Congestion at flow level and the impact of user behaviour

So-called elastic flows, corresponding to document transfers of various types, constitute the bulk of Internet traffic. This paper presents models of a single bottleneck link handling elastic traffic, accounting for random flow arrivals. The transport protocol and packet scheduling are taken into account approximately by assuming perfectly realized bandwidth sharing objectives.We refer to the demand as the product of the flow arrival rate and the average flow size. It is shown that per-flow throughput performance is generally satisfactory as long as demand is only slightly less than capacity. In overload, on the other hand, some flows must be abandoned. A fraction of link bandwidth is then wasted and performance critically depends on user behaviour. The models are useful in appraising the effectiveness of proposed schemes for Internet service differentiation.

[1]  J. W. Cohen,et al.  The multiple phase service network with generalized processor sharing , 1979, Acta Informatica.

[2]  David L. Black,et al.  An Architecture for Differentiated Service , 1998 .

[3]  Sara Oueslati,et al.  Quality of service and flow level admission control in the Internet , 2002, Comput. Networks.

[4]  Anja Feldmann,et al.  Characteristics of TCP Connection Arrivals , 2002 .

[5]  Thomas Bonald,et al.  Insensitivity results in statistical bandwidth sharing , 2001 .

[6]  Sally Floyd,et al.  Wide-area traffic: the failure of Poisson modeling , 1994 .

[7]  S. Wittevrongel,et al.  Queueing Systems , 2019, Introduction to Stochastic Processes and Simulation.

[8]  Laurent Massoulié,et al.  Arguments in favour of admission control for TCP flows , 1999 .

[9]  Alain Jean-Marie,et al.  On the transient behavior of the processor sharing queue , 1994, Queueing Syst. Theory Appl..

[10]  Thomas Bonald,et al.  Statistical bandwidth sharing: a study of congestion at flow level , 2001, SIGCOMM.

[11]  Alexandre Proutière,et al.  Statistical bandwidth sharing: a study of congestion at flow level , 2001, SIGCOMM.

[12]  Walter Willinger,et al.  Self-Similar Network Traffic and Performance Evaluation , 2000 .

[13]  M. E. Crovessa.  Self-Similarity in World Wide Wed Traffic : Evidence and Prssible Causes , 1996, SIGMETRICS 1996.

[14]  Azer Bestavros,et al.  Self-similarity in World Wide Web traffic: evidence and possible causes , 1996, SIGMETRICS '96.

[15]  Isi Mitrani,et al.  Sharing a Processor Among Many Job Classes , 1980, JACM.

[16]  Sally Floyd,et al.  Wide area traffic: the failure of Poisson modeling , 1995, TNET.