QaSAL: QoS-aware State-Augmented Learnable Algorithms for Coexistence of 5G NR-U/Wi-Fi

2025-03-01

AI Summary

To address the QoS guarantee challenge for multi-priority traffic in coexistence scenarios of 5G NR-U and Wi-Fi over unlicensed spectrum, this paper proposes a QoS-aware, state-enhanced reinforcement learning framework. The method explicitly encodes latency constraints into the state representation and jointly models traffic priority with channel access decisions to dynamically optimize MAC-layer parameters (e.g., contention window size and AIFS). Its key innovation lies in the first incorporation of hard real-time constraints directly into the state space—thereby ensuring deterministic latency guarantees without sacrificing policy adaptability. Simulation results demonstrate that, under mixed high- and low-priority traffic loads, the proposed approach strictly satisfies end-to-end latency requirements for high-priority flows while significantly improving channel access fairness and overall system throughput.

Technology Category

• Planning, Routing, and Scheduling: Scheduling under Uncertainty
• Reasoning under Uncertainty: Sequential Decision Making
• Search and Optimization: Learning to Search

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• 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

With the increasing demand for wireless connectivity, ensuring the efficient coexistence of multiple radio access technologies in shared unlicensed spectrum has become an important issue. This paper focuses on optimizing Medium Access Control (MAC) parameters to enhance the coexistence of 5G New Radio in Unlicensed Spectrum (NR-U) and Wi-Fi networks operating in unlicensed spectrum with multiple priority classes of traffic that may have varying quality-of-service (QoS) requirements. In this context, we tackle the coexistence parameter management problem by introducing a QoS-aware State-Augmented Learnable (QaSAL) framework, designed to improve network performance under various traffic conditions. Our approach augments the state representation with constraint information, enabling dynamic policy adjustments to enforce QoS requirements effectively. Simulation results validate the effectiveness of QaSAL in managing NR-U and Wi-Fi coexistence, demonstrating improved channel access fairness while satisfying a latency constraint for high-priority traffic.

Problem

• Optimize MAC parameters for 5G NR-U/Wi-Fi coexistence
• Enhance network performance with varying QoS requirements
• Ensure fair channel access and meet latency constraints

Innovation

• QoS-aware State-Augmented Learnable (QaSAL) framework
• Dynamic policy adjustments for QoS requirements
• Enhanced channel access fairness with latency constraints