Toward Scalable SDN for LEO Mega-Constellations: A Graph Learning Approach

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Krishnan, Sivaram, Homssi, Bassel Al, Gu, Zhouyou, Park, Jihong, Oh, Sung-Min, Choi, Jinho
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909003737464832
author Krishnan, Sivaram
Homssi, Bassel Al
Gu, Zhouyou
Park, Jihong
Oh, Sung-Min
Choi, Jinho
author_facet Krishnan, Sivaram
Homssi, Bassel Al
Gu, Zhouyou
Park, Jihong
Oh, Sung-Min
Choi, Jinho
contents Terrestrial network limitations drive the integration of non-terrestrial networks (NTNs), notably mega-constellations comprising thousands of low Earth orbit (LEO) satellites. While these satellites act as interconnected network switches via inter-satellite links (ISLs), their massive scale creates severe bottlenecks for network management. To address this, we propose a scalable, hierarchical software-defined networking (SDN) framework. Our architecture leverages graph neural networks (GNNs) to compactly represent the constellation topology, and Koopman theory to linearize nonlinear dynamics. Specifically, a Graph Koopman Autoencoder (GKAE) forecasts spatio-temporal behavior within a linear subspace for each orbital shell. A central SDN controller then aggregates these shell-level predictions for globally coordinated control. Simulations on the Starlink constellation demonstrate that our approach achieves at least a 42.8\% improvement in spatial compression and a 10.81\% improvement in temporal forecasting compared to established baselines, all while utilizing a significantly smaller model footprint.
format Preprint
id arxiv_https___arxiv_org_abs_2604_27478
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Toward Scalable SDN for LEO Mega-Constellations: A Graph Learning Approach
Krishnan, Sivaram
Homssi, Bassel Al
Gu, Zhouyou
Park, Jihong
Oh, Sung-Min
Choi, Jinho
Machine Learning
Systems and Control
Terrestrial network limitations drive the integration of non-terrestrial networks (NTNs), notably mega-constellations comprising thousands of low Earth orbit (LEO) satellites. While these satellites act as interconnected network switches via inter-satellite links (ISLs), their massive scale creates severe bottlenecks for network management. To address this, we propose a scalable, hierarchical software-defined networking (SDN) framework. Our architecture leverages graph neural networks (GNNs) to compactly represent the constellation topology, and Koopman theory to linearize nonlinear dynamics. Specifically, a Graph Koopman Autoencoder (GKAE) forecasts spatio-temporal behavior within a linear subspace for each orbital shell. A central SDN controller then aggregates these shell-level predictions for globally coordinated control. Simulations on the Starlink constellation demonstrate that our approach achieves at least a 42.8\% improvement in spatial compression and a 10.81\% improvement in temporal forecasting compared to established baselines, all while utilizing a significantly smaller model footprint.
title Toward Scalable SDN for LEO Mega-Constellations: A Graph Learning Approach
topic Machine Learning
Systems and Control
url https://arxiv.org/abs/2604.27478