GNU Radio implementation for Multiuser Multi-Armed Bandit learning algorithms in IoT networks

Abstract : Novel access schemes based on multi-armed bandit (MAB) learning approaches has been proposed to support the increasing number of devices in IoT networks in unlicensed bands. In the present work, a GNU radio framework is implemented to recreate an IoT network where IoT devices embedding MAB algorithms are able to learn the availability of the channels for their packet transmissions to the gateway. It allows to incorporate several IoT users recognized by an identifier (ID), and provides a gateway to handle a large number of IDs as well as the packet collisions among IoT devices. The experimental results show that the introduction of decentralized learning mechanism in access schemes can improve the performance of the IoT devices, both in terms of energy consumption and spectrum overload, thanks to radio collision mitigation.
Complete list of metadatas

Cited literature [3 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02263703
Contributor : Julio Cesar Manco <>
Submitted on : Monday, August 5, 2019 - 3:13:54 PM
Last modification on : Tuesday, September 17, 2019 - 1:05:18 AM

File

paper_gnuradio.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02263703, version 1

Citation

Julio Manco-Vasquez, Christophe Moy, Faouzi Bader. GNU Radio implementation for Multiuser Multi-Armed Bandit learning algorithms in IoT networks. European GNURadio Days 2019, Jun 2019, Besancon, France. ⟨hal-02263703⟩

Share

Metrics

Record views

45

Files downloads

23