text-only page produced automatically by Usablenet Assistive Skip all navigation and go to page content Skip top navigation and go to directorate navigation Skip top navigation and go to page navigation
National Science Foundation
Awards
design element
Search Awards
Recent Awards
Presidential and Honorary Awards
About Awards
Grant Policy Manual
Grant General Conditions
Cooperative Agreement Conditions
Special Conditions
Federal Demonstration Partnership
Policy Office Website



Award Abstract #1321115

NeTS: Small: Beating the Odds in Traffic Measurements/Detection with Optimal Online Learning and Adaptive Policies

NSF Org: CNS
Division Of Computer and Network Systems
divider line
Initial Amendment Date: August 30, 2013
divider line
Latest Amendment Date: May 29, 2015
divider line
Award Number: 1321115
divider line
Award Instrument: Standard Grant
divider line
Program Manager: John Brassil
CNS Division Of Computer and Network Systems
CSE Direct For Computer & Info Scie & Enginr
divider line
Start Date: October 1, 2013
divider line
End Date: September 30, 2016 (Estimated)
divider line
Awarded Amount to Date: $300,000.00
divider line
Investigator(s): Chen-Nee Chuah chuah@ucdavis.edu (Principal Investigator)
Qing Zhao (Co-Principal Investigator)
divider line
Sponsor: University of California-Davis
OR/Sponsored Programs
Davis, CA 95618-6134 (530)754-7700
divider line
NSF Program(s): RES IN NETWORKING TECH & SYS
divider line
Program Reference Code(s): 7923, 9102
divider line
Program Element Code(s): 7363

ABSTRACT

A key tool for understanding and engineering Internet backbone is the analysis of packet traces. However, given the increasing backbone speed towards 100Gbps, it is prohibitive to monitor individual flows at all times. This project develops optimal online learning and adaptation strategies for accurate traffic sampling, inference, and detection under hard resource constraints (e.g., limited CPU or memory at routers) and dynamic network/traffic conditions. Based on theories and techniques in multi-arm bandits, group testing, and compressed sensing, optimal or near-optimal solutions will be developed by exploiting the unique structures of the specific measurement application under study. Challenges addressed include learning from observations with heavy-tailed distributions and long-range dependencies, coping with sparse and/or imperfect observations, and distributed learning strategies that involve multiple monitors and decision points.

If successful, this research will provide fundamental design principles for a flexible traffic measurement infrastructure under the software-defined networking (SDN) paradigm. Reconfigurable measurements based on a learning process can be realized in commodity router/switches using SDN APIs such as OpenFlow, leading to potential development of new services. As this project examines problems at the intersection of networking and stochastic learning/optimization, it provides interdisciplinary training to graduate and undergraduate students in a team environment.


PUBLICATIONS PRODUCED AS A RESULT OF THIS RESEARCH

Note:  When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).

Some links on this page may take you to non-federal websites. Their policies may differ from this site.


K. Cohen and Q. Zhao. "Active Hypothesis Testing for Anomaly Detection," IEEE Transactions on Information Theory, v.61, 2015, p. 1432.

K. Cohen and Q. Zhao. "Asymptotically Optimal Anomaly Detection via Sequential Testing," IEEE Transactions on Signal Processing, v.63, 2015, p. 2929.

 

Please report errors in award information by writing to: awardsearch@nsf.gov.

 

 

Print this page
Back to Top of page
  FUNDING   AWARDS   DISCOVERIES   NEWS   PUBLICATIONS   STATISTICS   ABOUT NSF   FASTLANE  
Research.gov  |  USA.gov  |  National Science Board  |  Recovery Act  |  Budget and Performance  |  Annual Financial Report
Web Policies and Important Links  |  Privacy  |  FOIA  |  NO FEAR Act  |  Inspector General  |  Webmaster Contact  |  Site Map
National Science Foundation Logo
The National Science Foundation, 4201 Wilson Boulevard, Arlington, Virginia 22230, USA
Tel: (703) 292-5111, FIRS: (800) 877-8339 | TDD: (800) 281-8749
  Text Only Version