Share Email Print
cover

Proceedings Paper

Impact of aggregation on scaling behavior of Internet backbone traffic
Author(s): Zhi-Li Zhang; Vinay J. Ribeiro; Sue B. Moon; Christophe Diot
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

We study the impact of aggregation on the scaling behavior of Internet backbone tra ffic, based on traces collected from OC3 and OC12 links in a tier-1 ISP. We make two striking observations regarding the sub-second small time scaling behaviors of Internet backbone traffic: 1) for a majority of these traces, the Hurst parameters at small time scales (1ms - 100ms) are fairly close to 0.5. Hence the traffic at these time scales are nearly uncorrelated; 2) the scaling behaviors at small time scales are link-dependent, and stay fairly invariant over changing utilization and time. To understand the scaling behavior of network traffic, we develop analytical models and employ them to demonstrate how traffic composition -- aggregation of traffic with different characteristics -- affects the small-time scalings of network traffic. The degree of aggregation and burst correlation structure are two major factors in traffic composition. Our trace-based data analysis confirms this. Furthermore, we discover that traffic composition on a backbone link stays fairly consistent over time and changing utilization, which we believe is the cause for the invariant small-time scalings we observe in the traces.

Paper Details

Date Published: 8 July 2002
PDF: 11 pages
Proc. SPIE 4868, Scalability and Traffic Control in IP Networks II, (8 July 2002); doi: 10.1117/12.475273
Show Author Affiliations
Zhi-Li Zhang, Sprint Advanced Technology Labs. and Univ. of Minnesota (United States)
Vinay J. Ribeiro, Sprint Advanced Technology Labs. and Rice Univ. (United States)
Sue B. Moon, Sprint Advanced Technology Labs. (United States)
Christophe Diot, Sprint Advanced Technology Labs. (United States)


Published in SPIE Proceedings Vol. 4868:
Scalability and Traffic Control in IP Networks II
Victor Firoiu; Zhi-Li Zhang, Editor(s)

© SPIE. Terms of Use
Back to Top