Accelerating Network Slice Placement with Multi-Agent Reinforcement Learning

2025-09-22

AI Summary

Addressing the challenge of jointly ensuring QoS and minimizing cost in network slicing deployment across heterogeneous multi-cloud environments, this paper proposes a modular, decentralized multi-agent reinforcement learning (MARL) framework for autonomous, collaborative virtual network function (VNF) placement. The framework integrates software-defined networking control with real-traffic-driven resource demand prediction, striking a balance between decision-making efficiency and deployment performance. Experiments on a multi-cloud testbed demonstrate that our approach accelerates deployment by 19× compared to conventional combinatorial optimization methods, while incurring only a 7.8% cost penalty relative to the global optimum—significantly reducing computational complexity. The key innovation lies in the first application of a lightweight MARL mechanism to heterogeneous multi-cloud slicing deployment, achieving scalability, real-time adaptability, and near-optimal performance.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Learning on the Edge & Model Compression
• Search and Optimization: Learning to Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Virtualization and resource management in Web systems and infrastructures
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

Cellular networks are increasingly realized through software-based entities, with core functions deployed as Virtual Network Functions (VNFs) on Commercial-off-the-Shelf (COTS) hardware. Network slicing has emerged as a key enabler of 5G by providing logically isolated Quality of Service (QoS) guarantees for diverse applications. With the adoption of cloud-native infrastructures, the placement of network slices across heterogeneous multi-cloud environments poses new challenges due to variable resource capabilities and slice-specific requirements. This paper introduces a modular framework for autonomous and near-optimal VNF placement based on a disaggregated Multi-Agent Reinforcement Learning (MARL) approach. The framework incorporates real traffic profiles to estimate slice resource demands and employs a MARL-based scheduler to minimize deployment cost while meeting QoS constraints. Experimental evaluation on a multi-cloud testbed shows a 19x speed-up compared to combinatorial optimization, with deployment costs within 7.8% of the optimal. While the method incurs up to 2.42x more QoS violations under high load, the trade-off provides significantly faster decision-making and reduced computational complexity. These results suggest that MARL-based approaches offer a scalable and cost-efficient solution for real-time network slice placement in heterogeneous infrastructures.

Problem

• Placing network slices across heterogeneous multi-cloud environments efficiently
• Minimizing deployment costs while meeting Quality of Service constraints
• Achieving faster decision-making compared to combinatorial optimization methods

Innovation

• Multi-Agent Reinforcement Learning for VNF placement
• Modular framework using real traffic profiles
• Minimizes deployment cost while meeting QoS constraints