2026-04-17T11:42:11Zhttps://recercat.cat/oai/request

oai:recercat.cat:2117/4489762026-02-07T11:53:30Zcom_2072_1033col_2072_452950

Artificial Intelligence Control Plane for deterministic networks Proof-of-Concept Calvillo Fernández, Alejandro Ravalli, Matteo Brenes Baranzano, Juan Carcel Cervera, José Luis Rico Menendez, David Agraz Bujan, Fernando Giardina, Pietro G. Spadaro, Salvatore Velasco Esteban, Luis Domingo Universitat Politècnica de Catalunya. Departament d'Arquitectura de Computadors Universitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions Universitat Politècnica de Catalunya. GCO - Grup de Comunicacions Òptiques Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Telemàtica i xarxes d'ordinadors Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial Deterministic network controller Network management services Control plane Multi-domain networks This paper presents the design and implementation of an Artificial Intelligence Control Plane (AICP) for deterministic networks, emphasizing the Proof-of-Concept (PoC) demonstration. The AICP framework integrates AI, digital twin technology, and real-time telemetry to manage complex network environments, ensuring reliable and low-latency communication. The PoC showcases the practical viability of the AICP by dynamically adapting to varying network demands and maintaining stringent to the Key Performance Indicator (KPI)s of the service. Extensive testing and real-world simulations highlight the framework's potential to enhance the efficiency and resilience of industrial communication networks. This work has been partially funded by the European Commission Horizon Europe SNS JU PREDICT-6G (GA101095890) Project and by the Spanish Ministry of Economic Affairs and Digital Transformation and the European Union-Next Generation EU through the UNICO 5G I+D 6G-EDGEDT-4 (TSI-063000-2021-124). Peer Reviewed Postprint (author's final draft) 2024 Conference report Calvillo, A. [et al.]. Artificial Intelligence Control Plane for deterministic networks Proof-of-Concept. A: Annual International Conference on Mobile Computing and Networking. «ACM MobiCom'24: proceedings of the Thirtieth International Conference on Mobile Computing and Networking: November 18-November 22, 2024, Washington D.C., DC, USA». New York: Association for Computing Machinery (ACM), 2024, p. 2407-2412. ISBN 979-8-4007-0489-5. DOI 10.1145/3636534.3696725 . 979-8-4007-0489-5 https://hdl.handle.net/2117/448976 10.1145/3636534.3696725 eng https://dl.acm.org/doi/abs/10.1145/3636534.3696725 info:eu-repo/grantAgreement/EC/HE/101095890/EU/PRogrammable AI-Enabled DeterminIstiC neTworking for 6G/PREDICT-6G Open Access 6 p. application/pdf Association for Computing Machinery (ACM)