Abstract: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.
| Comments: | 6 pages, 4 figures, 3 tables, and submitted to 2026 IEEE Globecom |
| Subjects: | Networking and Internet Architecture (cs.NI); Machine Learning (cs.LG) |
| MSC classes: | 68M10, 68T05 |
| ACM classes: | C.2.2; I.2.6; I.2.11 |
| Cite as: | arXiv:2605.02413 [cs.NI] |
| (or arXiv:2605.02413v1 [cs.NI] for this version) | |
| https://doi.org/10.48550/arXiv.2605.02413 arXiv-issued DOI via DataCite (pending registration) |
From: Po-Heng Chou [view email]
[v1]
Mon, 4 May 2026 10:05:43 UTC (226 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。