Predicting the power grid frequency of European islands
Modelling, forecasting and overall understanding of the dynamics of the power grid and its frequency are essential for the safe operation of existing and future power grids. Much previous research was focused on large continental areas, while small systems, such as islands are less well-studied. The...
Published in: | Journal of Physics: Complexity |
---|---|
Main Authors: | , , , , , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
IOP Publishing
2023
|
Subjects: | |
Online Access: | https://doi.org/10.1088/2632-072X/acbd7f https://doaj.org/article/52c125afd1d046389873b72257af7070 |
id |
ftdoajarticles:oai:doaj.org/article:52c125afd1d046389873b72257af7070 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:52c125afd1d046389873b72257af7070 2023-06-11T04:11:36+02:00 Predicting the power grid frequency of European islands Thorbjørn Lund Onsaker Heidi S Nygård Damiá Gomila Pere Colet Ralf Mikut Richard Jumar Heiko Maass Uwe Kühnapfel Veit Hagenmeyer Benjamin Schäfer 2023-01-01T00:00:00Z https://doi.org/10.1088/2632-072X/acbd7f https://doaj.org/article/52c125afd1d046389873b72257af7070 EN eng IOP Publishing https://doi.org/10.1088/2632-072X/acbd7f https://doaj.org/toc/2632-072X doi:10.1088/2632-072X/acbd7f 2632-072X https://doaj.org/article/52c125afd1d046389873b72257af7070 Journal of Physics: Complexity, Vol 4, Iss 1, p 015012 (2023) Machine learning forecasting power grid time series analysis Europe frequency synchronisation Science Q Physics QC1-999 article 2023 ftdoajarticles https://doi.org/10.1088/2632-072X/acbd7f 2023-04-23T00:34:49Z Modelling, forecasting and overall understanding of the dynamics of the power grid and its frequency are essential for the safe operation of existing and future power grids. Much previous research was focused on large continental areas, while small systems, such as islands are less well-studied. These natural island systems are ideal testing environments for microgrid proposals and artificially islanded grid operation. In the present paper, we utilise measurements of the power grid frequency obtained in European islands: the Faroe Islands, Ireland, the Balearic Islands and Iceland and investigate how their frequency can be predicted, compared to the Nordic power system, acting as a reference. The Balearic Islands are found to be particularly deterministic and easy to predict in contrast to hard-to-predict Iceland. Furthermore, we show that typically 2–4 weeks of data are needed to improve prediction performance beyond simple benchmarks. Article in Journal/Newspaper Faroe Islands Iceland Directory of Open Access Journals: DOAJ Articles Faroe Islands Journal of Physics: Complexity 4 1 015012 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
Machine learning forecasting power grid time series analysis Europe frequency synchronisation Science Q Physics QC1-999 |
spellingShingle |
Machine learning forecasting power grid time series analysis Europe frequency synchronisation Science Q Physics QC1-999 Thorbjørn Lund Onsaker Heidi S Nygård Damiá Gomila Pere Colet Ralf Mikut Richard Jumar Heiko Maass Uwe Kühnapfel Veit Hagenmeyer Benjamin Schäfer Predicting the power grid frequency of European islands |
topic_facet |
Machine learning forecasting power grid time series analysis Europe frequency synchronisation Science Q Physics QC1-999 |
description |
Modelling, forecasting and overall understanding of the dynamics of the power grid and its frequency are essential for the safe operation of existing and future power grids. Much previous research was focused on large continental areas, while small systems, such as islands are less well-studied. These natural island systems are ideal testing environments for microgrid proposals and artificially islanded grid operation. In the present paper, we utilise measurements of the power grid frequency obtained in European islands: the Faroe Islands, Ireland, the Balearic Islands and Iceland and investigate how their frequency can be predicted, compared to the Nordic power system, acting as a reference. The Balearic Islands are found to be particularly deterministic and easy to predict in contrast to hard-to-predict Iceland. Furthermore, we show that typically 2–4 weeks of data are needed to improve prediction performance beyond simple benchmarks. |
format |
Article in Journal/Newspaper |
author |
Thorbjørn Lund Onsaker Heidi S Nygård Damiá Gomila Pere Colet Ralf Mikut Richard Jumar Heiko Maass Uwe Kühnapfel Veit Hagenmeyer Benjamin Schäfer |
author_facet |
Thorbjørn Lund Onsaker Heidi S Nygård Damiá Gomila Pere Colet Ralf Mikut Richard Jumar Heiko Maass Uwe Kühnapfel Veit Hagenmeyer Benjamin Schäfer |
author_sort |
Thorbjørn Lund Onsaker |
title |
Predicting the power grid frequency of European islands |
title_short |
Predicting the power grid frequency of European islands |
title_full |
Predicting the power grid frequency of European islands |
title_fullStr |
Predicting the power grid frequency of European islands |
title_full_unstemmed |
Predicting the power grid frequency of European islands |
title_sort |
predicting the power grid frequency of european islands |
publisher |
IOP Publishing |
publishDate |
2023 |
url |
https://doi.org/10.1088/2632-072X/acbd7f https://doaj.org/article/52c125afd1d046389873b72257af7070 |
geographic |
Faroe Islands |
geographic_facet |
Faroe Islands |
genre |
Faroe Islands Iceland |
genre_facet |
Faroe Islands Iceland |
op_source |
Journal of Physics: Complexity, Vol 4, Iss 1, p 015012 (2023) |
op_relation |
https://doi.org/10.1088/2632-072X/acbd7f https://doaj.org/toc/2632-072X doi:10.1088/2632-072X/acbd7f 2632-072X https://doaj.org/article/52c125afd1d046389873b72257af7070 |
op_doi |
https://doi.org/10.1088/2632-072X/acbd7f |
container_title |
Journal of Physics: Complexity |
container_volume |
4 |
container_issue |
1 |
container_start_page |
015012 |
_version_ |
1768386780871000064 |