Random Access Protocol Learning in LEO Satellite Networks via Reinforcement Learning
Random Access Protocol Learning in LEO Satellite Networks via Reinforcement Learning
复制标题
通过强化学习在 LEO 卫星网络中进行随机接入协议学习
DOI：
--
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Joongheon Kim
中科院分区：
文献类型：
--
作者：
Ju;Hyowoon Seo;Jihong Park;M. Bennis;Young;Joongheon Kim
设想低空地球轨道（LEO）卫星（SAT）的巨型星座以在超过第五代（5G）蜂窝系统中提供全球覆盖的SAT网络。然而，这样的宽覆盖反而使得难以应用现有的多址协议，诸如随机接入信道（RACH）。为了克服这个问题，在本文中，我们提出了一种新的随机接入解决方案，LEO SAT网络，称为S-RACH。与现有的标准化协议相比，S-RACH是一种使用深度强化学习（DRL）的无模型方法。与RACH相比，我们从各种模拟中表明，我们提出的S-RACH产生大约2倍的平均接入延迟。
A mega-constellation of low-altitude earth orbit (LEO) satellites (SATs) are envisaged to provide a global coverage SAT network in beyond fifth-generation (5G) cellular systems. However, such wide coverage rather makes it difficult to apply existing multiple access protocols, such as random access channel (RACH). To overcome this issue, in this paper, we propose a novel random access solution for LEO SAT networks, called as S-RACH. In contrast to existing standardized protocols, S-RACH is a model-free approach using deep reinforcement learning (DRL). Compared to RACH, we show from various simulations that our proposed S-RACH yields around 2x lower average access delay.