News Release

NetSage tool will help us understand big data networks

Grant and Award Announcement

University of California - Davis

Every day, thousands of researchers rely on robust data networks to share petabytes of data with their colleagues around the world. A new $5 million, five-year National Science Foundation grant, awarded to Indiana University, the University of California, Davis and the University of Hawaii at Manoa, seeks to bolster these networks by enabling unprecedented measurement and analysis.

The grant will fund NetSage, a network measurement, analysis and visualization service designed to address the needs of today's international networks. The principal investigators are: Jennifer Schopf at Indiana University; Sean Peisert, assistant professor of computer science at UC Davis; and Jason Leigh at the University of Hawaii.

"It's about helping people to do better science," said Peisert. Scientists increasingly rely on moving vast of data around the world, for example from the Large Hadron Collider in Switzerland, or from telescopes such as the planned Large Synoptic Survey Telescope located on mountain tops in Chile or Hawaii.

These international networks move data at an unprecedented scale. But there can be problems especially with "elephant flows," when a large volume has to move across the pipe in a limited time, Peisert said. Even a small degradation in the network can have a big impact on performance.

The NetSage service will help network engineers gain a better understanding of current traffic patterns across the NSF's international network links, where large data flows come from and where they go, and where loss of data is occurring, and whether it is caused by network congestion or other issues.

The award (#1540933) is part of the NSF's International Research Network Connections (IRNC) program.

###


Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.