I am a Research Staff Member at Seagate Research Center in
Pittsburgh, PA. My current focus is on designing new storage devices
that are aware of and adaptive to the highly dynamic operational environment
of computer systems (publications).
I completed my PhD at the Computer Science Department of the College of
William & Mary in December 2002. The thesis of my PhD was that
carefull workload characterization and accurate modeling assists
systems analysis both off- and on-line for higher adaptivity in todays
dynamic operational environment.
In my PhD, I extended and developed a new aggregation-based methodology,
called ETAQA, that efficiently solves Markov processes of M/G/1 and QBD type.
I used these type of processes to model and analyze clustered Web servers
(publications).
Using workload characterization and parameterization techniques proposed in
my thesis as well as ETAQA, I have succesfully modeled, analysed, and
proposed new content-aware resource allocation policies in clusters of
Web servers that take into account the dynamic behavior of Internet traffic
(publications).