Concurrent decentralized channel allocation and access point selection using multi-armed bandits in multi BSS WLANs

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author López Raventós, Álvaro
• dc.contributor.author Bellalta, Boris
• dc.date.accessioned 2020-07-20T08:35:07Z
• dc.date.issued 2020
• dc.description.abstract Enterprise Wireless Local Area Networks (WLANs) consist of multiple Access Points (APs) covering a given area. In these networks, interference is mitigated by allocating different channels to neighboring APs. Besides, stations are allowed to associate to any AP in the network, selecting by default the one from which receive higher power, even if it is not the best option in terms of the network performance. Finding a suitable network configuration able to maximize the performance of enterprise WLANs is a challenging task given the complex dependencies between APs and stations. Recently, in wireless networking, the use of reinforcement learning techniques has emerged as an effective solution to efficiently explore the impact of different network configurations in the system performance, identifying those that provide better performance. In this paper, we study if Multi-Armed Bandits (MABs) are able to offer a feasible solution to the decentralized channel allocation and AP selection problems in Enterprise WLAN scenarios. To do so, we empower APs and stations with agents that, by means of implementing the Thompson sampling algorithm, explore and learn which is the best channel to use, and which is the best AP to associate, respectively. Our evaluation is performed over randomly generated scenarios, which enclose different network topologies and traffic loads. The presented results show that the proposed adaptive framework using MABs outperform the static approach (i.e., using always the initial default configuration, usually random) regardless of the network density and the traffic requirements. Moreover, we show that the use of the proposed framework reduces the performance variability between different scenarios. Also, results show that we achieve the same performance (or better) than static strategies with less APs for the same number of stations. Finally, special attention is placed on how the agents interact. Even if the agents operate in a completely independent manner, their decisions have interrelated effects, as they take actions over the same set of channel resources.en
• dc.description.sponsorship This work has been partially supported by the Spanish Ministry of Economy and Competitiveness under the Maria de Maeztu Units of Excellence Programme (MDM2015-0502), by the Spanish Government under grant WINDMAL PGC2018-099959-B-I00 (MCIU/AEI/FEDER,UE), by the Catalan Government under grant 2017-SGR-1188, and by a Gift from the Cisco University Research Program (CG#890107, Towards Deterministic Channel Access in High-Density WLANs) Fund, a corporate advised fund of Silicon Valley Community Foundation.
• dc.format.mimetype application/pdf
• dc.identifier.citation López-Raventós Á, Bellalta B. Concurrent decentralized channel allocation and access point selection using multi-armed bandits in multi BSS WLANs. Computer Networks. 2020 Oct;180:107381. DOI: 10.1016/j.comnet.2020.107381
• dc.identifier.doi http://dx.doi.org/10.1016/j.comnet.2020.107381
• dc.identifier.issn 1389-1286
• dc.identifier.uri http://hdl.handle.net/10230/45134
• dc.language.iso eng
• dc.publisher Elsevier
• dc.relation.ispartof Computer Networks. 2020 Oct;180:107381
• dc.relation.projectID info:eu-repo/grantAgreement/ES/2PE/PGC2018-099959-B-I00
• dc.rights © Elsevier http://dx.doi.org/10.1016/j.comnet.2020.107381
• dc.rights.accessRights info:eu-repo/semantics/openAccess
• dc.subject.keyword IEEE 802.11en
• dc.subject.keyword Machine learningen
• dc.subject.keyword Access point selectionen
• dc.subject.keyword Channel allocationen
• dc.subject.keyword Multi-armed banditsen
• dc.title Concurrent decentralized channel allocation and access point selection using multi-armed bandits in multi BSS WLANsen
• dc.type info:eu-repo/semantics/article
• dc.type.version info:eu-repo/semantics/acceptedVersion