|
Title:
|
A PACKET STREAMS APPROACH TO MODEL INTERNET TRAFFIC |
|
Author(s):
|
H. Hassan , J.m. Garcia , O. Brun |
|
ISBN:
|
978-972-8924-40-9 |
|
Editors:
|
Jörg Roth, Jairo Gutiérrez and Ajith P. Abraham (series editors: Piet Kommers, Pedro Isaías and Nian-Shing Chen) |
|
Year:
|
2007 |
|
Edition:
|
Single |
|
Keywords:
|
Traffic, Modeling, Aggregate, Packet streams, ARFIMA, Performance |
|
Type:
|
Full Paper |
|
First Page:
|
84 |
|
Last Page:
|
91 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
Analysis and modeling of Internet traffic is essential for network performance evaluation. Although, some Internet traffic
models have been proposed previously, we still lack a traffic model capable of handling huge traffic traces and offering
an acceptable queuing performance at the packet level. In this paper, we present a new approach to model Internet traffic
that fulfills these two goals. Our model is based on a Mixture-ARFIMA time series model. The model can handle huge
traffic traces using aggregate count processes and it offers good queuing performance by modeling packet streams inside
the traffic trace instead of modeling the whole trace as one packet stream. We validate our approach on different traffic
traces. Our experimental results show a better performance using this approach compared to old methods. |
|
|
|
|
|
|
