Network Tomography: Identifiability and Fourier Domain Estimation
Authors:
Preprint
Abstract
The statistical problem for network tomography is to infer the distribution of $\mathbf{X}$, with mutually independent components, from a measurement model $\mathbf{Y}=A\mathbf{X}$, where $A$ is a given binary matrix representing the routing topology of a network under consideration. The challenge is that the dimension of $\mathbf{X}$ is much larger than that of $\mathbf{Y}$ and thus the problem is often called ill-posed. This paper studies some statistical aspects of network tomography. We first address the identifiability issue and prove that the $\mathbf{X}$ distribution is identifiable up to a shift parameter under mild conditions. We then use a mixture model of characteristic functions to derive a fast algorithm for estimating the distribution of $\mathbf{X}$ based on the General method of Moments. Through extensive model simulation and real Internet trace driven simulation, the proposed approach is shown to be favorable comparing to previous methods using simple discretization for inferring link delays in a heterogeneous network.
Keywords
All Related Versions
- Version 1, 2007-12-21, ArXiv
- Published version: (0743166X), 1875.
This publication has 16 references indexed in Scilit:
- Statistical Aspects of the Analysis of Data NetworksTechnometrics, 2007
- Estimating Network Loss Rates Using Active TomographyJournal of the American Statistical Association, 2006
- Network Delay Tomography using Flexicast ExperimentsJournal of the Royal Statistical Society Series B: Statistical Methodology, 2006
- A bottom-up inference of loss rateComputer Communications, 2005
- Network delay tomographyIEEE Transactions on Signal Processing, 2003
- Unicast-based inference of network link delay distributions with finite mixture modelsIEEE Transactions on Signal Processing, 2003
- Maximum pseudo likelihood estimation in network tomographyIEEE Transactions on Signal Processing, 2003
- Multicast-based inference of network-internal delay distributionsIEEE/ACM Transactions on Networking, 2002
- GENERALIZATION OF GMM TO A CONTINUUM OF MOMENT CONDITIONSEconometric Theory, 2000
- Multicast-based inference of network-internal loss characteristicsIEEE Transactions on Information Theory, 1999