Data-driven Arctic wind energy analysis by statistical and machine learning approaches
Norway's Arctic region is rich in wind resources and developing wind energy in the region can promote a green transition and economic development. However, the region's unique topography with fjords and mountains and cold climate conditions make wind resource assessment, generation analysi...
Main Author: | |
---|---|
Format: | Doctoral or Postdoctoral Thesis |
Language: | English |
Published: |
UiT Norges arktiske universitet
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/10037/26938 |
id |
ftunivtroemsoe:oai:munin.uit.no:10037/26938 |
---|---|
record_format |
openpolar |
institution |
Open Polar |
collection |
University of Tromsø: Munin Open Research Archive |
op_collection_id |
ftunivtroemsoe |
language |
English |
topic |
VDP::Mathematics and natural science: 400::Information and communication science: 420::Mathematical modeling and numerical methods: 427 VDP::Matematikk og Naturvitenskap: 400::Informasjons- og kommunikasjonsvitenskap: 420::Matematisk modellering og numeriske metoder: 427 VDP::Mathematics and natural science: 400::Information and communication science: 420::Simulation visualization signal processing image processing: 429 VDP::Matematikk og Naturvitenskap: 400::Informasjons- og kommunikasjonsvitenskap: 420::Simulering visualisering signalbehandling bildeanalyse: 429 VDP::Technology: 500::Electrotechnical disciplines: 540::Electrical power engineering: 542 VDP::Teknologi: 500::Elektrotekniske fag: 540::Elkraft: 542 DOKTOR-004 |
spellingShingle |
VDP::Mathematics and natural science: 400::Information and communication science: 420::Mathematical modeling and numerical methods: 427 VDP::Matematikk og Naturvitenskap: 400::Informasjons- og kommunikasjonsvitenskap: 420::Matematisk modellering og numeriske metoder: 427 VDP::Mathematics and natural science: 400::Information and communication science: 420::Simulation visualization signal processing image processing: 429 VDP::Matematikk og Naturvitenskap: 400::Informasjons- og kommunikasjonsvitenskap: 420::Simulering visualisering signalbehandling bildeanalyse: 429 VDP::Technology: 500::Electrotechnical disciplines: 540::Electrical power engineering: 542 VDP::Teknologi: 500::Elektrotekniske fag: 540::Elkraft: 542 DOKTOR-004 Chen, Hao Data-driven Arctic wind energy analysis by statistical and machine learning approaches |
topic_facet |
VDP::Mathematics and natural science: 400::Information and communication science: 420::Mathematical modeling and numerical methods: 427 VDP::Matematikk og Naturvitenskap: 400::Informasjons- og kommunikasjonsvitenskap: 420::Matematisk modellering og numeriske metoder: 427 VDP::Mathematics and natural science: 400::Information and communication science: 420::Simulation visualization signal processing image processing: 429 VDP::Matematikk og Naturvitenskap: 400::Informasjons- og kommunikasjonsvitenskap: 420::Simulering visualisering signalbehandling bildeanalyse: 429 VDP::Technology: 500::Electrotechnical disciplines: 540::Electrical power engineering: 542 VDP::Teknologi: 500::Elektrotekniske fag: 540::Elkraft: 542 DOKTOR-004 |
description |
Norway's Arctic region is rich in wind resources and developing wind energy in the region can promote a green transition and economic development. However, the region's unique topography with fjords and mountains and cold climate conditions make wind resource assessment, generation analysis, and power forecasting particularly challenging. The accumulation of wind data and the emergence of data science give new promise to this issue. “Can advanced statistical and machine learning methods deliver effective and accurate analysis for wind energy in these Arctic landscapes that are characteristics with dramatically fluctuating wind?” The thesis systemically answers the question with the chronological order of the wind power generation process. First, a statistical probabilistic modeling approach is utilized to assess wind energy resources in particular wind speed and its volatility, both from measured and numerically modeled wind data. The accurate assessment results contribute to evaluating wind resources of sites in the Arctic region. Then, we propose a wind power curve model to monitor wind power generation for the Arctic wind park. The model involves quantifying wind turbulence, clustering meteorological data, and ensemble learning and reaching a satisfactory modeling result for the park power curve. Finally, we demonstrate that traditional machine learning methods can be used to make short-term wind power forecasts for the Arctic wind parks, and these forecasts could be improved to some extent by applying appropriate meteorological wind data, as inputs, to the forecasting models. Moreover, we developed a novel approach for turbine forecasting with appropriate data processing techniques, and loading the data into large deep learning models allows for more accurate forecasting in different terrain conditions. Further, we utilized a variety of transfer learning techniques to make it possible to refine the raw data information and transfer large accurate but slow training forecasting models to smaller and faster ... |
format |
Doctoral or Postdoctoral Thesis |
author |
Chen, Hao |
author_facet |
Chen, Hao |
author_sort |
Chen, Hao |
title |
Data-driven Arctic wind energy analysis by statistical and machine learning approaches |
title_short |
Data-driven Arctic wind energy analysis by statistical and machine learning approaches |
title_full |
Data-driven Arctic wind energy analysis by statistical and machine learning approaches |
title_fullStr |
Data-driven Arctic wind energy analysis by statistical and machine learning approaches |
title_full_unstemmed |
Data-driven Arctic wind energy analysis by statistical and machine learning approaches |
title_sort |
data-driven arctic wind energy analysis by statistical and machine learning approaches |
publisher |
UiT Norges arktiske universitet |
publishDate |
2022 |
url |
https://hdl.handle.net/10037/26938 |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic Arctic |
genre_facet |
Arctic Arctic |
op_relation |
Paper I A: Chen, H., Birkelund, Y., Anfinsen, S.N., Staupe-Delgado, R. & Yuan, F. (2021). Assessing probabilistic modeling for wind speed from numerical weather prediction model and observation in the Arctic. Scientific Reports, 11 , 7613. Also available in Munin at https://hdl.handle.net/10037/21754 . Paper I B: Chen, H., Anfinsen, S.N., Birkelund, Y. & Yuan, F. (2021). Probability distributions for wind speed volatility characteristics: A case study of Northern Norway. Energy Reports, 7 , 248-255. Also available in Munin at https://hdl.handle.net/10037/23177 . Paper II: Chen, H. (2022). Cluster-based ensemble learning for wind power modeling from meteorological wind data. Renewable and Sustainable Energy Reviews, 167 , 112652. Also available in Munin at https://hdl.handle.net/10037/26461 . Paper III A: Chen, H., Birkelund, Y., Anfinsen, S.N. & Yuan, F. (2021). Comparative study of data-driven short-term wind power forecasting approaches for the Norwegian Arctic region. Journal of Renewable and Sustainable Energy, 13 (2), 023314. Also available in Munin at https://hdl.handle.net/10037/24533 . Paper III B: Chen, H., Birkelund, Y. & Yuan, F. (2021). Examination of turbulence impacts on ultra-short-term wind power and speed forecasts with machine learning. Energy Reports, 7 (Suppl. 6), 332-338. Also available in Munin at https://hdl.handle.net/10037/23188 . Paper IV: Chen, H., Birkelund, Y. & Qixia, Z. (2021). Data-augmented sequential deep learning for wind power forecasting. Energy Conversion and Management, 248 , 114790. Also available in Munin at https://hdl.handle.net/10037/23515 . Paper V: Chen, H. & Birkelund, Y. Knowledge distillation with error-correcting transfer learning for wind power prediction. (Manuscript). Also available in Researchgate at http://dx.doi.org/10.13140/RG.2.2.12410.57286 . 978-82-8236-497-3 https://hdl.handle.net/10037/26938 |
op_rights |
openAccess Copyright 2022 The Author(s) |
_version_ |
1766302255449899008 |
spelling |
ftunivtroemsoe:oai:munin.uit.no:10037/26938 2023-05-15T14:28:07+02:00 Data-driven Arctic wind energy analysis by statistical and machine learning approaches Chen, Hao 2022-10-14 https://hdl.handle.net/10037/26938 eng eng UiT Norges arktiske universitet UiT The Arctic University of Norway Paper I A: Chen, H., Birkelund, Y., Anfinsen, S.N., Staupe-Delgado, R. & Yuan, F. (2021). Assessing probabilistic modeling for wind speed from numerical weather prediction model and observation in the Arctic. Scientific Reports, 11 , 7613. Also available in Munin at https://hdl.handle.net/10037/21754 . Paper I B: Chen, H., Anfinsen, S.N., Birkelund, Y. & Yuan, F. (2021). Probability distributions for wind speed volatility characteristics: A case study of Northern Norway. Energy Reports, 7 , 248-255. Also available in Munin at https://hdl.handle.net/10037/23177 . Paper II: Chen, H. (2022). Cluster-based ensemble learning for wind power modeling from meteorological wind data. Renewable and Sustainable Energy Reviews, 167 , 112652. Also available in Munin at https://hdl.handle.net/10037/26461 . Paper III A: Chen, H., Birkelund, Y., Anfinsen, S.N. & Yuan, F. (2021). Comparative study of data-driven short-term wind power forecasting approaches for the Norwegian Arctic region. Journal of Renewable and Sustainable Energy, 13 (2), 023314. Also available in Munin at https://hdl.handle.net/10037/24533 . Paper III B: Chen, H., Birkelund, Y. & Yuan, F. (2021). Examination of turbulence impacts on ultra-short-term wind power and speed forecasts with machine learning. Energy Reports, 7 (Suppl. 6), 332-338. Also available in Munin at https://hdl.handle.net/10037/23188 . Paper IV: Chen, H., Birkelund, Y. & Qixia, Z. (2021). Data-augmented sequential deep learning for wind power forecasting. Energy Conversion and Management, 248 , 114790. Also available in Munin at https://hdl.handle.net/10037/23515 . Paper V: Chen, H. & Birkelund, Y. Knowledge distillation with error-correcting transfer learning for wind power prediction. (Manuscript). Also available in Researchgate at http://dx.doi.org/10.13140/RG.2.2.12410.57286 . 978-82-8236-497-3 https://hdl.handle.net/10037/26938 openAccess Copyright 2022 The Author(s) VDP::Mathematics and natural science: 400::Information and communication science: 420::Mathematical modeling and numerical methods: 427 VDP::Matematikk og Naturvitenskap: 400::Informasjons- og kommunikasjonsvitenskap: 420::Matematisk modellering og numeriske metoder: 427 VDP::Mathematics and natural science: 400::Information and communication science: 420::Simulation visualization signal processing image processing: 429 VDP::Matematikk og Naturvitenskap: 400::Informasjons- og kommunikasjonsvitenskap: 420::Simulering visualisering signalbehandling bildeanalyse: 429 VDP::Technology: 500::Electrotechnical disciplines: 540::Electrical power engineering: 542 VDP::Teknologi: 500::Elektrotekniske fag: 540::Elkraft: 542 DOKTOR-004 Doctoral thesis Doktorgradsavhandling 2022 ftunivtroemsoe 2022-10-05T23:00:52Z Norway's Arctic region is rich in wind resources and developing wind energy in the region can promote a green transition and economic development. However, the region's unique topography with fjords and mountains and cold climate conditions make wind resource assessment, generation analysis, and power forecasting particularly challenging. The accumulation of wind data and the emergence of data science give new promise to this issue. “Can advanced statistical and machine learning methods deliver effective and accurate analysis for wind energy in these Arctic landscapes that are characteristics with dramatically fluctuating wind?” The thesis systemically answers the question with the chronological order of the wind power generation process. First, a statistical probabilistic modeling approach is utilized to assess wind energy resources in particular wind speed and its volatility, both from measured and numerically modeled wind data. The accurate assessment results contribute to evaluating wind resources of sites in the Arctic region. Then, we propose a wind power curve model to monitor wind power generation for the Arctic wind park. The model involves quantifying wind turbulence, clustering meteorological data, and ensemble learning and reaching a satisfactory modeling result for the park power curve. Finally, we demonstrate that traditional machine learning methods can be used to make short-term wind power forecasts for the Arctic wind parks, and these forecasts could be improved to some extent by applying appropriate meteorological wind data, as inputs, to the forecasting models. Moreover, we developed a novel approach for turbine forecasting with appropriate data processing techniques, and loading the data into large deep learning models allows for more accurate forecasting in different terrain conditions. Further, we utilized a variety of transfer learning techniques to make it possible to refine the raw data information and transfer large accurate but slow training forecasting models to smaller and faster ... Doctoral or Postdoctoral Thesis Arctic Arctic University of Tromsø: Munin Open Research Archive Arctic |