General Method for Finding the Most Economical Distributed Router

In this work we present a novel method to determine the optimal parameters of a router architecture when certain router performance constraints are given. The total financial expense, or cost, is the optimality criterion. We introduce a general, essentially distributed, router architecture model, consisting of locally or remotely located forwarding engines or processing units gathered around a switch of variable speed. Given the following constraints: number of inputs, maximum line interface bandwidth, and maximum packet delay in a router, the presented method finds the optimal amount and distribution of processing power among the various available processing units and the optimal parameters for the switching element. The optimization employs an estimated market-based cost function per element and finds the most economical system solution.

The results show that the optimal solutions gather around two extreme points of the solution space, distinguishable by the distribution of the processing power mass and corresponding switch speed. We discuss when, depending on the customer input, one or the other solution is appropriate.

By: Lukas Kencl and Bozidar Radunovic

Published in: RZ3384 in 2001

LIMITED DISTRIBUTION NOTICE:

This Research Report is available. This report has been submitted for publication outside of IBM and will probably be copyrighted if accepted for publication. It has been issued as a Research Report for early dissemination of its contents. In view of the transfer of copyright to the outside publisher, its distribution outside of IBM prior to publication should be limited to peer communications and specific requests. After outside publication, requests should be filled only by reprints or legally obtained copies of the article (e.g., payment of royalties). I have read and understand this notice and am a member of the scientific community outside or inside of IBM seeking a single copy only.

rz3384.pdf

Questions about this service can be mailed to reports@us.ibm.com .