Centralized and Decentralized ML-Enabled Integrated Terrestrial and Non-Terrestrial Networks
Non-terrestrial networks (NTNs) are a critical enabler of the persistent connectivity vision of sixth-generation networks, as they can service areas where terrestrial infrastructure falls short. However, the integration of these networks with the terrestrial network is laden with obstacles. The dyna...
Published in: | 2023 IEEE Future Networks World Forum (FNWF) |
---|---|
Main Authors: | , , , , |
Format: | Conference Object |
Language: | English |
Published: |
Zenodo
2024
|
Subjects: | |
Online Access: | https://doi.org/10.1109/FNWF58287.2023.10520439 |
id |
ftzenodo:oai:zenodo.org:12546900 |
---|---|
record_format |
openpolar |
spelling |
ftzenodo:oai:zenodo.org:12546900 2024-09-15T18:03:49+00:00 Centralized and Decentralized ML-Enabled Integrated Terrestrial and Non-Terrestrial Networks Ali Aygül, Mehmet Türkmen, Halise Izzet Saglam, Mehmet Ali Cirpan, Hakan Arslan, Hüseyin 2024-05-13 https://doi.org/10.1109/FNWF58287.2023.10520439 eng eng Zenodo https://doi.org/10.1109/FNWF58287.2023.10520439 oai:zenodo.org:12546900 info:eu-repo/semantics/openAccess Creative Commons Attribution Share Alike 4.0 International https://creativecommons.org/licenses/by-sa/4.0/legalcode FNWF, IEEE Future Networks World Forum, Baltimore, MD, USA, 13–15 November 2023 5G 4G Internet of things Artificial intelligence Smart sensors info:eu-repo/semantics/conferencePaper 2024 ftzenodo https://doi.org/10.1109/FNWF58287.2023.10520439 2024-07-26T06:00:14Z Non-terrestrial networks (NTNs) are a critical enabler of the persistent connectivity vision of sixth-generation networks, as they can service areas where terrestrial infrastructure falls short. However, the integration of these networks with the terrestrial network is laden with obstacles. The dynamic nature of NTN communication scenarios and numerous variables render conventional model-based solutions computationally costly and impracticable for resource allocation, parameter optimization, and other problems. Machine learning (ML)-based solutions, thus, can perform a pivotal role due to their inherent ability to uncover the hidden patterns in time-varying, multi-dimensional data with superior performance and less complexity. Centralized ML (CML) and decentralized ML (DML), named so based on the distribution of the data and computational load, are two classes of ML that are being studied as solutions for the various complications of terrestrial and non-terrestrial networks (TNTN) integration. Both have their benefits and drawbacks under different circumstances, and it is integral to choose the appropriate ML approach for each TNTN integration issue. To this end, this paper goes over the TNTN integration architectures as given in the 3rd generation partnership project standard releases, proposing possible scenarios. Then, the capabilities and challenges of CML and DML are explored from the vantage point of these scenarios. Conference Object DML Zenodo 2023 IEEE Future Networks World Forum (FNWF) 1 6 |
institution |
Open Polar |
collection |
Zenodo |
op_collection_id |
ftzenodo |
language |
English |
topic |
5G 4G Internet of things Artificial intelligence Smart sensors |
spellingShingle |
5G 4G Internet of things Artificial intelligence Smart sensors Ali Aygül, Mehmet Türkmen, Halise Izzet Saglam, Mehmet Ali Cirpan, Hakan Arslan, Hüseyin Centralized and Decentralized ML-Enabled Integrated Terrestrial and Non-Terrestrial Networks |
topic_facet |
5G 4G Internet of things Artificial intelligence Smart sensors |
description |
Non-terrestrial networks (NTNs) are a critical enabler of the persistent connectivity vision of sixth-generation networks, as they can service areas where terrestrial infrastructure falls short. However, the integration of these networks with the terrestrial network is laden with obstacles. The dynamic nature of NTN communication scenarios and numerous variables render conventional model-based solutions computationally costly and impracticable for resource allocation, parameter optimization, and other problems. Machine learning (ML)-based solutions, thus, can perform a pivotal role due to their inherent ability to uncover the hidden patterns in time-varying, multi-dimensional data with superior performance and less complexity. Centralized ML (CML) and decentralized ML (DML), named so based on the distribution of the data and computational load, are two classes of ML that are being studied as solutions for the various complications of terrestrial and non-terrestrial networks (TNTN) integration. Both have their benefits and drawbacks under different circumstances, and it is integral to choose the appropriate ML approach for each TNTN integration issue. To this end, this paper goes over the TNTN integration architectures as given in the 3rd generation partnership project standard releases, proposing possible scenarios. Then, the capabilities and challenges of CML and DML are explored from the vantage point of these scenarios. |
format |
Conference Object |
author |
Ali Aygül, Mehmet Türkmen, Halise Izzet Saglam, Mehmet Ali Cirpan, Hakan Arslan, Hüseyin |
author_facet |
Ali Aygül, Mehmet Türkmen, Halise Izzet Saglam, Mehmet Ali Cirpan, Hakan Arslan, Hüseyin |
author_sort |
Ali Aygül, Mehmet |
title |
Centralized and Decentralized ML-Enabled Integrated Terrestrial and Non-Terrestrial Networks |
title_short |
Centralized and Decentralized ML-Enabled Integrated Terrestrial and Non-Terrestrial Networks |
title_full |
Centralized and Decentralized ML-Enabled Integrated Terrestrial and Non-Terrestrial Networks |
title_fullStr |
Centralized and Decentralized ML-Enabled Integrated Terrestrial and Non-Terrestrial Networks |
title_full_unstemmed |
Centralized and Decentralized ML-Enabled Integrated Terrestrial and Non-Terrestrial Networks |
title_sort |
centralized and decentralized ml-enabled integrated terrestrial and non-terrestrial networks |
publisher |
Zenodo |
publishDate |
2024 |
url |
https://doi.org/10.1109/FNWF58287.2023.10520439 |
genre |
DML |
genre_facet |
DML |
op_source |
FNWF, IEEE Future Networks World Forum, Baltimore, MD, USA, 13–15 November 2023 |
op_relation |
https://doi.org/10.1109/FNWF58287.2023.10520439 oai:zenodo.org:12546900 |
op_rights |
info:eu-repo/semantics/openAccess Creative Commons Attribution Share Alike 4.0 International https://creativecommons.org/licenses/by-sa/4.0/legalcode |
op_doi |
https://doi.org/10.1109/FNWF58287.2023.10520439 |
container_title |
2023 IEEE Future Networks World Forum (FNWF) |
container_start_page |
1 |
op_container_end_page |
6 |
_version_ |
1810441282531622912 |