of Russia B.N. Yeltsin, Ekaterinburg 620062, RussiaUral Power Engineering Institute, Ural Federal University Named After the First President of Russia B.N. Yeltsin, Ekaterinburg 620062, RussiaUral Power Engineering Institute, Ural Federal University Named After the First President of Russia B.N. Yeltsin, Ekaterinburg 620062, RussiaThe accurate prediction of wind power generation, as well as the development of a digital twin of a wind turbine, require estimation of the power curve. Actual measurements of generated power, especially over short-term intervals, show that in many cases the power generated differs from the calculated power, which considers only the wind speed and the technical parameters of the wind turbine. Some of these measurements are erroneous, while others are influenced by additional factors affecting generation beyond wind speed alone. This study presents an investigation of the features influencing the accuracy of calculations of wind turbine power at short-term intervals. The open dataset of SCADA-system measurements from a real wind turbine is used. It is discovered that using ensemble machine learning models and additional features, including the actual power from the previous time step, enhances the accuracy of the wind power calculation. The root-mean-square error achieved is 113 kW, with the nominal capacity of the wind turbine under consideration being 3.6 MW. Consequently, the ratio of the root-mean-square error to the nominal capacity is 3%.https://www.mdpi.com/2571-5577/7/6/105wind turbinewind power forecastingpower curveensemble modelsmachine learningfeature importance
spellingShingle Pavel V. Matrenin
Dmitry A. Harlashkin
Marina V. Mazunina
Alexandra I. Khalyasmaa
Investigation of the Features Influencing the Accuracy of Wind Turbine Power Calculation at Short-Term Intervals
Applied System Innovation
wind turbine
wind power forecasting
power curve
ensemble models
machine learning
feature importance
title Investigation of the Features Influencing the Accuracy of Wind Turbine Power Calculation at Short-Term Intervals
title_full Investigation of the Features Influencing the Accuracy of Wind Turbine Power Calculation at Short-Term Intervals
title_fullStr Investigation of the Features Influencing the Accuracy of Wind Turbine Power Calculation at Short-Term Intervals
title_full_unstemmed Investigation of the Features Influencing the Accuracy of Wind Turbine Power Calculation at Short-Term Intervals
title_short Investigation of the Features Influencing the Accuracy of Wind Turbine Power Calculation at Short-Term Intervals
title_sort investigation of the features influencing the accuracy of wind turbine power calculation at short term intervals
topic wind turbine
wind power forecasting
power curve
ensemble models
machine learning
feature importance
url https://www.mdpi.com/2571-5577/7/6/105
work_keys_str_mv AT pavelvmatrenin investigationofthefeaturesinfluencingtheaccuracyofwindturbinepowercalculationatshorttermintervals
AT dmitryaharlashkin investigationofthefeaturesinfluencingtheaccuracyofwindturbinepowercalculationatshorttermintervals
AT marinavmazunina investigationofthefeaturesinfluencingtheaccuracyofwindturbinepowercalculationatshorttermintervals
AT alexandraikhalyasmaa investigationofthefeaturesinfluencingtheaccuracyofwindturbinepowercalculationatshorttermintervals