Fast accurate computation of large-scale IP traffic matrices from link loads

A matrix giving the traffic volumes between origin and destination in a network has tremendously potential utility for network capacity planning and management. Unfortunately, traffic matrices are generally unavailable in large operational IP networks. On the other hand, link load measurements are readily available in IP networks. In this paper, we propose a new method for practical and rapid inference of traffic matrices in IP networks from link load measurements, augmented by readily available network and routing configuration information. We apply and validate the method by computing backbone-router to backbone-router traffic matrices on a large operational tier-1 IP network -- a problem an order of magnitude larger than any other comparable method has tackled. The results show that the method is remarkably fast and accurate, delivering the traffic matrix in under five seconds.

[1]  Kavé Salamatian,et al.  Traffic matrix estimation: existing techniques and new directions , 2002, SIGCOMM '02.

[2]  Anja Feldmann,et al.  Deriving traffic demands for operational IP networks: methodology and experience , 2001, TNET.

[3]  Christophe Diot,et al.  Taxonomy of IP traffic matrices , 2002, SPIE ITCom.

[4]  Albert G. Greenberg,et al.  Experience in measuring backbone traffic variability: models, metrics, measurements and meaning , 2002, IMW '02.

[5]  Michael A. West,et al.  Bayesian Inference on Network Traffic Using Link Count Data , 1998 .

[6]  Anja Feldmann,et al.  Deriving traffic demands for operational IP networks: methodology and experience , 2000, SIGCOMM.

[7]  Bing Yu,et al.  Time-Varying Network Tomography: Router Link Data , 2000 .

[8]  Larry Peterson,et al.  Inter-AS traffic patterns and their implications , 1999, Seamless Interconnection for Universal Services. Global Telecommunications Conference. GLOBECOM'99. (Cat. No.99CH37042).

[9]  Don Towsley,et al.  The use of end-to-end multicast measurements for characterizing internal network behavior , 2000, IEEE Commun. Mag..

[10]  J. Tinbergen.  Shaping the World Economy: Suggestions for an International Economic Policy , 1964 .

[11]  Anja Feldmann,et al.  NetScope: traffic engineering for IP networks , 2000, IEEE Netw..

[12]  Jacek Kowalski,et al.  Modelling Traffic Demand Between Nodes in a Telecommunications Network , 1995 .

[13]  Jennifer Widom,et al.  Teletraffic modeling for personal communications services , 1997 .

[14]  Kihong Park,et al.  The Internet as a Large-Scale Complex System , 2005, Santa Fe Institute Studies in the Sciences of Complexity.

[15]  Robert Nowak,et al.  Internet tomography , 2002, IEEE Signal Process. Mag..

[16]  Jennifer Rexford,et al.  Passive Traac Measurement for Ip Operations , 2002 .

[17]  Nick Feamster,et al.  Controlling the impact of bgp policy changes on ip traffic , 2001 .

[18]  Y. Vardi,et al.  Network Tomography: Estimating Source-Destination Traffic Intensities from Link Data , 1996 .

[19]  Mikkel Thorup,et al.  Optimizing OSPF/IS-IS weights in a changing world , 2002, IEEE J. Sel. Areas Commun..