Online Learning for Dynamic Constellation Topologies

TL;DR

This paper introduces an online learning approach for configuring satellite network topologies that adapt to orbital movements without assuming prior structural knowledge, matching offline methods' performance.

Contribution

It presents a novel online learning framework for dynamic satellite network topology configuration that is flexible and does not rely on predefined network structures.

Findings

The approach matches the performance of state-of-the-art offline methods.

It can incorporate constraints and balances complexity with convergence.

Demonstrates effectiveness in dynamic, maneuvering satellite networks.

Abstract

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.