UCSB will be awarded a $500,000 grant from the National Science Foundation to research cloud computing.
The grant is part of a $5 million series of grants awarded to 14 universities by the NSF Cluster Exploratory program for the IBM-Google Cloud Computing Initiative, a program designed to help universities train their computer science students in the art of building applications with cloud computing. This new method will allow researchers to access applications on Web servers and does not require users to install software on their own computers.
Cloud computing – which is the concept of drawing the many facets of the Internet as a cloud in flowcharts and diagrams – seeks to speed up data-intensive computing by processing information in centralized databanks rather than on individual computers.
According to Ben Zhao, assistant professor of computer science and one of the principle investigators of the C.L.u.E. project at UCSB, current applications of cloud computing are present in Web sites such as Facebook.
“What’s interesting about cloud computing is that most people don’t realize they use it every day,” Zhao said in a press release. “Amazon, Facebook and Gmail, for example, have hundreds of thousands of machines that are providing all the application functionality in a reliable and scalable way.”
According to IBM’s Web site, the IBM-Google Initiative has provided several hundred computers for cloud computing research and plans to increase the number of processors to 1,600. Programmers use the computers remotely through the Internet.
The group at UCSB will look for solutions for data-intensive applications, such as social network searches and bioinformatic protein matching. Since these processes perform complex operations on large amounts of data, current systems may be bogged down by the sheer amount of communications and data transfers between machines.
UCSB’s Massive Graphs in Clusters project, also known as M.A.G.I.C., will seek to produce a user-friendly interface for database searches and analysis. The project will also seek to utilize resources such as large data centers for efficient information processing and management of search queries.
Of the four principle investigators, Zhao specializes in social networking. Xifeng Yan, an assistant professor of computer science, is looking into biological networking and data mining. Amr El Abbadi and Divyakant Agralwal are both professors of computer science and are researching improvements for database graphing and searches.
The grants will also fund projects at UCI, UCSD, Carnegie-Mellon University, Florida International University, MIT, Purdue University, University of Maryland-College Park, University of Massachusetts-Amherst, University of Virginia, University of Washington, University of Wisconsin-Madison, University of Utah and Yale University.