Research Article
A stochastic model for the throughput of non-persistent TCP flows
@INPROCEEDINGS{10.1145/1190095.1190169, author={Francois Baccelli and David R. McDonald}, title={A stochastic model for the throughput of non-persistent TCP flows}, proceedings={1st International ICST Conference on Performance Evaluation Methodologies and Tools}, publisher={ACM}, proceedings_a={VALUETOOLS}, year={2012}, month={4}, keywords={Congestion control protocol throughput additive increase--multiplicative decrease algorithm TCP IP traffic on-off flow HTTP Markov process ordinary differential equation.}, doi={10.1145/1190095.1190169} }- Francois Baccelli
David R. McDonald
Year: 2012
A stochastic model for the throughput of non-persistent TCP flows
VALUETOOLS
ACM
DOI: 10.1145/1190095.1190169
Abstract
The general aim of this paper is to analyze the throughput of a HTTP flow. For this, we introduce a simplified model of such a flow which consists of a succession of idle and download periods. The file downloads are subject to a fixed packet loss probability. The same TCP connection is possibly used for the download of a random number of files, for which the effect of the slow start is taken into account. For this stochastic model, we derive a closed form formula for the stationary throughput obtained by a flow. We also derive closed form expressions for the mean time to transfer a file and for the distribution of the throughput. Several laws of file sizes and idle times are considered including heavy tailed distributions. We also briefly discuss how the formulas can be applied to predict bandwidth sharing among competing HTTP flows.