Proactive Network Maintenance Using Machine Learning

R. Sasisekharan, V. Seshadri, and S. M. Weiss

A new approach to proactively maintain a massively interconnected communications network is described. Tl'fis approach has been applied to the detection and prediction of chronic transmission faults in AT&T’s digital communications network. A windowing technique was applied to large volumes of diagnostic data, and these data were analyzed by machine learning methods. A set of conditions has been found that is highly predictive of chronic circuit problems, that is, problems that are likely to continue in the immediate future without diagnosis and repair. In addition, a few conditions have been found that are predictive Of problems that affect multiple circuits. Such analyses over the complete network are helpful in proactively maintaining the network and in spotring trends for circuit problems. Proacfive maintenance of the network can help in greatly improving the quality and reliability of a network by identifying potentially serious problems before they occur.


This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.