About cookies on this site Our websites require some cookies to function properly (required). In addition, other cookies may be used with your consent to analyze site usage, improve the user experience and for advertising. For more information, please review your options. By visiting our website, you agree to our processing of information as described in IBM’sprivacy statement. To provide a smooth navigation, your cookie preferences will be shared across the IBM web domains listed here.
Conference paper
Introduction to queueing network models
Abstract
Queueing network theory is an appropriate tool for constructing computer performance models. The principal parameters that characterize the workload in a given queueing network are the transaction routing and service times. Other important aspects in the characterization of a queueing network are user classes, queueing disciplines, and open or closed networks. Exact calculation of the performance of a queueing network model can be accomplished if the model has a product form solution i.e., if the overall state probability is a product of terms each relating to a single server. The so called BCMP model, which allows for multiple user classes and diverse queueing disciplines, is of this class. Many algorithms, including convolution and mean value analysis, have been devised for calculating the solutions. For models that do not have a product form solution, or that are too large for the exact solution to be calculated, approximate solution methods must be applied. One class of such methods, known as approximate mean value analysis, is very simple, fast, and sufficiently accurate for many real-life problems.