Distributed Learning over Markovian Fading Channels for Stable Spectrum Access

TL;DR

This paper introduces a distributed learning algorithm for multi-user spectrum access over Markovian channels, achieving stable allocations with proven convergence and low regret, even with user-specific channel rates.

Contribution

It develops the DSSL algorithm for distributed stable matching in multi-user spectrum access with Markovian channels, handling user-specific rates and proving convergence and regret bounds.

Findings

DSSL converges to stable matchings in the system.

Regret of DSSL grows logarithmically over time.

Simulation results confirm strong performance of DSSL.

Abstract

We consider the problem of multi-user spectrum access in wireless networks. The bandwidth is divided into K orthogonal channels, and M users aim to access the spectrum. Each user chooses a single channel for transmission at each time slot. The state of each channel is modeled by a restless unknown Markovian process. Previous studies have analyzed a special case of this setting, in which each channel yields the same expected rate for all users. By contrast, we consider a more general and practical model, where each channel yields a different expected rate for each user. This model adds a significant challenge of how to efficiently learn a channel allocation in a distributed manner to yield a global system-wide objective. We adopt the stable matching utility as the system objective, which is known to yield strong performance in multichannel wireless networks, and develop a novel Distributed Stable Strategy Learning (DSSL) algorithm to achieve the objective. We prove theoretically that DSSL converges to the stable matching allocation, and the regret, defined as the loss in total rate with respect to the stable matching solution, has a logarithmic order with time. Finally, simulation results demonstrate the strong performance of the DSSL algorithm.