Researchers working on Artificial Intelligence (AI) need suitable datasets for training and testing 9 their models. When it comes to applications running through a mobile network, these datasets 10 are difficult to obtain, because network operators are hardly willing to expose their network data 11 or to open their network to experimentation. In this paper we show how Simu5G, a popular 5G 12 network simulator based on OMNeT++, can be used to circumvent this problem: it allows users 13 to log data at arbitrary spatial and temporal resolution, belonging to every network layer – from 14 the application to the physical one.
Exploiting Simu5G for Generating Datasets for Training and Testing AI Models for 5G/6G Network Applications
Giovanni Nardini
;Alessandro Noferi;Pietro Ducange;Giovanni Stea
2023-01-01
Abstract
Researchers working on Artificial Intelligence (AI) need suitable datasets for training and testing 9 their models. When it comes to applications running through a mobile network, these datasets 10 are difficult to obtain, because network operators are hardly willing to expose their network data 11 or to open their network to experimentation. In this paper we show how Simu5G, a popular 5G 12 network simulator based on OMNeT++, can be used to circumvent this problem: it allows users 13 to log data at arbitrary spatial and temporal resolution, belonging to every network layer – from 14 the application to the physical one.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.