Distributed Learning in Markovian Restless Bandits Over Interference Graphs for Stable Spectrum Sharing
IEEE Journal on Selected Areas in Communications · 2026 · 44 · 6066-6084
DOI: 10.1109/jsac.2026.3745718 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Journal on Selected Areas in Communications, 2026. Verfasst von Liad Lea Didi und 1 weiteren Autor:innen. Die Arbeit nennt 50 Literaturangaben. Gefördert von: U.S.–Israel Binational Science Foundation.
Abstract (Originalsprache)
We study distributed learning for spectrum access and sharing among multiple cognitive communication entities, such as cells, subnetworks, or cognitive radio users (collectively referred to as cells), in communication-constrained wireless networks modeled by interference graphs. Our goal is to achieve a globally stable and interference-aware channel allocation. Stability is defined through a generalized Gale–Shapley multi-to-one matching, a well-established solution concept in wireless resource allocation. We consider wireless networks where $L$ cells share $S$ orthogonal channels and cannot simultaneously use the same channel as their neighbors. Each channel evolves as an unknown restless Markov process with cell-dependent rewards, making this the first work to establish global Gale–Shapley stability for channel allocation in a stochastic, temporally varying restless environment. To address this challenge, we develop SMILE (Stable Multi-matching with Interference-aware LEarning), a communication-efficient distributed learning algorithm that integrates restless bandit learning with graph-constrained coordination. SMILE enables cells to distributedly balance exploration of unknown channels with exploitation of learned information. We prove that SMILE converges to the optimal stable allocation and achieves logarithmic regret relative to a genie with full knowledge of expected utilities. Simulations validate the theoretical guarantees and demonstrate SMILEs robustness, scalability, and efficiency across diverse spectrum-sharing scenarios.
Förderung
- U.S.–Israel Binational Science Foundation
Zitieren
APA
Didi, L. L., & Cohen, K. (2026). Distributed Learning in Markovian Restless Bandits Over Interference Graphs for Stable Spectrum Sharing. IEEE Journal on Selected Areas in Communications, 44, 6066-6084. https://doi.org/10.1109/jsac.2026.3745718
Vancouver
Didi LL, Cohen K. Distributed Learning in Markovian Restless Bandits Over Interference Graphs for Stable Spectrum Sharing. IEEE Journal on Selected Areas in Communications. 2026;44:6066-6084. doi:10.1109/jsac.2026.3745718
BibTeX
@article{Didi2026,
author = {Didi, Liad Lea and Cohen, Kobi},
title = {Distributed Learning in Markovian Restless Bandits Over Interference Graphs for Stable Spectrum Sharing},
journal = {IEEE Journal on Selected Areas in Communications},
year = {2026},
volume = {44},
pages = {6066--6084},
doi = {10.1109/jsac.2026.3745718}
}
EUVIMED