NET2 – Network management, and Applications
Thursday, 5 June 2025, 11:00-12:30, room 1.A
Session Chair: Johann Marquez-Barja (Univ. of Antwerpen & IMEC, BE)
RAN Slicing Design Policy for Integrated Sensing, Communication, and Computation
Ranyin Wang and Vasilis Friderikos (King’s College London, United Kingdom (Great Britain))
In the emerging 6G era, achieving ubiquitous intelligence requires perception technology to sense and collect information from the surrounding environment. While it presents significant challenges, it also offers substantial opportunities for delivering intelligent applications. Integrated sensing, communication, and computation (ISCC) has emerged as a key enabler for achieving this vision of intelligence in 6G. However, conventional one-size-fits-all network architectures are inadequate for meeting the diverse service demands of ISCC, as its performance spans multiple dimensions. In response, network slicing comes into view as a transformative architecture, redefining traditional networks to support multiple slices over a shared physical infrastructure, thereby satisfying the heterogeneous service requirements of various applications. In this context, we propose a RAN slicing framework for ISCC, enabling the simultaneous support of sensing, communication, and computation (SCC) services through tailored network slices. To this end, we formulate a slice design objective that accounts for the distinct SCC requirements. We further introduce a Deep Deterministic Policy Gradient (DDPG)-based algorithm of network slicing design policy, which determines the optimal strategy for jointly optimizing sensing accuracy, transmission latency, and processing delay. Numerical simulations show that the proposed algorithm achieves stable convergence and outperforms baseline Deep Reinforcement Learning (DRL) methods in terms of latency performance and sensing accuracy.
Data Unit Groups Implementation and Validation for Multi-Domain and Multi-Technology Deterministic 6G Systems
Sebastian Robitzsch and Abinaya Babu (InterDigital, United Kingdom (Great Britain)); Muhammad Awais Jadoon (InterDigital Inc, United Kingdom (Great Britain)); Filipe Conceição (InterDigital Europe, United Kingdom (Great Britain)); Laksh Bhatia (InterDigital, United Kingdom (Great Britain))
Deterministic 6G systems fill the gap of providing end-to-end networking capabilities across multiple domains and technologies for applications that are in need for stringent Key Performance Indicator realisation, e.g. Industry 4.0 verticals. In this paper, a solution is realised to enable 6G deterministic communications for all IP traffic in a multi-domain and multi-technology environment. Special focus is given to a proposed data plane concept, called Data Unit Group, and the integration of a Data Unit Group-enabled DetNet router in an end-to-end Network Digital Twin-driven control plane, which manages the entire service provisioning ensuring deterministic Key Performance Indicators fulfilment. The proffered data plane solution and implementation has been validated in a lab testbed and shows that the realisation can operate at line speed without any networking performance impact.
Toward Adaptive and High-Performance XR Services via Network Programmability and Monitoring
Carolina Fernández-Martínez and Sergio Giménez-Antón (i2CAT Foundation, Spain); Amr Abdel Nabi (i2CAT, Spain); César Cajas Parra and Genís Castillo Gómez-Raya (i2CAT Foundation, Spain); Mario Montagud (Universitat de València & i2CAT Foundation, Spain)
Contemporary eXtended Reality (XR) services typically encounter performance and reliability limitations, especially when deployed over distributed environments with varying resources. This paper presents a modular and flexible XR-aware framework that (i) exposes network programmability interfaces to control different resources and segments in an unified manner, being capable of (ii) comprehensively monitoring and alerting cross-layer metrics from the XR service, network and cloud continuum infrastructure domains; and (iii) exploiting this comprehensive awareness to trigger dynamic (re-)configurations and mitigation actions, based on a set of criteria and Levels of Service (LoS) rules, with the goals of maximising the adaptivity, reliability and efficiency of the underlying XR services. Validation tests under a real Beyond 5G (B5G) testbed, derived from relevant use cases within the holographic communications domain, prove the efficiency and responsiveness of the proposed framework and anticipate its potential benefits.
A Functional Framework for Network Digital Twins
Sébastien Faye (Luxembourg Institute of Science and Technology (LIST), Luxembourg); Paola Soto (IMEC, Belgium & Universidad de Antioquia, Colombia); Gaetano Volpe (Politecnico di Bari, Italy); Ayat Zaki-Hindi (Luxembourg Institute of Science and Technology (LIST), Luxembourg); Burkhard Hensel (Technische Universität Dresden, Germany); German Castellanos (Accelleran NV, Belgium); Ion Turcanu (Luxembourg Institute of Science and Technology, Luxembourg); Christoph Sommer (TU Dresden, Germany); Sidi-Mohammed Senouci (University of Bourgogne – ISAT Nevers, France); Andrey Belogaev (University of Antwerp, Belgium & IMEC, Belgium); Miguel Camelo Botero (IMEC, Belgium)
This paper proposes a structured framework for Network Digital Twin (NDT) in 6G, addressing the lack of formal definitions and standardised architectural guidelines in the field. By refining the conceptual foundations of NDT, it introduces a functional architecture, clarifies key components such as AI-driven workflows, a simulation framework, data management, and orchestration, and provides concrete examples illustrating their role in network automation, optimisation, and predictive analytics. The goal is to offer a cohesive reference model that guides the community in shaping NDT development, ensuring interoperability, scalability, adaptability, and seamless integration into future AI-native 6G networks for enhanced intelligence and efficiency.
Integrating 3GPP and Non-3GPP Technologies for Hybrid Positioning in B5G Networks
Viktoria-Maria Alevizaki (National and Kapodistrian University of Athens, Greece); Alexandros Manolopoulos (National Kapodistrian University of Athens, Greece); Markos Anastasopoulos and Anna Tzanakaki (National and Kapodistrian University of Athens, Greece)
Positioning is crucial for Beyond 5G (B5G) networks, enabling applications like industrial automation, autonomous transportation, and augmented reality. Despite 3GPP’s progress, seamless integration with non-3GPP technologies for indoor localization remains challenging. This work introduces a hybrid fingerprinting method that combines signal strength from both 3GPP and non-3GPP networks, utilizing a private 5G testbed with integrated Wi-Fi access points. The positioning algorithm operates as an xApp within the near-RT RAN Intelligent Controller (RIC). We also propose a novel scheme to link non-3GPP networks with the RIC, enhancing real-time decision-making and improving localization accuracy. Experimental results confirm the effectiveness of our approach.
