Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 3
Encontrada(s) 1 página(s)

e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Artículo científico (JournalArticle)

Energy-aware Joint Orchestration of 5G and Robots: Experimental Testbed and Field Validation

  • Groshev, Milan
  • Zanzi, Lanfranco
  • Delgado, Carmen
  • Li, Xi
  • Oliva Delgado, Antonio de la
  • Costa-Pérez, Xavier
5G mobile networks introduce a new dimension for connecting and operating mobile robots in outdoor environments, leveraging cloud-native and offloading features of 5G networks to enable fully flexible and collaborative cloud robot operations. However, the limited battery life of robots remains a significant obstacle to their effective adoption in real-world exploration scenarios. This paper explores, via field experiments, the potential energy-saving gains of, a joint orchestration of 5G and Robot Operating System (ROS) that coordinates multiple 5G-connected robots both in terms of navigation and sensing, as well as optimizes their cloud-native service resource utilization while minimizing total resource and energy consumption on the robots based on real-time feedback. We designed, implemented and evaluated our proposed in an experimental testbed composed of commercial off-the-shelf robots and a local 5G infrastructure deployed on a campus. The experimental results demonstrated that significantly outperforms state-of-the-art approaches in terms of energy savings by offloading demanding computational tasks to the 5G edge infrastructure and dynamic energy management of on-board sensors (e.g., switching them off when they are not needed). This strategy achieves approximately ~15% energy savings on the robots, thereby extending battery life, which in turn allows for longer operating times and better resource utilization., The research leading to these results has been supported in part by the CERCA Programme / Generalitat de Catalunya, by the European Union’s H2020 6GGOALS Project (grant no. 101139232), by the SNS JU under the European Union’s Horizon Europe MultiX Project (grant no. 101192521) and Predict Project (grant no. 101095890), and by the Spanish Ministry of Economic Affairs and Digital Transformation and the European Union – NextGeneration EU (Call UNICO I+D 5G 2021, ref. number TSI-063000-2021-6 and TSI-063000-2021-122).
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Artículo científico (JournalArticle)

AI as a Service for Intelligent Mobile Networks: Extending Network Data Analytics Functions

  • Barroso Fernández, Carlos
  • Zahir Rodriguez, Adam
  • Picazo Martínez, Pablo
  • Oliva Delgado, Antonio de la
  • Bernardos Cano, Carlos Jesús
The integration of Artificial Intelligence (AI) into 5G networks has the potential to significantly enhance network resilience, adaptability, and service delivery. This work presents the design and implementation of an Artificial Intelligence as a Service (AIaaS) platform deployed within the 5G Core, enabling both network functions and end-user equipment (UEs) to access AI capabilities in a scalable, low-latency, and energy-efficient manner. Unlike cloud-based AI services or on-device inference, the proposed platform leverages the proximity and flexibility of the 5G network to deliver advanced AI models without overburdening the user device or incurring high transmission delays. The architecture is composed of distributed AI workers¿partially reusing the standardized Network Data Analytics Function (NWDAF)¿and a centralized control layer responsible for service orchestration and resource management. The solution is designed to support both internal (i.e., other application functions) and external consumers, and is adaptable to centralized or edge deployments. A Proof-of-Concept (PoC) implementation was developed using the SLICES-Madrid research infrastructure to validate the approach, demonstrating the feasibility of AIaaS within realistic 5G environments. The results underline the potential of AIaaS as a flexible enabler for intelligent network functions and AI-powered services across a wide range of verticals., This work has been partially funded by the Regional Government of Comunidad de Madrid under grant agreement No. TEC-2024COM-360 (Disco6G), by the European Commission Horizon Europe SNS JU MultiX (GA 101192521) Project, and by the Spanish Ministry of Economic Affairs and Digital Transformation and the European UnionNextGenerationEU through the UNICO 6G I+D 6G-EDGEDT and 6G-DATADRIVEN. This publication is part of the project 6GINSPIRE PID2022-137329OB-C42, funded by MCIN/ AEI/10.13039/501100011033/”, and the ESFRI-SLICES-CM2023 project, funded by the Comunidad de Madrid.
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Contribución de congreso (ConferenceOutput)

Bridging the gap between TSN and Open-Source

  • Rico Menéndez, David
  • Oliva Delgado, Antonio de la
  • Barroso Fernández, Carlos
  • Luque Schempp, Francisco
Proceedings of: 25th Anniversary International Conference on Transparent Optical Networks (ICTON), Barcelona (Spain), 7-10 July 2025, This paper presents a fully open-source TSN-enabled programmable software switch and Detnet router platform built atop eXpress Data Path (XDP) and Extended Berkeley Packet Filter (eBPF) in the Linux kernel. Our platform integrates IEEE 802.1Qbv time-aware shaping, IEEE 802.1Qcr Asynchronous Traffic Shaping, IEEE 802.1AS-based Precision Time Protocol (PTP) time synchronization, as well as DetNet functionalities including packet replication, elimination and ordering functions (PREOF).We evaluated the system in various traffic profiles and topologies, demonstrating that our software-based approach can achieve competitive performance while offering unprecedented programmability and rapid adaptability to evolving standards and use cases. We aim to catalyze further research, standardization, and deployment of TSN and DetNet solutions in diverse networking environments by openly releasing this platform., This work has been partially funded by the European Commission Horizon Europe SNS JU PREDICT-6G (GA 101095890), MultiX (GA 101192521), 6G-SANDBOX (GA 101096328) projects and the Spanish Ministry of Economic Affairs and Digital Transformation and the European Union- NextGenerationEU through the UNICO 5G I+D 6G-EDGEDT and 6GDATADRIVEN.