Spatial-Temporal Learning-Based Distributed Routing for Dynamic LEO Satellite Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chou, Po-Heng, Wang, Chiapin, Chen, Shou-Yu, Wang, Hsiang-Ming
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915977138012160
author Chou, Po-Heng
Wang, Chiapin
Chen, Shou-Yu
Wang, Hsiang-Ming
author_facet Chou, Po-Heng
Wang, Chiapin
Chen, Shou-Yu
Wang, Hsiang-Ming
contents In this paper, we propose a spatial-temporal learning-based distributed routing framework for dynamic Low Earth Orbit (LEO) satellite networks, where graph attention networks (GAT) and long short-term memory (LSTM) are integrated within a deep Q-network (DQN)-based architecture to enable distributed and adaptive routing decisions based on local observations. The routing problem is formulated as a partially observable Markov decision process (POMDP) to address partial observability under dynamic topology and time-varying traffic. Simulation results show that the proposed method significantly outperforms conventional and learning-based routing schemes in terms of throughput, packet loss, queue length, and end-to-end delay, while achieving proactive congestion avoidance with up to 23.26% queue reduction. In addition, the proposed approach maintains low computational overhead with negligible carbon emissions, demonstrating its efficiency from a Green AI perspective.
format Preprint
id arxiv_https___arxiv_org_abs_2605_02413
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Spatial-Temporal Learning-Based Distributed Routing for Dynamic LEO Satellite Networks
Chou, Po-Heng
Wang, Chiapin
Chen, Shou-Yu
Wang, Hsiang-Ming
Networking and Internet Architecture
Machine Learning
68M10, 68T05
C.2.2; I.2.6; I.2.11
In this paper, we propose a spatial-temporal learning-based distributed routing framework for dynamic Low Earth Orbit (LEO) satellite networks, where graph attention networks (GAT) and long short-term memory (LSTM) are integrated within a deep Q-network (DQN)-based architecture to enable distributed and adaptive routing decisions based on local observations. The routing problem is formulated as a partially observable Markov decision process (POMDP) to address partial observability under dynamic topology and time-varying traffic. Simulation results show that the proposed method significantly outperforms conventional and learning-based routing schemes in terms of throughput, packet loss, queue length, and end-to-end delay, while achieving proactive congestion avoidance with up to 23.26% queue reduction. In addition, the proposed approach maintains low computational overhead with negligible carbon emissions, demonstrating its efficiency from a Green AI perspective.
title Spatial-Temporal Learning-Based Distributed Routing for Dynamic LEO Satellite Networks
topic Networking and Internet Architecture
Machine Learning
68M10, 68T05
C.2.2; I.2.6; I.2.11
url https://arxiv.org/abs/2605.02413