Title: Towards Traffic Benchmarks for Empirical Networking Research: The
Role of Structure in Modeling Application Data Exchanges

Spreaker: Jai Aikat

Abstract: 
With the rise of phenomena such as social networks, cloud computing, and
wireless devices, the number of different types of applications that
constitute network traffic keeps constantly changing and ever
increasing. This has compounded the problem of modeling these
applications for realistic empirical evaluations.

Network testbeds and simulators remain the dominant platforms for
evaluating networking technologies today. The results of such
experiments are valid only to the extent that the traffic generated to
drive these experiments accurately represents the traffic carried in
real production networks.

In this talk, I shall discuss our research, demonstrating how certain
components of network traffic, such as the structure of application data
exchanges, can have a larger impact on the results obtained through
experimentation than other dimensions of traffic such as round-trip
time. Such findings point to the pressing need for traffic benchmarks in
networking research; such benchmarks are common in many other areas of
computing.

Through testbed experiments performed with synthetically generated
network traffic, emulating a large number of applications from two very
different traffic sources, and using several models of application data
exchanges (ADEs), we demonstrate the strong effects of ADE modeling on
performance measures such as queue length at routers, number of active
connections in the network, user response times, and connection
durations. We intend to use these results to advance the discussion of
standards for empirical networking research, and to create a traffic
benchmark suite, refreshing it as networked applications evolve.

Biography.

Dr. Jay Aikat is a postdoctoral researcher in the Department of Computer
Science at the University of North Carolina at Chapel Hill (UNC-CH).

She received her B.S. in Electrical Engineering at Birla Institute of
Technology in India.  After an 8-year stint in leadership roles in Information
Technology, she graduated with a Ph.D. in Computer Science in 2010 from UNC-CH.
Her dissertation is titled: An Investigation of the Effects of Application
Workload Modeling and Path Characteristics on Network Performance.

Dr. Aikat is a member of the networking research group led by Dr. Kevin Jeffay.
Her research focuses on measurement, modeling, and realistic generation of
Internet traffic, and developing better experimental methods in networking
research and education.