Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 13
Encontrada(s) 1 página(s)

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

A 5G mobile network architecture to support vertical industries

  • Banchs Roca, Albert
  • Gutiérrez-Estévez, David M.
  • Fuentes, Manuel
  • Boldi, Mauro
  • Provvedi, Silvia
The telecom industry is moving from a "horizontal" service delivery model, where services are defined independent of their consumers, toward a "vertical" delivery model, where the provided services are tailored to specific industry sectors and verticals. In order to enable this transition, an end-to-end comprehensive 5G architecture is needed, with capabilities to support the use cases of the different vertical industries. A key feature of this architecture is the implementation of network slicing over a single infrastructure to provision highly heterogeneous vertical services, as well as a network slicing management system capable of handling simultaneous slices. On top of the network slicing technology, functionality needs to be devised to deploy the slices required by the different vertical players and provide them with a suitable interface to manage their slice. In this article, we design a 5G mobile network architecture to support vertical industries. The proposed architecture builds on ongoing standardization efforts at 3GPP and ETSI, and incorporates additional modules to provide enhanced MANO and control functionality as well as artificial-intelligence-based data analytics. On top of these modules, a service layer is provided to offer vertical players an easyto- use interface to manage their services., This work was supported by the H2020 5G-TOURS European project (Grant Agreement No. 856950).
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Artículo científico (JournalArticle)

AI-based Autonomous Control, Management, and Orchestration in 5G: from Standards to Algorithms

  • Bega, Dario
  • Gramaglia, Marco
  • Pérez, Ramón
  • Fiore, Marco
  • Banchs Roca, Albert
  • Costa-Pérez, Xavier
While the application of Artificial Intelligence (AI) to 5G networks has raised a strong interest, standard solutions to bring AI into 5G systems are still in their infancy and have a long way to go before they can be used to build an operational system. In this paper, we contribute to bridging the gap between standards and a working solution, by defining a framework that brings together the relevant standard specifications and complements them with additional building blocks. We populate this framework with concrete AI-based algorithms that serve different purposes towards developing a fully operational system. We evaluate the performance resulting from applying our framework to control, management and orchestration functions, showing the benefits that AI can bring to 5G systems., This work was supported by the H2020 5G-TOURS European project (Grant Agreement No. 856950).
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Artículo científico (JournalArticle)

A unified service-based capability exposure framework for closed-loop network automation

  • Gramaglia, Marco
  • Kajo, Marton
  • Mannweiler, Christian
  • Bulakci, Ömer
  • Wei, Qing
The ongoing quest for the tight integration of network operation and the network service provisioning initiated with the introduction of 5G often clashes with the capacity of current network architectures to provide means for such integration. Owing to the traditional design of mobile networks, which barely required a tight interaction, network elements offer capabilities for their continuous optimization just within their domain (eg, access, or core), allowing for a "silo-style" automation that falls short when aiming at closed-loop automation that embraces all the actors involved in the network, from network functions up to the service-provider network functions. To this end, in this article, we make the case for the network-wide capability exposure framework for closed-loop automation by (i) defining the different entities that shall expose capabilities, and (ii) discussing why the state of the art solutions are not enough to support this vision. Our proposed architecture, which relies on registration and discovery, and exposure functions, allows for enhanced use cases that are currently not possible with state of the art solution. We prove the feasibility of our solution by implementing it in a real-world testbed, employing Artificial Intelligence algorithms to close the loop for the management of the radio access network., Part of this work was performed in the context of the H2020 5G-MoNArch project (grant agreement no. 761445). The work of Marco Gramaglia has been partially funded by the H2020 5G-TOURS project (grant agreement no. 856950), and by the Spanish Ministry of Economic Affairs and Digital Transformation and the European Union-NextGenerationEU through the UNICO 5G I+D projects 6G-CLARION-NFD, 6G-CLARION-OR, 6G-CLARION-SI, and 6G-CLARION-OE
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Artículo científico (JournalArticle)

A unified service-based capability exposure framework for closed-loop network automation

  • Gramaglia, Marco
  • Kajo, Marton
  • Mannweiler, Christian
  • Bulakci, Ömer
  • Wei, Qing
The ongoing quest for the tight integration of network operation and the network service provisioning initiated with the introduction of 5G often clashes with the capacity of current network architectures to provide means for such integration. Owing to the traditional design of mobile networks, which barely required a tight interaction, network elements offer capabilities for their continuous optimization just within their domain (eg, access, or core), allowing for a "silo-style" automation that falls short when aiming at closed-loop automation that embraces all the actors involved in the network, from network functions up to the service-provider network functions. To this end, in this article, we make the case for the network-wide capability exposure framework for closed-loop automation by (i) defining the different entities that shall expose capabilities, and (ii) discussing why the state of the art solutions are not enough to support this vision. Our proposed architecture, which relies on registration and discovery, and exposure functions, allows for enhanced use cases that are currently not possible with state of the art solution. We prove the feasibility of our solution by implementing it in a real-world testbed, employing Artificial Intelligence algorithms to close the loop for the management of the radio access network., Part of this work was performed in the context of the H2020 5G-MoNArch project (grant agreement no. 761445). The work of Marco Gramaglia has been partially funded by the H2020 5G-TOURS project (grant agreement no. 856950), and by the Spanish Ministry of Economic Affairs and Digital Transformation and the European Union-NextGenerationEU through the UNICO 5G I+D projects 6G-CLARION-NFD, 6G-CLARION-OR, 6G-CLARION-SI, and 6G-CLARION-OE.
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Artículo científico (JournalArticle)

Analysis of mobility homophily in Stockholm based on social network data

  • Heine, Cate
  • Márquez Colás, María Cristina
  • Santi, Paolo
  • Sundberg, Marcus
  • Nordfors, Miriam
  • Ratti, Carlo
We present a novel metric for measuring relative connection between parts of a city using geotagged Twitter data as a proxy for co-occurrence of city residents. We find that socioeconomic similarity is a significant predictor of this connectivity metric, which we call “linkage strength”: neighborhoods that are similar to one another in terms of residents’ median income, education level, and (to a lesser extent) immigration history are more strongly connected in terms of the of people who spend time there, indicating some level of homophily in the way that individuals choose to move throughout a city’s districts., The authors would like to acknowledge the Senseable Stockholm Lab and its partners: City of Stockholm, KTH Royal Institute of Technology, the Stockholm Chamber of Commerce and Newsec, in collaboration with MIT Senseable City Lab. We would also like to acknowledge the H2020 5G-TOURS project. Finally, we would like to thank the City of Stockholm municipality's Statistical Information Service for provision of population counts and socioeconomic data.
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Artículo científico (JournalArticle)

Resource allocation for network slicing in mobile networks

  • Banchs Roca, Albert
  • De Veciana, Gustavo
  • Sciancalepore, Vincenzo
  • Costa-Pérez, Xavier
This paper provides a survey of resource allocation for network slicing. We focus on two classes of existing solutions: (i) reservation-based approaches, which allocate resources on a reservation basis, and (ii) share-based approaches, which allocate resources based on static overall shares associated to individual slices. We identify the requirements that a slice-based resource allocation mechanism should satisfy, and evaluate the performance of both approaches against these requirements. Our analysis reveals that reservation-based approaches provide a better level of isolation as well as stricter guarantees, by enabling tenants to explicitly reserve resources, but one must pay a price in terms of efficiency unless reservations can be updated very dynamically; in particular, efficiency falls below 50\% when reservations are performed over long timescales. We provide further comparisons in terms of customizability, complexity, privacy and cost predictability, and discuss which approach might be more suitable depending on the network slices' characteristics. We also describe the additional mechanisms required to implement the desired resource allocations while meeting the latency and reliability requirements of the different slice types, and outline some issues for future work., The work of Albert Banchs was supported in part by the H2020 5G-TOURS European project under Grant 856950, and in part by the Spanish State Research Agency (TRUE5G project) under Grant PID2019-108713RB-C52/AEI/10.13039/501100011033. The work of Gustavo de Veciana was supported by NSF Grant CNS-1910112.
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Artículo científico (JournalArticle)

A unified service-based capability exposure framework for closed-loop network automation

  • Gramaglia, Marco
  • Kajo, Marton
  • Mannweiler, Christian
  • Bulakci, Ömer
  • Wei, Qing
The ongoing quest for the tight integration of network operation and the network service provisioning initiated with the introduction of 5G often clashes with the capacity of current network architectures to provide means for such integration. Owing to the traditional design of mobile networks, which barely required a tight interaction, network elements offer capabilities for their continuous optimization just within their domain (eg, access, or core), allowing for a "silo-style" automation that falls short when aiming at closed-loop automation that embraces all the actors involved in the network, from network functions up to the service-provider network functions. To this end, in this article, we make the case for the network-wide capability exposure framework for closed-loop automation by (i) defining the different entities that shall expose capabilities, and (ii) discussing why the state of the art solutions are not enough to support this vision. Our proposed architecture, which relies on registration and discovery, and exposure functions, allows for enhanced use cases that are currently not possible with state of the art solution. We prove the feasibility of our solution by implementing it in a real-world testbed, employing Artificial Intelligence algorithms to close the loop for the management of the radio access network., Part of this work was performed in the context of the H2020 5G-MoNArch project (grant agreement no. 761445). The work of Marco Gramaglia has been partially funded by the H2020 5G-TOURS project (grant agreement no. 856950), and by the Spanish Ministry of Economic Affairs and Digital Transformation and the European Union-NextGenerationEU through the UNICO 5G I+D projects 6G-CLARION-NFD, 6G-CLARION-OR, 6G-CLARION-SI, and 6G-CLARION-OE.
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Artículo científico (JournalArticle)

Network slicing meets artificial intelligence: an AI-based framework for slice management

  • Bega, Dario
  • Gramaglia, Marco
  • García-Saavedra, Andrés
  • Banchs Roca, Albert
  • Fiore, Marco
  • Costa-Pérez, Xavier
Network slicing is an emerging paradigm in mobile networks that leverages Network Function Virtualization (NFV) to enable the instantiation of multiple virtual networks -named slices- over the same physical network infrastructure. The operator can allocate to each slice dedicated resources and customized functions that allow meeting the highly heterogeneous and stringent requirements of modern mobile services. Managing functions and resources under network slicing is a challenging task that requires making efficient decisions at all network levels, in some cases even in real-time, which can be achieved by integrating artificial intelligence (AI) in the network. We outline a general framework for AI-based network slice management, introducing AI in the different phases of the slice lifecycle, from admission control to dynamic resource allocation in the network core and at the radio access. A sensible use of AI for network slicing results in strong benefits for the operator, with expected performance gains between 25% and 80% in representative case studies., The work of University Carlos III of Madrid was supported by the H2020 5G-TOURS project (grant agreement no. 856950). The work of NEC Laboratories Europe was supported by H2020 5GROWTH project (grant agreement no. 856709). The research of Marco Fiore was partially supported by the ANR CANCAN project (ANR-18-CE25-0011).
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Artículo científico (JournalArticle)

ACHO: a framework for flexible re-orchestration of virtual network functions

  • García Avilés, Ginés
  • Donato, Carlos
  • Gramaglia, Marco
  • Serrano Yáñez-Mingot, Pablo
  • Banchs Roca, Albert
Network Function Virtualization enables network slicing as a novel paradigmfor service provisioning. With network slicing, Virtual Network Functions(VNFs) can be instantiated at different locations of the infrastructure, choosing their optimal placement based on parameters such as the requirementsof the service or the resources available. One limitation of state-of-the-arttechnology for network slicing is the inability to re-evaluate orchestration decisions once the slice has been deployed, in case of changing service demandsor network conditions.In this paper, we present ACHO, a novel software framework that enablesseamless re-orchestration of VNFs of any kind, including RAN and Core.With ACHO, VNFs and resources can be easily re-assigned to match, e.g.,varying user demands or changes in the nodes' load. ACHO uses lightweightmechanisms, such as splitting the engine of a VNF from the data it requiresto perform its operation, in such a way that, when re-allocating a VNF, onlythe data is moved (a new engine is instantiated in the new location). Wedemonstrate the use of ACHO in a small scale testbed, showing that (i) theproposed re-orchestration is feasible, (ii) it results much faster than existingalternatives (especially for relocation), and (iii) the framework can be readilyapplied to existing VNFs after minimal changes to their implementation., This work was partially supported by the European Commission in the framework of the H2020 5G-PPP 5G-TOURS (Grant no. 856950) project and the 5G-EVE (Grant no. 815074) project.
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Artículo científico (JournalArticle)

Experimenting with open source tools to deploy a multi-service and multi-slice mobile network

  • García Avilés, Ginés
  • Gramaglia, Marco
  • Serrano Yáñez-Mingot, Pablo
  • Gringoli, Francesco
  • Fuente Pascual, Sergio
  • Labrador Pavón, Ignacio
With network slicing, the infrastructure is divided into separate networks, each one customized to provide a specific service. Network slicing is a key technology to efficiently support services with very diverse requirements, such as the ones that should support 5G networks. While the architectural work for 5G is well advanced, and many theoretical solutions that address diverse aspects such as resource assignment or service composition exist, the experimental work lags behind. In this paper, we aim at filling this gap by describing our implementation experiences when deploying a small-scale multi-service prototype. We consider a video streaming service and an augmented reality service, each one provided over a different network slice, and extend existing open-source software solutions for a better provision of them. Our implementation showcases key features of future 5G networks, such as radio slicing with service differentiation, support for local breakout, or multi-slice orchestration with QoE-triggered optimization. With the core of our implementation being open-source, we believe that our results will prove very useful to researchers and practitioners working on this area of research., This work was supported by the H2020 5G-MoNArch (grant agree-ment no. 761445), 5G EVE (grant agreement No. 815074) and 5G-Tours (grant agreement No. 856950) Projects
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Artículo científico (JournalArticle)

DeepCog: optimizing resource provisioning in network slicing with AI-based capacity forecasting

  • Bega, Dario
  • Gramaglia, Marco
  • Fiore, Marco
  • Banchs Roca, Albert
  • Costa-Pérez, Xavier
The dynamic management of network resources is both a critical and challenging task in upcoming multi-tenant mobile networks, which requires allocating capacity to individual network slices so as to accommodate future time-varying service demands. Such an anticipatory resource configuration process must be driven by suitable predictors that take into account the monetary cost associated to overprovisioning or underprovisioning of networking capacity, computational power, memory, or storage. Legacy models that aim at forecasting traffic demands fail to capture these key economic aspects of network operation. To close this gap, we present DeepCog, a deep neural network architecture inspired by advances in image processing and trained via a dedicated loss function. Unlike traditional traffic volume predictors, DeepCog returns a cost-aware capacity forecast, which can be directly used by operators to take short- and long-term reallocation decisions that maximize their revenues. Extensive performance evaluations with real-world measurement data collected in a metropolitan-scale operational mobile network demonstrate the effectiveness of our proposed solution, which can reduce resource management costs by over 50% in practical case studies., The work of University Carlos III of Madrid was supported by H2020 5G-TOURS project (grant agreement no. 856950). The work of NEC Laboratories Europe was supported by H2020 5G-TRANSFORMER project (grant agree-ment no. 761536) and 5GROWTH project (grant agreement no. 856709).
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Artículo científico (JournalArticle)

vrAIn: Deep Learning based Orchestration for Computing and Radio Resources in vRANs

  • Ayala Romero, José A.
  • García Saavedra, Andrés
  • Gramaglia, Marco
  • Banchs Roca, Albert
  • Costa-Pérez, Xavier
  • Alcaraz, Juan J.
The virtualization of radio access networks (vRAN) is the last milestone in the NFV revolution. However, the complexrelationship between computing and radio dynamics make vRAN resource control particularly daunting. We present vrAIn, a resourceorchestrator for vRANs based on deep reinforcement learning. First, we use an autoencoder to project high-dimensional context data(traffic and channel quality patterns) into a latent representation. Then, we use a deep deterministic policy gradient (DDPG) algorithmbased on an actor-critic neural network structure and a classifier to map contexts into resource control decisions.We have evaluated vrAIn experimentally, using an open-source LTE stack over different platforms, and via simulations over aproduction RAN. Our results show that: (i) vrAIn provides savings in computing capacity of up to 30% over CPU-agnostic methods;(ii) it improves the probability of meeting QoS targets by 25% over static policies; (iii) upon computing capacity under-provisioning,vrAIn improves throughput by 25% over state-of-the-art schemes; and (iv) it performs close to an optimal offline oracle. To ourknowledge, this is the first work that thoroughly studies the computational behavior of vRANs and the first approach to a model-freesolution that does not need to assume any particular platform or context., This work was partially supported by the European Commission through Grant No. 856709 (5Growth) and Grant No. 856950 (5G-TOURS); by Science Foundation Ireland (SFI) through Grant No. 17/CDA/4760; and AEI/FEDER through project AIM under Grant No. TEC2016-76465-C2-1-R. Furthermore, the work is closely related to the EU project DAEMON (Grant No. 101017109).
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Artículo científico (JournalArticle)

Analysis of scaling policies for NFV providing 5G/6G reliability levels with fallible servers

  • Ortin, Jorge
  • Serrano Yáñez-Mingot, Pablo
  • García Reinoso, Jaime José
  • Banchs Roca, Albert
The softwarization of mobile networks enables an efficient use of resources, by dynamically scaling and re-assigning them following variations in demand. Given that the activation of additional servers is not immediate, scaling up resources should anticipate traffic demands to prevent service disruption. At the same time, the activation of more servers than strictly necessary results in a waste of resources, and thus should be avoided. Given the stringent reliability requirements of 5G applications (up to 6 nines) and the fallible nature of servers, finding the right trade-off between efficiency and service disruption is particularly critical. In this paper, we analyze a generic auto-scaling mechanism for communication services, used to de(activate) servers in a cluster, based on occupation thresholds. We model the impact of the activation delay and the finite lifetime of the servers on performance, in terms of power consumption and failure probability. Based on this model, we derive an algorithm to optimally configure the thresholds. Simulation results confirm the accuracy of the model both under synthetic and realistic traffic patterns as well as the effectiveness of the configuration algorithm. We also provide some insights on the best strategy to support an energy-efficient highly-reliable service: deploying a few powerful and reliable machines versus deploying many machines, but less powerful and reliable., The work of Jorge Ortin was funded in part by the Spanish Ministry of Science under Grant RTI2018-099063-B-I00, in part by the Gobierno de Aragon through Research Group under Grant T31_20R, in part by the European Social Fund (ESF), and in part by Centro Universitario de la Defensa under Grant CUD-2021_11. The work of Pablo Serrano was partly funded by the European Commission (EC) through the H2020 project Hexa-X (Grant Agreement no. 101015956), and in part by Spanish State Research Agency (TRUE5G project, PID2019-108713RB-52PID2019-108713RB-C52/AEI/10.13039/501100011033). The work of Jaime Garcia-Reinoso was partially supported by the EC in the framework of H2020-EU.2.1.1. 5G EVE project (Grant agreement no. 815074). The work of Albert Banchs was partially supported by the EC in the framework of H2020-EU.2.1.1. 5G-TOURS project (Grant agreement no. 856950) also partially supported by the Spanish State Research Agency (TRUE5G project, PID2019-108713RB-C52PID2019-108713RB-C52/AEI/10.13039/501100011033).