|
CMU-CS-01-101
Computer Science Department
School of Computer Science, Carnegie Mellon University
CMU-CS-01-101
Data Mining Meets Performance Evaluation:
Fast Algorithms for Modeling Bursty Traffic
Mengzhi Wang, Tara Madhyastha, Ngai Hang Chan,
Spiros Papadimitriou, Christos Faloutsos
April 2001
CMU-CS-01-101.ps
CMU-CS-01-101.pdf
Keywords: Datamining, bursty traffic modeling, trace generation
Network, web, and disk I/O traffic are usually bursty, self-similar
and therefore can not be modeled adequately with Poisson arrivals.
However, we do want to model these types of traffic and to generate
realistic traces, because of obvious applications for disk scheduling,
network management, web server design. Previous models (like fractional
Brownian motion, ARFIMA etc) tried to capture the 'burstiness'. However
the proposed models either require too many parameters to fit and/or
require prohibitively large (quadratic) time to generate large traces.
We propose a simple, parsimonious method, the b-model, which solves
both problems: It requires just one parameter (b), and it can easily
generate large traces. In addition, it has many more attractive properties:
(a) With our proposed estimation algorithm, it requires just a single
pass over the actual trace to estimate b. For example, a one-day-long
disk trace in milliseconds contains about 86Mb data points and requires
about 3 minutes for model fitting and 5 minutes for generation.
(b) The resulting synthetic traces are very realistic: our experiments on
real disk and web traces show that our synthetic traces match the real
ones very well in terms of queuing behavior.
18 pages
|