Please use this identifier to cite or link to this item:
|Title:||Performance preserving network downscaling||Authors:||Govindan, Ramesh
|Keywords:||Internet;Traffic control;Network topology;Telecommunication traffic;Delay;IP networks;Testing;Protocols;Performance analysis;Analytical models||Category:||Electrical Engineering - Electronic Engineering - Information Engineering||Field:||Engineering and Technology||Issue Date:||10-Nov-2005||Source:||38th Annual Simulation Symposium||Conference:||Annual Simulation Symposium||Abstract:||The Internet is a large, complex, heterogeneous system operating at very high speeds and consisting of a large number of users. Researchers use a suite of tools and techniques in order to understand the performance of networks: measurements, simulations, and deployments on small to medium-scale testbeds. This work considers a novel addition to this suite: a class of methods to scale down the topology of the Internet that enables researchers to create and observe a smaller replica, and extrapolate its performance to the expected performance of the larger Internet. The key insight that we leverage in this work is that only the congested links along the path of each flow introduce sizable queueing delays and dependencies among flows. Hence, one might hope that the network properties can be captured by a topology that consists of the congested links only. We show that for a network that is shared by TCP flows it is possible to achieve this kind of performance scaling. We also show that simulating a scaled topology can be up to two orders of magnitude faster than simulating the original topology. © 2005 IEEE.||ISSN:||0-7695-2322-6||DOI:||10.1109/ANSS.2005.36||Type:||Conference Papers|
|Appears in Collections:||Δημοσιεύσεις σε συνέδρια /Conference papers - poster -presentation|
Show full item record
checked on Mar 28, 2020
checked on Apr 3, 2020
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.