SDN-Based Routing Framework for Elephant and Mice Flows Using Unsupervised Machine Learning

Al-Saadi, Muna and Khan, Asiya and Kelefouras, Vasilios and Walker, David J. and Al-Saadi, Bushra (2023) SDN-Based Routing Framework for Elephant and Mice Flows Using Unsupervised Machine Learning. Network, 3 (1). pp. 218-238. ISSN 2673-8732

[thumbnail of network-03-00011.pdf] Text
network-03-00011.pdf - Published Version

Download (6MB)

Abstract

Software-defined networks (SDNs) have the capabilities of controlling the efficient movement of data flows through a network to fulfill sufficient flow management and effective usage of network resources. Currently, most data center networks (DCNs) suffer from the exploitation of network resources by large packets (elephant flow) that enter the network at any time, which affects a particular flow (mice flow). Therefore, it is crucial to find a solution for identifying and finding an appropriate routing path in order to improve the network management system. This work proposes a SDN application to find the best path based on the type of flow using network performance metrics. These metrics are used to characterize and identify flows as elephant and mice by utilizing unsupervised machine learning (ML) and the thresholding method. A developed routing algorithm was proposed to select the path based on the type of flow. A validation test was performed by testing the proposed framework using different topologies of the DCN and comparing the performance of a SDN-Ryu controller with that of the proposed framework based on three factors: throughput, bandwidth, and data transfer rate. The results show that 70% of the time, the proposed framework has higher performance for different types of flows.

Item Type: Article
Subjects: STM Repository > Computer Science
Depositing User: Managing Editor
Date Deposited: 13 Jun 2023 04:27
Last Modified: 25 Jan 2024 04:08
URI: http://classical.goforpromo.com/id/eprint/3475

Actions (login required)

View Item
View Item