This Article Full Text (PDF) References Alert me when this article is cited Alert me if a correction is posted Services Email this article to a friend Similar articles in this journal Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via Google Scholar Google Scholar Articles by Mahabhashyam, S. R. Articles by Kumara, S. R. T. Search for Related Content

Resource-Sharing Queueing Systems with Fluid-Flow Traffic

Oracle Corporation, King of Prussia, Pennsylvania 19406
Department of Industrial and Systems Engineering, Texas A&M University, College Station, Texas 77843
Department of Industrial and Manufacturing Engineering, Pennsylvania State University, University Park, Pennsylvania 16802
mahabhashyam{at}yahoo.com
gautam{at}tamu.edu
skumara{at}psu.edu

A system consisting of two buffers, each with independent fluid sources, is considered in this paper. Due to ease of implementation, the output capacities for the two buffers depend on the workload of only one of the buffers that is measured. A threshold-based policy is considered to dynamically assign output capacities for both buffers. Marginal workload distributions for the two buffers need to be evaluated for this policy. The key contribution of this paper is the performance analysis to derive the workload distribution in the two buffers. In addition, the paper also provides some guidelines to choose the output capacities for the two buffers as well as a mathematical program to determine an optimal threshold to dynamically switch between output capacities. Further, various applications of such systems to computer-communication networks are discussed.

Subject classifications: probability; stochastic model applications; queues; information systems; management.
History: Received May 2006; revision received May 2007; accepted June 2007.