Online Learning for Dynamic Constellation Topologies

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Norberto, João, Ferreira, Ricardo, Soares, Cláudia
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915893399781376
author Norberto, João
Ferreira, Ricardo
Soares, Cláudia
author_facet Norberto, João
Ferreira, Ricardo
Soares, Cláudia
contents The use of satellite networks has increased significantly in recent years due to their advantages over purely terrestrial systems, such as higher availability and coverage. However, to effectively provide these services, satellite networks must cope with the continuous orbital movement and maneuvering of their nodes and the impact on the network's topology. In this work, we address the problem of (dynamic) network topology configuration under the online learning framework. As a byproduct, our approach does not assume structure about the network, such as known orbital planes (that could be violated by maneuvering satellites). We empirically demonstrate that our problem formulation matches the performance of state-of-the-art offline methods. Importantly, we demonstrate that our approach is amenable to constrained online learning, exhibiting a trade-off between computational complexity per iteration and convergence to a final strategy.
format Preprint
id arxiv_https___arxiv_org_abs_2603_25954
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Online Learning for Dynamic Constellation Topologies
Norberto, João
Ferreira, Ricardo
Soares, Cláudia
Machine Learning
Optimization and Control
The use of satellite networks has increased significantly in recent years due to their advantages over purely terrestrial systems, such as higher availability and coverage. However, to effectively provide these services, satellite networks must cope with the continuous orbital movement and maneuvering of their nodes and the impact on the network's topology. In this work, we address the problem of (dynamic) network topology configuration under the online learning framework. As a byproduct, our approach does not assume structure about the network, such as known orbital planes (that could be violated by maneuvering satellites). We empirically demonstrate that our problem formulation matches the performance of state-of-the-art offline methods. Importantly, we demonstrate that our approach is amenable to constrained online learning, exhibiting a trade-off between computational complexity per iteration and convergence to a final strategy.
title Online Learning for Dynamic Constellation Topologies
topic Machine Learning
Optimization and Control
url https://arxiv.org/abs/2603.25954