Download:
|
by Mark Coates, Robert Nowak
Proc. ITC Conf. IP Traffic, Modeling and Management
http://www.ece.mcgill.ca/~coates/publications/coatesitc00.ps.gz
Add To MetaCart
Abstract:
The fundamental objective of this work is to determine the extent to which unicast, endto-end network measurement is capable of determining internal network losses. We show that it is not possible to determine internal losses based solely on unicast, end-to-end measurement. However, by identifying and incorporating reasonable prior information or constraints, we demonstrate that it is possible to resolve these losses. The major contributions of this paper are three-fold: we formulate a measurement procedure for network loss inference based on end-to-end packet pair measurements, we identify suitable prior probability models for network inference, and we develop a novel factor graph framework for inference calculation. Simulation experiments demonstrate the potential of our new framework.
Citations
|
2322
|
Stochastic relaxation, Gibbs distributions and the Bayesian restoration of images
– Geman, Geman
- 1984
|
|
607
|
End-to-end Internet Packet Dynamics
– Paxson
- 1999
|
|
505
|
The EM Algorithm and Extensions
– McLachlan, Krishnan
- 1996
|
|
264
|
End-to-end Packet Delay and Loss Behavior in the Internet
– Bolot
- 1993
|
|
175
|
Multicastbased inference of network-internal delay distributions
– Presti, Duffield, et al.
- 2002
|
|
166
|
Graphical Models for Machine Learning and Digital Communication
– Frey
|
|
132
|
An architecture for large-scale internet measurement
– Paxson, Mahdavi, et al.
- 1988
|
|
128
|
Network tomography : Estimating sourcedestination traffic intensities from link data
– Vardi
- 1996
|
|
96
|
The case for FEC-based error control for packet audio
– Bolot, Garcia
|
|
93
|
Detecting Shared Congestion of Flows Via End-to-end Measurement
– Rubenstein, Kurose, et al.
- 2000
|
|
73
|
Inference of multicast routing trees and bottleneck bandwidths using end-to-end measurements
– Ratnasamy, McCanne
- 1999
|
|
63
|
A statistical perspective on ill-posed inverse problems
– O’Sullivan
- 1986
|
|
56
|
Time-varying Network Tomography: Router Link Data
– Cao, Davis, et al.
- 2000
|
|
55
|
Bayesian inference on network traffic using link count data
– Tebaldi, West
- 1998
|
|
21
|
The Bayesian Choice - A Decision Theoretic Motivation
– Robert
- 1994
|
|
15
|
Integrated likelihood methods for eliminating nuisance parameters
– Berger, Liseo, et al.
- 1999
|
|
4
|
Network inference from passive unicast measurement
– Coates, Nowak
- 2000
|
|
3
|
Multicast-based inference of networkinternal loss characteristics
– Cceres, Duftield, et al.
- 1999
|