Matches in SemOpenAlex for { <https://semopenalex.org/work/W4315777675> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4315777675 abstract "Beam management has been considered as one of the most challenging issues in mobile communications, especially in non-terrestrial networks with high-speed low-earth orbit satellites. When the user and the satellite are moving, the satellite equipped with multiple antennas needs to sweep different beam directions periodically to provide continuous service to the user. To reduce the signaling overhead in beam sweeping, we develop a recurrent graph neural network (RGNN) to predict the next beam direction that maximizes the signal strength. Compared with state-of-the-art recurrent neural networks with gated recurrent units (GRU), RGNN reduces the number of training parameters by 99.8% by exploiting a graph representation of the beams. To improve the generalization ability of RGNN in satellite communications with dynamic antenna directions, we integrate RGNN with a first-order meta-learning algorithm. After meta training, no sample is required to fine-tune the RGNN in unseen scenarios, and this approach is referred to as zero-shot meta-learning. Our simulation results show that the RGNN outperforms the GRU in terms of the convergence time and generalization ability, and the prediction accuracy with zero-shot meta-learning can be up to 97%. Even for unseen antenna directions, instead of sweeping all the neighboring beam directions, the satellite only needs to send reference signals towards few beam directions (e.g., two out of six neighboring beam directions) according to the output of the RGNN. In this way, the signaling overhead for beam sweeping can be reduced by 66%." @default.
- W4315777675 created "2023-01-13" @default.
- W4315777675 creator A5043371405 @default.
- W4315777675 creator A5046529904 @default.
- W4315777675 creator A5057320824 @default.
- W4315777675 creator A5061656949 @default.
- W4315777675 creator A5079772530 @default.
- W4315777675 creator A5081782440 @default.
- W4315777675 date "2022-12-04" @default.
- W4315777675 modified "2023-10-02" @default.
- W4315777675 title "Zero-Shot Recurrent Graph Neural Networks for Beam Prediction in Non-Terrestrial Networks" @default.
- W4315777675 cites W2014925754 @default.
- W4315777675 cites W2936608441 @default.
- W4315777675 cites W2971598376 @default.
- W4315777675 cites W3089706104 @default.
- W4315777675 cites W3093835058 @default.
- W4315777675 cites W3104650338 @default.
- W4315777675 cites W3178636644 @default.
- W4315777675 cites W3192973400 @default.
- W4315777675 cites W3206701721 @default.
- W4315777675 cites W3212093355 @default.
- W4315777675 cites W4285049557 @default.
- W4315777675 doi "https://doi.org/10.1109/gcwkshps56602.2022.10008701" @default.
- W4315777675 hasPublicationYear "2022" @default.
- W4315777675 type Work @default.
- W4315777675 citedByCount "0" @default.
- W4315777675 crossrefType "proceedings-article" @default.
- W4315777675 hasAuthorship W4315777675A5043371405 @default.
- W4315777675 hasAuthorship W4315777675A5046529904 @default.
- W4315777675 hasAuthorship W4315777675A5057320824 @default.
- W4315777675 hasAuthorship W4315777675A5061656949 @default.
- W4315777675 hasAuthorship W4315777675A5079772530 @default.
- W4315777675 hasAuthorship W4315777675A5081782440 @default.
- W4315777675 hasConcept C111919701 @default.
- W4315777675 hasConcept C11413529 @default.
- W4315777675 hasConcept C120665830 @default.
- W4315777675 hasConcept C121332964 @default.
- W4315777675 hasConcept C127413603 @default.
- W4315777675 hasConcept C132525143 @default.
- W4315777675 hasConcept C146978453 @default.
- W4315777675 hasConcept C147168706 @default.
- W4315777675 hasConcept C154945302 @default.
- W4315777675 hasConcept C168834538 @default.
- W4315777675 hasConcept C19269812 @default.
- W4315777675 hasConcept C2779960059 @default.
- W4315777675 hasConcept C41008148 @default.
- W4315777675 hasConcept C50644808 @default.
- W4315777675 hasConcept C80444323 @default.
- W4315777675 hasConceptScore W4315777675C111919701 @default.
- W4315777675 hasConceptScore W4315777675C11413529 @default.
- W4315777675 hasConceptScore W4315777675C120665830 @default.
- W4315777675 hasConceptScore W4315777675C121332964 @default.
- W4315777675 hasConceptScore W4315777675C127413603 @default.
- W4315777675 hasConceptScore W4315777675C132525143 @default.
- W4315777675 hasConceptScore W4315777675C146978453 @default.
- W4315777675 hasConceptScore W4315777675C147168706 @default.
- W4315777675 hasConceptScore W4315777675C154945302 @default.
- W4315777675 hasConceptScore W4315777675C168834538 @default.
- W4315777675 hasConceptScore W4315777675C19269812 @default.
- W4315777675 hasConceptScore W4315777675C2779960059 @default.
- W4315777675 hasConceptScore W4315777675C41008148 @default.
- W4315777675 hasConceptScore W4315777675C50644808 @default.
- W4315777675 hasConceptScore W4315777675C80444323 @default.
- W4315777675 hasLocation W43157776751 @default.
- W4315777675 hasOpenAccess W4315777675 @default.
- W4315777675 hasPrimaryLocation W43157776751 @default.
- W4315777675 hasRelatedWork W2028024605 @default.
- W4315777675 hasRelatedWork W2102105610 @default.
- W4315777675 hasRelatedWork W2357857148 @default.
- W4315777675 hasRelatedWork W2386387936 @default.
- W4315777675 hasRelatedWork W2625550807 @default.
- W4315777675 hasRelatedWork W2767525681 @default.
- W4315777675 hasRelatedWork W2800726910 @default.
- W4315777675 hasRelatedWork W2902723393 @default.
- W4315777675 hasRelatedWork W3107474891 @default.
- W4315777675 hasRelatedWork W4242263690 @default.
- W4315777675 isParatext "false" @default.
- W4315777675 isRetracted "false" @default.
- W4315777675 workType "article" @default.