TE-Based Machine Learning Techniques for Link Fault Localization in Complex Networks

TL;DR: The proposed machine learning model adopts a passive mechanism to learn the network traffic behavior from propagation delay, number of flows and average packet loss at every node in the network under normal working conditions and failure scenarios.

Abstract: Communication networks such as wireless sensor networks, Internet of Things and vehicular ad-hoc networks are becoming more complex and increasing in size. This leads to high overhead (network and computation) and difficulty in determining the accurate network topology, which is an important information for traffic engineering and network management. Localization of link failures in such networks is a challenging problem and requires a novel approach to achieve the goal without any prior information about the network topology. In this paper, we present a traffic engineering (TE)-based machine learning approach to detect and localize link failures. Instead of using topology information and actively injecting additional packets to localize a failed link, the proposed machine learning model adopts a passive mechanism to learn the network traffic behavior from propagation delay, number of flows and average packet loss at every node in the network under normal working conditions and failure scenarios. We train the learning model with machine learning algorithms such as naive Bayes, logistic regression, support vector machine, multi-layer perceptron, decision tree and random forest. We implement the proposed approach and carry out extensive experiments using the Mininet platform. The performance study shows that our proposed approach localizes link failures with at least 90% accuracy using random forest algorithm while requiring less time-to-localization of a link failure compared to other existing works.