A Correlation and Clustering Algorithm for Time Series Monitoring of Network Flows

,Aneesh C Rao,Shobha G

doi:10.35940/ijeat.e9701.069520

Abstract

Over the last few decades the advent of machine learning has found applications in large number of domains. The ability to learn and identify patterns in data and make predictions on deviations from these patterns has found large scope in several fields. In computer networks, this problem can be applied to understanding the behavior of a network at any point of time and predicting when the behavior may change over time. This paper discusses an approach that uses a statistical machine learning algorithm for the time series behavior analysis of computer networks. The proposed algorithm makes use of unsupervised learning and statistical data analysis methods over the flows in the network. The novel aspect being explored is the analysis of the inter-dependencies between flows, in addition to monitoring anomalies of individual flows. The results presented, provide waveform representations of the correlation and clustering patterns of some sample flows based on packet sizes.

Highlights

Computer networks, in the real world, see the transfer of a large number of packets over multiple hops, at almost every second
An algorithm based on statistical machine learning is discussed for the time series monitoring of network flows in complex computer networks such as industrial networks, large data centres, etc
Machine learning will be used to identify patterns in the packet flows, which will be used to monitor their behaviour over time

Summary

Introduction

In the real world, see the transfer of a large number of packets over multiple hops, at almost every second. It is important to ensure quality-of-service (QoS) in such networks to ensure efficient and effective transfers of packets through flows. An algorithm based on statistical machine learning is discussed for the time series monitoring of network flows in complex computer networks such as industrial networks, large data centres, etc. The quality-of-service checks are generally incorporated at intermediate and end nodes in the network, between incoming and outgoing flows (ingress and egress). Machine learning will be used to identify patterns in the packet flows, which will be used to monitor their behaviour over time. The challenge is to ensure a real-time implementation, as flows in the network are dynamic in nature

Methods

Results

Conclusion