Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 6
Encontrada(s) 1 página(s)

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

LACO: A Latency-Driven Network Slicing Orchestration in Beyond-5G Networks (In Press)

  • Zanzi, Lanfranco
  • Sciancalepore, Vincenzo
  • García Saavedra, Andrés
  • Schotten, Hans D.
  • Costa-Pérez, Xavier
In Press / En Prensa, Network Slicing is expected to become a game changer in the upcoming 5G networks and beyond, enlarging the telecom business ecosystem through still-unexplored vertical industry profits. This implies that heterogeneous service level agreements (SLAs) must be guaranteed per slice given the multitude of predefined requirements. In this paper, we pioneer a novel radio slicing orchestration solution that simultaneously provides latency and throughput guarantees in a multi-tenancy environment. Leveraging on a solid mathematical framework, we exploit the exploration-vs-exploitation paradigm by means of a multi-armed-bandit-based (MAB) orchestrator, LACO, that makes adaptive resource slicing decisions with no prior knowledge on the traffic demand or channel quality statistics. As opposed to traditional MAB methods that are blind to the underlying system, LACO relies on system structure information to expedite decisions. After a preliminary simulations campaign empirically proving the validness of our solution, we provide a robust implementation of LACO using off-the-shelf equipment to fully emulate realistic network conditions: near-optimal results within affordable computational time are measured when LACO is in place., The research leading to these results has been supported in part by the H2020 MonB5G Project (grant agreement no. 871780) and in part by the H2020 5Growth Project (grant agreement no. 856709).
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publicación Artículo científico (JournalArticle)

Fog-enabled Scalable C-V2X Architecture for Distributed 5G and Beyond Applications

  • Sarrigiannis, Ioannis
  • Contreras Murillo, Luis Miguel
  • Ramantas, Kostas
  • Antonopoulos, Angelos
  • Verikoukis, Christos
The Internet of Things (IoT) ecosystem, as fostered by fifth generation (5G) applications, demands a highly available network infrastructure. In particular, the internet of vehicles use cases, as a subset of the overall IoT environment, require a combination of high availability and low latency in big volumes support. This can be enabled by a network function virtualization architecture that is able to provide resources wherever and whenever needed, from the core to the edge up to the end user proximity, in accordance with the fog computing paradigm. In this article, we propose a fog-enabled cellular vehicle-to-everything architecture that provides resources at the core, the edge and the vehicle layers. The proposed architecture enables the connection of virtual machines, containers and unikernels that form an application-as-a-service function chain that can be deployed across the three layers. Furthermore, we provide lifecycle management mechanisms that can efficiently manage and orchestrate the underlying physical resources by leveraging live migration and scaling functionalities. Additionally, we design and implement a 5G platform to evaluate the basic functionalities of our proposed mechanisms in real-life scenarios. Finally, the experimental results demonstrate that our proposed scheme maximizes the accepted requests, without violating the applications’ service level agreement., This work has been supported in part by the research projects SPOTLIGHT (722788), AGAUR (2017-SGR-891), 5G-DIVE (859881), SPOT5G (TEC2017-87456-P), MonB5G (871780) and 5G-Routes (951867).
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Continuous multi-objective zero-touch network slicing via twin delayed DDPG and OpenAI gym

  • Rezazadeh, Farhad
  • Chergui, Hatim
  • Alonso Zárate, Luis Gonzaga|||0000-0002-6608-0862
  • Verikoukis, Christos
Artificial intelligence (AI)-driven zero-touch network slicing (NS) is a new paradigm enabling the automation of resource management and orchestration (MANO) in multi-tenant beyond 5G (B5G) networks. In this paper, we tackle the problem of cloud-RAN (C-RAN) joint slice admission control and resource allocation by first formulating it as a Markov decision process (MDP). We then invoke an advanced continuous deep reinforcement learning (DRL) method called twin delayed deep deterministic policy gradient (TD3) to solve it. In this intent, we introduce a multi-objective approach to make the central unit (CU) learn how to re-configure computing resources autonomously while minimizing latency, energy consumption and virtual network function (VNF) instantiation cost for each slice. Moreover, we build a complete 5G C-RAN network slicing environment using OpenAI Gym toolkit where, thanks to its standardized interface, it can be easily tested with different DRL schemes. Finally, we present extensive experimental results to showcase the gain of TD3 as well as the adopted multi-objective strategy in terms of achieved slice admission success rate, latency, energy saving and CPU utilization., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

A collaborative statistical actor-critic learning approach for 6G network slicing control

  • Rezazadeh, Farhad
  • Chergui, Hatim
  • Blanco Botana, Luis
  • Alonso Zárate, Luis Gonzaga|||0000-0002-6608-0862
  • Verikoukis, Christos
Artificial intelligence (AI)-driven zero-touch massive network slicing is envisioned to be a disruptive technology in beyond 5G (B5G)/6G, where tenancy would be extended to the final consumer in the form of advanced digital use-cases. In this paper, we propose a novel model-free deep reinforcement learning (DRL) framework, called collaborative statistical Actor-Critic (CS-AC) that enables a scalable and farsighted slice performance management in a 6G-like RAN scenario that is built upon mobile edge computing (MEC) and massive multiple-input multiple-output (mMIMO). In this intent, the proposed CS-AC targets the optimization of the latency cost under a long-term statistical service-level agreement (SLA). In particular, we consider the Q-th delay percentile SLA metric and enforce some slice-specific preset constraints on it. Moreover, to implement distributed learners, we propose a developed variant of soft Actor-Critic (SAC) with less hyperparameter sensitivity. Finally, we present numerical results to showcase the gain of the adopted approach on our built OpenAI-based network slicing environment and verify the performance in terms of latency, SLA Q-th percentile, and time efficiency. To the best of our knowledge, this is the first work that studies the feasibility of an AI-driven approach for massive network slicing under statistical SLA., This work has been supported in part by the research projects MonB5G (871780), ZEROTO6G, AGAUR (2017-SGR-891), and PROGRESSUS (876868)., Peer Reviewed
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

A collaborative statistical actor-critic learning approach for 6G network slicing control

  • Rezazadeh, Farhad
  • Chergui, Hatim
  • Blanco Botana, Luis
  • Alonso Zárate, Luis Gonzaga
  • Verikoukis, Christos
Artificial intelligence (AI)-driven zero-touch massive network slicing is envisioned to be a disruptive technology in beyond 5G (B5G)/6G, where tenancy would be extended to the final consumer in the form of advanced digital use-cases. In this paper, we propose a novel model-free deep reinforcement learning (DRL) framework, called collaborative statistical Actor-Critic (CS-AC) that enables a scalable and farsighted slice performance management in a 6G-like RAN scenario that is built upon mobile edge computing (MEC) and massive multiple-input multiple-output (mMIMO). In this intent, the proposed CS-AC targets the optimization of the latency cost under a long-term statistical service-level agreement (SLA). In particular, we consider the Q-th delay percentile SLA metric and enforce some slice-specific preset constraints on it. Moreover, to implement distributed learners, we propose a developed variant of soft Actor-Critic (SAC) with less hyperparameter sensitivity. Finally, we present numerical results to showcase the gain of the adopted approach on our built OpenAI-based network slicing environment and verify the performance in terms of latency, SLA Q-th percentile, and time efficiency. To the best of our knowledge, this is the first work that studies the feasibility of an AI-driven approach for massive network slicing under statistical SLA., This work has been supported in part by the research projects MonB5G (871780), ZEROTO6G, AGAUR (2017-SGR-891), and PROGRESSUS (876868)., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Continuous multi-objective zero-touch network slicing via twin delayed DDPG and OpenAI gym

  • Rezazadeh, Farhad
  • Chergui, Hatim
  • Alonso Zárate, Luis Gonzaga
  • Verikoukis, Christos
Artificial intelligence (AI)-driven zero-touch network slicing (NS) is a new paradigm enabling the automation of resource management and orchestration (MANO) in multi-tenant beyond 5G (B5G) networks. In this paper, we tackle the problem of cloud-RAN (C-RAN) joint slice admission control and resource allocation by first formulating it as a Markov decision process (MDP). We then invoke an advanced continuous deep reinforcement learning (DRL) method called twin delayed deep deterministic policy gradient (TD3) to solve it. In this intent, we introduce a multi-objective approach to make the central unit (CU) learn how to re-configure computing resources autonomously while minimizing latency, energy consumption and virtual network function (VNF) instantiation cost for each slice. Moreover, we build a complete 5G C-RAN network slicing environment using OpenAI Gym toolkit where, thanks to its standardized interface, it can be easily tested with different DRL schemes. Finally, we present extensive experimental results to showcase the gain of TD3 as well as the adopted multi-objective strategy in terms of achieved slice admission success rate, latency, energy saving and CPU utilization., Peer Reviewed, Postprint (published version)