The rapid evolution of telecommunication networks is poised to have a profound impact on the complexity of future networks, promising a revolutionary leap in the field of communications. This rapid evolution necessitates the exploration of novel techniques that enable adaptive, flexible, and intelligent decision-making in resource management, orchestration and access control. One promising approach to implementing the network intelligence paradigm is through the adoption of the Network Digital Twin (NDT) paradigm, aiming at modeling the behavior of devices, communication links, operating environments, and applications within complex networking systems. The main objective of this article is to define IDLE, an Intent-based Digital twin LEarning framework that enables the possibility of performing simultaneous What-if Scenario analyses to support decision-making for real-time network management and orchestration. A proof-of-concept (POC) of the proposed architecture is described, targeted to manage horizontal offload inside a Flying Ad-Hoc Network (FANET) providing edge computing to ground devices in remote areas. Some numerical results are presented to demonstrate the gain achieved thanks to the proposed framework.
IDLE: A Digital Twin Framework for 6G Network Intelligence
Caruso A.;Grasso C.;Raftopoulos R.;Schembra G.
2024-01-01
Abstract
The rapid evolution of telecommunication networks is poised to have a profound impact on the complexity of future networks, promising a revolutionary leap in the field of communications. This rapid evolution necessitates the exploration of novel techniques that enable adaptive, flexible, and intelligent decision-making in resource management, orchestration and access control. One promising approach to implementing the network intelligence paradigm is through the adoption of the Network Digital Twin (NDT) paradigm, aiming at modeling the behavior of devices, communication links, operating environments, and applications within complex networking systems. The main objective of this article is to define IDLE, an Intent-based Digital twin LEarning framework that enables the possibility of performing simultaneous What-if Scenario analyses to support decision-making for real-time network management and orchestration. A proof-of-concept (POC) of the proposed architecture is described, targeted to manage horizontal offload inside a Flying Ad-Hoc Network (FANET) providing edge computing to ground devices in remote areas. Some numerical results are presented to demonstrate the gain achieved thanks to the proposed framework.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.