On the Robustness of Age for Learning-Based Wireless Scheduling in Unknown Environments

2026-01-09

arXiv.org

AI Summary

This work addresses the instability of conventional virtual-queue-based wireless scheduling algorithms under unknown and time-varying channel conditions, where infeasible constraints can lead to unbounded queues and system instability. The paper proposes a novel learning-based scheduling policy that, for the first time, replaces virtual queue lengths with head-of-line age as a constraint-tracking mechanism. By integrating combinatorial multi-armed bandit modeling with online learning, the approach achieves state-of-the-art performance in i.i.d. environments while significantly enhancing robustness and recovery capability during channel abrupt changes or constraint violations. This ensures long-term system stability even under challenging and unpredictable network dynamics.

Technology Category

• Planning, Routing, and Scheduling: Scheduling under Uncertainty
• Machine Learning: Online Learning & Bandits
• 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
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

The constrained combinatorial multi-armed bandit model has been widely employed to solve problems in wireless networking and related areas, including the problem of wireless scheduling for throughput optimization under unknown channel conditions. Most work in this area uses an algorithm design strategy that combines a bandit learning algorithm with the virtual queue technique to track the throughput constraint violation. These algorithms seek to minimize the virtual queue length in their algorithm design. However, in networks where channel conditions change abruptly, the resulting constraints may become infeasible, leading to unbounded growth in virtual queue lengths. In this paper, we make the key observation that the dynamics of the head-of-line age, i.e. the age of the oldest packet in the virtual queue, make it more robust when used in algorithm design compared to the virtual queue length. We therefore design a learning-based scheduling policy that uses the head-of-line age in place of the virtual queue length. We show that our policy matches state-of-the-art performance under i.i.d. network conditions. Crucially, we also show that the system remains stable even under abrupt changes in channel conditions and can rapidly recover from periods of constraint infeasibility.

Problem

• wireless scheduling
• throughput optimization
• constraint infeasibility
• virtual queue
• channel conditions

Innovation

• head-of-line age
• learning-based scheduling
• virtual queue
• constraint robustness
• wireless scheduling