The Application of Fluid Models to the Analysis of Peer-to-Peer Network

Abstract


The application of the fluid models to the analysis of the streams in information and communication networks is presented. The models, considered in the paper, take into account the specificities of widespread P2P networks (peer-to-peer), used for file-sharing, parallel computing, IP telephony, video streaming, etc. The review of the main types of P2P networks and their associated analytical models are presented in the paper. The fluid models, presented in the paper, describe network traffic in terms of the changes over time data stream rates between users and in terms of the number of network users. The first model is a system of ordinary differential equations and allows to analyze the average file download time. The second model is the extension of the first model and is represented in the form of partial differential equation. It takes into account a random amount of data requested by users. It can be used to analyze both the transient state and steady state during the download. This model is suitable to study the behavior of the system with a large number of users. In addition to the average download time the second model, taking into account the population in the network, allows to analyze such parameters of the network performance as the number of leechers and seeders in the network.

About the authors

Y V Gaidamaka

RUDN University (Peoples’ Friendship University of Russia)

Email: ygaidamaka@mail.ru
Moscow, Russia

E V Bobrikova

RUDN University (Peoples’ Friendship University of Russia)

Email: ebobrikova@gmail.com
Moscow, Russia

E G Medvedeva

RUDN University (Peoples’ Friendship University of Russia)

Email: kathynote@mail.ru
Moscow, Russia

References

Statistics

Views

Abstract - 963

PDF (Russian) - 210

Cited-By



Copyright (c) 2016 Гайдамака Ю.В., Бобрикова Е.В., Медведева Е.Г.

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

This website uses cookies

You consent to our cookies if you continue to use our website.

About Cookies