A Non-intrusive Failure Prediction Mechanism for Deployed Optical Networks

Abstract

Failures in optical network backbone can lead to major disruption of internet data traffic. Hence, minimizing such failures is of paramount importance for the network operators. Even better, if the network failures can be predicted and preventive steps can be taken in advance to avoid any disruption in traffic. Various data driven and machine learning techniques have been proposed in literature for failure prediction. Most of these techniques need real time data from the networks and also need different monitors to measure key optical parameters. This means provision for failure prediction has to be available in network nodes, e.g., routers and network management systems. However, sometimes deployed networks do not have failure prediction built into their initial design but subsequently need arises for such mechanisms. For such systems, there are two key challenges. Firstly, statistics of failure distribution, data, etc., are not readily available. Secondly, major changes cannot be made to the network nodes which are already commercially deployed. This paper proposes a novel implementable nonintrusive failure prediction mechanism for deployed network nodes using information from log files of those devices. Numerical results show that the mechanism has near perfect accuracy in predicting failures of individual network nodes.