PulseAugur
实时 07:18:46
English(EN) Spatial-Temporal Learning-Based Distributed Routing for Dynamic LEO Satellite Networks

AI路由框架提升LEO卫星网络性能与效率

研究人员开发了一种新颖的、基于时空学习的分布式路由框架,专为动态低地球轨道(LEO)卫星网络设计。该框架将图注意力网络(GAT)和长短期记忆(LSTM)集成在深度Q网络(DQN)架构中,能够基于局部观测做出自适应路由决策。该系统被构建为一个部分可观察马尔可夫决策过程(POMDP),以处理动态网络条件和流量变化。仿真结果表明,与现有方法相比,吞吐量、丢包率、队列长度和端到端延迟均有显著改善,队列长度减少高达23.26%。此外,该方法还因其低计算开销和最小碳排放而受到关注,符合绿色AI原则。 AI

影响 这种新的路由框架可以提高卫星通信网络的效率并降低延迟,可能对未来的天基互联网服务产生影响。

排序理由 这是一篇发表在arXiv上的研究论文,详细介绍了一种用于卫星网络的新型路由框架。

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →

AI路由框架提升LEO卫星网络性能与效率

报道来源 [3]

  1. arXiv cs.LG TIER_1 English(EN) · Po-Heng Chou, Chiapin Wang, Shou-Yu Chen, Hsiang-Ming Wang ·

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

    arXiv:2605.02413v1 Announce Type: cross 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 …

  2. arXiv cs.LG TIER_1 English(EN) · Hsiang-Ming Wang ·

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

    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 t…

  3. Hugging Face Daily Papers TIER_1 English(EN) ·

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

    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 t…