US DOE  logo

Network Research Problems and Challenges for DOE Scientists Workshop

BETHESDA NORTH MARRIOTT
HOTEL & CONVENTION CENTER
BETHESDA, MD
FEBRUARY 1-2, 2016

The Network Research Problems and Challenges for DOE Scientists workshop will be held at the Bethesda North Marriott Hotel & Convention Center, 5701 Marinelli Road, North Bethesda, Maryland, 20852. The workshop will begin on Monday, February 1, 2016, at 8:30 AM, and end on Tuesday, February 2, 2016, by 5:00 PM. Registration and Continental breakfast will begin at 7:30 AM on Tuesday, February 2, 2016. A registration fee of $92.00 will be charged to attend this meeting. The registration fee includes continental breakfast, lunch, and AM and PM breaks.

 

Network Research Problems and Challenges for DOE Scientists

The mission of the Department of Energy Office of Science (DOE/SC) is the delivery of scientific discoveries and major scientific tools to transform our understanding of nature and to advance the energy, economic, and national security of the United States. One of the defining characteristics of the DOE/SC is its support of unique open-access scientific user facilities (supercomputers, large particle accelerators, high-intensity x-ray light sources, neutron scattering sources, and facilities for nanoscience, plasma science, genomic sequencing, microbiology, and atmospheric monitoring) for the Nation.

These unique open-access facilities are routinely used by scientists located at government laboratories, research universities, and industrial facilities. The global Research and Educations (REN) Internet, together with the commercial Internet, forms the infrastructure that allows access to these DOE/SC facilities. For the past 20 years the DOE/SC Energy Science network (ESnet) has seen a 10x growth in traffic every 47 months and this growth has shown no signs of slowing down.

While the growth of science data traffic shows no signs of leveling off, the ability of the network infrastructure to effectively carry this traffic is showing great strain. Several indications of this strain include low throughput for reliable transfers over all but nearly lossless paths, interactions between very long and very short flows, poor support for multipath routing and parallel channels, and side-effects of optimizations to reduce congestion.

The DOE/SC Advanced Scientific Computing Research (ASCR) program office is hosting a 2 day invitation-only workshop to identify and articulate the network and transport protocol research challenges that must be overcome to ensure data flows are able to take full advantage of future network infrastructures.

 

Organizing Committee

Richard Carlson
Lars Eggert
Christos Papadopoulos
Nageswara Rao
Brian Tierney
Joe Touch
Don Towsley
Lixia Zhang