基于协同学习的低轨卫星网络 VNF 缓存与placement 优化框架

低轨道卫星网络(LSN)是支持多种 modern applications 的关键组成部分，这些 applications 通常建模为 Service Function Chains(SFCs)。每个 SFC 由 Virtual Network Functions(VNFs)组成，其中每个 VNF 执行特定任务。本 work tackle two key challenges in deploying SFCs across an LSN。首先，我们旨在通过最小化 average end-to-end SFC execution delay 来优化 long-term system performance， given that each satellite comes with a pre-installed/cached subset of VNFs。为 achieve optimal SFC placement，我们 formulation offline Dynamic Programming(DP) equation。为 overcome DP 的 challenges，such as complexity, 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 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。