Performance Analysis of a Client–Server System Using Queueing Networks: A Case Study

Queueing Network Models (QNMs) with Finite Capacity provide powerful and realistic tools for the performance evaluation and prediction of discrete flow systems such as computer systems, communication networks and flexible manufacturing systems. Over recent years, there has been a great deal of progress towards the analysis and application of QNMs with finite capacity, and high quality research work has appeared in diverse scientific journals of learning and conference proceedings in the fields of Operations Research, Computer Science, Telecommunication Networks, Management and Industrial Engineering. However, there are still many important and interesting finite capacity queues and QNMs to be resolved, such as those involving multiple-job classes, bounds and theoretical properties, exact analysis, numerical solutions and approximate methods, as well as application studies to computer and distributed systems, high-speed networks and production systems.This volume of Annals of Operations Research on Queueing Networks with Finite Capacity presents 17 extended research papers, both from industry and academia, reflecting current original contributions in the theory and applications of finite capacity queues and networks worldwide. Earlier short versions of these papers were amongst those presented at QNets '95, The Third International Workshop on Queueing Networks with Finite Capacity, 6th-7th July, 1995, Ilkley, West Yorkshire, UK. The papers are classified into four parts covering exact analysis, approximate methods, error bounds and performance modelling studies.

In this paper, we present an approach for model transformation from Queueing Network Models (QNMs) into Queueing Petri Nets (QPNs). The performance of QPNs can be analyzed using a powerful simulation engine, SimQPN, designed to exploit the knowledge and behavior of QPNs to improve the efficiency of simulation. When QNMs are transformed into QPNs, their performance can be analyzed efficiently using SimQPN. To validate our approach, we apply it to analyze the performance of several queueing network models including a model of a database system. The evaluation results show that the performance analysis of the transformed QNMs has high accuracy and low overhead. In this context, model transformation enables the performance analysis of queueing networks using different ways that can be more efficient.

A framework for stochastic traffic flow modeling over the U. S. National airspace based on queuing network models is advanced. The proposed framework allows the inclusion of a wide variety of trajectory uncertainties such as delays due to weather deviation, air traffic control actions, en route wind, aircraft performance, navigation system precision and flight control. En route queuing networks models are developed at origin-destination airport-level, Center-level, Sector-level and Latitude/Longitude-level spatial resolutions. Queuing models for the taxi, runway and TRACON flight segments have also been developed. Two approximations are employed to derive closed-form solutions to the queuing networks. Comparisons with Monte Carlo simulations and historic traffic data are used to validate the queuing network models. Validated queuing network models are then used to analyze a few next-generation air traffic operations concepts. The present research demonstrates that queuing network model solutions can closely approximate the Monte Carlo simulations, while delivering results at substantial savings in computational effort.

BackgroundPreparation for a disaster or accident-related mass casualty events is often based on experience. The objective measures or tools for evaluating decision-making and effectiveness during such events are underdeveloped. Queueing theory has been suggested to evaluate the effectiveness of mass causality incidents (MCI) plans.ObjectiveUsing different types of real MCI, we aimed to determine if a queueing network model could be used as a tool to assist in preparing plans to address mass causality incidents.MethodsWe collected information from two types of mass casualty events: a motor vehicle accident and a dust explosion. Patient characteristics, time intervals of every working station, numbers of physicians and nurses attending, and time required by physicians and nurses during these two MCIs were collected and used for calculation in a queueing network model. Balanced efficiency was determined by calculating the numbers of server, i.e., nurses and physicians, in the two MCIs.ResultsEfficient patient flows were found in both MCIs. However, excessive medical manpower supply was revealed when the queueing network model was applied to assess the MCIs. The best fitting result, i.e., the most efficient man power utilization, can be calculated by the queueing network models. Furthermore, balanced efficiency may be a more suitable condition than the highest efficiency man power utilization when faced with MCIs.ConclusionThe queueing network model is a flexible tool that could be used in different types of MCIs to observe the degree of efficiency when handling MCIs.

Applications of queueing network models to computer system performance prediction typically involve the computation of their equilibrium solution. When numerous alternative systems are to be examined and the numbers of devices and customers are large, however, the expense of computing the exact solutions may not be warranted by the accuracy required. In such situations, it is desirable to be able to obtain bounds on the system solution with very little computation. Asymptotic bound analysis (ABA) is one technique for obtaining such bounds. In this paper, we introduce another bounding technique, called balanced job bounds (BJB), which is based on the analysis of systems in which all devices are equally utilized. These bounds are tighter than ABA bounds in many cases, but they are based on more restrictive assumptions (namely, those that lead to separable queueing network models).

The subject of this paper is networks of queues with an infinite number of servers at each node in the system. Our purpose is to point out that independent motions of customers in the system, which are characteristic of infinite-server networks, lead in a simple way to time-dependent distributions of state, and thence to steady-state distributions; moreover, these steady-state distributions often exhibit an invariance with regard to distributions of service in the network. We consider closed systems in which a fixed and finite number of customers circulate through the network and no external arrivals or departures are permitted, and open systems in which customers originate from an external source according to a Poisson process, possibly non-homogeneous, and each customer eventually leaves the system.

Discrete event simulation is used to explore the robustness of queuing network models, a set of powerful analytical techniques for evaluating computer system performance. These techniques are shown to give good results even when some of the basic assumptions used to derive them are violated. It is also shown that simulation provides additional insights into computer system performance which are not available when using the mean value analysis characteristic of separable queuing network approaches.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Time delays in queueing networks are assuming increasing importance with the proliferation of transaction processing and time-critical real time systems. Mean values are insufficient and it is necessary to estimate time intervals that are not exceeded with a specified probability, i.e. quantiles. This paper presents results on time delay distributions in single server queues of various types and extends these to networks of queues. In particular, the class of Jackson networks that permit exact solution are analysed in both the open and closed cases, and approximation techniques for more general networks are proposed.

Queueing network models are commonly used for performance modelling. However, through application development stage analytical models might not be able to continuously reflect performance, for example due to performance bugs or minor changes in the application code that cannot be readily reflected in the queueing model. To cope with this problem, a measurement-based approach adopting Design of Experiments (DoE) technique is proposed. The applicability of the proposed method is demonstrated on a complex 3-tier e-commerce application that is difficult to model with queueing networks.

Because it is more intuitively understandable than the previously existing convolution algorithms, Mean Value Analysis (MVA) has gained great popularity as an exact solution technique for separable queueing networks. However, the derivations of MVA presented to date apply only to closed queueing network models. Additionally, the problem of the storage requirement of MVA has not been dealt with satisfactorily. In this paper we address both these problems, presenting MVA solutions for open and mixed load independent networks, and a storage maintenance technique that we postulate is the minimum possible of any “reasonable” MVA technique.

In this paper, we present a modelling framework for patient flow in a healthcare system using semi-open queueing network models, which introduces a total bed constraint, above which new patients will be refused admission. Hence this model provides a realistic representation of a real system. This approach enables us to have access to a range of established methods that deals with queueing network models. We demonstrate the usefulness of the model in the context of a geriatric department and show that hospital managers can use this model to gain better understanding of the dynamics of patient flow and to study potential long-term impacts of policy changes.

Software performance based on performance models can be applied at early phases of the software development cycle to characterize the quantitative behavior of software systems. We propose an approach based on queueing networks models for performance prediction of software systems at the software architecture level, specified by UML. Starting from annotated UML Use Case, Activity and Deployment diagrams we derive a performance models based on multichain and multiclass Queueing Networks (QN). The UML model is annotated according to the UML Profile for Schedulability, Performance and Time Specification. The proposed algorithm translates the annotated UML specification into QN performance models, which can then be analyzed using standard solution techniques. Performance results are reported back at the software architecture level in the UML diagrams. As our approach can be fully automated and uses standard UML annotations, it can be integrated with other performance modeling approaches. Specifically, we discuss how this QN-based approach can be integrated with an existing simulation-based performance modeling tool.

Because it is more intuitively understandable than the previously existing convolution algorithms, Mean Value Analysis (MVA) has gained great popularity as an exact solution technique for separable queueing networks. However, the derivations of MVA presented to date apply only to closed queueing network models. Additionally, the problem of the storage requirement of MVA has not been dealt with satisfactorily. In this paper we address both these problems, presenting MVA solutions for open and mixed load independent networks, and a storage maintenance technique that we postulate is the minimum possible of any “reasonable” MVA technique.

Closed queueing networks with finite capacities: blocking types, product-form solution and performance indices

Procurement, i.e., the process of obtaining materials or services and managing their inflow into organizations, is a critical process in supply chain management. Internet technologies offer attractive opportunities to reduce purchasing costs while increasing the speed and efficiency of the procurement process through seamless network integration and automated execution of key tasks. The paper attempts to model e-procurement from a lead time perspective, to capture the effects of Internet technologies on the procurement lead time. The model we develop is a multiclass queueing network called a probabilistic reentrant line. The model captures several important facets of an e-procurement process, such as use of electronic RFQ (request for quotation) in systematic sourcing, use of Internet auctions in spot purchasing, contention for procurement resources, randomness in execution times of procurement tasks, and concurrent execution of multiple procurement activities. The analysis of the queueing model suggests that end-to-end lead times in e-procurement can be compressed in ingenious ways using standard queueing theoretic techniques.