Reproducing Traffic

This chapter examines the statistical characteristics of source-level
trace replay experiments, comparing them to those of their corresponding
original traces.
As discussed in Chapter 5, and illustrated in
Figure 5.1, a packet header trace
and its source-level trace replay can be compared at two levels.
The first level is how well the set of connection vectors
extracted from are preserved by the trace replay experiments.
This means to collect a packet header trace
from the replay
and extract a new set of connection vectors
.
Section 5.2 presented a comparison of
and
for three traces. It demonstrated that the characteristics of
captured by are accurately reproduced by the traffic generation
method and its implementation.
The second level at which traces and their
replays can be compared is to directly extract statistics from and
. If these statistics are *reasonably* close,
we can say that the traffic generation method *reproduces*
the original traffic using closed-loop traffic generation.
This is the type of comparison discussed in this chapter. As we will show,
source-level trace replay generally results in a good approximation of the
statistical characteristics of the original traffic, which supports the
use of the a-b-t model as a foundation for realistic traffic generation.

- Beyond Comparing Connection Vectors
- Source-level Replay of Leipzig-II
- Time Series of Byte Throughput
- Time Series of Packet Throughput
- Marginal Distributions
- Long-Range Dependence
- Time Series of Active Connections

- Source-level Replay of UNC 1 PM
- Time Series of Byte Throughput
- Time Series of Packet Throughput
- Marginal Distributions
- Long-Range Dependence
- Time Series of Active Connections

- Mid-Chapter Review
- Observations on Byte Throughput
- Observations on Packet Throughput
- Observations on Active Connections

- Source-level Replay of UNC 1 AM
- Time Series of Byte Throughput
- Time Series of Packet Throughput
- Marginal Distributions
- Long-Range Dependence
- Time Series of Active Connections

- Source-level Replay of UNC 7:30 PM
- Time Series of Byte Throughput
- Time Series of Packet Throughput
- Marginal Distributions
- Long-Range Dependence
- Time Series of Active Connections

- Source-level Replay of Abilene-I
- Time Series of Byte Throughput
- Time Series of Packet Throughput
- Marginal Distributions
- Long-Range Dependence
- Time Series of Active Connections

- Summary

Doctoral Dissertation: *Generation and Validation of Empirically-Derived TCP Application Workloads*

© 2006 Félix Hernández-Campos