Pasar al contenido principal

Resultados relacionados

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

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

FlexDRAN: Flexible centralization in disaggregated radio access networks

  • Chang, Chia-Yu
  • Nikaein, Navid
  • Spyropoulos, Thrasyvoulos
  • De Schepper, Koen
Radio Access Network (RAN) disaggregation allows operators to mix-and-match multivendor components and bring RAN services from one end to the other. Despite this goal, issues of resource misuse or performance undershoot may arise because of inflexible RAN function deployment and uncoordinated decision-making across different network segments. To address these issues, this paper considers full flexibility in the synthesis of end-to-end RAN services from a set of disaggregated and uncoordinated components. In particular, five design factors are jointly considered to maximize the overall network spectral efficiency: (1) User association, (2) Remote radio unit clustering, (3) RAN functional split, (4) Fronthaul network routing, and (5) Baseband unit placement. To efficiently deal with the formulated problem, we propose a two-level turbo-based solution and compare its performance with several related works. The simulation results show that our proposed solution can not only achieve a 1.33-times spectral efficiency gain compared with state-of-the-art methods, but also provides 1.27 and 1.74 multiplexing benefits for computing and networking resources, respectively., This work is supported by the European Union’s Horizon 2020 research and innovation programme under grant agreement 5Growth (No. 856709), Affordable5G (No. 957317), DAEMON (No. 101017109), and 6GBrain (No. 101017226).
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Dynamic slicing reconfiguration for virtualized 5G networks using ML forecasting of computing capacity

  • Camargo Barragán, Juan Sebastián
  • Coronado Calero, Estefanía
  • Ramirez Almonte, Wilson
  • Camps Mur, Daniel
  • Sánchez Deutsch, Sergi
  • Pérez Romero, Jordi|||0000-0001-9131-5013
  • Antonopoulos, Angelos|||0000-0002-3546-1080
  • Trullols Cruces, Óscar
  • González Díaz, Sergio
  • Otura García, Borja
  • Rigazzi, Giovanni
As 5G deployments continue to increase worldwide, new applications can fully leverage the exceptional features of the emerging mobile networks. Ultra-Reliable Low Latency Communications (URLLC) serve as an excellent example of applications highly sensitive to jitter and packet loss. To meet these demanding requirements, 5G relies on network slicing, network virtualization, and software-defined networks. This ecosystem enables the precise allocation of resources for each network slice. However, the applications’ resource demands may vary over time. In this challenging and overwhelming environment, traditional human decision-making for slice reconfiguration is not suitable anymore, due to the multitude of parameters and the need for extremely fast response times. Machine Learning (ML) comes as a tool that can enable better use of the available resources with faster and more intelligent management. This paper introduces an ML model that can predict slices’ traffic and dynamically reconfigure computational capacity. With these forecasting capabilities, the virtualized resources can be fine-tuned to suit the slices’ requirements, guaranteeing their Quality of Service (QoS). By doing so, Mobile Network Operators can make optimized use of the equipment, tailoring their needs to each service while complying with the QoS level. The results obtained demonstrate that the proposed ML model, in combination with a specific set of hysteresis rules, can accurately predict the saturation of virtualized capacity with up to 91% accuracy and proactively adapt it to the network slice requirements., This work has been partially supported by the Affordable5G project, funded by the European Commission under Grant Agreement H2020-ICT-2020-1, number 957317 through the Horizon 2020 and 5G-PPP programs (www.affordable5g.eu). The authors would also like to acknowledge CERCA Programme / Generalitat de Catalunya for sponsoring part of this work. This work has been also supported by the EU “NextGenerationEU/PRTR”, MCIN and AEI (Spain) under project IJC2020-043058-I. The authors would also like to acknowledge the fundings of NANCY, number 101096456 through the Horizon Europe project., Peer Reviewed
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Dynamic slicing reconfiguration for virtualized 5G networks using ML forecasting of computing capacity

  • Camargo Barragán, Juan Sebastián
  • Coronado Calero, Estefanía
  • Ramirez Almonte, Wilson
  • Camps Mur, Daniel
  • Sánchez Deutsch, Sergi
  • Pérez Romero, Jordi
  • Antonopoulos, Angelos
  • Trullols Cruces, Óscar
  • González Díaz, Sergio
  • Otura García, Borja
  • Rigazzi, Giovanni
As 5G deployments continue to increase worldwide, new applications can fully leverage the exceptional features of the emerging mobile networks. Ultra-Reliable Low Latency Communications (URLLC) serve as an excellent example of applications highly sensitive to jitter and packet loss. To meet these demanding requirements, 5G relies on network slicing, network virtualization, and software-defined networks. This ecosystem enables the precise allocation of resources for each network slice. However, the applications’ resource demands may vary over time. In this challenging and overwhelming environment, traditional human decision-making for slice reconfiguration is not suitable anymore, due to the multitude of parameters and the need for extremely fast response times. Machine Learning (ML) comes as a tool that can enable better use of the available resources with faster and more intelligent management. This paper introduces an ML model that can predict slices’ traffic and dynamically reconfigure computational capacity. With these forecasting capabilities, the virtualized resources can be fine-tuned to suit the slices’ requirements, guaranteeing their Quality of Service (QoS). By doing so, Mobile Network Operators can make optimized use of the equipment, tailoring their needs to each service while complying with the QoS level. The results obtained demonstrate that the proposed ML model, in combination with a specific set of hysteresis rules, can accurately predict the saturation of virtualized capacity with up to 91% accuracy and proactively adapt it to the network slice requirements., This work has been partially supported by the Affordable5G project, funded by the European Commission under Grant Agreement H2020-ICT-2020-1, number 957317 through the Horizon 2020 and 5G-PPP programs (www.affordable5g.eu). The authors would also like to acknowledge CERCA Programme / Generalitat de Catalunya for sponsoring part of this work. This work has been also supported by the EU “NextGenerationEU/PRTR”, MCIN and AEI (Spain) under project IJC2020-043058-I. The authors would also like to acknowledge the fundings of NANCY, number 101096456 through the Horizon Europe project., Peer Reviewed, Postprint (author's final draft)