Abstrael-It hasbeen proved that it is possible toguaranteedelay bounds in a GeueralizedProeessor Sharing (GPS) server when traffic is regulated by the Leaky Bueket algorithm. However, the Leaky Bucket is not an appropriate regulator for long-range d e pendent (LRD) traffic. This paper introduces the computation of backlog and delay bounds for a GPS server under LRD )traffic. Traffic is assumed to be regulated by the Fractal Leaky Bucket, which is proved to be au effective policing mechanism for LRD traffic.
We propose a novel policy called Proportional Sharing with Load Reservation (PSLR) for scheduling upstream flows in Ethernet Passive Optical Networks. This policy provides bandwidth guarantees on a per flow basis and redistributes the unused bandwidth among active flows in proportion to their priority level.
Resumo -Neste artigo, propoe-se 0 uso de urn processo en velope denominado Processo de Chegada com Limitante Fra ciomirio (Fractional Bounded Arrival Process, FBAP) para a representac;ao de trMego auto-similar. A analise de sistemas de filas para 0 trMego FBAP e desenvolvida, e limitantes para o tamanho da fila (backlog) e para 0 atraso sao apresenta dos. 0 policiamento de trMego FBAP tambem e estudado.Os resultados sao estendidos para 0 caso do trMego multifrac tal, para 0 qual se apresenta urn processo envelope denomi nado Processo de Chegada com Limitante Multifractal (Mul tifractal Bounded Arrival Process, MFBAP). Tanto 0 FBAP como 0 MFBAP sao validados utilizando trac;os de trMego real, sendo comprovado que sao capazes de representar ade quadamente 0 trMego com caracterfsticas fractais.Palavras-chave: Analise de desempenho de redes, engenha ria de trMego, Internet, redes de comunicac;oes banda larga, trMego multifractal, processos envelope.Abstract -In this paper, an envelope process called Frac tional Bounded Arrival Process (FBAP) is proposed for self similar traffic representation. A queueing analysis for FBAP traffic is developed, and upper bounds for the backlog and for the delay are obtained. The policing of FBAP traffic is also investigated. Results are then extended to the multifrac tal traffic case, for which an envelope process called Multi fractal Bounded Arrival Process (MFBAP) is proposed. The FBAP and the MFBAP models are validated against real traf fic traces, and they are proved to provide an adequate repre sentation for fractal traffic.Keywords: Network performance analysis, traffic engineer ing, Internet, wideband communications networks, multifrac tal traffic, envelope processes. INTRODUC;:AOEstudos recentes indicam que 0 trMego em diversos tipos de redes apresenta propriedades fractais [I,2,3,4,5,6,7,8,9,10,II,12,13]. Em outras palavras, as propriedades estatfs ticas do trMego nao variam em relac;ao 11 escala de tempo de observac;ao, nao sendo possfvel apontar uma escala de tempo dominante [2,3,6]. Varios trabalhos tern sido direcionados 11 modelagem do trMego fractal [13]. A importancia destes estudos advem dos efeitos nocivos deste tipo de trMego no desempenho das re des, os quais nao podem ser adequadamente analisados me diante 0 uso de modelos de trMego tradicionais [13]. De fato, o trMego fractal e caracterizado pela ocorrencia de surtos de grande intensidade em varias escalas de tempo. Alem disso, este tipo de trMego apresenta dependencia de longa durac;ao, que leva a persistencia temporal dos surtos de trMego, oca sionando significativas perdas por transbordo nos nos de co mutac;ao [13].Diversos autores argumentam que 0 conceito de auto similaridade estatfstica pode ser utilizado para caracterizar 0 comportamento do trMego fractal [2,3,4,6]. Considera-se que urn processo Z(t) com incrementos estacionarios e auto similar se a relac;aoe valida para algum 0 < H < 1. 0 sfmbolo ~ indica igual dade em distribuic;ao.Modelos auto-similares foram propostos para a repre sentac;ao do trMego ...
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.