Link Scheduling in Satellite Networks via Machine Learning Over Riemannian Manifolds
Low Earth Orbit (LEO) satellites play a crucial role in enhancing global connectivity, serving a complementary solution to existing terrestrial systems. In wireless networks, scheduling is a vital process that allocates time-frequency resources to users for interference management. However, LEO sate...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Open Journal of the Communications Society |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10851312/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825207022219427840 |
|---|---|
| author | Joarder Jafor Sadique Imtiaz Nasim Ahmed S. Ibrahim |
| author_facet | Joarder Jafor Sadique Imtiaz Nasim Ahmed S. Ibrahim |
| author_sort | Joarder Jafor Sadique |
| collection | DOAJ |
| description | Low Earth Orbit (LEO) satellites play a crucial role in enhancing global connectivity, serving a complementary solution to existing terrestrial systems. In wireless networks, scheduling is a vital process that allocates time-frequency resources to users for interference management. However, LEO satellite networks face significant challenges in scheduling their links towards ground users due to the satellites’ mobility and overlapping coverage. This paper addresses the dynamic link scheduling problem in LEO satellite networks by considering spatio-temporal correlations introduced by the satellites’ movements. The first step in the proposed solution involves modeling the network over Riemannian manifolds, thanks to their representation as symmetric positive definite matrices. We introduce two machine learning (ML)-based link scheduling techniques that model the dynamic evolution of satellite positions and link conditions over time and space. To accurately predict satellite link states, we present a recurrent neural network (RNN) over Riemannian manifolds, which captures spatio-temporal characteristics over time. Furthermore, we introduce a separate model, the convolutional neural network (CNN) over Riemannian manifolds, which captures geometric relationships between satellites and users by extracting spatial features from the network topology across all links. Simulation results demonstrate that both RNN and CNN over Riemannian manifolds deliver comparable performance to the fractional programming-based link scheduling (FPLinQ) benchmark. Remarkably, unlike other ML-based models that require extensive training data, both models only need 30 training samples to achieve over 99% of the sum rate while maintaining similar computational complexity relative to the benchmark. |
| format | Article |
| id | doaj-art-626558ce0321491794b6f4752fde2cb9 |
| institution | Kabale University |
| issn | 2644-125X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of the Communications Society |
| spelling | doaj-art-626558ce0321491794b6f4752fde2cb92025-02-07T00:01:58ZengIEEEIEEE Open Journal of the Communications Society2644-125X2025-01-01697298510.1109/OJCOMS.2025.353329610851312Link Scheduling in Satellite Networks via Machine Learning Over Riemannian ManifoldsJoarder Jafor Sadique0https://orcid.org/0000-0002-2973-9023Imtiaz Nasim1https://orcid.org/0000-0001-5972-815XAhmed S. Ibrahim2https://orcid.org/0000-0002-6206-6625Department of Electrical and Computer Engineering, Florida International University, Miami, FL, USAData Science and Applied Statistics, Idaho National Laboratory, Idaho Falls, ID, USADepartment of Electrical and Computer Engineering, Florida International University, Miami, FL, USALow Earth Orbit (LEO) satellites play a crucial role in enhancing global connectivity, serving a complementary solution to existing terrestrial systems. In wireless networks, scheduling is a vital process that allocates time-frequency resources to users for interference management. However, LEO satellite networks face significant challenges in scheduling their links towards ground users due to the satellites’ mobility and overlapping coverage. This paper addresses the dynamic link scheduling problem in LEO satellite networks by considering spatio-temporal correlations introduced by the satellites’ movements. The first step in the proposed solution involves modeling the network over Riemannian manifolds, thanks to their representation as symmetric positive definite matrices. We introduce two machine learning (ML)-based link scheduling techniques that model the dynamic evolution of satellite positions and link conditions over time and space. To accurately predict satellite link states, we present a recurrent neural network (RNN) over Riemannian manifolds, which captures spatio-temporal characteristics over time. Furthermore, we introduce a separate model, the convolutional neural network (CNN) over Riemannian manifolds, which captures geometric relationships between satellites and users by extracting spatial features from the network topology across all links. Simulation results demonstrate that both RNN and CNN over Riemannian manifolds deliver comparable performance to the fractional programming-based link scheduling (FPLinQ) benchmark. Remarkably, unlike other ML-based models that require extensive training data, both models only need 30 training samples to achieve over 99% of the sum rate while maintaining similar computational complexity relative to the benchmark.https://ieeexplore.ieee.org/document/10851312/Convolutional neural networkLEO satellitelink schedulingrecurrent neural networkRiemannian geometrysymmetric positive definite matrices |
| spellingShingle | Joarder Jafor Sadique Imtiaz Nasim Ahmed S. Ibrahim Link Scheduling in Satellite Networks via Machine Learning Over Riemannian Manifolds IEEE Open Journal of the Communications Society Convolutional neural network LEO satellite link scheduling recurrent neural network Riemannian geometry symmetric positive definite matrices |
| title | Link Scheduling in Satellite Networks via Machine Learning Over Riemannian Manifolds |
| title_full | Link Scheduling in Satellite Networks via Machine Learning Over Riemannian Manifolds |
| title_fullStr | Link Scheduling in Satellite Networks via Machine Learning Over Riemannian Manifolds |
| title_full_unstemmed | Link Scheduling in Satellite Networks via Machine Learning Over Riemannian Manifolds |
| title_short | Link Scheduling in Satellite Networks via Machine Learning Over Riemannian Manifolds |
| title_sort | link scheduling in satellite networks via machine learning over riemannian manifolds |
| topic | Convolutional neural network LEO satellite link scheduling recurrent neural network Riemannian geometry symmetric positive definite matrices |
| url | https://ieeexplore.ieee.org/document/10851312/ |
| work_keys_str_mv | AT joarderjaforsadique linkschedulinginsatellitenetworksviamachinelearningoverriemannianmanifolds AT imtiaznasim linkschedulinginsatellitenetworksviamachinelearningoverriemannianmanifolds AT ahmedsibrahim linkschedulinginsatellitenetworksviamachinelearningoverriemannianmanifolds |