TCP - IP White Papers
Inferring Path Sharing Based on Flow Level TCP Measurements
Overview This paper develops methods to infer path or bottleneck sharing among TCP flow classes based on flow level measurements available from current traffic monitoring tools. The premise is that flows that temporally overlap on congested resources will have correlated throughputs. The paper proposes to use factor analysis to explore the correlation structure of flow class throughputs in order to hypothesize which flow classes might share congested resources. The effectiveness of this "black box" approach is studied using empirical data. It shows that making such inferences based on flow level statistics is viable in practice, and can serve as an effective, novel tool for network design and configuration decisions.
| Publisher | University of Texas at Austin | File Format | |
|---|---|---|---|
| Date Published | March 2004 | ||
| Format | White Papers | ||
| Topics | |||
-
Did you find this white paper useful? 5 out of 7 users found this white paper useful
White Paper RSS
Download
Register
