arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.17666cs.LGcs.ITmath.IT
收藏

用于分布式卫星路由的多智能体深度强化学习

Multi-Agent Deep Reinforcement Learning for Distributed Satellite Routing

Telecommunications Research Institute, University of Malaga(马拉加大学电信研究所)

Federico Lozano-Cuadra, Beatriz Soret

AI总结:

针对低轨卫星星座的分布式路由问题,本文提出两阶段 MA-DRL 框架,通过离线全局 DNN 学习最优路径并在星载本地 DNN 上在线部署,实现对网络与流量变化的快速适应。

摘要:

本文介绍了一种用于低轨卫星星座(LSatCs)路由的多智能体深度强化学习(MA-DRL)方法。每颗卫星都是一个独立的决策智能体,只掌握环境的部分知识,并借助从邻近智能体接收的反馈获得支持。在我们先前提出 Q-routing 解决方案的工作基础上,本文的贡献是将其扩展为一个能够快速适应网络和流量变化的深度学习框架,该框架基于两个阶段:(1)离线探索学习阶段,依赖全局深度神经网络(DNN),在每个可能的位置和拥塞程度下学习最优路径;(2)在线利用阶段,使用本地、星载、预训练的 DNN。结果表明,MA-DRL 能够在离线阶段高效学习最优路由,随后将其加载,以在在线阶段实现高效的分布式路由。

英文摘要:

This paper introduces a Multi-Agent Deep Reinforcement Learning (MA-DRL) approach for routing in Low Earth Orbit Satellite Constellations (LSatCs). Each satellite is an independent decision-making agent with a partial knowledge of the environment, and supported by feedback received from the nearby agents. Building on our previous work that introduced a Q-routing solution, the contribution of this paper is to extend it to a deep learning framework able to quickly adapt to the network and traffic changes, and based on two phases: (1) An offline exploration learning phase that relies on a global Deep Neural Network (DNN) to learn the optimal paths at each possible position and congestion level; (2) An online exploitation phase with local, on-board, pre-trained DNNs. Results show that MA-DRL efficiently learns optimal routes offline that are then loaded for an efficient distributed routing online.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑