Departmental Papers (ESE)

Abstract

The goal of this paper is to design optimal scheduling and memory management so as to minimize packet loss in input queued switches with finite input buffers. The contribution is to obtain closed-form optimal strategies that minimize packet loss in 2 x 2 switches with equal arrival rates for all streams. For arbitrary arrival rates, the contribution is to identify certain characteristics of the optimal strategy, and use these characteristics to design a near-optimal heuristic. A lower bound for the cost associated with packet loss for N x N switches is obtained. This lower bound is used to design a heuristic which attains near-minimum packet loss in N x N switches with arbitrary N. These policies reduce packet loss by about 25% as compared to the optimal strategy for the infinite buffer case. The framework and the policies proposed here apply to buffer-constrained wireless networks as well.

Document Type

Journal Article

Date of this Version

December 2004

Comments

Copyright 2004 IEEE. Reprinted from IEEE Transactions on Information Theory, Volume 50, Issue 12, December 2004, pages 3197-3220.
Publisher URL: http://ieeexplore.ieee.org/xpl/tocresult.jsp?isNumber=29865&page=1

This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of the University of Pennsylvania's products or services. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to pubs-permissions@ieee.org. By choosing to view this document, you agree to all provisions of the copyright laws protecting it.

Keywords

Finite buffer, input queued switch, Markov decision process (MDP), memory management, scheduling

Share

COinS
 

Date Posted: 20 February 2005

This document has been peer reviewed.