Network heavy traffic modeling using α-stable self-similar processes

“…Our approach is different of the ones used in the literature, i.e., [2], [5], [8], [11], since we use the power series expansion of the probability distribution function of the fLm. …”

Section: Asymptotic Lower Bound For the Probability Of Buffer Ovementioning

confidence: 99%

Fractional lévy motion and its application to network traffic modeling

Laskin

Lambadaris

Harmantzis

et al. 2001

Teletraffic Engineering in the Internet Era, Proceedings of the International Teletraffic Congress - ITC-I7

View full text Add to dashboard Cite

“…To simulate realistic network conditions, our specification model includes bursty traffic generators [13]. Bursty traffic is an infinite sequence of frames with subsequences of closely spaced (in time) frames interspersed with sub-sequences of widely spaced (in time) frames, i.e., a plot of frames over time shows peaks and plateaus.…”

Section: Channel Modelmentioning

confidence: 99%

Transaction Level Modeling of Best-Effort Channels for Networked Embedded Devices

Banerjee

Gerstlauer

2009

IFIP Advances in Information and Communication Technology

View full text Add to dashboard Cite

Abstract. We use Transaction Level Modeling techniques to specify and validate best-effort channels for networked embedded devices, to integrate the generated specification model in system-level design flow, for prototyping, exploration and validation of design alternatives. A best-effort channel does not provide any guarantees on final data delivery or delivery rate. With more embedded devices existing in networked environments, often sharing a common communication channel, devices compete with each other for all common network resources, e.g., in a wireless sensor network where low power devices share a low bandwidth best-effort channel. To examine such systems, we specify Half-Duplex Ethernet using the SpecC language and Transaction Level Modeling techniques. All models are validated in a multi-station test setup using Ethernet-based network algorithms.

show abstract

“…Estudos recentes indicam que 0 processo A( t) tam bern pode ser utilizado para a modelagem de trMego com distribuhrao marginal o-estavel, assumindo que Z(t) e urn processo do tipo movimento estavel [15,16]. A analise de urn sistema de filas simples, alimentado por trMego Browniano fracionario foi apresentada em [17,14].…”

Section: Introduc;:aounclassified

“…A partir da defini<;ao do processo envelope do movi mento Browniano fracionario, urn mecanismo de policia mento de trafego auto-similar, denominado algoritmo do Balde Furado Fractal, foi apresentado em [19]. Note que, por defini<;ao, 0 processo envelope do movi mento Browniano fracionario assume que 0 trafego tern dis tribui<;ao marginal Gaussiana, 0 que nem sempre e ver dadeiro [16,15,20]. Alem disso, este processo nao repre senta adequadamente os incrementos de trafego, em particu lar quando sao supostos estacionarios.…”

Section: Introduc;:aounclassified

Modelagem de Trafego Fractal Utilizando Processos Envelope

Pereira¹,

Fonseca²,

Arantes³

2004

Journal of Communication and Information Systems

View full text Add to dashboard Cite

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 ...

show abstract

Network heavy traffic modeling using α-stable self-similar processes

Cited by 115 publications

References 14 publications

Fractional lévy motion and its application to network traffic modeling

Fractional lévy motion and its application to network traffic modeling

Transaction Level Modeling of Best-Effort Channels for Networked Embedded Devices

Modelagem de Trafego Fractal Utilizando Processos Envelope

Contact Info

Product

Resources

About