Content area

Abstract

The Quality of Service (QoS) paradigm plays a vital role within the context of Software-Defined Networking (SDN), as it facilitates the efficient allocation of network resources to satisfy the diverse performance demands of various applications and services. Concurrently, it is imperative to address security concerns within the SDN framework, given that the distinctive architecture of SDN introduces novel vulnerabilities and associated risks, including control plane vulnerabilities, data plane vulnerabilities, and threats such as Distributed Denial-of-Service attacks. Nevertheless, the trade-off between security and QoS in SDN is daunting because the traditional QoS management methods, which rely primarily on static configuration and heuristics, cannot manage to optimize the allocation of resources to SDN traffic patterns with dynamic security controls, influencing the overall user experience (Bagaa et al., 2022). The incapacity to properly distribute resources for the implementation of security mechanisms under different network situations is a serious risk, which can leave the network vulnerable to intrusion and security breach.

This paper introduces ResSDN, a framework that incorporates Machine Learning into SDN network traffic routing and management to enhance both QoS and security in the scenario of complicated SDN. Through the joint use of novel Machine Learning algorithms, ResSDN preemptively blocks the malicious traffic and offers instructions on routing decisions on the benign traffic, thus protecting against the cyber threats while ensuring a smooth user experience.

Details

1010268
Title
ResSDN: A Machine Learning-Based Tool for Joint QoS-Security Optimization in Software-Defined Networking
Number of pages
106
Publication year
2025
Degree date
2025
School code
0075
Source
DAI-B 86/10(E), Dissertation Abstracts International
ISBN
9798310300941
Committee member
Etemadi, Amir; Blackford, Joseph
University/institution
The George Washington University
Department
Cybersecurity Analytics
University location
United States -- District of Columbia
Degree
D.Engr.
Source type
Dissertation or Thesis
Language
English
Document type
Dissertation/Thesis
Dissertation/thesis number
31933906
ProQuest document ID
3186838319
Document URL
https://www.proquest.com/dissertations-theses/ressdn-machine-learning-based-tool-joint-qos/docview/3186838319/se-2?accountid=208611
Copyright
Database copyright ProQuest LLC; ProQuest does not claim copyright in the individual underlying works.
Database
ProQuest One Academic