End-to-End Delivery in LEO Mega-constellations and the Reordering Problem

TL;DR

This paper studies the reordering problem that arises in end-to-end delivery over LEO mega-constellations with inter-satellite links. It uses an emulation framework to evaluate three congestion control algorithms—Cubic, Reno, and BBR—under a OneWeb-like constellation and to perform a sensitivity analysis on constellation parameters. The results show that route changes induce large transient shifts in goodput and trigger loss-recovery behaviors, with Reno most adversely affected and Cubic/BBR more robust but still experiencing dips. The work highlights the need for mobility-aware transport and network-layer solutions to stabilize performance, and outlines directions such as queue management, delayed forwarding, and potential loss-detection adaptations.

Abstract

Low Earth orbit (LEO) satellite mega-constellations with hundreds or thousands of satellites and inter-satellite links (ISLs) have the potential to provide global end-to-end connectivity. Furthermore, if the physical distance between source and destination is sufficiently long, end-to-end routing over the LEO constellation can provide lower latency when compared to the terrestrial infrastructure due to the faster propagation of electromagnetic waves in space than in optic fiber. However, the frequent route changes due to the movement of the satellites result in the out-of-order delivery of packets, causing sudden changes to the Round-Trip Time (RTT) that can be misinterpreted as congestion by congestion control algorithms. In this paper, the performance of three widely used congestion control algorithms, Cubic, Reno, and BBR, is evaluated in an emulated LEO satellite constellation with Free-Space Optical (FSO) ISLs. Furthermore, we perform a sensitivity analysis for Cubic by changing the satellite constellation parameters, length of the routes, and the positions of the source and destination to identify problematic routing scenarios. The results show that route changes can have profound transient effects on the goodput of the connection, posing problems for typical broadband applications.

Figures (9)

• Figure 1: Considered use case of remote Internet access, connecting remote through a satellite constellation with .
• Figure 2: Packet-level diagram of the reordering problem.
• Figure 3: Baseline scenario: Shortest-path routing through OneWeb's constellation between Madrid and Tokyo.
• Figure 4: Empirical CDF of the goodput (x-axis in non-linear scale).
• Figure 5: Empirical of the .