A Data Augmented Bayesian Network for Node Failure Prediction in Optical Networks

TL;DR

This paper introduces a Bayesian network model that predicts failures in optical network nodes using minimal log data and data augmentation, achieving high accuracy without extensive real-time data collection.

Contribution

It presents a novel data augmentation approach with Bayesian networks for failure prediction in optical networks, addressing data scarcity issues.

Findings

High prediction accuracy achieved

Effective use of basic log data and data augmentation

Applicable to deployed network devices

Abstract

Failures in optical network backbone can cause significant interruption in internet data traffic. Hence, it is very important to reduce such network outages. Prediction of such failures would be a step forward to avoid such disruption of internet services for users as well as operators. Several research proposals are available in the literature which are applications of data science and machine learning techniques. Most of the techniques rely on significant amount of real time data collection. Network devices are assumed to be equipped to collect data and these are then analysed by different algorithms to predict failures. Every network element which is already deployed in the field may not have these data gathering or analysis techniques designed into them initially. However, such mechanisms become necessary later when they are already deployed in the field. This paper proposes a Bayesian network based failure prediction of network nodes, e.g., routers etc., using very basic information from the log files of the devices and applying power law based data augmentation to complement for scarce real time information. Numerical results show that network node failure prediction can be performed with high accuracy using the proposed mechanism.