AI-Empowered Software-Defined WLANs

The complexity of wireless and mobile networks is growing at an unprecedented pace. This trend is set to make current network control and management techniques based on analytical models and simulations impractical, especially if combined with the data deluge expected from future applications like A...

Descripción completa

Detalles Bibliográficos
Autores: Bayhan, Suzan, Coronado, Estefanía, Riggio, Roberto, Thomas, Abin
Tipo de recurso: artículo
Estado:Versión aceptada para publicación
Fecha de publicación:2021
País:España
Institución:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
Repositorio:Recercat. Dipósit de la Recerca de Catalunya
OAI Identifier:oai:recercat.cat:2072/531539
Acceso en línea:http://hdl.handle.net/2072/531539
Access Level:acceso abierto
Palabra clave:Software Networks
5G / 6G & Internet of Things
Artificial Intelligence & Big Data
621.3
Descripción
Sumario:The complexity of wireless and mobile networks is growing at an unprecedented pace. This trend is set to make current network control and management techniques based on analytical models and simulations impractical, especially if combined with the data deluge expected from future applications like Augmented and Mixed Reality. This is especially true for Software-Defined WLANs (SD-WLANs). It is our standpoint that to tame this increase in complexity, future SD-WLANs must follow an Artificial Intelligence (AI) native approach. In this paper, we present aiOS, an AI-based platform for SD-WLANs control and management. Our proposal is aligned with the most recent trends in in-network AI pushed by ITU-T and with the architecture for disaggregated radio access networks pushed by O-RAN. We validate aiOS in a practical use case, namely frame size optimisation in SD-WLANs, and elaborate on the long term evolution, challenges, and scenarios for AI-assisted network automation in the wireless and mobile networking domain.