Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 4
Encontrada(s) 1 página(s)

e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Contribución de congreso (ConferenceOutput)

kaNSaaS: Combining Deep Learning and Optimization for Practical Overbooking of Network Slices

  • Alcalá Marín, Sergi
  • Bazco-Nogueras, Antonio
  • Banchs Roca, Albert
  • Fiore, Marco
Cloud-native mobile networks pave the road for Network Slicing as a Service (NSaaS), where slice overbooking is a promising management strategy to maximize the revenues from admitted slices by exploiting the fact they are unlikely to fully utilize their reserved resources concurrently. While seminal works have shown the potential of overbooking for NSaaS in simplistic cases, its realization is challenging in practical scenarios with realistic slice demands, where its actual performance remains to be tested. In this paper, we propose kaNSaaS, a complete solution for NSaaS management with slice overbooking that combines deep learning and classical optimization to jointly solve the key tasks of admission control and resource allocation. Experiments with large-scale measurement data of actual tenant demands show that kaNSaaS increases the network operator profits by 300% with respect to NSaaS management strategies that do not employ overbooking, while outperforming by more than 20% state-of-the-art overbooking-based approaches., We thank the Mobihoc anonymous reviewers for their helpful comments and guidance. The work of S. Alcalá-Marín was supported by the European Union's Horizon 2020 research and innovation programme under grant agreements no. 101017109 "DAEMON". The work of A. Bazco-Nogueras was supported by the Regional Government of Madrid through the grant 2020-T2/TIC-20710 for Talent Attraction. The work of A. Banchs was also supported in part by the European Union's Horizon-JU-SNS-2022 Research and Innovation Programme under Grant Agreement No. 101095871 (TrialsNet) and by the Spanish Ministry of Economic Affairs and Digital Transformation and the European Union-NextGeneration EU through the UNICO 5G I+D 6G-CLARION project. The work of M. Fiore was supported by the European Union-NextGenerationEU through the UNICO 5G I+D project no. TSI-063000-2021-52 "AEON-ZERO".
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Contribución de congreso (ConferenceOutput)

Trials Supported by Smart Networks Beyond 5G: the TrialsNet Approach

  • Bianzino, Aruna Prem
  • Gramaglia, Marco
  • Munafó, Maurizio
  • Basso, Andrea
  • Osman, Hassan
  • Pantazi, Niki
  • Caratti, Giancarlo
  • Papagiannopoulos, Nikos
  • Pessotto, Lorenzo
  • Petrache, Cristian
  • Provvedi, Silvia
  • Trogolo, Alessandro
  • Scivoletto, Gabriele
  • Vidal, Albert
  • Iovanna, Paola
  • Comsa, Ciprian
  • Di Giglio, Andrea
  • García, Carolina
  • Georgakopoulos, Andreas
  • Giaccone, Paolo
  • Giannopoulou, Nelly
  • Karanassiou, Gianna
  • Laurino, Marco
  • Márquez-Barja, Johann M.
  • Maiettini, Elisa
  • Martínez López, Miguel A.
  • Natale, Lorenzo
  • Osman, Hassan
  • Pantazi, Niki
  • Papagiannopoulos, Nikos
  • Pessotto, Lorenzo
  • Petrache, Cristian
  • Provvedi, Silvia
  • Scivoletto, Gabriele
  • Trogolo,Alessandro
  • Vidal, Albert
Proceedings of: 2023 IEEE Future Networks World Forum (FNWF). 13–15 November 2023 // Baltimore, MD, USA, TrialsNet is a project focused on improving European urban ecosystems through 13 innovative use cases in the three representative domains of Infrastructure, Transportation, Security and Safety; eHealth and Emergency; and Culture, Tourism, and Entertainment. These use cases will be implemented across different clusters in Italy, Spain, Greece, and Romania, involving real users. This paper provides an overview of the various use cases that will be trialled in different contexts through the platform and network solutions that will be deployed by the project based on advanced functionalities such as dynamic slicing management, NFV, MEC, AI/ML, and others. To this end, TrialsNet will develop assessment frameworks to measure the impact of use cases on a technical, socio-economic, and societal level through the definition and measurement of proper Key Performance Indicators (KPIs) and Key Value Indicators (KVIs). The project seeks to identify network limitations, optimize infrastructure, and define new requirements for next-generation mobile networks. Ultimately, TrialsNet aims to enhance livability in urban environments by driving advancements in various domains., The TrialsNet project has received funding from the European Union’s Horizon-JU-SNS-2022 Research and Innovation Programme under Grant Agreement No. 101095871.
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Contribución de congreso (ConferenceOutput)

Quantum Computing in the RAN with Qu4Fec: Closing Gaps Towards Quantum-based FEC processors

  • Apostolakis, Nikolaos
  • Sierra Obea, Marta
  • Gramaglia, Marco
  • Ayala Romero, José A.
  • García Saavedra, Andrés
  • Fiore, Marco
  • Banchs Roca, Albert
  • Costa Pérez, Xavier
Proceedings of: ACM SIGMETRICS 2025, 9-13 june 2025. Stony Brook, New York (USA), In mobile communication systems, the increasing densification of radio access networks is creating unprecedented computational stress for baseband processing, threatening the industry's sustainability, and new computing paradigms are urgently needed to improve the efficiency of wireless processors. Quantum computing promises to revolutionize many computing-intensive tasks across diverse fields and therefore may be the key to realizing ultra-dense next-generation mobile systems that remain economically and environmentally viable. This paper investigates the potential of Quantum computing to accelerate Forward Error Correction (FEC), the most compute-heavy component of wireless processors. We first propose Qu4Fec, a novel solution for decoding Low-Density Parity Check (LDPC) codes on Quantum Processing Units (QPUs), which we show to outperform state-of-the-art approaches, by reducing the Block Error Rate (BLER) by nearly an order of magnitude in simulation. We then implement Qu4Fec on a real-world QPU platform to study its practical viability and performance. Our experiments reveal that current cutting-edge QPU architectures curb the capabilities of FEC and expose the underlying factors, including long qubit chains, scaling, and quantization. Based on these insights, we suggest original blueprints for future QPUs that can better support Quantum-based wireless processors. Overall, this paper provides a reliable reality check for the feasibility of wireless processing on Quantum annealers: as QPUs start to be considered part of a possible 6G landscape, our work may open new research paths towards the design of FEC methods for Quantum-powered wireless processors., This work is supported by the ORIGAMI and TrialsNet projects, which have received funding from the SmartNetworks and Services Joint Undertaking (SNS JU) under the European Union’s Horizon Europe research and innovation program under Grant Agreement No. 101139270 and 101095871. This work is also partially supported by the Spanish Ministry of Economic Affairs and Digital Transformation and the European Union- NextGenerationEU through the UNICO 5G I+D 6G-CLARION project.
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Contribución de congreso (ConferenceOutput)

Optimizing Predictive Analytics in 5G Networks Through Zero-Trust Operator-Customer Cooperation

  • Milani, Mattia
  • Bega, Dario
  • Gramaglia, Marco
  • Mannweiler, Christian
Data availability in softwarized networks plays a fundamental role in various operations, including network function control, management, and orchestration. Despite early trends of designing domain-specific architectures in isolation, interactions between network operators and their customers have often resulted in limited data exchange, and only recently, standardization bodies have addressed this challenge. In this paper, we advocate for a more robust collaboration between operators and customers by introducing a zero-trust analytics service. This service enables the creation of tailored models for the different customers of network operators. We outline the necessary procedures to support such analytics and present a use case that demonstrates how specific operator-provided analytics (network flow detection) can be enhanced through the incorporation of external signals from a customer., The work of the University Carlos III of Madrid has been funded by the H2020 Projects TrialsNet (Grant Agreement 101095871) and also partially supported by the Spanish Ministry of Economic Affairs and Digital Transformation and the European Union-NextGenerationEU through the UNICO 5G I+D 6G-CLARION project.