Multi-Armed Bandit Learning in IoT Networks: Learning helps even in non-stationary settings

TL;DR

This paper demonstrates that Multi-Armed Bandit learning algorithms, specifically UCB1 and Thompson Sampling, significantly improve spectrum access efficiency in IoT networks, even under non-stationary and highly dynamic conditions.

Contribution

It evaluates the effectiveness of classical MAB algorithms for decentralized spectrum management in IoT, showing their robustness and performance gains in complex, evolving environments.

Findings

Up to 16% increase in successful transmission probabilities.

MAB algorithms perform near optimally in non-stationary, non-i.i.d. settings.

Learning enables more devices to coexist efficiently in IoT networks.

Abstract

Setting up the future Internet of Things (IoT) networks will require to support more and more communicating devices. We prove that intelligent devices in unlicensed bands can use Multi-Armed Bandit (MAB) learning algorithms to improve resource exploitation. We evaluate the performance of two classical MAB learning algorithms, UCB1 and Thompson Sampling, to handle the decentralized decision-making of Spectrum Access, applied to IoT networks; as well as learning performance with a growing number of intelligent end-devices. We show that using learning algorithms does help to fit more devices in such networks, even when all end-devices are intelligent and are dynamically changing channel. In the studied scenario, stochastic MAB learning provides a up to 16% gain in term of successful transmission probabilities, and has near optimal performance even in non-stationary and non-i.i.d. settings with a majority of intelligent devices.