Usage of network simulators in machine-learning-assisted 5G/6G networks

Without any doubt, Machine Learning (ML) will be an important driver of future communications due to its foreseen performance when applied to complex problems. However, the application of ML to networking systems raises concerns among network operators and other stakeholders, especially regarding tr...

Descripción completa

Detalles Bibliográficos
Autores: Wilhelmi Roca, Francesc, Carrascosa Zamacois, Marc, Cano, Cristina, Jonsson, Anders, 1973-, Ram, Vishnu, Bellalta, Boris
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:10230/56118
Acceso en línea:http://hdl.handle.net/10230/56118
http://dx.doi.org/10.1109/MWC.001.2000206
Access Level:acceso abierto
Palabra clave:Training data
Communication systems
Machine learning
Stakeholders
Reliability
Wireless fidelity
5G mobile ommunication
6G mobile communication
Descripción
Sumario:Without any doubt, Machine Learning (ML) will be an important driver of future communications due to its foreseen performance when applied to complex problems. However, the application of ML to networking systems raises concerns among network operators and other stakeholders, especially regarding trustworthiness and reliability. In this article, we devise the role of network simulators for bridging the gap between ML and communications systems. In particular, we present an architectural integration of simulators in ML-aware networks for training, testing, and validating ML models before being applied to the operative network. Moreover, we provide insights into the main challenges resulting from this integration, and then give hints discussing how they can be overcome. Finally, we illustrate the integration of network simulators into ML-assisted communications through a proof-of-concept testbed implementation of a residential WiFi network.