Modeling Link Events in High Reliability Networks With Support Vector Machines

High reliability communication networks (HRCN) are characterized by very low failure rates, and extremely short unavailability periods. The accurate modeling of the link availability in HRCN is a non-trivial problem, given that an extremely low number of historic events have been observed. We propose a statistical learning model for link event prediction in HRCN based on support vector machines (SVM) for nonlinear regression. The model flexibility can be improved by grouping predictor variables of different nature. A surrogate data set is made, which mimics the basic properties of links in a real network, and it is used for simulations that yield basic knowledge about the use and performance of the proposed SVM model. A true network example, based on two years of historic data, is also analysed. The proposed SVM model yields better performance than other tested methods (frequentist, and neural network estimators), specially during the first years obtaining the historic data in a HRCN, when the number of events is critically low.

[1]  José Luis Rojo-Álvarez,et al.  Support vector machines framework for linear signal processing , 2005, Signal Process..

[2]  G. Strbac,et al.  Evaluation of electricity distribution system design strategies , 1999 .

[3]  Robert H. Deng,et al.  A Probabilistic Approach to Fault Diagnosis in Linear Lightware Networks , 1993, IEEE J. Sel. Areas Commun..

[4]  José Luis Rojo-Álvarez,et al.  Kernel Methods in Bioengineering, Signal And Image Processing , 2007 .

[5]  Stephen P. Boyd,et al.  Convex Optimization , 2004, Algorithms and Theory of Computation Handbook.

[6]  Roy Sterritt,et al.  NETEXTRACT - Extracting Belief Networks in Telecommunications Data , 2000 .

[7]  James C. Ford,et al.  Proactive network design , 1999, 1999 IEEE Aerospace Conference. Proceedings (Cat. No.99TH8403).

[8]  D. O. Koval,et al.  Development of transmission system reliability performance benchmarks , 1999, 1999 IEEE Industrial and Commercial Power Systems Technical Conference (Cat. No.99CH36371).

[9]  Roy Sterritt,et al.  Fusing hard and soft computing for fault management in telecommunications systems , 2002, IEEE Trans. Syst. Man Cybern. Part C.

[10]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[11]  K. Nara,et al.  Configuration of new power delivery system for reliable power supply , 1999, 1999 IEEE Power Engineering Society Summer Meeting. Conference Proceedings (Cat. No.99CH36364).

[12]  M. Aizerman,et al.  Theoretical Foundations of the Potential Function Method in Pattern Recognition Learning , 1964 .

[13]  D. Saric,et al.  Fault analysis and prediction in telecommunication access network , 2000, 2000 10th Mediterranean Electrotechnical Conference. Information Technology and Electrotechnology for the Mediterranean Countries. Proceedings. MeleCon 2000 (Cat. No.00CH37099).

[14]  Roy Sterritt,et al.  Facing Fault Management as It Is, Aiming for What You Would Like It to Be , 2002, Soft-Ware.

[15]  José Luis Rojo-Álvarez,et al.  Support Vector Machines for Nonlinear Kernel ARMA System Identification , 2006, IEEE Transactions on Neural Networks.

[16]  J.L. Rojo-Alvarez,et al.  Discriminating between supraventricular and ventricular tachycardias from EGM onset analysis , 2002, IEEE Engineering in Medicine and Biology Magazine.

[17]  Yoshiyasu Takefuji,et al.  Knowledge-Based Intelligent Techniques in Industry , 1998 .

[18]  Luca Podofillini,et al.  Optimal design of reliable network systems in presence of uncertainty , 2005, IEEE Transactions on Reliability.