Lightweight testbed for machine learning evaluation in 5G networks
Visualitza/Obre
Estadístiques de LA Referencia / Recolecta
Inclou dades d'ús des de 2022
Cita com:
hdl:2117/185190
Tipus de documentText en actes de congrés
Data publicació2019
Condicions d'accésAccés obert
Llevat que s'hi indiqui el contrari, els
continguts d'aquesta obra estan subjectes a la llicència de Creative Commons
:
Reconeixement-NoComercial-SenseObraDerivada 3.0 Espanya
Abstract
The adoption of Software Define Networking, Network Function Virtualization and Machine Learning will play a key role in the control and management of fifth-generation (5G) networks in order to meet the specific requirements of vertical industries and the stringent requirements of 5G. Machine learning could be applied in 5G networks to deal with issues such as traffic prediction, routing optimization and resource management. To evaluate the adoption of machine learning in 5G networks, an adequate testing environment is required. In this paper, we introduce a lightweight testbed, which utilizes the benefits of container lightweight virtualization technology to create machine learning network functions over the well-known Mininet network emulator. As a use case of this testbed, we present an experimental real-time bandwidth prediction using the Long Short Term Memory recurrent neural network.
CitacióHernández, C.; Cervelló-Pastor, C. Lightweight testbed for machine learning evaluation in 5G networks. A: Jornadas de Ingeniería Telemática. "JITEL 2019 - XIV Jornadas de Ingeniería Telemática, Zaragoza, Spain: 22-24 octubre de 2019: proceedings book". 2019, p. 1-6.
Fitxers | Descripció | Mida | Format | Visualitza |
---|---|---|---|---|
Lightweight Testbed for Machine Learning-5G.pdf | article principal | 335,9Kb | Visualitza/Obre |