Share Email Print

Proceedings Paper

Issues in performance modeling of data teletraffic
Author(s): Daniel P. Heyman
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Data teletraffic is characterized by bursty arrival processes. Performance models are characterized by a desire to know under what circumstances is the probability that an arrival finds a full input buffer very small. In this paper I examine how four models proposed in the literature perform on two data sets of local-area-network traffic. Among my conclusions are (1) the protocol governing the data transmission may have a substantial effect on the statistical properties of the packet stream, (2) approximating the probability that a finite buffer of size b overflows may not be adequately approximated by the probability that an infinite buffer has at least b packets in it, and (3) a data-based estimate of large-deviation rate-function does the best job of estimating packet loss on these data sets. This method may overestimate the loss rate by several orders of magnitude, so there is room for further refinements.

Paper Details

Date Published: 10 October 1997
PDF: 12 pages
Proc. SPIE 3231, Performance and Control of Network Systems, (10 October 1997); doi: 10.1117/12.290418
Show Author Affiliations
Daniel P. Heyman, AT&T Labs. (United States)

Published in SPIE Proceedings Vol. 3231:
Performance and Control of Network Systems
Wai Sum Lai; Hisashi Kobayashi, Editor(s)

© SPIE. Terms of Use
Back to Top