Network tomography for integer-valued traffic
From MaRDI portal
Abstract: A classic network tomography problem is estimation of properties of the distribution of route traffic volumes based on counts taken on the network links. We consider inference for a general class of models for integer-valued traffic. Model identifiability is examined. We investigate both maximum likelihood and Bayesian methods of estimation. In practice, these must be implemented using stochastic EM and MCMC approaches. This requires a methodology for sampling latent route flows conditional on the observed link counts. We show that existing algorithms for doing so can fail entirely, because inflexibility in the choice of sampling directions can leave the sampler trapped at a vertex of the convex polytope that describes the feasible set of route flows. We prove that so long as the network's link-path incidence matrix is totally unimodular, it is always possible to select a coordinate system representation of the polytope for which sampling parallel to the axes is adequate. This motivates a modified sampler in which the representation of the polytope adapts to provide good mixing behavior. This methodology is applied to three road traffic data sets. We conclude with a discussion of the ramifications of the unimodularity requirements for the routing matrix.
Recommendations
Cites work
- Ascent-Based Monte Carlo Expectation– Maximization
- Bayesian Inference on Network Traffic Using Link Count Data
- Estimating Latent Processes on a Network From Indirect Measurements
- Estimation of Origin–Destination Trip Rates in Leicester
- scientific article; zbMATH DE number 3121293 (Why is no real title available?)
- scientific article; zbMATH DE number 3768770 (Why is no real title available?)
- Identifiability of flow distributions from link measurements with applications to computer networks
- Integral Extreme Points
- Lectures on Polytopes
- Network Delay Tomography using Flexicast Experiments
- Network tomography for integer-valued traffic
- Network Tomography: Estimating Source-Destination Traffic Intensities from Link Data
- Network tomography: recent developments
- Statistical analysis of network data. Methods and models
- Time-Varying Network Tomography: Router Link Data
- Tools for statistical inference. Methods for the exploration of posterior distributions and likelihood functions.
Cited in
(14)- Conditional expectations in network traffic estimation
- Bayesian forecasting of multivariate time series: scalability, structure uncertainty and decisions
- Network tomography for integer-valued traffic
- Two applications of statistics to traffic models
- Network Tomography: Estimating Source-Destination Traffic Intensities from Link Data
- Polytope samplers for network tomography
- Latent binary MRF for online reconstruction of large scale systems
- Network tomography: a review and recent developments
- Identifiability of flow distributions from link measurements with applications to computer networks
- Traffic rate network tomography with higher‐order cumulants
- A ternary-arithmetic topological based algebraic method for networks traffic observability
- When lattice bases are Markov bases
- Some rapidly mixing hit-and-run samplers for latent counts in linear inverse problems
- Distributed online expectation-maximization algorithm for Poisson mixture model
This page was built for publication: Network tomography for integer-valued traffic
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2349589)
