Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Online Learning for Dynamic Constellation Topologies

João Norberto, Ricardo Ferreira, Cláudia Soares

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.

Online Learning for Dynamic Constellation Topologies

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.

Paper Structure

This paper contains 6 sections, 3 equations, 3 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Online Learning
  4. Problem Formulation
  5. Results
  6. Discussion

Figures (3)

  • Figure 1: An example of the use of a hyperplane to simulate the field of view (FOV) of a satellite. The area colored in green represents the FOV of satellite 1, while the area colored in red represents the area outside of the satellite's FOV. If a satellite falls within the green area, it can connect with satellite 1.
  • Figure 2: An example of the use of both a hyperplane and a conical surface to approximate the FOV of a satellite. The area colored in green represents the FOV of satellite 1, while the area colored in red represents the area outside of the satellite's FOV. If a satellite falls within the green area, it can connect with satellite 1.
  • Figure 3: Average residual per entry between Laplacian matrices produced by the online algorithms and our offline method, following \ref{['eq:plot_formula']}. The lower the residual, the closer the resulting matrices are to the offline method.