Prediction Framework for Fault Resolution in Networks

Abstract

The continued increase in the size and complexity of modern networks has led to a commensurate increase in the size of their logs. To ensure high availability and correct operation of networks, it is essential that failures be detected promptly and quickly, their causes have to be diagnosed and remedial actions taken. Router logs are an invaluable resource to systems administrators during fault resolution. A lot of time spent in fault resolution is in sifting through large volumes of information, which includes router logs, to find the root cause of the problem. Therefore, the ability to analyse log files automatically and accurately will lead to significant savings in the time and cost of downtime events for any organization. The automatic search, analysis and prediction of errors using router logs is the primary motivation for the work carried out in this project. Different supervised machine learning techniques are compared and it is shown that a prediction model framework using RandomForest Algorithm can be used for automated fault detection as it has more accuracy and efficiency.