BackAboutNetwork Information CentreProjects

GLORIAD: USA-Russia Lightpath Enables Fast Data Transfer of Terabyte-sized Scientific Datasets

Scientists from the National Center for Data Mining (NCDM) at the University of Illinois at Chicago and the Geophysical Center at the Space Research Institute, Russian Academy of Sciences, Moscow, demonstrated a new method for distributing extremely large volumes of scientific information across the world. They successfully moved 1.4 TeraBytes (TB) of data in about 4.5 hours over a 1 Gbps lightpath between Chicago and Moscow as part of the Teraflow Network initiative. This event, which represents the highest performance information transfer ever recorded between these two countries, was made possible by a unique international organizational partnership.

Although the amount of science information is growing rapidly, the ability to move it on the regular Internet is still very limited. NCDM partnered with Russia's Geophysical Center to demonstrate a new capability for moving science data by transferring the Sloan Digital Sky Survey (SDSS) dataset between their two sites, using a specialized international communications facility.

This new capability uses two integrated innovations. One requires placing information directly on lightwaves while avoiding the slower services that are used by the traditional Internet. The other uses specialized communications technologies (new network protocols) for high performance streaming to avoid the limitations of standard Internet communications.

Using NCDM's open-source, high-performance network transport protocol UDT (UDP-based Data Transfer) on the Teraflow Network, researchers were able to quickly transfer the SDSS astronomy catalog data, between Chicago and Moscow. The 2.5 TB catalog is compressed to 1.4 TB, split into 60 files and, is distributed to astronomers around the world from the NCDM in Chicago. Using UDT, the 1.4 TB was transferred over a 1 Gbps lightpath and then decompressed in Moscow to its original size. It now resides on a local server in Moscow.

This data transfer had a sustained rate of 711 Mbps and a peak rate of 844 Mbps, and took about 4.5 hours to complete. This is about the speed that the data could be moved across the city of Chicago over a 1Gbps network, which graphically illustrates how barriers of distance are being eliminated by the new communications infrastructures and technologies. These techniques are required for research and experimentation for many science disciplines, and in the future it may also be used for many types of data intensive commercial applications.

This accomplishment was made possible through a unique partnership among organizations in eleven countries that have created international advanced communication facilities at locations literally around the world. GLORIAD, the Global Ring Network for Advanced Applications Development, is a consortium of several countries, notably the USA, Russia, China, Korea, Canada, the Netherlands, and the Nordic countries (Denmark, Sweden, Norway, Finland and Iceland), that are contributing networking capabilities to build a global 10 Gbps optical network around the northern hemisphere of the globe in support of advanced science and engineering. In the USA, GLORIAD is supported by the National Science Foundation's International Research Network Connections (IRNC) program, which also funds a 10 Gbps path between Chicago and Amsterdam called TransLight/StarLight. GLORIAD has been provided with a 3 Gbps path on TransLight/StarLight to allow a direct high- performance connection between the USA and Europe.

GLORIAD's Russian partners recently installed a 10 Gbps path from Amsterdam to Moscow, provided by the Russian Research Center "Kurchatov Institute". This allowed a 1 Gbps lightpath to be dedicated to the Teraflow Network, from Chicago (the StarLight facility), to Amsterdam (the NetherLight facility) and then on to Moscow (the MoscowLight facility). GLORIAD participants are part of a global initiative called the Global Lambda Integrated Facility (GLIF), which promotes the paradigm of lightpaths, or lambda networks, for data-intensive scientific research and applications.

This science demonstration was also supported by NCDM's Teraflow Network, an international facility designed to develop innovative technologies to stream massive distributed datasets over high- performance networks, at 1 Gbps, 10 Gbps and multiple 10 Gbps. The TeraFlow Network is being used as a next-generation platform, capable of supporting data-intensive applications, including many requiring information transfers that cannot be supported by traditional networks. The TeraFlow Network is developing techniques that will be required by future global applications.

"This is the latest in a string of demonstrations that proves that it is now practical for the working scientist to efficiently access terabyte size datasets from anywhere in the world. All it takes are today's high-performance networks and new network protocols, such as UDT," said Robert Grossman, NCDM director at the University of Illinois at Chicago. "With the technology now available, there is no reason for scientists not to have access to the latest data available in order to advance their research."

"We look forward to using these new technologies to share and mine very large databases in global change, space weather and remote sensing studies," said Mikhail Zhizhin, head of the Telematics Lab at the Geophysical Center in Moscow, "and to applying the technologies from the Teraflow Network to the larger GLORIAD infrastructure. In particular, the Research Group is working with the USA National Geophysical Data Center (NOAA) on the Space Physics Interactive Data Resource (SPIDR), and is working with Microsoft Research Cambridge on the Environmental Scenario Search Engine (ESSE). Additionally, there is strong demand to transmit real-time data streams and high- resolution images, which has not previously been possible. "

This is a significant achievement between USA and Russian scientists," stated Alexey Soldatov, co-director of GLORIAD/Russia and director of the Institute of Information Systems, Russian Research Center "Kurchatov Institute" (RRC "KI"), - "GLORIAD/Russia, based at RRC "KI", provides support and development of the networking infrastructure for scientist and educators. In addition, our Research Center is one of the leaders of the nationwide Russian Data Intensive Grid program, that will use GLORIAD's advanced networking infrastructure to support data-intensive projects and frontier experiments in high-energy physics, nanotechnology, gravitational wave research, digital astronomy and molecular genomics."

"The ability to move multi-terabyte datasets internationally in a matter of hours, and ultimately minutes, has been based on the cooperation and efforts among many international teams and it builds a solid foundation for future international science projects," said Natalia Bulashova, GLORIAD/USA co-principal investigator.

"Lessons learned on the Teraflow Network can be expanded to the entire GLORIAD community, and ultimately other GLIF international partners, said Greg Cole, GLORIAD/USA principal investigator. "No matter how fast we increase capacity and services on the GLORIAD network, the various science groups out there are moving faster. It's a real challenge for us, but it's a good challenge."

BackTerms of UseHome Page