Multifractal modeling of counting processes of long-range dependent network traffic

✍ Scribed by Jianbo Gao; Izhak Rubin

• Publisher: Elsevier Science
• Year: 2001
• Tongue: English
• Weight: 284 KB
• Volume: 24
• Category: Article
• ISSN: 0140-3664
• DOI: 10.1016/s0140-3664(01)00297-3

✦ Synopsis

Source traf®c streams as well as aggregated traf®c ¯ows often exhibit long-range-dependent (LRD) properties. In this paper, we study traf®c streams through their counting process representation. We ®rst study the condition for the measured LRD traf®c, as described by the interarrival time and packet size sequences, to be suf®ciently well approximated by a synthesized stream formed by recording the counting state of the traf®c at the start of each time slot. We then demonstrate that the burstiness of the counting processes is not well characterized by the Hurst parameter. We model a counting process by constructing a multiplicative multifractal process, which contains only one or two parameters. We study the LRD property of such processes, and show that the model has well-de®ned burstiness descriptors, and are easy to construct. We consider a single server queueing system, which is loaded, on one hand, by the measured processes, and, on the other hand, by properly parameterized multifractal processes. In comparing the system-size tail distributions, we demonstrate our model to effectively track the behavior exhibited by the system driven by the actual traf®c processes. Our study may help resolve a hot debate on the modeling of an often used trace of VBR video traf®c.