2026-04-17T02:49:11Zhttps://recercat.cat/oai/request

oai:recercat.cat:2117/4493832026-01-16T10:30:46Zcom_2072_1033col_2072_452950

Digital twin as a service for 6G radio access networks: Functional model and key challenges Campoy García, David Vilà Muñoz, Irene Pérez Romero, Jordi Sallent Roig, Oriol Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Telemàtica i xarxes d'ordinadors Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic 6G RAN Digital twin Functional model Network optimization Capacity modeling This paper presents a scalable and flexible functional model for the 6G-Radio Access Network Digital Twin (6G-RANDT), designed through a service-oriented approach to support next-generation radio access network optimization and intelligent management. The proposed model includes an application programming interface for seamless interaction with a 6G-RANDT consumer, 6G-RANDT instances for RAN emulation and simulation, and a 6G-RANDT orchestrator for management and data integration. Several 6G-RANDT typologies and measurement requirements are explored to address diverse use cases. Moreover, key challenges in 6GRANDT development are discussed. To evaluate the impact of modeling accuracy in 6G-RANDTs, we conducted a cellular capacity modeling experiment in which different 6G-RANDT instances were used to train a reinforcement learning (RL)-based capacity-sharing algorithm. Results show that the impact of capacity modeling strategies on the 6G-RANDT instance accuracy and RL agent performance is highly dependent on the cell environment, emphasizing the need for tailored 6G-RANDT services based on specific RAN environment conditions and applications. This work has been partially funded by the Smart Networks and Services Joint Undertaking (SNS JU) under the European Union’s Horizon Europe research and innovation programme under Grant Agreement No. 101096034 (VERGE project), grant ARTIST (PID2020-115104RB-I00) and TRAINER-6G (PID2023-146748OB-I00) funded by MCIN/AEI/10.13039/501100011033 and by ERDF/EU. Peer Reviewed Postprint (author's final draft) 2025 Conference report https://ieeexplore.ieee.org/document/11046305 info:eu-repo/grantAgreement/EC/HE/101096034/EU/AI-powered eVolution towards opEn and secuRe edGe architEctures/VERGE info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/PID2020-115104RB-I00/ES/ACCESO RADIO INTELIGENTE CON INTEGRACION DE DISPOSITIVOS DE USUARIO/ info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023/PID2023-146748OB-I00/ES/HACIA REDES DE ACCESO A RADIO AI-NATIVAS Y CONFIABLES PARA LA ERA 6G/ Open Access Institute of Electrical and Electronics Engineers (IEEE)