SemOpenAlex |

SemOpenAlex

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313443611> ?p ?o ?g. }

Showing items 1 to 99 of 99 with 100 items per page.

W4313443611 endingPage "120565" @default.
W4313443611 startingPage "120565" @default.
W4313443611 abstract "This study focuses on multi-step spatio-temporal wind speed forecasting for the Norwegian continental shelf. The study aims to leverage spatial dependencies through the relative physical location of different measurement stations to improve local wind forecasts. Our multi-step forecasting models produce either 10-minute, 1- or 4-hour forecasts, with 10-minute resolution, meaning that the models produce more informative time series for predicted future trends. A graph neural network (GNN) architecture was used to extract spatial dependencies, with different update functions to learn temporal correlations. These update functions were implemented using different neural network architectures. One such architecture, the Transformer, has become increasingly popular for sequence modelling in recent years. Various alterations have been proposed to better facilitate time series forecasting, of which this study focused on the Informer, LogSparse Transformer and Autoformer. This is the first time the LogSparse Transformer and Autoformer have been applied to wind forecasting and the first time any of these or the Informer have been formulated in a spatio-temporal setting for wind forecasting. By comparing against spatio-temporal Long Short-Term Memory (LSTM) and Multi-Layer Perceptron (MLP) models, the study showed that the models using the altered Transformer architectures as update functions in GNNs were able to outperform these. Furthermore, we propose the Fast Fourier Transformer (FFTransformer), which is a novel Transformer architecture based on signal decomposition and consists of two separate streams that analyse the trend and periodic components separately. The FFTransformer and Autoformer were found to achieve superior results for the 10-minute and 1-hour ahead forecasts, with the FFTransformer significantly outperforming all other models for the 4-hour ahead forecasts." @default.
W4313443611 created "2023-01-06" @default.
W4313443611 creator A5015174757 @default.
W4313443611 creator A5033850106 @default.
W4313443611 creator A5088173483 @default.
W4313443611 creator A5090446312 @default.
W4313443611 date "2023-03-01" @default.
W4313443611 modified "2023-10-18" @default.
W4313443611 title "Spatio-temporal wind speed forecasting using graph networks and novel Transformer architectures" @default.
W4313443611 cites W1968378534 @default.
W4313443611 cites W1969927657 @default.
W4313443611 cites W1984061847 @default.
W4313443611 cites W1989092102 @default.
W4313443611 cites W2034954612 @default.
W4313443611 cites W2036681246 @default.
W4313443611 cites W2064675550 @default.
W4313443611 cites W2067201152 @default.
W4313443611 cites W2073004501 @default.
W4313443611 cites W2076492086 @default.
W4313443611 cites W2272499513 @default.
W4313443611 cites W2284726324 @default.
W4313443611 cites W2469077086 @default.
W4313443611 cites W2511683089 @default.
W4313443611 cites W2801503429 @default.
W4313443611 cites W2807252330 @default.
W4313443611 cites W2884486887 @default.
W4313443611 cites W2910279921 @default.
W4313443611 cites W2913872388 @default.
W4313443611 cites W2949676527 @default.
W4313443611 cites W2986268142 @default.
W4313443611 cites W3004665554 @default.
W4313443611 cites W3016252900 @default.
W4313443611 cites W3034467175 @default.
W4313443611 cites W3135523675 @default.
W4313443611 cites W3136101012 @default.
W4313443611 cites W3171884590 @default.
W4313443611 cites W3173985852 @default.
W4313443611 cites W3177318507 @default.
W4313443611 cites W3200304500 @default.
W4313443611 cites W4220801201 @default.
W4313443611 cites W4223651176 @default.
W4313443611 cites W4223926961 @default.
W4313443611 cites W4224981792 @default.
W4313443611 cites W4226065447 @default.
W4313443611 cites W4285725512 @default.
W4313443611 cites W4287729747 @default.
W4313443611 doi "https://doi.org/10.1016/j.apenergy.2022.120565" @default.
W4313443611 hasPublicationYear "2023" @default.
W4313443611 type Work @default.
W4313443611 citedByCount "12" @default.
W4313443611 countsByYear W43134436112023 @default.
W4313443611 crossrefType "journal-article" @default.
W4313443611 hasAuthorship W4313443611A5015174757 @default.
W4313443611 hasAuthorship W4313443611A5033850106 @default.
W4313443611 hasAuthorship W4313443611A5088173483 @default.
W4313443611 hasAuthorship W4313443611A5090446312 @default.
W4313443611 hasBestOaLocation W43134436111 @default.
W4313443611 hasConcept C119599485 @default.
W4313443611 hasConcept C124101348 @default.
W4313443611 hasConcept C127413603 @default.
W4313443611 hasConcept C153294291 @default.
W4313443611 hasConcept C154945302 @default.
W4313443611 hasConcept C161067210 @default.
W4313443611 hasConcept C165801399 @default.
W4313443611 hasConcept C205649164 @default.
W4313443611 hasConcept C41008148 @default.
W4313443611 hasConcept C66322947 @default.
W4313443611 hasConceptScore W4313443611C119599485 @default.
W4313443611 hasConceptScore W4313443611C124101348 @default.
W4313443611 hasConceptScore W4313443611C127413603 @default.
W4313443611 hasConceptScore W4313443611C153294291 @default.
W4313443611 hasConceptScore W4313443611C154945302 @default.
W4313443611 hasConceptScore W4313443611C161067210 @default.
W4313443611 hasConceptScore W4313443611C165801399 @default.
W4313443611 hasConceptScore W4313443611C205649164 @default.
W4313443611 hasConceptScore W4313443611C41008148 @default.
W4313443611 hasConceptScore W4313443611C66322947 @default.
W4313443611 hasLocation W43134436111 @default.
W4313443611 hasLocation W43134436112 @default.
W4313443611 hasLocation W43134436113 @default.
W4313443611 hasLocation W43134436114 @default.
W4313443611 hasOpenAccess W4313443611 @default.
W4313443611 hasPrimaryLocation W43134436111 @default.
W4313443611 hasRelatedWork W2347219288 @default.
W4313443611 hasRelatedWork W2350741829 @default.
W4313443611 hasRelatedWork W2358668433 @default.
W4313443611 hasRelatedWork W2366221835 @default.
W4313443611 hasRelatedWork W2376932109 @default.
W4313443611 hasRelatedWork W2382290278 @default.
W4313443611 hasRelatedWork W2390279801 @default.
W4313443611 hasRelatedWork W2748952813 @default.
W4313443611 hasRelatedWork W2899084033 @default.
W4313443611 hasRelatedWork W3004735627 @default.
W4313443611 hasVolume "333" @default.
W4313443611 isParatext "false" @default.
W4313443611 isRetracted "false" @default.
W4313443611 workType "article" @default.