Queueing Models for Computer Communications System Analysis

Modeling and performance prediction are becoming increasingly important issues in the design and operation of computer communications systems. Complexities in their configuration and sophistications in resource sharing found in today's computer communications demand our intensive effort to enhance the modeling capability. The present paper is intended to review the state of affairs of analytic methods, queueing analysis techniques in particular, which are essential to modeling of computer communication systems. First we review basic properties of exponential queueing systems, and then give an overview of recent progress made in the areas of queueing network models and discrete-time queueing systems. A unified treatment of buffer storage overflow problems will be discussed as an application example, in which we call attention to the analogy between buffer behavior and waiting time in theGI/G/1queue. Another application deals with the analysis of various multiplexing techniques and network configuration. An extensive reference list of the subject fields is also provided.     

Design and analysis of cellular mobile communications system basedon DQRAP/CDMA MAC protocol

Future third-generation mobile communication systems will need multi-access control (MAC) protocols suitable for multimedia code division multiple access (CDMA) radio communications. Distributed queueing random access protocol (DQRAP)/CDMA is a general purpose MAC protocol oriented to the CDMA environment. Analytical model expressions and computer simulations have shown its capacity to achieve near-optimum performance under heterogeneous traffic scenarios in a unicellular environment. A cellular environment has been designed to verify that DQPAP/CDMA maintains its near-optimum performance in a packet switched mobile communication system. A new handover technique based on the protocol is proposed to further improve the system performance     

Two Parallel Queues with Dynamic Routing

We consider two parallelM/M/1queueing systems where a new arrival (customer, job, message) joins the shorter of the two queues. Such problems arise naturally in computer communications and packet switched data networks. An asymptotic approach is developed to obtain approximations to the steady-state joint distribution of the number of customers in the two systems. We first analyze the case where the two queueing systems are identical and then consider the case when the two servers work at different rates. Our results are shown to agree with the expansions of known exact solutions, when such solutions are available, and to yield new approximations when such solutions are not available.     

无冲突NC-IPRMA协议下的数据--话音综合

提出了一个面向微蜂窝通信的支持数据─话音综合业务的无冲突分组预约多址协议─—NC-IPRMA协议,通过M／M／N／／M．排队模型分析了NC-IPRMA协议的话音子系统性能,通过系统仿真分析了数据一话音综合性能。研究结果表明,在支持数据─话音综合业务方面,NC-IPRMA协议比PRMA和IPRMA协议更高效,这包括更高的信道利用率,更短的数据分组时延和更大的话音终端容量。由于采用排队等待方式接入时隙信道,NC-IPRMA协议彻底消除了以竞争方式接入信道的PRMA协议（及其各种改进方案）存在的重负荷下的不稳定问题。     

Performance Analysis of Buffered CSMA/CD Systems

This paper presents a new approximation approach, called tagged user approach (TUA), for the queueing analysis of slotted CSMA/CD systems with a finite user population having either finite or infinite user buffer capacity. By assuming a symmetric channel, the performance analysis of the overall system is determined by the performance of an arbitrarily selected user, called the tagged user. With the further assumption that each user always operates with its equilibrium probability, the packet service time distribution can be obtained using a state flow graph by studying the channel contention scheme. The obtained packet service time distribution is then applied to the queueing analysis of the tagged user using the standard queueing theory. That is, the analysis of the channel contention scheme and the analysis of the user queueing behavior are decoupled in this paper. Hence, TUA can be applied to complicated systems such as those where each user buffer may have bulk packet arrivals and random service discipline as long as the corresponding queueing theory is available. Since a state transition probability matrix is not required in TUA, the required amount of computation is quite small. Simulation results verify the high accuracy of the analysis.     

Analysis of a Finite Storage System with Batch Input Arising out of Message Packetization

A Markovian queueing model with finite waiting space is developed for the communications controller which buffers the flow of packets from a host computer to its associated packet switch. The segmentation of messages into packets by the host is modeled by a batch input to the communications controller. The probabilities of state are determined by numerical recursion and subsequently used in expressions developed for the blocking probabilities and waiting-time distribution as a function of two proposed batch acceptance strategies. Representative numerical results as would be useful in the dimensioning and performance analysis of the communications controller are presented. A more general non-Markovian model is investigated by means of simulation, showing that the initial Markovian model is very accurate in determining the system performance.     

清除阻塞的M/P/C/C 排队系统仿真

对清除阻塞型M／P／C／C排队系统进行了大量的仿真研究,结果表明在平均到达率及平均服务时间分别对应相同的情况下,其呼叫损失概率与爱尔兰-B公式符合得很好。这一结论对通信网络规划过程中考虑业务流的自相似性有重要意义。     

On learning how to predict

To meet performance guarantees, we should consider building computer systems more like queueing models we do understand, rather than trying to build complex queueing models of systems we do not understand. This approach is already familiar to software engineers, who use models to constrain software development so that the results are more reliable and understandable. Four real examples illustrate how a performance model can guide a system's design. The need for experimentation with models is emphasized.     

Queueing study of a 3-priority policy with distinct servicestrategies

A discrete-time, single server, 3-queue system is presented and analyzed. A distinct service strategy, namely the consistent-gated (c-G), 1-limited (L) and head-of-line (HoL), is applied to each of the queues (c-G/L/HoL policy). It is shown that this queueing system provides for an accurate analytical model for a DQDB station, as well as a means for an approximate evaluation of the correlation associated with key traffic processes in that network. In addition, the developed queueing system could be useful for the modeling of the queueing behavior of an ATM link shared by high-priority, low priority and control traffic. Through an asymptotic analysis under heavy low-priority traffic, the worst case performance for the high priority traffic is determined. Furthermore, it is illustrated that the asymptotic analysis provides for a potentially tight delay bounding technique. Finally, the delay performance of the developed queueing system is compared to that of a similar system in which one of the queues receives 1-limited service and the other two exhaustive (HoL^-/L/HoL⁺ policy)     

Performance evaluation of input and output queueing techniques inATM switching systems

Modeling alternatives for a fast packet switching system are analyzed. A nonblocking switch fabric that runs at the same speed as the input/output links is considered. The performance of the considered approaches are derived by theoretical analysis and computer simulations. Performance comparison between input queueing approaches with different selection policies are presented. Novel input and output queueing techniques are also proposed. In particular it is shown that, depending on the implementation, the input queueing approach studied in this paper achieves the same performance as the optimum (output) queueing alternative, without resorting to a faster packet switch fabric     

Some remarks regarding asymptotic packet loss in the Pareto/M/1/K queueing system

Many asymptotic results and numerical techniques have appeared in literature to evaluate the packet loss of GI/M/1/K queueing systems and some of them are applicable to heavy-tail distributed interarrival times. We have found a closed-form expression for the Laplace transform of Pareto probability distributions and it allows us to have a better setting to evaluate different performance measures of Pareto queueing systems. Particularly, in this paper we consider the evaluation of the asymptotic packet loss for the Pareto distributed interarrival times, i.e., Pareto/M/1/K queueing systems, through the use of the Pareto Laplace transform and its derivative.     

Increased capacity using CDMA for mobile satellite communication

The performance of a spread-spectrum CDMA (code-division multiple access) system in a mobile satellite environment is analyzed. Comparisons to single-channel-per-carrier FDMA systems are presented which show that the CDMA approach provides greater capacity. Results from computer simulations, laboratory tests, and field tests of a prototype modem are also presented. The tests results show excellent performance of the modem in the mobile environment and also the feasibility of the spread-spectrum approach to satellite mobile communications     

离散时间多重休假的Geom<em>x/G/1 排队系统的队长分布

近几年来,由于在制造系统与电讯交换系统的设计和控制中和在计算机通信网络的模型刻画和分析中的广泛应用,使得离散时间排队系统受到越来越多的注意.本文考虑离散时间多重休假成批到达的Geom/G/1排队系统,从任意初始状态出发,使用全概率分解技术和u-变换,研究了队长的瞬态性质和稳态性质,首次导出了队长瞬态分布的u-变换形式的递推表达式和队长稳态分布的递推表达式,进一步也获得稳态队长的随机分解结果.特别地,通过本文可直接获得一系列特殊离散时间排队系统相应的结果.     

Applications of computer communications in education: an overview

Applications of computer communications can be used in many ways in education. An overview is given of a number of categories of computer communications applications in learning-related activities. Particular attention is given to a new type of system called a course-support environment. In this type of system a database is integrated with Web-based tools and applications, and used to generate a course-support environment accessed via a standard Web browser. Some examples are given. The article moves on to an overview of various issues confronting the acceptance of computer communication systems in educational settings, and indicates some of the ways in which computer communications engineers will have to deal with those issues     

Waiting time distribution in M/D/1 queueing systems

The well-known formula for the waiting time distribution of M/D/1 queueing systems is numerically unsuitable when the load is close to 1.0 and/or the results for a large waiting time are required. An algorithm for any load and waiting time is presented, based on the state probabilities of M/D/1. The principles are also applicable for other queueing systems     

Reliability analysis of M/G/1 queueing system with repairable service station of reliability series structure

This paper considers the M/G/1 queueing system where the service station consists of r units and it operates if and only if all of the r units operate. Assume that each unit has a constant failure rate and arbitrary repair time distribution. We obtain the queueing quantities of the system and the reliability quantities of the service station, using the supplementary variable method and Takács' results.     

M θ/G/1/m and M θ/G/1 systems with the service time dependent on the queue length

The M ^θ/G/1/m and M ^θ/G/1 queueing systems, in which the service time depends on the queue length and is determined at the beginning of service of a customer, are investigated. The average busy period and the stationary distribution of the number of customers in the system have been found via the approach based on the idea of V.S. Korolyuk’s potential method. As a special case, the M ^θ/G/1 queue with a single threshold of switching of service modes is examined. The results are checked using the simulation model constructed with the use of GPSS World software tools.     

G/G/m queueing system with discouragement via diffusion approximation

This paper provides an approximation technique for a G/G^y/m queueing system with discouragement. The approximation is based on the theory of diffusion, depending on the means and variances of interarrival time and service time distributions. The arriving customers are assumed to be discouraged when a large number of customers are present in the system. The expressions for the probability of there being n customers in the system and the mean number of customers in the system, are obtained.     

Decay rate (ER) modelling of G/D/1 queue, and results for ATMtelecommunications

The authors present a new formula for calculating the decay rate in the queueing system G/D/1. This queueing model has potential for application in cell-based telecommunication systems, such as ATM, since it allows generally distributed inter-cell arrival times, while keeping the cell transmission time constant. The results presented here show that considerable improvements in accuracy are now available