The Quantification of Overlay Network Congestion Based on Compressive Sensing

Abstract:

To obtain overlay network traffic and delay information between two hosts is important for network management, monitoring, design, planning and assessment. Traffic matrix and delay matrix represent the traffic and delay information between two hosts, so introduce the concept of the overlay network traffic matrix and delay matrix. Compressive sensing theory restores traffic matrix and delay matrix but is not suitable for overlay network. This paper improves compressive sensing algorithm to make it more applicable to overlay network traffic matrix and delay matrix restoration. After calculating the traffic matrix and delay matrix this paper quantifies overlay network congestion, which reflect the current network security situation. The experimental results show the restoration effect of traffic matrix and delay matrix is well and the congestion degree reflects the actual network state.

• Periodical: Advanced Materials Research (Volumes 268-270)
• Pages: 1564-1567
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.268-270.1564
• Online since: July 2011
• Authors: Hui He, Ming Chang, Xing Wang, Wen Juan Li, Hong Li Zhang, Hong Mei Ma
• Keywords: Compressive Sensing (CS), Delay Matrix, Network Congestion, Overlay Network, Traffic Matrix

References

[1] Yin, Z., Matthew, R., Walter, W., Lili, Q.: Spatial-temporal compressive sensing and internet traffic matrices. SIGCOMM, 267-278(2009).

[2] Tae, H. K., Dong, S.K., Sang, M.L., and Jong, S.P.: Detecting DDoS Attacks Using Dispersible Traffic Matrix and Weighted Moving Average Jun. (2009).

[3] Matthew, R., Mikke, T., Yin, Z.: Traffic Engineering with Estimated Traffic Matrices. 3rd ACM SIGCOMM (2003).

[4] Kwok, S.H., and Kwok, W.C.: Capacity Planning of Link Restorable Optical Networks Under Dynamic Change of Traffic. IEEE/ACM Transactions (2007).

[5] Cao, J., Davis, D., Wiel, S V., et al.: Time-varying network tomography: router link data .J. Journal of America Statistical Association, 95: 106321075(2009).

DOI: 10.1080/01621459.2000.10474303

[6] Zhang, Y., Roughan, M., Duffield, N., Greenberg, A.: Fast Accurate Computation of Large-Scale IP Traffic Matrices from Link Loads.C. Sigmetrics'03. San Diego, California, USA (2003).

DOI: 10.1145/885651.781053

[7] Zhang, Y., Roughan, M., Lund, C., et al.: An information-theoretic approach to traffic matrix estimation .C. SIGCOMM'03. Karlsruhe, Germany (2003).

[8] Medina, A., Taft, N., Salamatian, K., et al.: Traffic matrix estimation: Existing techniques and new directions .C. SIGCOMM'02. Pittsburgh, Pennsylvania , USA(2002).

DOI: 10.1145/964725.633041