Cyberinfrastructure in New York State - Grid Computing: Infrastructure, Service, and Applications - page 40

2.2.2.3 An Integrated Data and Computational Grid

The development of data storage solutions for the grid and the integration
of such solutions into grid portals is critical to the success of heteroge-
neous production-level grids that incorporate high-end computing, stor-
age, visualization, sensors, and instruments. Data grids typically house
and serve data to grid users by providing virtualization services to effec-
tively manage data in the storage network. The Storage Resource Broker*
is an example of such a system. Our Intelligent Migrator is integrated into
our grid portal in an effort to provide a scalable and robust data service to
NYS Grid users. The Intelligent Migrator examines and models user utili-
zation patterns in an effort to make efi cient use of limited storage so that
the performance of our physical data grid and the services provided to
our computational grid are signii cantly enhanced. Our integrated data
grid provides the NYS Grid users with seamless access to their i les, which
may be distributed across multiple storage devices. Our system imple-
ments data virtualization and a simple storage element installation proce-
dure that provides a scalable and robust system to users. In addition, our
system provides a set of online tools for the users so that they may main-
tain and utilize their data while not having to be burdened with details of
physical storage location (see Ruby and Miller , in press, for additional
information).

2.2.2.4 Intelligent Grid Scheduling

An ongoing project with very positive, yet preliminary, results is our intel-
ligent scheduling system. This system uses optimization algorithms and
proi les of users, their data, their applications, as well as network band-
width and latency, to improve a grid meta-scheduling system.

2.3
The Grid Computing Research Laboratory † (GCRL) at Binghamton
University conducts cyberinfrastructure and grid research in a variety of
areas, including various techniques for Web and grid service performance
optimization, component frameworks for grids, instruments and sensors
for grid environments, adaptive information dissemination protocols
across grid overlays, emulation framework for grid computation on multi-
core processors, and secure grid data transfer.

Cyberinfrastructure in Binghamton

* www.sdsc.edu/srb/index.php/Main_Page
† www.grid.cs.binghamton.edu.