An Approximate Approach to End-to-End Traffic in Communication Networks

Article Contents

Article Navigation > Chinese Journal of Electronics > 2012 > 21(4): 705-710

“An Approximate Approach to End-to-End Traffic in Communication Networks,” Chinese Journal of Electronics, vol. 21, no. 4, pp. 705-710, 2012,

Citation:

“An Approximate Approach to End-to-End Traffic in Communication Networks,” Chinese Journal of Electronics, vol. 21, no. 4, pp. 705-710, 2012,

“An Approximate Approach to End-to-End Traffic in Communication Networks,” Chinese Journal of Electronics, vol. 21, no. 4, pp. 705-710, 2012,

Citation:

“An Approximate Approach to End-to-End Traffic in Communication Networks,” Chinese Journal of Electronics, vol. 21, no. 4, pp. 705-710, 2012,

PDF( 275 KB)

An Approximate Approach to End-to-End Traffic in Communication Networks

Funds: null

Received Date: 2011-12-01
Rev Recd Date: 2012-01-01
Publish Date: 2012-10-25

Abstract

Abstract

All end-to-end traffic in a network constructs Traffic matrix (TM) which reveals all traffic traversing the whole networks. In this paper, we investigate TM estimation problem in large-scale backbone networks. We propose an accurate approach to estimate it, based on the Recurrent multilayer perceptron (RMLP) which has a powerful ability of modeling. According to constraint relations between link loads and TM, we introduce their temporal and spatial correlation to modify the traditional RMLP and establish our models. And the outputs of our models take into account the constraints that TM itself is satisfied with. Trained with input-output data pairs, our models can learn and grasp all kinds of characteristics of TM and all weight parameters are determined. Finally, we use the real data to validate our method. Simulation results show that our method can perform the accurate and fast estimation of TM very well.

FullText(HTML)

References(25)

References

A. Soule, F. Silveira, H. Ringberg, C. Diot, “Challenging thesupremacy of traffic matrices in anomaly detection”, in Proc.of ACM IMC, 2007.

A. Soule, A. Lakhina, N. Taft et al., “Traffic matrices: Balancingmeasurements, inference and modeling”, in Proc. of ACMSIGMETRICS, 2005.

A. Lakhina, K. Papagiannaki, M. Crovella, C. Diot, E. Kolacyzk,N. Taft, “Structural analysis of network traffic flows”, inProc. of ACM SIGMETRICS, 2004.

L. Guo, “LSSP: A novel local segment shared protection formulti-domain optical mesh networks”, Computer Communications,Vol.30, pp.1794-1801, June 2007.

K. Papagiannaki, N. Taft, A. Lakhina, “A distributed approachto measure traffic matrix”, in Proc. of ACM IMC, 2004.(5+1)

D. Jiang, Z. Xu, Z. Chen et al., “Joint time-frequency sparseestimation of large-scale network traffic”, Computer Networks,Vol.55, No.10, pp.3533-3547, 2011.

L. Guo, J. Cao, H. Yu et al., “Path-based routing provisioningwith mixed shared protection inWDM mesh networks”, Journalof Lightwave Technology, Vol.24, pp.1129-1141, Mar. 2006.

Y. Zhang, M. Roughan, C. Lund, D. Donoho, “An informationtheoretic approach to traffic matrix estimation”, in Proc. ofACM SIGCOMM, 2003.

Y. Zhang, M. Roughan, N. Duffield, A. Greenberg, “Fast accuratecomputation of large-scale IP traffic matrices from linkloads”, ACM SIGMETRICS Performance Evaluation Review,Vol.31, No.3, pp.206-217, 2003.

J. Ni, S. Tatikonda, E.M. Yeh, “A large-scale distributed trafficmatrix estimation algorithm”, in Proc. of IEEE Globecom,2006.

A. Soule, K. Salamatian, A. Nucci, N. Taft, “Traffic matrixtracking using Kalman filtering”, LIP6 Research Report RPLIP6-2004-07-10, LIP6, 2004.

Y. Zhang, M. Roughan, W. Willinger, L. Qiu, “Spatio-temporalcompressive sensing and Internet traffic matrices”, in Proc. ofACM SIGCOMM, 2009.

I. Juva, “Sensitivity of traffic matrix estimation techniques totheir underlying assumption”, in Proc. of IEEE ICC, 2007.

S. Stoev, G. Michailidis, J. Vaughan, “Global modeling of backbonenetwork traffic”, in Proc. of IEEE Globecom, No.13, 2010.

K.V. Vishwanath, A. Vahdat, “Swing: Realistic and responsivenetwork traffic generation”, IEEE/ACM Transactions onNetworking, Vol.17, No.3, pp.712-725, 2009.

A. Nucci, R. Cruz, N. Taft, C. Diot, “Design of IGP link weightchanges for estimation of traffic matrix”, in Proc. of IEEE Infocom,2004.

A. Soule, A. Nucci, E. Leonardi, R. Cruz, N. Taft, “How toidentify and estimate the largest traffic matrix elements in adynamic environment”, in Proc. of ACM Sigmetrics, 2004.

A. Gunnar, M. Johansson, T. Telkamp, “Traffic matrix estimationon a large IP backbone: A comparison on real data”, inProc. of ACM IMC, 2004.

V. Erramilli, M. Crovella, N. Taft, “An independent-connectionmodel for traffic matrices”, in Proc. of ACM IMC, 2006.

Dingde Jiang, Zhengzheng Xu, Hongwei Xu, Yang Han, ZhenhuaChen, “An approximation method of origin-destination flowtraffic from link load counts”, Computers and Electrical Engineering,Vol.37, No.6, pp.1106-1121, Nov. 2011.

D. Jiang, J. Chen, L. He. “An accurate approach of large-scaleIP traffic matrix estimation”, IEICE Transactions on Communications,Vol.E90-B, No.12, pp.3673-3676, 2007.

D. Jiang, X. Wang, L. Guo, “Mahalanobis distance-based trafficmatrix estimation”, European Transactions on Telecommunications,Vol.21, No.3, pp.195-201, 2010.

S. Li, “Wind power prediction using recurrent multilayer perceptronneural networks”, IEEE Power Engineering SociertyGeneral Meeting, Vol.4, pp.13-17, 2003.

K. Hornik, M. Stinchcombe, H. White, “Multilayer feedforwardnetworks are universal approximators”, Neural Networks, Vol.2,pp.359-366, 1989.

D. Jiang, G. Hu, “Large-scale IP traffic matrix estimation basedon the recurrent multilayer perceptron network”, in Proceedingsof the IEEE International Conference on Communications,Beijing, China, pp.366-370, May 2008.

Relative Articles

Supplements(0)

Cited By

Proportional views