Showing papers in "Performance Evaluation in 2002"

TL;DR: The classical single server vacation model is generalized to consider a server which works at a different rate rather than completely stops during the vacation period, which approximates a multi-queue system whose service rate is one of the two speeds for which the fast speed mode cyclically moves from queue to queue with an exhaustive schedule.

TL;DR: It is demonstrated that the stationary distribution of the network state is insensitive to the distribution of service times if and only if the service capacities are balanced.

TL;DR: This paper shows how an extension of G-networks that includes novel "reset" customers can be used to model this behavior, and shows that a general G-network model with resets has product form, and proves existence and uniqueness of its solution.

TL;DR: This paper considers pre-recorded CM applications and uses the following metrics in evaluating the performance of multi-path streaming as compared to single- path streaming: data loss rate, conditional error burst length distribution, and lag1-autocorrelation.

TL;DR: It is proved that as job size increases to infinity, all work conserving policies converge almost surely with respect to this metric to no more than 1/(1 - ρ), where ρ denotes the load.

TL;DR: Two extensions of the Erlang multi-rate loss model (EMLM) are reviewed, whereby the call-level quality-of-service (QoS) of ATM networks is assessed and the connection-dependent threshold model (CDTM) is proposed, which resembles the threshold models, but the state dependency is individualized among call-connections.

TL;DR: The paper formulates a relevant OSPF routing optimisation problem, proves its NP-completeness, and discusses possible heuristic approaches and related optimisation methods for solving it.

TL;DR: The "entropy plots" are proposed to quantify the correlation and a new statistical model, the "PQRS" model, is developed to capture the burstiness and correlation of the real spatio-temporal traffic.

TL;DR: An algorithm to infer the CT-HMM from a series of end-to-end delay and loss observations of probe packets is developed, which can be used to simulate network environments for network performance evaluation.

TL;DR: The recursive formulas and the continuous approximation together provide a powerful tool for the performance analysis of this quite general system in the sense that they allow the calculation of the blocking probabilities and the mean throughputs in medium and large systems as well.

TL;DR: The impact of mobility on secure rekeying of group communication in a hierarchical key-distribution framework is characterized and it is shown that the FEDRP and SR inter-area re keying algorithms are superior under different circumstances.

TL;DR: This paper considers a discrete-time queueing system with head-of-line (HOL) non-preemptive priority scheduling with two classes of traffic, i.e., high-priority and low-priority traffic, which both generate variable-length packets.

TL;DR: Routing in loss networks in the framework of a non-cooperative game with selfish users is studied, and it is shown that uniqueness of equilibria or even of utilizations atEquilibria may fail even in the case of simple topology of parallel links.

TL;DR: This paper presents a flexible and efficient generator of self-similar traces, based on a simple M/G/∞ model which uses a new heavy-tailed discrete distribution.

TL;DR: In this article, the authors present a mathematical analysis of two asymmetric competing TCP connections where loss probabilities are directly related to their instantaneous window size, and occur when the sum of throughputs attains a given level.

TL;DR: A new recursion is developed in this paper, which significantly simplifies and enhances the applicability of the technique, and makes it easy to program on computers.

TL;DR: This work presents a performance evaluation study of hierarchical cellular networks using Performance Evaluation Process Algebra (PEPA), and shows that this formalism can easily be used to model such systems.

TL;DR: A queue with finite buffer where the buffer size limits the amount of work that can be stored in the queue, which models the systems in the Internet more realistically than the usual M/GI/1/K queue.

TL;DR: A framework for analytical performance evaluation of a single GSM/GPRS cell based on a multidimensional Markov chain model is provided and the influence of typical GPRS applications like Internet browsing on traditional GSM services has been studied.

TL;DR: A finite difference solution method is presented, which confirms to the boundary conditions and satisfies the normalization condition at the same time, and obtains the transient solution of the fluid dynamics.

TL;DR: The decomposition methodology presented in this paper is based on Markovian arrival processes, whose correlation structure is determined from the busy-period behavior of the upstream queues, whose resulting compact MAPs in connection with sophisticated moment-matching techniques allow an efficient decomposition of large queueing networks.

TL;DR: This paper introduces a new formalism of temporal rewards that allows complex quantitative properties to be expressed in terms of temporal reward formulas and implicitly defines an extended Markov chain that allows the determination of the quantitative property by traditional techniques for computing long-run averages.

TL;DR: This paper evaluates and compares the performance of two approaches for locating an agent in a mobile agent environment that dynamically creates a chain of forwarders to locate a moving agent, whereas the second one relies on a centralized server to perform this task.

TL;DR: It is proved that the policy that maximizes total discounted revenue consists of a set of monotonically decreasing thresholds as functions of the occupancy of each queue, and monotonicity properties with respect to system parameters are proved.

TL;DR: The results show that scalable streaming protocols require significantly lower server bandwidth in comparison to download protocols for start-up delays up to a large fraction of the media playback duration, and tight lower bounds on required server bandwidth can be approached by implementable policies.

TL;DR: The experiments in this paper demonstrate the feasibility of high-performance wide area network (WAN) emulation using parallel discrete-event simulation (PDES) techniques on a single shared-memory multiprocessor.

TL;DR: In this article, the authors consider a system with two service classes, one of which supports elastic traffic, and examine the user-level performance of the elastic traffic using the generalized processor sharing (GPS) discipline.

TL;DR: Examples are presented that demonstrate the application of the tools for answering questions related to network management and dimensioning, such as the maximum link utilization when some quality of service is guaranteed, how this utilization is affected by the link buffer and traffic shaping, the acceptance region and the effects of the scheduling discipline.

TL;DR: A construction which guarantees the insensitivity of certain concurrently enabled non-conflicting SPA activities is described, and a derived combinator for constructing process algebra models is given, which guarantees that the stochastic process underlying the model is insensitive to a particular set of activities.

TL;DR: Two queueing models are proposed for a network operating under the IEEE 1394 specification, and the average waiting time in steady state of an asynchronous packet is calculated and the effect on it due to isochronous traffic is studied.