On Utilizing Model Transformation for the Performance Analysis of Queueing Networks

Queueing Petri nets with product form solution

Predictive performance models are used increasingly throughout the phases of the software engineering lifecycle of distributed systems. However, as systems grow in size and complexity, building models that accurately capture the different aspects of their behavior becomes a more and more challenging task. The challenge stems from the limited model expressiveness on the one hand and the limited scalability of model analysis techniques on the other. This chapter presents a novel methodology for modeling and performance analysis of distributed systems [Kounev, 2006]. The methodology is based on queueing Petri nets (QPNs) which provide greater modeling power and expressiveness than conventional modeling paradigms such as queueing networks and generalized stochastic Petri nets. Using QPNs, one can integrate both hardware and software aspects of system behavior into the same model. In addition to hardware contention and scheduling strategies, QPNs make it easy to model software contention, simultaneous resource possession, synchronization, blocking and asynchronous processing. These aspects have significant impact on the performance of modern distributed systems. To avoid the problem of state space explosion, our methodology uses discrete event simulation for model analysis. We propose an efficient and reliable method for simulation of QPNs [Kounev & Buchmann, 2006]. As a validation of our approach, we present a case study of a real-world distributed system, showing how our methodology is applied in a step-by-step fashion to evaluate the system performance and scalability. The system studied is a deployment of the industry-standard SPECjAppServer2004 benchmark. A detailed model of the system and its workload is built and used to predict the system performance for several deployment configurations and workload scenarios of interest. Taking advantage of the expressive power of QPNs, our approach makes it possible to model systems at a higher degree of accuracy providing a number of important benefits. The rest of this chapter is organized as follows. In Section 2, we give a brief introduction to QPNs. Following this, in Section 3, we present a method for quantitative analysis of QPNs based on discrete event simulation. The latter enables us to analyze QPN models of realistic size and complexity. In Section 4, we present our performance modeling methodology for distributed systems. The methodology is introduced in a step-by-step

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.

Queueing networks have been widely used to evaluation performance of mainframe computer systems. In contrast, few results have been reported for modern open systems, so it was not clear whether queueing networks are useful for modern systems or not. We think this situation has partly been due to lack of handy evaluation tools. This paper presents tow tools that we developed to evaluate open system performance. On is a measuring tool that is capable of accurately obtaining the service times of system resources requested by an application transaction. The other is an estimating tool which calculates various performance measures based on queueing network models. This paper also describes a case study in which the performance of a medium‐sized UNIX client–server system (up to 24 clients) is estimated using the tools and these estimates are then compared with experimental results. The estimates closely agree with the measured results and are accurate enough for practical applications. Based on this, we conclude that queueing network models are also useful for modern systems.

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.

In this paper, we present a tool (DIMON) for distributed modeling of nets such as queueing networks or Petri nets or combinations of both over an IP based computer network, together with a 3-D graphical editor (DIM3ON) for modeling hierarchical nets utilizing that tool. Both the tool and the editor are implemented in Java. In this implementation, the net concept is considered as a superclass and thus can be extended by inheritance to any more specialized concept, e.g., to a stochastic Petri net (note that the Petri net concept itself is a subclass of the net concept). The editor is designed to be extensible in a rather easy manner in order to consider yet unsupported net classes. The nets are specified using the Extensible Markup Language (XML) in order to facilitate storage and interchange across a computer network. Keywords—combined queueing network and Petri nets, modeling tool, distributed modeling, hierarchi-

In recent years, many approximate methods have been developed for analyzing queueing models of complex computer systems. These ad hoc methods usually focus on specific aspects of system operation, and appear to be different from one another, making it difficult to see the underlying principles of model development, to understand the relationship between different models of the same system, or to apply the existing methods to new situations. This book presents the first systematic study of approximation methods in queueing network modeling and of the way these methods are developed. Metamodeling identifies the underlying modeling process and provides tools and techniques for model development that will allow students and researchers to sort through the many different methods, understand them, and apply them to new problems. Using the metamodeling characterization, the book surveys and classifies a large number of approximation methods, catalogs a large number of useful model transformations, characterizes iterative solution procedures and gives theorems for proofs of convergence. This work has led to several other significant results, most notably: an approximation that works well for systems containing semaphores that serialize processes; and the discovery of multiple stable operating points for systems in which there are processes at several priority levels. Contents Queueing Network Models of Computer Systems • The Structure of the Modeling Process • Behavior Sequence Transformations and Models with Shadow Servers • State Space Transformations • Consistent Solution, Iteration, and Convergence This book inaugurates the MIT Press series in Computer Systems (Research Reports and Notes), edited by Herb Schwetman.

This paper presents a systematic survey of the existing database system performance evaluation models based on the queueing theory. The continuous evolution of the methodologies developed is classified according to the mathematical modeling language used. This survey covers formal models – from queueing systems and queueing networks to queueing Petri nets. Some fundamentals of the queueing system theory are presented and queueing system models are classified according to service time distribution. The paper introduces queueing networks and considers several classification criteria applicable to such models. This survey distinguishes methodologies, which evaluate database performance at the integrated system level. Finally, queueing Petri nets are introduced, which combine modeling power of queueing networks and Petri nets. Two performance models within this formalism are investigated. We find that an insufficient amount of research effort is directed into the area of NoSQL data stores. Vast majority of models developed focus on traditional relational models. These models should be adapted to evaluate performance of non-relational data stores.

Queueing networks are a powerful abstraction for modeling systems involving contention for resources, e.g., manufacturing lines and computer systems. Queueing networks are especially effective in modeling computer communication systems. Most papers concerning queueing models of communication describe analytic solution of queueing models. This paper describes simulation models based on "extended" queueing networks. The primary advantage of using a queueing network representation for simulation of a computer communication system is the high level of description, in comparison with conventional simulation programming languages. For queueing network models to be used effectively for simulation of contention systems, appropriate software is needed. The research queueing package (RESQ) is a general purpose tool for modeling contention for resources and associated system characteristics. RESQ facilitates i) appropriate abstraction of system characteristics through its definitions of extended queueing networks, ii) efficient and convenient definition and revision of models through its integrated interactive and batch model definition interface, and iii) effective experimentation with simulation models through facilities for parameterized sets of experiments, interactive running of simulations and statistical analysis of simulation results. With a tool such as RESQ, an analyst can produce results in days instead of weeks, and so an analyst can answer questions which otherwise would be left unanswered.

Grids must ensure that the systems they operate not only provide all relevant services, but also meet the users' performance expectations. The paper proposes a novel performance modeling methodology based on Queueing Petri Nets (QPNs) for large-scale heterogeneous distributed systems, with an emphasis on enterprise Grid environment. A hierarchical structure of enterprise grid system and the concept of grid service execution graph are described, firstly. Then a detailed performance model is built in a step-by-step fashion, which showing how QPNs models can be exploited as a powerful performance tool. In order to reflect the system performance characteristics, three scenarios including service dependency, reliability impact, recovery ability of grid nodes and links are discussed. The simulations show that this solution can be helpful to design and develop enterprise grid system more efficiently.

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.

In recent years, software defined networking (SDN) has been proposed for enhancing the security of industrial control networks. However, its ability to guarantee the quality of service (QoS) requirements of such networks in the presence of adversarial flow still needs to be investigated. Queueing theory and particularly queueing network models have long been employed to study the performance and QoS characteristics of networks. The latter appears to be particularly suitable to capture the behaviour of SDN owing to the dependencies between layers, planes and components in an SDN architecture. Also, several authors have used queueing network models to study the behaviour of different application of SDN architectures, but none of the existing works have considered the strong periodic network traffic in software-defined industrial control networks. In this paper, we propose a queueing network model for softwaredefined industrial control networks, taking into account the strong periodic patterns of the network traffic in the data plane. We derive the performance measures for the analytical model and apply the queueing network model to study the effect of adversarial flow in software-defined industrial control networks.

Inventory control in a multi-supplier system

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.