Definition of Characteristics for Computer’s Network Traffic

Authors: BoychenkoM.K., Ivanov I.P., Lokhturov V.A. Published: 14.04.2015
Published in issue: #2(101)/2015  
DOI: 10.18698/0236-3933-2015-2-133-140

Category: Informatics, Computer Engineering and Control  
Keywords: computer network, network interface card, self- similarity, network traffic, Hurst parameter, scaled range, aggregation

The results of experimental studies of self-similarity of the investigated computer network traffic, are presented. To determine the Hurst parameter, scalable sequence range value of random variables time double turnover is calculated for frames sent from the source computer to the destination computer without intermediate transit nodes between them. Similar investigations are carried out for the flow of frames sent to the address loopback, i.e. stream entering the network adapter input. An alternative way to calculate the scaled range value is an aggregation method used in determining the self-similar process dispersion. On the basis of analysis of the obtained Hurst exponent values calculated by two methods, it is concluded that the computer network traffic is self-similar.


[1] Norros I. A storage model with self-similar input. Queueing Systems, 1994, vol. 16, pp. 387-396.

[2] Hurst H., Black R., Simaika Y. Long-term Storage: An Experimental Study, CityplaceLondon, Constable, 1965.

[3] Kleykrok L. Russ. ed.: Vychislitel’nye sistemy s ocheredyami [Queueing Computer Systems]. Moscow, Mir Publ., 1979. 595 p.

[4] Stollings V. Russ. ed.: Sovremennye komp’yuternye seti [Contemporary Computer Networks], St. Petersburg, Piter Publ., 2003. 782 p.

[5] Erramilli A., Narayan O., Willinger W. Experimental Queuing Analysis with. Long-Range Dependent Packet Traffic. IEEE/ACM Transactions on Networking, April 1996.

[6] Ivanov I.P. Matematicheskie modeli, metody analiza i upravleniya v korporativnykh setyakh. Avtoreferat dis. dokt. tekhn. nauk [Mathematical Models, Methods of Analysis and Management in Corporate Networks. Dr. tehn. sci. diss. abstr.]. Moscow, MGTU im. N.E. Baumana, 2010. 34 p.

[7] Ivanov I.P., Kondrat’ev A.Yu., Lokhturov V.A. Modernization of process of measuring time intervals in operating systems of contemporary computers. Vestn. Mosk. Gos. Tekh. Univ. im. N.E. Baumana, Priborostr. [Herald of the Bauman Moscow State Tech. Univ., Instrum. Eng.], 2012, pp. 44-59 (in Russ.).