Lancaster EPrints

Flow classification by histograms: or how to go on safari in the internet.

Salamatian, Kave and Emilion, Richard and Soule, Augustin and Taft, Nina (2004) Flow classification by histograms: or how to go on safari in the internet. ACM SIGMETRICS Performance Evaluation Review, 32 (1). pp. 49-60.

Full text not available from this repository.

Abstract

In order to control and manage highly aggregated Internet traffic flows efficiently, we need to be able to categorize flows into distinct classes and to be knowledgeable about the different behavior of flows belonging to these classes. In this paper we consider the problem of classifying BGP level prefix flows into a small set of homogeneous classes. We argue that using the entire distributional properties of flows can have significant benefits in terms of quality in the derived classification. We propose a method based on modeling flow histograms using Dirichlet Mixture Processes for random distributions. We present an inference procedure based on the Simulated Annealing Expectation Maximization algorithm that estimates all the model parameters as well as flow membership probabilities - the probability that a flow belongs to any given class. One of our key contributions is a new method for Internet flow classification. We show that our method is powerful in that it is capable of examining macroscopic flows while simultaneously making fine distinctions between different traffic classes. We demonstrate that our scheme can address issues with flows being close to class boundaries and the inherent dynamic behaviour of Internet flows.

Item Type: Article
Journal or Publication Title: ACM SIGMETRICS Performance Evaluation Review
Additional Information: This paper develops a classification method classifying BGP Internet flows into a small set of homogeneous classes. The main innovation of this paper was to develop a new classification method based on modeling flow histograms using Dirichlet Mixture Processes for random distributions. We presented an inference based on Simulated Annealing Expectation Maximization algorithm. The classification method was developed in the context of network flow classification however but had impact also in other areas of statistics such as Financial analysis as it enabled to classify different investment portfolio based on the contents. RAE_import_type : Journal article RAE_uoa_type : Computer Science and Informatics
Subjects: T Technology > T Technology (General)
Departments: Faculty of Science and Technology > School of Computing & Communications
ID Code: 2605
Deposited By: ep_importer
Deposited On: 28 Mar 2008 12:44
Refereed?: Yes
Published?: Published
Last Modified: 26 Jul 2012 16:28
Identification Number:
URI: http://eprints.lancs.ac.uk/id/eprint/2605

Actions (login required)

View Item