# "Upper-Confidence Bound for Channel Selection in LPWA Networks with Retransmissions" This repository contains the LaTeX code of a research article written by [Rémi Bonnefoi](http://remibonnefoi.wordpress.com/), [Lilian Besson](https://perso.crans.org/besson/), Julio Cesar Manco Vasquez and [Christophe Moy](https://moychris.wordpress.com/), entitled "Upper-Confidence Bound for Channel Selection in LPWA Networks with Retransmissions". Our article ([see this PDF](https://perso.crans.org/besson/articles/BMBM__IEEE_WCNC__2019.pdf)) was sent to the [MOTION 2019 workshop](https://sites.google.com/view/wcncworkshop-motion2019) at [IEEE WCNC 2019](http://wcnc2019.ieee-wcnc.org/authors/call-papers) conference in January 2019. - PDF : [BMBM_IEEEWCNC_2019.pdf](https://hal.inria.fr/hal-XXX/document) - HAL notice : [BMBM_IEEEWCNC_2019](https://hal.inria.fr/hal-XXX/) - BibTeX : [BMBM_IEEEWCNC_2019.bib](https://hal.inria.fr/hal-XXX/bibtex) - Source code and documentation: [on Bitbucket](https://bitbucket.org/scee_ietr/ucb_smart_retrans) [![Published](https://img.shields.io/badge/Published%3F-yes-green.svg)](https://hal.inria.fr/hal-XXX) [![Maintenance](https://img.shields.io/badge/Maintained%3F-done-blue.svg)](https://bitbucket.org/lbesson/XXX/) [![Ask Me Anything !](https://img.shields.io/badge/Ask%20me-anything-1abc9c.svg)](https://bitbucket.org/lbesson/ama) > [I (Lilian Besson)](https://perso.crans.org/besson/) have [started my PhD](https://perso.crans.org/besson/phd/) in October 2016, and this is a part of my **on going** research in 2019. ---- ## Abstract In this paper, we propose and evaluate different learning strategies based on Multi-Arm Bandit (MAB) algorithms. They allow Internet of Things (IoT) devices to improve their access to the network and their autonomy, while taking into account the impact of encountered radio collisions. For that end, several heuristics employing Upper-Confident Bound (UCB) algorithms are examined, to explore the contextual information provided by the number of retransmissions. Our results show that approaches based on UCB obtain a significant improvement in terms of successful transmission probabilities. Furthermore, it also reveals that a pure UCB channel access is as efficient as more sophisticated learning strategies. ## Thanks This work is partially supported by the French National Research Agency (ANR), under the projects SOGREEN and EPHYL (grants coded: N ANR-14-CE28-0025-02, and by N. ANR-16-CE25-0002-03, respectively), by Région Bretagne, France, the French Ministry of Higher Education and Research (MENESR), by École Normale Supérieure de Paris-Saclay, by European Union, through the European Regional Development Fund (ERDF), and by Ministry of Higher Education and Research, Brittany and Rennes Métropole, through the CPER Project SOPHIE / STIC & Ondes. Note that Rémi Bonnefoi is now with Edison Ways. ---- ## :scroll: License ? [![GitHub license](https://img.shields.io/github/license/Naereen/badges.svg)](https://bitbucket.org/lbesson/XXX/src/master/LICENSE) [MIT Licensed](https://lbesson.mit-license.org/) (file [LICENSE](LICENSE)). © 2018-2019 [Rémi Bonnefoi](http://remibonnefoi.wordpress.com/), [Lilian Besson](https://perso.crans.org/besson/), Julio César Manco Vasquez and [Christophe Moy](https://moychris.wordpress.com/) [![Published](https://img.shields.io/badge/Published%3F-yes-green.svg)](https://hal.inria.fr/hal-XXX) [![Maintenance](https://img.shields.io/badge/Maintained%3F-done-blue.svg)](https://bitbucket.org/lbesson/XXX/) [![Ask Me Anything !](https://img.shields.io/badge/Ask%20me-anything-1abc9c.svg)](https://bitbucket.org/lbesson/ama) [![Analytics](https://ga-beacon.appspot.com/UA-38514290-17/bitbucket.org/lbesson/XXX/README.md?pixel)](https://bitbucket.org/lbesson/XXX/) [![ForTheBadge uses-badges](http://ForTheBadge.com/images/badges/uses-badges.svg)](http://ForTheBadge.com) [![ForTheBadge uses-git](http://ForTheBadge.com/images/badges/uses-git.svg)](https://GitHub.com/) [![forthebadge made-with-overleaf](https://img.shields.io/badge/Made%20with-OverLeaf-1f425f.svg)](https://www.overleaf.com/) [![forthebadge made-with-latex](https://img.shields.io/badge/Made%20with-LaTeX-1f425f.svg)](https://www.latex-project.org/) [![ForTheBadge built-with-science](http://ForTheBadge.com/images/badges/built-with-science.svg)](https://perso.crans.org/besson/)