Probabilistic forecasts of wind power generation in regions with complex topography using deep learning methods: An Arctic case
The energy market relies on forecasting capabilities of both demand and power generation that need to be kept in dynamic balance. Nowadays, contracts and auctions of renewable energy in a liberalized electricity market heavily rely on forecasting future power generation. The highly intermittent natu...
Published in: | Energy Conversion and Management: X |
---|---|
Main Authors: | , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Elsevier
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/10037/27600 https://doi.org/10.1016/j.ecmx.2022.100239 |
id |
ftunivtroemsoe:oai:munin.uit.no:10037/27600 |
---|---|
record_format |
openpolar |
spelling |
ftunivtroemsoe:oai:munin.uit.no:10037/27600 2023-11-05T03:37:50+01:00 Probabilistic forecasts of wind power generation in regions with complex topography using deep learning methods: An Arctic case Foldvik Eikeland, Odin Hovem, Finn Dag Olsen, Tom Eirik Chiesa, Matteo Bianchi, Filippo Maria 2022-05-27 https://hdl.handle.net/10037/27600 https://doi.org/10.1016/j.ecmx.2022.100239 eng eng Elsevier Eikeland, O.F. (2023). Enhancing Decision-making in the Electric Power Sector with Machine Learning and Optimization. (Doctoral thesis). https://hdl.handle.net/10037/31514 . Energy Conversion and Management: X https://pdf.sciencedirectassets.com/320469/1-s2.0-S2590174522X00032/1-s2.0-S2590174522000629/main.pdf?X-Amz-Security-Token=IQoJb3JpZ2luX2VjEK7%2F%2F%2F%2F%2F%2F%2F%2F%2F%2FwEaCXVzLWVhc3QtMSJGMEQCIEMYz Foldvik Eikeland, Hovem, Olsen, Chiesa, Bianchi. Probabilistic forecasts of wind power generation in regions with complex topography using deep learning methods: An Arctic case. Energy Conversion and Management: X. 2022;15 FRIDAID 2053510 doi:10.1016/j.ecmx.2022.100239 2590-1745 https://hdl.handle.net/10037/27600 Attribution 4.0 International (CC BY 4.0) openAccess Copyright 2022 The Author(s) https://creativecommons.org/licenses/by/4.0 VDP::Teknologi: 500::Miljøteknologi: 610 VDP::Technology: 500::Environmental engineering: 610 Deep learning / Deep learning Energidataanalyse / Energy analytics Vindkraft / Wind power Journal article Tidsskriftartikkel Peer reviewed publishedVersion 2022 ftunivtroemsoe https://doi.org/10.1016/j.ecmx.2022.100239 2023-10-11T23:07:51Z The energy market relies on forecasting capabilities of both demand and power generation that need to be kept in dynamic balance. Nowadays, contracts and auctions of renewable energy in a liberalized electricity market heavily rely on forecasting future power generation. The highly intermittent nature of renewable energy sources increases the uncertainty about future power generation. Since point forecast does not account for such uncertainties, it is necessary to rely on probabilistic forecasts. This work first introduces probabilistic forecasts with deep learning. Then, we show how deep learning models can be used to make probabilistic forecasts of day-ahead power generation from a wind power plant located in Northern Norway. The performance, in terms of the quality of the prediction intervals, is compared to different deep learning models and sets of covariates. The findings show that the accuracy of the predictions improves by 37% when historical data on measured weather and numerical weather predictions (NWPs) were included as exogenous variables. In particular, historical data allows the model to auto-correct systematic biases in the NWPs. Finally, we observe that when using only NWPs or only measured weather as exogenous variables, worse performances are obtained. The work shows the importance of understanding which variables must be included to improve the prediction performance, which is of fundamental value for the energy market that relies on accurate forecasting capabilities. Article in Journal/Newspaper Arctic Arctic Northern Norway University of Tromsø: Munin Open Research Archive Energy Conversion and Management: X 15 100239 |
institution |
Open Polar |
collection |
University of Tromsø: Munin Open Research Archive |
op_collection_id |
ftunivtroemsoe |
language |
English |
topic |
VDP::Teknologi: 500::Miljøteknologi: 610 VDP::Technology: 500::Environmental engineering: 610 Deep learning / Deep learning Energidataanalyse / Energy analytics Vindkraft / Wind power |
spellingShingle |
VDP::Teknologi: 500::Miljøteknologi: 610 VDP::Technology: 500::Environmental engineering: 610 Deep learning / Deep learning Energidataanalyse / Energy analytics Vindkraft / Wind power Foldvik Eikeland, Odin Hovem, Finn Dag Olsen, Tom Eirik Chiesa, Matteo Bianchi, Filippo Maria Probabilistic forecasts of wind power generation in regions with complex topography using deep learning methods: An Arctic case |
topic_facet |
VDP::Teknologi: 500::Miljøteknologi: 610 VDP::Technology: 500::Environmental engineering: 610 Deep learning / Deep learning Energidataanalyse / Energy analytics Vindkraft / Wind power |
description |
The energy market relies on forecasting capabilities of both demand and power generation that need to be kept in dynamic balance. Nowadays, contracts and auctions of renewable energy in a liberalized electricity market heavily rely on forecasting future power generation. The highly intermittent nature of renewable energy sources increases the uncertainty about future power generation. Since point forecast does not account for such uncertainties, it is necessary to rely on probabilistic forecasts. This work first introduces probabilistic forecasts with deep learning. Then, we show how deep learning models can be used to make probabilistic forecasts of day-ahead power generation from a wind power plant located in Northern Norway. The performance, in terms of the quality of the prediction intervals, is compared to different deep learning models and sets of covariates. The findings show that the accuracy of the predictions improves by 37% when historical data on measured weather and numerical weather predictions (NWPs) were included as exogenous variables. In particular, historical data allows the model to auto-correct systematic biases in the NWPs. Finally, we observe that when using only NWPs or only measured weather as exogenous variables, worse performances are obtained. The work shows the importance of understanding which variables must be included to improve the prediction performance, which is of fundamental value for the energy market that relies on accurate forecasting capabilities. |
format |
Article in Journal/Newspaper |
author |
Foldvik Eikeland, Odin Hovem, Finn Dag Olsen, Tom Eirik Chiesa, Matteo Bianchi, Filippo Maria |
author_facet |
Foldvik Eikeland, Odin Hovem, Finn Dag Olsen, Tom Eirik Chiesa, Matteo Bianchi, Filippo Maria |
author_sort |
Foldvik Eikeland, Odin |
title |
Probabilistic forecasts of wind power generation in regions with complex topography using deep learning methods: An Arctic case |
title_short |
Probabilistic forecasts of wind power generation in regions with complex topography using deep learning methods: An Arctic case |
title_full |
Probabilistic forecasts of wind power generation in regions with complex topography using deep learning methods: An Arctic case |
title_fullStr |
Probabilistic forecasts of wind power generation in regions with complex topography using deep learning methods: An Arctic case |
title_full_unstemmed |
Probabilistic forecasts of wind power generation in regions with complex topography using deep learning methods: An Arctic case |
title_sort |
probabilistic forecasts of wind power generation in regions with complex topography using deep learning methods: an arctic case |
publisher |
Elsevier |
publishDate |
2022 |
url |
https://hdl.handle.net/10037/27600 https://doi.org/10.1016/j.ecmx.2022.100239 |
genre |
Arctic Arctic Northern Norway |
genre_facet |
Arctic Arctic Northern Norway |
op_relation |
Eikeland, O.F. (2023). Enhancing Decision-making in the Electric Power Sector with Machine Learning and Optimization. (Doctoral thesis). https://hdl.handle.net/10037/31514 . Energy Conversion and Management: X https://pdf.sciencedirectassets.com/320469/1-s2.0-S2590174522X00032/1-s2.0-S2590174522000629/main.pdf?X-Amz-Security-Token=IQoJb3JpZ2luX2VjEK7%2F%2F%2F%2F%2F%2F%2F%2F%2F%2FwEaCXVzLWVhc3QtMSJGMEQCIEMYz Foldvik Eikeland, Hovem, Olsen, Chiesa, Bianchi. Probabilistic forecasts of wind power generation in regions with complex topography using deep learning methods: An Arctic case. Energy Conversion and Management: X. 2022;15 FRIDAID 2053510 doi:10.1016/j.ecmx.2022.100239 2590-1745 https://hdl.handle.net/10037/27600 |
op_rights |
Attribution 4.0 International (CC BY 4.0) openAccess Copyright 2022 The Author(s) https://creativecommons.org/licenses/by/4.0 |
op_doi |
https://doi.org/10.1016/j.ecmx.2022.100239 |
container_title |
Energy Conversion and Management: X |
container_volume |
15 |
container_start_page |
100239 |
_version_ |
1781693546626023424 |