Analysis of RAN slicing for cellular V2X and mobile broadband services based on reinforcement learning

Radio Access Network (RAN) slicing is one of the key enablers to provide the design flexibility and enable 5G system to support heterogeneous services over a common platform (i.e., by creating a customized slice for each service). In this regard, this paper provides an analysis of a Reinforcement Le...

Descripción completa

Detalles Bibliográficos
Autores: Albonda, Haider Daami Resin, Pérez Romero, Jordi|||0000-0001-9131-5013
Tipo de recurso: artículo
Fecha de publicación:2020
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/329738
Acceso en línea:https://hdl.handle.net/2117/329738
https://dx.doi.org/10.4108/eai.13-7-2018.163841
Access Level:acceso abierto
Palabra clave:Mobile communication systems
Computer networks
Vehicle-to-everything (V2X)
Reinforcement learning
Network slicing
RAN slicing
Comunicacions mòbils, Sistemes de
Ordinadors, Xarxes d'
Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Radiocomunicació i exploració electromagnètica::Comunicacions mòbils
Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Telemàtica i xarxes d'ordinadors
Descripción
Sumario:Radio Access Network (RAN) slicing is one of the key enablers to provide the design flexibility and enable 5G system to support heterogeneous services over a common platform (i.e., by creating a customized slice for each service). In this regard, this paper provides an analysis of a Reinforcement Learning (RL)-based RAN slicing strategy for a heterogeneous network with two generic services of 5G, namely enhanced mobile broadband (eMBB) and vehicle-to-everything (V2X). In particular, this paper investigates the RAN slicing by evaluating the proposed scheme under different algorithm configurations (i.e., number of actions of RL) and parameters in order to analyze the performance in terms of metrics such as RL convergence time and to demonstrate the capability of the algorithm to perform an efficient allocation of resources among slices. In addition, this study compares the results obtained by the proposed solution to those obtained with a Proportional Scheme.