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 2409.05025cs.ITcs.SYeess.SYmath.IT
收藏

基于协作学习的低轨卫星网络 VNF 缓存与放置优化框架

Cooperative Learning-Based Framework for VNF Caching and Placement Optimization over Low Earth Orbit Satellite Networks

Khai Doan, Marios Avgeris, Aris Leivadeas, Ioannis Lambadaris, Wonjae Shin

AI总结:

针对低轨卫星网络中 SFC 的 VNF 放置与缓存问题,提出协作式 MAQL 在线放置和 BO 缓存优化机制,实现近优时延并提升请求服务率。

摘要:

低轨卫星网络(LSN)是支撑广泛现代应用的重要组成部分,这些应用通常被建模为服务功能链(SFC)。每条 SFC 由虚拟网络功能(VNF)组成,其中每个 VNF 执行一项特定任务。在本文中,我们解决在 LSN 中部署 SFC 的两个关键挑战。首先,鉴于每颗卫星都预装或缓存了一个 VNF 子集,我们旨在通过最小化平均端到端 SFC 执行时延来优化长期系统性能。为实现最优 SFC 放置,我们构建了一个离线动态规划(DP)方程。为克服 DP 相关挑战,例如其复杂性、对概率知识的需求以及集中式决策,我们提出了一种在线多智能体 Q 学习(MAQL)解决方案。我们的 MAQL 方法通过使卫星共享学习参数,并根据其所选动作的不同规则更新各自的 Q 表,解决了非平稳 LSN 环境中的收敛问题。其次,为确定用于卫星缓存的最优 VNF 子集,我们开发了一种基于贝叶斯优化(BO)的学习机制,该机制既可离线运行,也可在运行期间于后台持续运行。大量实验表明,我们的 MAQL 方法取得了与 DP 模型相当的近优性能,并显著优于现有基线。此外,基于 BO 的方法随时间推移有效提升了请求服务率。

英文摘要:

Low Earth Orbit Satellite Networks (LSNs) are integral to supporting a broad range of modern applications, which are typically modeled as Service Function Chains (SFCs). Each SFC is composed of Virtual Network Functions (VNFs), where each VNF performs a specific task. In this work, we tackle two key challenges in deploying SFCs across an LSN. Firstly, we aim to optimize the long-term system performance by minimizing the average end-to-end SFC execution delay, given that each satellite comes with a pre-installed/cached subset of VNFs. To achieve optimal SFC placement, we formulate an offline Dynamic Programming (DP) equation. To overcome the challenges associated with DP, such as its complexity, the need for probability knowledge, and centralized decision-making, we put forth an online Multi-Agent Q-Learning (MAQL) solution. Our MAQL approach addresses convergence issues in the non-stationary LSN environment by enabling satellites to share learning parameters and update their Q-tables based on distinct rules for their selected actions. Secondly, to determine the optimal VNF subsets for satellite caching, we develop a Bayesian Optimization (BO)-based learning mechanism that operates both offline and continuously in the background during runtime. Extensive experiments demonstrate that our MAQL approach achieves near-optimal performance comparable to the DP model and significantly outperforms existing baselines. Moreover, the BO-based approach effectively enhances the request serving rate over time.

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。

↑