NET2 – Network Softwarisation
Wednesday, 3 June 2026, 17:00-18:30, room Dirección de Certámenes (1st floor)
Session Chair: Johann Marquez-Barja (Univ. of Antwerpen & IMEC, BE)
Cloud-Native Orchestration for Transport Networks
Saptarshi Ghosh (Digital Catapult, United Kingdom (Great Britain) & London South Bank University, United Kingdom (Great Britain)); Alistair Duke (British Telecom, United Kingdom (Great Britain)); Ioannis Mavromatis, Mark Rouse, Konstantinos Antonakoglou and Konstantinos Katsaros (Digital Catapult, United Kingdom (Great Britain)); Andy Corston-Petrie (British Telecom, United Kingdom (Great Britain))
Transport networks form the backbone of large-scale communication systems, typically realised through the interconnection of transit autonomous systems (e.g., Internet Service Providers) that deliver IP connectivity between geographically distributed services with differentiated reliability and performance guarantees. Recent advances in large-scale Software-Defined Wide Area Networks (SD-WAN), together with the evolution of telco cloud orchestration and API-driven network operating systems, have created new opportunities for dynamic, on-demand provisioning of transport services across heterogeneous domains. In this paper, we present a proof-of-concept cross-domain orchestration architecture for cloud-native transport networks, introducing a novel \textbf abstraction that coordinates underlying multi-provider infrastructure. The proposed approach leverages telco cloud orchestration principles to enable Network-as-a-Service capabilities, including Quality-of-Service-aware inter-service connectivity, programmable network slicing, and fine-grained traffic control using eBPF-based data-plane mechanisms. An experimental evaluation demonstrates the architecture's feasibility and highlights its potential to improve scalability, service differentiation, and operational automation in next-generation transport networks.
Experimental Evaluation of Control-Based Beamforming for Interference Mitigation in O-RAN
Ilias Floudas, Christos Pallis and Markos Anastasopoulos (National and Kapodistrian University of Athens, Greece); Jesús Gutiérrez (IHP – Leibniz-Institut für Innovative Mikroelektronik, Germany); Anna Tzanakaki (National and Kapodistrian University of Athens, Greece)
Open Radio Access Network (O-RAN) architectures enable near-real-time programmability of radio functions through standardized interfaces, allowing external control applications to optimize Radio Access Network (RAN) performance. This capability is particularly relevant in interference- and jamming-challenged environments, where rapid adaptation is required to preserve reliable link performance. This paper presents a lightweight beam-steering mechanism implemented as a near-real-time RAN Intelligent Controller (near-RT RIC) xApp for uplink jamming mitigation. The proposed solution adopts a classic control-theoretic approach implementing a Proportional-Integral-Derivative (PID) controller to adjust beam parameters based on near-real-time throughput feedback. Unlike optimization- or learning-based approaches, the proposed method incurs minimal computational overhead and provides predictable control behavior compatible with near-real-time O-RAN constraints. Experimental evaluation under controlled jamming conditions demonstrates that the PID-based xApp effectively restores and stabilizes User Equipment (UE) throughput, while maintaining bounded and smooth control behavior under dynamic interference conditions.
Towards Trustworthy 6G Network Digital Twins: A Framework for Validating Counterfactual What-If Analysis in Edge Computing Resources
Julian Jimenez Agudelo (University of Antwerp, Belgium); Paola Soto (IMEC, Belgium & University of Antwerp, Belgium); Ayat Zaki-Hindi (Luxembourg Institute of Science and Technology (LIST), Luxembourg); Jean-Sébastien Sottet (Luxembourg Institute of Science and Technology, Luxembourg); Sébastien Faye (Luxembourg Institute of Science and Technology (LIST), Luxembourg); Nina Slamnik-Krijestorac (University of Antwerp-IMEC, Belgium); Johann Marquez-Barja (University of Antwerpen & IMEC, Belgium); Miguel Camelo Botero (University of Antwerp – imec, Belgium)
Network Digital Twins (NDT) enable safe what-if analysis for 6G cloud-edge infrastructures, but adoption is often limited by fragmented workflows from telemetry to validation. We present a data-driven NDT framework that extends 6G-TWIN with a scalable pipeline for cloud-edge telemetry aggregation and semantic alignment into unified data models. Our contributions include: (i) scalable cloud-edge telemetry collection, (ii) regime-aware feature engineering capturing the network's scaling behavior, and (iii) a validation methodology based on Sign Agreement and Directional Sensitivity. Evaluated on a Kubernetes-managed cluster, the framework extrapolates performance to unseen high-load regimes. Results show both DNN and XGBoost achieve high regression accuracy (R^2) > 0.99), while the XGBoost model delivers superior directional reliability (S_a > 0.90), making the NDT a trustworthy tool for proactive resource scaling in out-of-distribution scenarios.
Interoperable rApp/xApp Control over O-RAN for Mobility-Aware Dynamic Spectrum Allocation
Anastasios E. Giannopoulos (Four Dot Infinity, Greece); Sotirios Spantideas (Four Dot Infinity, Athens, Greece); Maria Lamprini Bartsioka (National Technical University of Athens, Greece); Panagiotis Trakadas (University of Athens, Greece)
Open Radio Access Networks (O-RAN) enable the disaggregation of radio access functions and the deployment of control applications across different timescales. However, designing interoperable control schemes that jointly exploit long-term traffic awareness and near-real-time radio resource optimization remains a challenging problem, particularly under dense multi-cell interference and heterogeneous service demands. This paper proposes an interoperable rApp/xApp-driven dynamic spectrum allocation (DSA) framework for O-RAN, based on a graph-theoretic formulation of physical resource block (PRB) assignment. The proposed architecture leverages a non-real-time radio intelligent controller (Non-RT RIC) rApp to predict aggregated traffic evolution and generate high-level spectrum policies at the minutes timescale, while a near-real-time RIC (Near-RT RIC) xApp constructs a user-centric conflict graph and performs fairness-aware PRB allocation at sub-second timescales. To mitigate persistent user starvation, a conflict-aware modified proportional fair (MPF) scheduling mechanism is applied, enabling controlled interference-free PRB time-sharing. Extensive simulation results demonstrate that the proposed framework significantly improves the PRB assignment success rate (above 90%) and service-share fairness (above 85%) across different channel configurations and user demands, while maintaining architectural separation and rApp/xApp interoperability in accordance with O-RAN principles.
An Evolved Open SDK for Federated 6G Testbeds Through the Open Operator Platform
César Cajas Parra (i2CAT Foundation, Spain); Claudia Carballo González (i2CAT, Spain); Miguel Catalan-Cid and August Betzler (i2CAT Foundation, Spain); Mohammadreza Mosahebfard (i2CAT Foundation, Spain & Universitat Politècnica de Catalunya, Spain); Sergio Giménez-Antón (i2CAT Foundation, Spain & UPC Universitat Politecnica de Catalunya, Spain)
The realisation of a federated 6G ecosystem requires practical mechanisms to expose and orchestrate heterogeneous network and edge resources across administrative domains in a scalable and standard-compliant manner. While initiatives such as CAMARA, GSMA Open Gateway, and O-RAN provide key building blocks for service exposure and programmability, their integration into a unified, multi-domain operational framework remains an open challenge. This paper presents the Open-source Software Development Kit (Open SDK) release 2 (R2), developed within the SUNRISE-6G project and contributed to the ETSI Software Development Group Open Operator Platform (SDG OOP). The evolved Open SDK serves as an abstraction and translation layer, enabling interoperable service exposure and federation across edge cloud platforms, 5G core networks, and O-RAN environments. Compared to its initial release, Open SDK R2 extends support for GSMA-compliant federation workflows, introduces a dedicated O-RAN Transformation Function (TF), and enhances standards compliance through schema-based validation. The paper details the architectural integration of the Open SDK within the SUNRISE-6G OP, the organisation of its TFs across multiple domains, and the validation of its functionality over heterogeneous platforms. The results demonstrate how the evolved Open SDK enables modular, reusable, and standards-aligned federation logic, supporting cross-operator service deployment.
