ABSTRACT
Principal Component Analysis (PCA) has been employed for structural analysis of network traffic flows in order to capture the periodic, anomalous and noisy components of traffic flows. PCA suffers from fundamental limitation stemmed from the assumption that the variables in question are continuous random variables. Analysis of data for discrete random variables has been traditionally performed by employing Correspondence Analysis. In this work, we present a novel idea of structural analysis of network traffic flows using Correspondence Analysis (CA). Apart from overcoming several limitations of PCA, CA has an edge over PCA in terms of visualization of large traffic matrices.
- E. J. Beh. Simple correspondence analysis: A bibliographic review. International Statistical Review, 72(2):257--284, 2004.Google ScholarCross Ref
- S. Kolenikov and G. Angeles. The Use of Discrete Data in PCA: Theory, Simulations, and Applications to Socioeconomic Indices, 2004.Google Scholar
- K.R.Gabriel. The biplot graphic display of matrices with application to principal component analysis 1. Biometrika, 58(3):453--467, 1971.Google ScholarCross Ref
- A. Lakhina, M. Crovella, and C. Diot. Diagnosing network-wide traffic anomalies. In In ACM SIGCOMM, pages 219--230, 2004. Google ScholarDigital Library
- A. Lakhina, K. Papagiannaki, M. Crovella, C. Diot, E. D. Kolaczyk, and N. Taft. Structural analysis of network traffic flows. SIGMETRICS Perform. Eval. Rev., 32(1):61--72, June 2004. Google ScholarDigital Library
- A. Soule, A. Lakhina, N. Taft, K. Papagiannaki, K. Salamatian, A. Nucci, M. Crovella, and C. Diot. Traffic matrices: balancing measurements, inference and modeling. In In Proceedings of the ACM SIGMETRICS, pages 362--373. Press, 2005. Google ScholarDigital Library
- Z. Wang, K. Hu, K. Xu, B. Yin, and X. Dong. Structural analysis of network traffic matrix via relaxed principal component pursuit. Comput. Netw., 56(7):2049--2067, May 2012. Google ScholarDigital Library
Index Terms
- Role of Correspondence Analysis in Network Traffic Flow Analysis
Recommendations
Structural analysis of network traffic flows
SIGMETRICS '04/Performance '04: Proceedings of the joint international conference on Measurement and modeling of computer systemsNetwork traffic arises from the superposition of Origin-Destination (OD) flows. Hence, a thorough understanding of OD flows is essential for modeling network traffic, and for addressing a wide variety of problems including traffic engineering, traffic ...
Structural analysis of network traffic flows
Network traffic arises from the superposition of Origin-Destination (OD) flows. Hence, a thorough understanding of OD flows is essential for modeling network traffic, and for addressing a wide variety of problems including traffic engineering, traffic ...
Sensitivity of PCA for traffic anomaly detection
SIGMETRICS '07 Conference ProceedingsDetecting anomalous traffic is a crucial part of managing IP networks. In recent years, network-wide anomaly detection based on Principal Component Analysis (PCA) has emerged as a powerful method for detecting a wide variety of anomalies. We show that ...
Comments