• Corpus ID: 22554209

Prediction of Bandwidth and Additive Metrics for Large Scale Network Tomography

  title={Prediction of Bandwidth and Additive Metrics for Large Scale Network Tomography},
  author={Philip A. Chou and Christoffer R{\o}dbro and {\"U}r{\"u}n Dogan},
For real time communication services over the Internet, it is important to be able to predict in advance the quality of a call before relaying it over a particular path. In this paper we show how to predict the distribution of the end-to-end bandwidth, latency, jitter, and loss of a call from an arbitrary user X to an arbitrary user Y through particular components of the Internet, given a dataset of millions of calls among other users. This work is the first to infer component bandwidth… 

Figures from this paper


Tomography-based overlay network monitoring
This work characterize end-to-end losses (this extends to any additive metrics, including latency) rather than individual link losses, and finds a minimal basis set of k linearly independent paths that can fully describe all the O(n,2) paths.
Network tomography on general topologies
This paper considers the problem of inferring link-level loss rates from end-to-end multicast measurements taken from a collection of trees, and presents two algorithms to perform the link- level inferences.
Multicast-based inference of network-internal loss characteristics
A maximum-likelihood estimator for loss rates on internal links based on losses observed by multicast receivers is developed, which exploits the inherent correlation between such observations to infer the performance of paths between branch points in the tree spanning a multicast source and its receivers.
Efficient and reliable network tomography in heterogeneous networks using BitTorrent broadcasts and clustering algorithms
This work counts the fragments exchanged during a BitTorrent broadcast to reconstruct logical clusters of nodes interconnected by high bandwidth, as well as bottlenecks between these logical clusters.
Multicast-based inference of network-internal delay distributions
End-to-end measurements of multicast traffic can be used to infer the packet delay distribution and utilization on each link of a logical multicast tree and is evaluated through simulation to establish desirable statistical properties of the estimator, namely consistency and asymptotic normality.
Simple network performance tomography
In network performance tomography, characteristics of the network interior are inferred by correlating end-to-end measurements. In much previous work, the presence of correlations must be arranged at
NetQuest: A Flexible Framework for Large-Scale Network Measurement
This paper presents NetQuest, a flexible framework for large-scale network measurement that can support a variety of design requirements, and demonstrates its effectiveness in providing differentiated monitoring, supporting continuous monitoring, and satisfying the requirements of multiple users.
A Network Coding Approach to Loss Tomography
A framework for estimating link loss rates is designed, which leverages network coding capabilities, and it is shown that it improves several aspects of tomography, including the identifiability of links, the trade-off between estimation accuracy and bandwidth efficiency, and the complexity of probe path selection.
Generalized network tomography
  • Gugan Thoppe
  • Mathematics, Computer Science
    2012 50th Annual Allerton Conference on Communication, Control, and Computing (Allerton)
  • 2012
A novel algorithm to uniquely estimate the distribution of X, a vector of independent non-negative random variables, using only IID samples of the components of the random vector Y = AX is proposed, which does not even require any prior knowledge of the unknown distributions.
Network tomography for internal delay estimation
  • M. Coates, R. Nowak
  • Computer Science
    2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221)
  • 2001
An EM algorithm is developed for computing MLE of the internal delay distributions in cases where the network dynamics are stationary over the observation period and a sequential Monte Carlo procedure capable of tracking non-stationary delay characteristics is proposed.