Guido H. Petit

Analytic derivation of tail probabilities for queue lengths and waiting times in ATM multiserver queues

Abstract In this paper we consider a discrete-time queueing model, useful for the design and the performance evaluation of many slotted communication system in general, and ATM-based networks in particular. The model assumes a general independent packet arrival process, an infinite waiting room, and an arbitrary number of servers. By means of an approximation technique, explicit closed-form expressions are derived for the tail probabilities of both the buffer contents (queue length) and the delay (or the waiting time). These formulas are very easy to evaluate. They are applied in the performance analysis of an ATM switching element with output queueing, in order to obtain predictions for such quantities as the cell loss ratio and the delay jitter. Also, an application with more bursty arrivals is discussed. In both cases, very good agreement between actual (numerical) and approximate (analytic) results is observed.

Assessing voice quality in packet-based telephony

Our goal is to extend recommendations ITU-T G.114 and G.131 to cover distorted phone calls transported (partly) over a packet-based network. We assume the user terminals to be optimally tuned and focus on how network parameters-delay, packet loss, jitter, and so on-influence voice quality. We then discuss how those parameters can be quantified and incorporated into a model that lets us predict the quality of any packet-based phone call.

Bandwidth resource optimization in video-on-demand network architectures

It is generally recognized that interactive video-on-demand (IVOD) will become an important residential service of this decade. However, many issues with respect to the way this service has to be offered to the users remain open and me still subject to vigorous research activities. The aim of the paper is to present a VOD network solution based upon the Broadband Integrated Digital Network (B-ISDN) that targets the mass deployment of the IVOD service and offers the ability to cope with future types of multimedia services. By means of a VOD reference network and traffic mode, it is demonstrated that the proposed solution can achieve an optimized use of network (bandwidth), online storage and processing resources while guaranteeing a desired grade of service (GoS) under all circumstances.<<ETX>>

A review of voice, data and video traffic models for ATM

This paper describes the main statistical features of voice, data and video sources, defines a set of selection criteria for selecting source models for these sources, describes a number of relevant source models for representing these sources and recommends the best source models based on the results of the parameterisation of these models from measured data.

Delay bounds for voice over IP calls transported over satellite access networks

Whether or not voice calls of traditional quality can be supported between two users connected to an IP backbone via satellite access systems depends largely on the mouth-to-ear delay, an important part of which is consumed by the satellite networks themselves. In this paper, a methodology is developed to calculate upper bounds for the latter delay component as a function of the used codec, the experienced packet loss ratio, the echo levels at both sides of the connection and the chosen voice packet size. Illustrations are provided.

Choosing the UMTS air interface parameters, the voice packet size and the dejittering delay for a voice-over-IP call between a UMTS and a PSTN party

We develop a methodology to set the VoIP application parameters (voice packet size and dejittering delay) and the UMTS air interface parameters in such a way that the quality of VoIP calls involving a UMTS party is ensured. We use analytical techniques to determine the delay and packet loss contributions of the various transmission stages crossed by the voice packet flow, and the E-model to predict the perceived quality. Our numerical results show that provided the parameters of the VoIP application and the UMTS air interface are chosen properly, UMTS access and the stringent delay and packet loss requirements of VoIP are reconcilable.

Guaranteeing quality of service to packetised voice over the UMTS air interface

A key feature of the air interface of the Universal Mobile Telecommunication System (UMTS) standardised by 3GPP is that its functionality can be tailored to the requirements of individual applications, In this paper we study how this flexibility can be exploited to meet the stringent delay and packet loss requirements of a voice-over-IP application (VoIP). We introduce an analytical model of the UMTS air interface that allows us to quantify the impact of the air interface parameters (power budget, interleaving span and channel coding rate) on the parameters that determine the perceived quality of VoIP calls (mouth-to-ear delay and packet loss probability). We use the model to explore the trade-offs that are inherent in the setting of the air interface parameters. The numerical results we present illustrate and quantify the trade-offs of bandwidth efficiency versus packet loss, and of packet loss versus packet delay. The latter trade-off is of particular importance for the feasibility of VoIP.

Performance study of an ATM self-routing multistage switch with bursty traffic: simulation and analytic approximation

An N x N self-routing multistage switching network with bursty and uniform traffic, which is composed of S x 5 switching elements with output queueing and has K = logS N stages, is considered in this paper. The input traffic is modelled by a two-state (active/silent) Markov chain. Each arriving cell selects one of the N outlets as its destination independently and with equal probability I/N. The performance of the switching network is studied by means of a simulation method. An approximate traffic model of a four-state Markov chain is proposed to characterize the cell arrival processes to further stages and its related switching element performance is analyzed. Comparison with the simulation results shows that the proposed traffic model gives a good approximation, which implies that the performance of the switching element mainly depends on the first two moments of the active and silent periods and is not sensitive to the shapes of their distributions. The influence of bursty traffic on the performance of the switching network is discussed and illustrated by some numerical examples. The impact of traffic randomization on the performance of the switching network is also investigated.

VLSI architecture of a SMDS/ATM router

This paper presents a set of custom components used to implement a connectionless service on top of an atm network. In a first part, the chosen architecture is described, together with the level of performance requested. Then we analyze how the architecture and other constraints influence the chip partitioning. Finally the three custom devices developed for this application are succinctly described.RésuméCet article présente un ensemble de circuits sur mesure utilisés pour réaliser un service sans connexion dans un environnement atm. La première partie décrit ľ architecture choisie en même temps que le niveau de performance requis. Ensuite ľ article analyse la manière dont ľ architecture et ď autres contraintes influencent la décomposition en circuits. En dernier lieu, les trois circuits sur mesure développés pour cette application sont succinctement présentés.

Choosing the Objectives for Traffic Engineering in IP Backbone Networks BAsed on Quality-of-Service Requirements

Objectives for traffic engineering in IP core networks can be different for different Quality-of-Service classes. In this paper we study the traffic engineering objectives for best-effort flows and for virtual leased line service flows. We propose mixed integer linear programming models that can be used for off-line centralized traffic engineering with label switched paths, and develop efficient algorithms for their approximate solution. We quantify the effect of the choice of the objective chosen for traffic engineering on the network performance, and assess the benefits of distributing the traffic between a single border node pair over multiple paths.