Results are noted from the analysis of traffic measured over a departmental switched Ethernet. Self-similar characteristics are seen throughout the network, for example, at the compute servers, web server and intermediate routers. It is shown that data shipped by the web server (i.e. including both static files from a file server and dynamically-generated data) have a heavy-tailed distribution, which is matched extremely well by a Cauchy distribution. It is also shown that the fragmentation of the data (i.e. into Ethernet frames) leads to a departure process whose power spectrum is shown to follow a power law very similar to that of the observed traffic. Importantly, the power law appears to be largely independent of the input process; self-similar behaviour is observed even with Poisson arrivals. This supports the suggested link between file/request size distribution and self-similarity in network traffic. The resulting implication that self-similarity and heavy tails are primarily due to server nodes, rather than being inherent in offered traffic, leads to the possibility of using conventional queueing network models of performance.
References
-
-
1)
-
P. Bak ,
C. Tang ,
K. Wiesenfeld
.
Self-organized criticality: an explanation of 1/f noise.
Phys. Rev. Lett.
,
381 -
384
-
2)
-
Crovella, M., Bestavros, A.: `Self-similarity in World Wide Web traffic: Evidence and possible causes', Proc. SIGMETRICS’96: ACM Int. Conf. on Measurement and Modelling of Computer Systems, May 1996, Philadelphia, PA, USA.
-
3)
-
J. Beran
.
(1994)
Statistics for long-memory processes.
-
4)
-
Irlam, G.: Unix file size survey, http://www.base.com/gordoni/ufs93.html.
-
5)
-
B. Pilgram ,
D.T. Kaplan
.
A comparison of estimators of 1/f noise.
Physica D
,
108 -
122
-
6)
-
F. Kelly ,
B. Engquist ,
W. Schmid
.
(2001)
Mathematical modelling of the internet, Mathematics unlimited – 2001 and beyond.
-
7)
-
P. Abry ,
D. Veitch
.
Wavelet analysis of long-range-dependent traffic.
IEEE Trans. Inf. Theory
,
1 ,
2 -
15
-
8)
-
Leland, W.E., Taqq, M.S., Willinger, W., Wilson, D.V.: `On the self-similar nature of Ethernet traffic', Proc. ACM SIGCOMM, 1993, San Francisco, CA, USA, p. 183–193.
-
9)
-
Measurement data, http://www.doc.ic.ac.uk/~uh/QUAINT/data/.
-
10)
-
J. Feder
.
(1988)
Fractals.
-
11)
-
ExtremeNetworks and documentation, http://www.extremenetworks.com.
-
12)
-
B. Mandelbrot
.
(1982)
The Fractal geometry of nature.
-
13)
-
Newman, D.E., Sizemore, N.D., Carreras, B.A., Lynch, V.E.: `Growth and propagation of disturbances in a communication network model. Presented at Hawaii Int', Conf. on Systems Sciences, January 2002.
-
14)
-
H.J. Larson ,
B.O. Shubert
.
(1979)
Probabilistic models in engineering sciences.
-
15)
-
P.G. Harrison ,
N.M. Patel
.
(1993)
Performance modelling of communication networks and computer architectures.
-
16)
-
S. Thurner ,
S.B. Lowen ,
M.C. Feurstein ,
C. Heneghan ,
H.G. Feichtinger ,
M.C. Teich
.
Analysis, synthesis, and estimation of fractal-rate stochastic point processes.
Fractals
,
4 ,
565 -
595
-
17)
-
N. Wiener
.
Generalized harmonic analysis.
Acta Math.
-
18)
-
Hernández-Campos, F., Marron, J.S., Samorodnitsky, G., Smith, F.D.: `Variable heavy tailed durations in internet traffic part I: Understanding heavy tails', MASCOTS Proc., 2002, p. 43–50.
-
19)
-
Pearce, D., Kelly, P., Harder, U., Field, T.: `GILK: A dynamic instrumentation tool for the Linux Kernel', Proc. 12th Int. Conf. on Modelling Tools and Techniques, TOOLS 2002, 14–17 April 2002, London, UK, p. 220–226.
-
20)
-
M.S. Taqqu ,
V. Teverovski ,
W. Willinger
.
Estimators for long-range dependence: an empirical study.
Fractals
,
4 ,
785 -
798
-
21)
-
Veres, A., Boda, M.: `The chaotic nature of TCP congestion control', Proc. INFOCOM, 2000, Tel Aviv, Israel, 3, p. 1715–1723.
-
22)
-
Field, T., Harder, U., Harrison, P.: `Network traffic behaviour in switched Ethernet systems', Proc. IEEE MASCOTS, Fort Worth, 2002, TX, USA, p. 32–42.
-
23)
-
A. Khintchine
.
Korrelationtheorie der stationären Prozesse.
Math. Ann.
-
24)
-
R.N. Mantegna ,
H.E. Stanley
.
(2000)
An introduction to econophysics.
-
25)
-
W.H. Press ,
S.A. Teukolsky ,
W.T. Vetterling ,
B.P. Flannery
.
(1996)
Numerical recipes in C.
-
26)
-
Schwefel, H.P.: `Behavior of TCP-like elastic traffic at a buffered bottleneck router', Proc. INFOCOM, 2001, p. 1698–1705.
-
27)
-
Downey, A.B.: `The structural cause of file size distributions', Proc. SIGMETRICS/Performance, 2001, p. 328–329.
-
28)
-
A. Erramilli ,
O. Narayan ,
W. Willinger
.
Experimental queueing analysis with long-range dependent packet traffic.
IEEE/ACM Trans Netw.
,
2 ,
209 -
223
-
29)
-
T. Huisinga ,
R. Barlovic ,
W. Knospe ,
A. Schadschneider ,
M. Schreckenberg
.
A microscopic model for packet transport in the internet.
Physica A
,
249 -
256
-
30)
-
J. Voit
.
(2001)
The statistical mechanics of financial market.
-
31)
-
Tcpdump and website, http://www.tcpdump.org/.
-
32)
-
J. Honerkamp
.
(2002)
Statistical physics.
-
33)
-
Sikdar, B., Vastola, K.: `The effect of tcp on the self-similarity of network traffic', Proc. 35th Conf. on Information Sciences and Systems, March 2001, Baltimore, MD, http: //citeseer.nj.nec.com/sikdar01effect.html.
-
34)
-
V. Jacobson
.
Congestion avoidance and control.
Comput. Commun. Rev.
,
4 ,
314 -
329
-
35)
-
K. Fukuda ,
H. Takayasu ,
M. Takayasu
.
Origin of critical behaviour in ethernet traffic.
Physica A
,
289 -
301
-
36)
-
F. Baskett ,
K.M. Chandy ,
R.R. Muntz ,
F.G. Palacios
.
Closed and mixed networks of queues with different classes of customers.
J. ACM
,
2 ,
248 -
260
-
37)
-
H.J. Jensen
.
(1998)
Self-organised criticality.
http://iet.metastore.ingenta.com/content/journals/10.1049/ip-com_20040368
Related content
content/journals/10.1049/ip-com_20040368
pub_keyword,iet_inspecKeyword,pub_concept
6
6