TCP - IP White Papers
On the Predictability of Large Transfer TCP Throughput
Overview With the advent of overlay and peer-to-peer networks, Grid computing, and CDNs, network performance prediction becomes an essential task. Predicting the throughput of large TCP transfers, in particular, has attracted much attention. This paper focuses on the design, empirical evaluation, and analysis of TCP throughput predictors for a broad class of applications. It first classifies TCP throughput prediction techniques into two categories: Formula-Based (FB) and History-Based (HB). Within each class, representative prediction algorithms are developed, which then evaluates empirically over the RON testbed. FB prediction relies on mathematical models that express the TCP throughput as a function of the characteristics of the network path (e.g., RTT, loss rate, available bandwidth).
| Publisher | Georgia Institute of Technology | File Format | |
|---|---|---|---|
| Date Published | January 2007 | ||
| Format | White Papers | ||
| Topics | |||
-
Did you find this white paper useful? 3 out of 6 users found this white paper useful
White Paper RSS
Download
Register
