Hierarchical Placement Learning for Network Slice Provisioning

2025-08-08

AI Summary

In edge mobile networks, network slicing deployment faces a fundamental trade-off between low slice request acceptance rates and high node resource utilization. To address this, we propose a two-tier cascaded Hierarchical Multi-Armed Bandit (HMAB) framework for online, adaptive learning of Service Function Chain (SFC) placement policies. Our approach decouples slice admission control from resource allocation into macro-level scheduling and micro-level deployment, enabling scalable, low-overhead real-time decision-making. Experiments on realistic network topologies demonstrate that our method reduces average node resource utilization to 5% while improving slice request acceptance by over 25%, all while satisfying end-to-end latency and reliability constraints. To the best of our knowledge, this is the first work to systematically introduce hierarchical reinforcement learning into online network slicing orchestration. It provides an efficient, lightweight solution for dynamic and heterogeneous slice provisioning in edge environments.

Technology Category

• Machine Learning: Online Learning & Bandits
• Planning, Routing, and Scheduling: Planning/Scheduling and Learning
• Search and Optimization: Learning to Search

Application Category

• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

In this work, we aim to address the challenge of slice provisioning in edge-based mobile networks. We propose a solution that learns a service function chain placement policy for Network Slice Requests, to maximize the request acceptance rate, while minimizing the average node resource utilization. To do this, we consider a Hierarchical Multi-Armed Bandit problem and propose a two-level hierarchical bandit solution which aims to learn a scalable placement policy that optimizes the stated objectives in an online manner. Simulations on two real network topologies show that our proposed approach achieves 5% average node resource utilization while admitting over 25% more slice requests in certain scenarios, compared to baseline methods.

Problem

• Optimize network slice provisioning in edge mobile networks
• Maximize request acceptance rate and minimize resource utilization
• Learn scalable placement policy using hierarchical bandit solution

Innovation

• Hierarchical Multi-Armed Bandit for placement
• Two-level online optimization policy
• Maximizes acceptance, minimizes resource use