ADVANCED DIGITAL NETWORK TECHNOLOGIES AND MIDDLEWARE SERVICES

Description:

Please Note that a Letter of Intent is due Tuesday, September 05, 2017

PROGRAM AREA OVERVIEW: OFFICE OF ADVANCED SCIENTIFIC COMPUTING RESEARCH

The primary mission of the Advanced Scientific Computing Research (ASCR) program is to discover, develop, and deploy computational and networking capabilities to analyze, model, simulate, and predict complex phenomena important to the Department of Energy. A particular challenge of this program is fulfilling the science potential of emerging computing systems and other novel computing architectures, which will require numerous significant modifications to today's tools and techniques to deliver on the promise of exascale science. To accomplish this mission, ASCR funds research at public and private institutions and at DOE laboratories to foster and support fundamental research in applied mathematics, computer science, and highperformance networks. In addition, ASCR supports multidisciplinary science activities under a computational science partnership program involving technical programs within the Office of Science and throughout the Department of Energy.

ASCR also operates high-performance computing (HPC) centers and related facilities, and maintains a highspeed network infrastructure (ESnet) at Lawrence Berkeley National Laboratory (LBNL) to support computational science research activities. The HPC facilities include the Oak Ridge Leadership Computing Facility (OLCF) at Oak Ridge National Laboratory (ORNL), the Argonne Leadership Computing Facility (ALCF) at Argonne National Laboratory (ANL), and the National Energy Research Scientific Computing Center (NERSC) at Lawrence Berkeley National Laboratory (LBNL).

ASCR supports research on applied computational sciences in the following areas:

 - Applied and Computational Mathematics to develop the mathematical algorithms, tools, and libraries to model complex physical and biological systems.
 - High-performance Computing Science to develop scalable systems software and programming models, and to enable computational scientists to effectively utilize petascale computers to advance science in areas important to the DOE mission.
 - Distributed Network Environment to develop integrated software tools and advanced network services to enable large-scale scientific collaboration and make effective use of distributed computing and science facilities in support of the DOE science mission.
 - Applied Computational Sciences Partnership to achieve breakthroughs in scientific advances via computer simulation technologies that are impossible without interdisciplinary effort.

For additional information regarding the Office of Advanced Scientific Computing Research priorities, click here.ADVANCED DIGITAL NETWORK TECHNOLOGIES AND MIDDLEWARE SERVICES
The primary mission of the Advanced Scientific Computing Research (ASCR) program is to discover, develop, and deploy computational and networking capabilities to analyze, model, simulate, and predict complex phenomena important to the Department of Energy. A particular challenge of this program is fulfilling the science potential of emerging computing systems and other novel computing architectures, which will require numerous significant modifications to today's tools and techniques to deliver on the promise of exascale science. To accomplish this mission, ASCR funds research at public and private institutions and at DOE laboratories to foster and support fundamental research in applied mathematics, computer science, and highperformance networks. In addition, ASCR supports multidisciplinary science activities under a computational science partnership program involving technical programs within the Office of Science and throughout the Department of Energy.

ASCR also operates high-performance computing (HPC) centers and related facilities, and maintains a highspeed network infrastructure (ESnet) at Lawrence Berkeley National Laboratory (LBNL) to support computational science research activities. The HPC facilities include the Oak Ridge Leadership Computing Facility (OLCF) at Oak Ridge National Laboratory (ORNL), the Argonne Leadership Computing Facility (ALCF) at Argonne National Laboratory (ANL), and the National Energy Research Scientific Computing Center (NERSC) at Lawrence Berkeley National Laboratory (LBNL).

ASCR supports research on applied computational sciences in the following areas:

 - Applied and Computational Mathematics to develop the mathematical algorithms, tools, and libraries to model complex physical and biological systems.
 - High-performance Computing Science to develop scalable systems software and programming models, and to enable computational scientists to effectively utilize petascale computers to advance science in areas important to the DOE mission.
 - Distributed Network Environment to develop integrated software tools and advanced network services to enable large-scale scientific collaboration and make effective use of distributed computing and science facilities in support of the DOE science mission.
 - Applied Computational Sciences Partnership to achieve breakthroughs in scientific advances via computer simulation technologies that are impossible without interdisciplinary effort.

For additional information regarding the Office of Advanced Scientific Computing Research priorities, click here.

 

Maximum Phase I Award Amount:  $225,000

Maximum Phase II Award Amount:  $1,500,000

Accepting SBIR Applications:  YES

Accepting STTR Applications:  YES

Advanced digital network technologies and middleware services play a significant role in the way DOE scientists communicate with peers and collect/process data. Optical networks operating at rates of more than 100 Gbps support the transfer of petabytes of data per day. These networks also peer with commercial networks allowing scientists remote access to instruments and facilities while also allowing citizens access to the data and knowledge that has been produced. Improvements in the tools and services used to manage and operate this infrastructure are needed to meet the needs of both network operators and users.

Advances in access link technologies for commercial networks are driving consumer network speeds. 100+ Mbps links are now common in many parts of the U.S. and Gigabit/sec links are now being advertised. While these developments offer physical connectivity at high rates, translating these rates into routine application performance remains a significant challenge. Key among these challenges is providing individuals and small businesses tools and services that can accurately and easily report performance problems to both the consumers and ISP operations staff.

This topic solicits proposals that address issues related to developing tools and services that generate, collection, and store network operations data in a manner suitable for network engineers or application users and the hardening of middleware tools and services that deal with analyzing this data.  

a. Network Analysis Tools and Services
Network operations staff collect a wide variety of data from the network itself. This includes, but is not limited to, SNMP based network interface counter data, NetFlow/SFlow aggregate based flow data, perfSONAR based delay, loss, and throughput data, and packet trace data. Routers and switches may also export exception or error messages back to a log host to inform operations staffs of significant changes or faults. Finally, IDS systems and other security appliances also generate data that impacts the status and performance of the network. Making sense of all this data is a daunting challenge that requires advanced analysis tools and services.

Grant applications are sought to improve the usability and scalability of network analysis tools and services. Analysis tools may operate in real-time, accepting data from links operating at 100 Gbps or greater speeds or they may provide post-hoc analysis capabilities from stored data archives. Tools may correlate data from multiple input sources or they may deeply analyze a single input data stream. Tools should use widely available data formats and visualization systems to display results. Proposals to develop new data collections tools or complete Network Management Systems are out-of-scope for this subtopic.

Questions – Contact: Richard Carlson, richard.carlson@science.doe.gov

b. Operations Focused Data Tools and Services
Network operations staff currently collect data from a wide variety of network devices (i.e., hosts, routers, switches, middleboxes). Common types of data include (1) active measurements of throughput, delay, and jitter along specific network paths; and (2) passive collection of log data from devices and higher level services or network level flow data. The majority of tools and services deployed today rely on the network paths being static or changing slowly over time to build up valid time series data sets to show trends and behaviors.

Grant applications are sought to create new data collection tools and services that work in more dynamic and adaptive settings. Examples include, but are not limited to:

  1. Measuring the throughput of each link in a bonded network path
  2. Measuring the delay between a client and all servers located behind a load balancer middleware box
  3. Measuring the jitter between a client and all servers acting as members of an anycast group.

Active or passive tools and services are both valid approaches that may be explored. Tools that build upon or augment the perfSONAR suite of measurement tools are strongly encouraged. Proposals to develop analysis tools or services that use this data are out-of-scope for this subtopic.

Questions – Contact: Richard Carlson, richard.carlson@science.doe.gov

c. User Focused Data Tools and Services
Network users currently have few tools to help them determine if applications are performing properly. It is well known that performance problems at any level of the stack (i.e., path level congestion, host level configuration, device limitations) impact performance and that the indicator is simply the application runs slower than expected. Network users also lack higher level services that assist in reporting when and where these performance problems exist (i.e., carrier backbone, provider access link, home Wi-Fi LAN, inside the server or client host).

Grant applications are sought to develop data collection, analysis, or reporting tools and services that can be used by individuals or small businesses to understand and report perceived performance problems. Reporting tools should present data to the user in a format that can be understood by novice users and contains both raw and analyzed data that can be forwarded to a network operations staff with enough detail to allow them to fix a problem. Proposals to develop tools for use by network operations staff are out-of-scope for this subtopic.

Questions – Contact: Richard Carlson, richard.carlson@science.doe.gov

d. Other
In addition to the specific subtopics listed above, the Department invites grant applications in other areas that fall within the scope of the topic description above.

Questions – Contact: Richard Carlson, richard.carlson@science.doe.gov

References: Subtopic a:

  1. Kanuparthy, P., Lee, D., Matthews, W., et al, 2013, Pythia: Detection, Localization, and Diagnosis of Performance Problems, Communications Magazine, IEEE 51, V. 11, pp. 55-62. http://www.cc.gatech.edu/~dovrolis/Papers/final-Pythia-Comms13.pdf
  2. Calyam, P., Pu, J., Mandrawa, W., Krishnamurthy, A., 2010, Ontimedetect: Dynamic Network Anomaly Notification in Perfsonar Deployments, In Modeling, Analysis & Simulation of Computer and Telecommunication Systems (MASCOTS), 2010 IEEE International Symposium, pp. 328-337. http://ieeexplore.ieee.org/abstract/document/5581579/
  3. Sampaio, L., Koga, I., Costa, R., Monteiro, H., et al., 2007, Implementing and Deploying Network Monitoring Service Oriented Architectures: Brazilian National Education and Research Network Measurement Experiments, 2007 Latin American Network Operations and Management Symposium, LANOMS 2007, Rio de Janeiro, Brazil. September 10-12, pp. 28-37. http://ieeexplore.ieee.org/document/4362457/

References: Subtopic b:

  1. U.S. Department of Energy, 2016, DOE Network 2025: Network Research Problems and Challenges for DOE Scientists Workshop, Workshop Report, p. 41. https://science.energy.gov/~/media/ascr/pdf/programdocuments/docs/2017/DOE_Network_2025.pdf
  2. Cardellini, V., Colajanni, M., and Yu., P.S., 1999, Dynamic Load Balancing on Web-server Systems, IEEE Internet computing 3.3, pp. 28-39. http://www.ics.uci.edu/~cs230/reading/DLB.pdf
  3. IEEE Standards Association (IEEE), IEEE Get Program, Get IEEE 802: Local and Metropolitan Area Network Standards. http://standards.ieee.org/getieee802/download/802.3-2015.zip
  4. Partridge, C., Mendez, T., and W. Milliken, 1993, Host Anycasting Service, RFC 1546, p. 9, DOI 10.17487/RFC1546. http://www.rfc-editor.org/info/rfc1546

References: Subtopic c:

  1. Federal Communications Commission (FCC) Office of Engineering and Technology, Consumer and Governmental Affairs Bureau, 2016, 2015 Measuring Broadband American Report, A Report in Consumer Fixed Broadband Performance in the United States, p. 62. http://www.measurementlab.net/publications/FCC_MBA_2015.pdf
  2. Mathis, M., Heffner, J., O’Neil, P., and Siemsen, P., 2008, Pathdiag: Automated TCP Diagnosis, Lecture Notes in Computer Science, Vol. 4979, Springer, Berlin, Heidelberg, pp. 152-161. http://www.ucar.edu/npad/presentations&publications/PathdiagPAM08paper.pdf
  3. Balakrishnan, H., Padmanabhan, V., Fairhurst, G., and M. Sooriyabandara, 2002, TCP Performance Implications of Network Path Asymmetry, BCP 69, RFC 3449, DOI 10.17487/RFC3449. http://www.rfceditor.org/info/rfc3449
  4. Dawkins, S., Montenegro, G., Kojo, M., Magret, V., and Vaidya, N., 2001, End-to-end Performance Implications of Links with Errors, BCP 50, RFC 3155, DOI 10.17487/RFC3155. http://www.rfceditor.org/info/rfc3155
  5. Borman, D., Braden, B., Jacobson, V., and Scheffenegger, R., 2014, TCP Extensions for High Performance, RFC 7323, DOI 10.17487/RFC7323. http://www.rfc-editor.org/info/rfc7323

 

Agency Micro-sites

SBA logo
Department of Agriculture logo
Department of Commerce logo
Department of Defense logo
Department of Education logo
Department of Energy logo
Department of Health and Human Services logo
Department of Homeland Security logo
Department of Transportation logo
Environmental Protection Agency logo
National Aeronautics and Space Administration logo
National Science Foundation logo
US Flag An Official Website of the United States Government