LiSFC-Search: Lifelong Search for Network SFC Optimization under Non-stationary Drifts

2026-02-16

AI Summary

This work addresses the challenge of service function chain (SFC) deployment in edge-cloud converged networks, where non-stationary graph drift severely degrades the performance of conventional static approaches. The authors formulate SFC optimization as a time-varying Markov decision process (MDP) and propose LiSFC-Search, a novel method that introduces a graph drift metric to theoretically bound the distance between MDPs. By integrating Lipschitz lifelong learning with an adaptive UCT reward mechanism within the LiZero framework, the approach ensures both bounded policy deviation and sample efficiency. Furthermore, a unified SFC-aware Monte Carlo Tree Search (MCTS) procedure is designed to enable knowledge transfer across diverse network configurations. Experimental results demonstrate that LiSFC-Search significantly reduces SFC blocking rates and improves tail latency under synthetic topologies and traffic loads, outperforming non-transfer MCTS and pure learning baselines.

Technology Category

• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Cloud, edge and content delivery systems for the Web
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

Edge-cloud convergence is reshaping service provisioning across 5G/6G and computing power networks (CPNs). Service function chaining (SFC) requires continuously placing and scheduling virtual network functions (VNFs) chains under compute/bandwidth and end-to-end QoS constraints. Most SFC optimizers assume static or stationary networks, and degrade under long-term topology/resource changes (failures, upgrades, expansions) that induce non-stationary graph drifts. We propose LiSFC, a Lipschitz lifelong planner that transfers MCTS statistics across drifting network configurations using an MDP-distance bound. More precisely, we formulate the problem as a sequence of MDPs indexed by the underlying network graph and constraints, and we define a \emph{graph drift} metric that upper-bounds the LiZero MDP distance. This allows LiSFC to import theoretical guarantees on bias and sample efficiency from the LiZero framework while being tailored to cloud-network convergence. We then design \emph{LiSFC-Search}, an SFC-aware unified MCTS (UMCTS) procedure that uses transferable adaptive UCT (aUCT) bonuses to reuse search statistics from prior CPN configurations. Preliminary results on synthetic CPN topologies and SFC workloads show that LiSFC consistently reduces SFC blocking probability and improves tail delay compared to non-transfer MCTS and purely learning-based baselines, highlighting its potential as an AI/ML building block for cloud-network convergence.

Problem

• Service Function Chaining
• Non-stationary Drifts
• Edge-cloud Convergence
• Network Optimization
• Graph Drift

Innovation

• Lifelong Planning
• Graph Drift
• Service Function Chaining
• Monte Carlo Tree Search
• Non-stationary Networks