Fluid Methods for Modeling Large, Heterogeneous Networks

Abstract

Researchers from the University of Massachusetts developed fluid-based methodologies for characterizing the behavior of large IP networks handling large numbers of TCP and UDP flows. These methodologies provide for rapid and efficient rates of individual and aggregate flows. These fluid models were also applied to the problems of characterizing the spread of worms and viruses and to the cascade of failures within the BGP routing infrastructure. The resulting fluid models were used to develop novel active queue management mechanisms resulting in more stable TCP performance and novel rate controllers for the purpose of providing minimum rate guarantees to TCP flow aggregates. Last, methodologies and tools were developed to integrate fluid network simulation with packet-level simulation.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Aug 01, 2005
Accession Number
ADA437100

Entities

People

  • Don Towsley
  • Kris Hollot
  • Vishal Misra
  • Weibo Gong
  • Yong Liu

Organizations

  • University of Massachusetts Amherst

Tags

Communities of Interest

  • Cyber
  • Energy and Power Technologies
  • Engineered Resilient Systems

DTIC Thesaurus Topics

  • Closed Loop Systems
  • Computational Science
  • Computer Networks
  • Control Systems
  • Control Systems Engineering
  • Cybersecurity
  • Detection
  • Detectors
  • Differential Equations
  • Digital Communications
  • Hypervelocity Flow
  • Intrusion Detection
  • Intrusion Detectors
  • Network Protocols
  • Network Science
  • Transport Protocols
  • Warning Systems

Fields of Study

  • Computer science

Readers

  • Computational Fluid Dynamics (CFD)
  • Computer Networking