Packet-level traffic measurements from the Sprint IP backbone

By C. Fraleigh, NetVMG Sue Moon, B. Lyles, Chase Cotton, Mujahid Khan, Deb Moll, Rob Rockell, T. Seely, Christophe Diot. IEEE Network, 2003

748 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Networks and Communications

View Paper: https://www.semanticscholar.org/paper/053310fd4885709670970037cda1eaeae4fdb2f5

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Networks and Communications

Citations in the corpus

On dominant characteristics of residential broadband internet traffic (2009, background): “[18] analyzed packet level traces recorded from the Sprint backbone in 2001, finding that in most traces HTTP contributed > 40% of all bytes, though several traces had P2P contributing 80%.”
The World’s Technological Capacity to Store, Communicate, and Compute Information (2011, methodology): “The average performance is estimated based on 112 models from the years 1991-2006 by the three largest manufacturers of digital cameras in the world: Canon, Kodak, and Sony (325-331).”
Characterization of failures in an IP backbone (2004, background): “These backbone networks are usually well-engineered and adequately provisioned, leading to very low packet losses and negligible queuing delays [1], [2].”
Is P2P dying or just hiding? [P2P traffic measurement] (2004, methodology): “These percentages reflect a typical approach for large backbone providers who overprovision capacity [8].”
Characterization of Failures in an Operational IP Backbone Network (2008, background): “These backbone networks are usually well-engineered and adequately provisioned, leading to very low packet losses and negligible queueing delays [1], [2].”
Toward the Accurate Identification of Network Applications (2005, background): “The state of the art in the identification of network applications through traffic monitoring relies on the use of well known ports: an analysis of the headers of packets is used to identify traffic associated with a particular port and thus of a particular application [1–3].”
On the design of green reconfigurable router toward energy efficient internet (2011, background): “It is now well known that the Internet traffic demand exhibits fluctuations over time due to end-user behavior, temporary link failures, anomalies, and so forth [5].”
Network traffic characteristics of data centers in the wild (2010, result): “Our work complements prior work on measuring Internet traffic [20, 10, 25, 9, 8, 17] by presenting an equivalent study on the flow characteristics of applications and link utilizations within data centers.”