ADROIT6G targets establishing a revolutionary 6G wireless system architecture designed to meet emerging ap- plications’ performance demands. The current 5G design is redesigned and enhanced by implementing a comprehensive distributed and dynamic framework, wherein compute nodes are dispersed across the far-edge, edge, and cloud domains. Additionally, this architecture incorporates 6G terrestrial and non-terrestrial communications to establish a resilient network. Distributed computing nodes located at the far-edge, edge, and cloud domains facilitate deploying virtual functions of software- defined disaggregated RAN and core networks, virtual applica- tions, and AI agents. These nodes are dynamically orchestrated as part of the overall network control and management strate- gies. The architecture of ADROIT6G comprises three primary frameworks that operate on a programmable inter-computing and inter-network infrastructure. These frameworks include the AI-driven Management and Orchestration Framework, the Fully distributed and secure AI/ML Framework for CrowdSourcing AI Framework, and the BDI-, AI-driven Unified, and Open Control Operations Framework. Additionally, implementing a closed-loop functions component is established and specifically engineered to enhance the efficiency of network and service operations over infrastructure resources. These components collaborate harmoniously to establish a complex and adaptable 6G network infrastructure capable of attaining the ambitious objectives and key performance indicators established for 6G, guaranteeing a future-oriented 6G network environment.
ADROIT6G A Fully Distributed and Dynamic AI-Powered Architecture for the 6G Networks / Ioannou, Iacovos; Christophorou, Christophoros; Vassiliou, Vasos; Christofi (eBOS Technologies, Loizos; Cyprus), ; S Vardakas, John; Seder, Erin E.; Chiasserini, Carla Fabiana; Iordache, Marius; Ben Issaid, Chaouki; Ioannis, Markopoulos; Franzese, Giulio; Järvet, Tanel; Verikoukis, Christos. - ELETTRONICO. - (2024). (Intervento presentato al convegno 2024 EuCNC & 6G Summit tenutosi a Antwerp (Belgium) nel June 2024).
ADROIT6G A Fully Distributed and Dynamic AI-Powered Architecture for the 6G Networks
Carla Fabiana Chiasserini;
2024
Abstract
ADROIT6G targets establishing a revolutionary 6G wireless system architecture designed to meet emerging ap- plications’ performance demands. The current 5G design is redesigned and enhanced by implementing a comprehensive distributed and dynamic framework, wherein compute nodes are dispersed across the far-edge, edge, and cloud domains. Additionally, this architecture incorporates 6G terrestrial and non-terrestrial communications to establish a resilient network. Distributed computing nodes located at the far-edge, edge, and cloud domains facilitate deploying virtual functions of software- defined disaggregated RAN and core networks, virtual applica- tions, and AI agents. These nodes are dynamically orchestrated as part of the overall network control and management strate- gies. The architecture of ADROIT6G comprises three primary frameworks that operate on a programmable inter-computing and inter-network infrastructure. These frameworks include the AI-driven Management and Orchestration Framework, the Fully distributed and secure AI/ML Framework for CrowdSourcing AI Framework, and the BDI-, AI-driven Unified, and Open Control Operations Framework. Additionally, implementing a closed-loop functions component is established and specifically engineered to enhance the efficiency of network and service operations over infrastructure resources. These components collaborate harmoniously to establish a complex and adaptable 6G network infrastructure capable of attaining the ambitious objectives and key performance indicators established for 6G, guaranteeing a future-oriented 6G network environment.File | Dimensione | Formato | |
---|---|---|---|
1571006033 final.pdf
accesso aperto
Tipologia:
1. Preprint / submitted version [pre- review]
Licenza:
Pubblico - Tutti i diritti riservati
Dimensione
225.07 kB
Formato
Adobe PDF
|
225.07 kB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/2987503