english Icono del idioma   español Icono del idioma  

Por favor, use este identificador para citar o enlazar este ítem: https://hdl.handle.net/20.500.12008/47034 Cómo citar
Título: Design and analysis of flow aware load balancing mechanisms for multi-service networks
Autor: Ferragut, Andres
Kofman, Daniel
Larroca, Federico
Oueslati, Sara
Tipo: Ponencia
Palabras clave: Load flow analysis, Load management, Ethernet networks, Traffic control
Fecha de publicación: 2008
Resumen: Ethernet technology is being deployed in metro and wide area networks. However, despite recent evolutions, Ethernet cannot be considered a carrier class technology due mainly to the lack of facilities for efficient traffic engineering (TE). In this article, we propose a Flow-aware TE approach for carrier class Ethernet networks providing services like those defined by the Metro Ethernet Forum. The flow-aware networking approach we consider is based on the Cross-protect router mechanisms, allowing satisfactory quality for streaming and elastic flows without explicitly identifying traffic classes by the combined use of fair queuing and admission control. Our proposal applies specifically to architectures where a tunnel is established between ingress and egress nodes (like Ethernet over MPLS). In this specific context, the Cross-protect mechanisms are applied on a per tunnel basis. We analyze the proposed approach in terms of flow blocking probabilities for which explicit formula are derived. We also extend the study framework to the case where several paths are established between a pair of ingress/egress nodes, and propose a simple load balancing scheme. We analyze its performance and derive approximate formula for the flow blocking probability in this case. The analysis is validated by extensive simulations.
Citación: Ferragut, A, Kofman, D, Larroca, F, Oueslati, S. "Design and Analysis of Flow Aware Load Balancing Mechanisms for Multi-Service Networks" Next Generation Internet Networks, Krakow, Poland, 2008, doi: 10.1109/NGI.2008.18.
Departamento académico: Telecomunicaciones
Grupo de investigación: Análisis de Redes, Tráfico y Estadísticas de Servicios
Aparece en las colecciones: Publicaciones académicas y científicas - Instituto de Ingeniería Eléctrica

Ficheros en este ítem:
Fichero Descripción Tamaño Formato   
FQLO08.pdf211,76 kBAdobe PDFVisualizar/Abrir


Este ítem está sujeto a una licencia Creative Commons Licencia Creative Commons Creative Commons