GNU Radio Implementation and Demonstration of MALIN: “Multi-Arm bandits Learning for Internet-of-things Networks”

  • Lilian Besson
  • Rémi Bonnefoi
  • Christophe Moy

Abstract

We implement1an IoT network the following way: one gateway, one or several intelligent (learning) objects, embedding the proposed solution, and a traffic generator that emulates radio interferences frommany other objects. Intelligent objects communicate with the gateway with a wireless ALOHA-based protocol with no specific overhead for learning needs. We model the network access as a discrete sequential decision making, and using theframework and algorithms from Multi-Armed Bandit (MAB) learning, we show that intelligent objects can improve their access to the network by using load complexity and decentralized algorithms, such as UCB and Thompson Sampling.

Published
2021-01-02
How to Cite
BESSON, Lilian; BONNEFOI, Rémi; MOY, Christophe. GNU Radio Implementation and Demonstration of MALIN: “Multi-Arm bandits Learning for Internet-of-things Networks”. Proceedings of the GNU Radio Conference, [S.l.], v. 1, n. 1, jan. 2021. Available at: <https://pubs.gnuradio.org/index.php/grcon/article/view/79>. Date accessed: 11 aug. 2022.