An Intelligent eUPF for Time-Sensitive Path Selection in B5G Edge Networks

2026-05-02

AI Summary

This study addresses the challenge of low-latency, high-reliability traffic scheduling in beyond-5G (B5G) edge networks by formulating path selection as a partially observable Markov decision process (POMDP). The authors design a deep Q-network (DQN)-based agent capable of making dynamic routing decisions between multi-access edge computing (MEC) and cloud nodes. A novel passive delay measurement technique leveraging eBPF is introduced, which extracts TEID-associated timestamps from GTP-U traffic to enable low-overhead, end-to-end latency estimation without active probing. Experimental results demonstrate that the proposed approach significantly reduces average latency and enhances reward stability compared to a random policy, while more reliably selecting low-latency paths.

Abstract

In Beyond 5G (B5G) networks, intelligent, flexible traffic management is essential to meet the stringent speed and reliability requirements of new applications. This paper presents an improved User Plane Function (eUPF) design that uses a Deep Q-Network (DQN) agent for real-time path selection between Multi-access Edge Computing (MEC) and cloud endpoints. The path selection problem is formulated as a Partially Observable Markov Decision Process (POMDP). We propose a novel passive delay measurement method that uses eBPF programs to link TEID-based timestamps in GTP-U traffic, allowing for low-cost delay estimation without active testing. Experiments show that the DQN agent substantially outperforms a random baseline, with lower average latency, more stable rewards, and more reliable low-delay path choices. These results demonstrate the effectiveness of AI-driven control in B5G core networks and the promise of reinforcement learning for modern network management.

Problem

• B5G
• time-sensitive networking
• path selection
• edge computing
• User Plane Function

Innovation

• Deep Q-Network
• eBPF
• POMDP
• Time-Sensitive Networking
• MEC