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

TL;DR

This paper evaluates how satellite movement in LEO mega-constellations affects end-to-end data delivery, focusing on congestion control performance and routing scenarios, highlighting transient effects on throughput.

Contribution

It provides an empirical analysis of congestion control algorithms in LEO satellite networks and identifies routing scenarios that cause performance issues.

Findings

Route changes cause significant transient throughput drops.

BBR outperforms Cubic and Reno in certain scenarios.

Routing parameters critically impact connection stability.

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.