NSF Signs Three-Year Agreement with NLANR Measurement and Network Analysis Group $3.28 Million to Team Based at San Diego Supercomputer Center

Published 08/06/2002

UNIVERSITY OF CALIFORNIA, SAN DIEGO - The National Science Foundation (NSF) will provide $3.28 million to the National Laboratory for Applied Network Research (NLANR) Measurement and Network Analysis (MNA) group for work to be conducted over the next three years. The new NLANR/MNA Cooperative Agreement is a follow-on to a program that began in 1997. Since the program's founding, NLANR's measurement and analysis activities have benefited thousands of researchers across the nation by improving the performance of the networks they depend on for high-speed access to supercomputing resources and on-line data libraries.

NLANR is an NSF-funded collaboration that provides technical, engineering, and traffic analysis support for NSF's High Performance Connections sites (universities, supercomputer centers, and government research laboratories) and the ultrafast networks that link them (the "next-generation Internets"). NLANR teams help administrators maintain these networks and provide scientists, engineers, and scholars at research institutions throughout the United States the tools they need to use the high-speed data links efficiently.

The mission of the NLANR Measurement and Network Analysis group is to study the operation of these networks, measuring the flow of traffic and analyzing performance issues, to better understand the theoretical and practical behavior of the systems and to deliver maximum end-to-end performance to users.

"We have been building an extensive network analysis infrastructure," said Hans-Werner Braun, Principal Investigator on the effort. "Traffic data collection devices have been installed at approximately 150 locations, most of them in the United States but with a handful in foreign countries as well. The infrastructure also encompasses a growing collection of measurement data and analyses, a body of tools and methods, and avenues for sharing information. The 'human infrastructure' is equally important - we are engaging in many collaborations with other researchers, in this country and in others, and within and outside of the network measurement community. This is the largest project of its kind (of which we are aware) that makes all of the data publicly available on an ongoing basis."

"I look forward to working with this seasoned and talented team of researchers," said Gregory E. Monaco, Program Director for NLANR in the Advanced Networking Infrastructure and Research (ANIR) division at NSF.

The NLANR/MNA group has deployed a total of 150 network sensor/analysis devices at volunteer sites throughout the nation and half a dozen in collaborating foreign countries, creating a large-scale network analysis infrastructure. NLANR has developed methods of using inexpensive data-gathering devices based on PC technologies with extensive post-processing, and has pioneered new techniques in problem detection and traffic analysis. The team makes all analyses, graphics, software, and raw data available to the public via the Web for use by engineers, systems administrators, researchers, and students.

"We are pushing the technology to increase understanding of the networks' evolution and performance issues," said Ronn Ritke, co-Principal Investigator on the program. "The interface speeds of the networks that we cover, the precision of timing measurements, the depth of analysis - all of these are on the leading edge in high-speed networking."

NLANR/MNA's collaborations with other researchers and organizations in the United States include work with Bell Labs, Google, the Internet2 Abilene network, and the NSF's vBNS high-speed research network. International activities include investigations subcontracted to researchers at the University of Waikato in New Zealand, cooperation with the Pacific Rim Applications and Grid Middleware Assembly (PRAGMA), and activities with the U.S./Asia TransPAC network, the STAR TAP and StarLight international access points, the Russian NaukaNet. and the Latin American AMPATH network, via the NSF's High Performance International Internet Services (HPIIS) project.

An extensive collaboration continues with the University of Waikato in New Zealand, with researchers there playing key roles in projects to characterize networks using active and passive monitoring techniques and to develop high-speed optical data interface hardware.

NLANR currently has research and support staff at three sites. NLANR/MNA is based at the San Diego Supercomputer Center, a research unit of the University of California, San Diego. The NLANR Distributed Applications Support Team (DAST) is located at the National Center for Supercomputing Applications (NCSA) at the University of Illinois, Urbana-Champaign, and provides support to high-performance network users and assistance with their applications. The NLANR Engineering Services Team is located at the Pittsburgh Supercomputing Center at Carnegie Mellon University, and provides information and technical support to campus network engineers and other networking professionals for connecting to and using HPC networks. NLANR/DAST also received additional NSF funding this summer; the Pittsburgh group will continue to operate under an existing contract.

For more information about NLANR, see http://www.nlanr.net/. For information about the NLANR Measurement and Network Analysis group, see http://mna.nlanr.net/ or contact Ronn Ritke, MNA Manager, 858-822-3648, ritke@nlanr.net. The NLANR/MNA award is NSF contract number ANI-0129677. Information on the new NSF Cooperative Agreement with NLANR/DAST is available at http://www.ncsa.uiuc.edu/News/Access/Releases/020710.DAST.html.

The San Diego Supercomputer Center (SDSC) is an organized research unit of UCSD and the leading-edge site of the National Partnership for Advanced Computational Infrastructure (NPACI). SDSC's mission is to develop and use technology to advance science, and SDSC provides leadership both nationally and internationally in computing, data management, biosciences, and other areas. As a national laboratory for computational science and engineering, SDSC is funded by the National Science Foundation through NPACI and other federal agencies, the State and University of California, and private organizations. For more information about SDSC, see http://www.sdsc.edu/ or contact David L. Hart, SDSC Communications, 858-534-8314, dhart@sdsc.edu.

---

Contact: Ronn Ritke, NLANR/MNA, 858-822-3648, ritke@nlanr.net