Optimizing Routing Strategy in Software Defined Networking

Traditional Network Architecture (TNA) is becoming inadequate due to its rigid, hardware-centric configurations, especially in environments where network conditions are highly variable. This has led to increased latency, congestion, and packet loss rates. This project aims to develop an optimized routing strategy for Software Defined Networking (SDN) that leverages machine learning techniques to enhance network traffic management's adaptability and efficiency. The project employs a combination of Dueling Deep Q-Networks (Dueling DQN) and real-time traffic state predictions to create a dynamic routing strategy. The methodology includes extensive simulation using SDN environments to evaluate the performance improvements over traditional routing methods. Preliminary results indicate that the proposed SDN-based routing strategy not only responds more efficiently to dynamic network conditions but also significantly optimizes performance metrics such as bandwidth utilization, latency reduction, and packet loss. The integration of Dueling DQN and real-time traffic predictions within SDN frameworks could potentially redefine network performance standards, offering a more adaptive, efficient, and robust network management system. This study contributes to the field by providing a scalable solution to the complexities of modern network environments, supporting the ongoing evolution of network infrastructure management.

Name dc:type.qualificationname

msc

Level dc:type.qualificationlevel

masters

Grantor dc:publisher.institution

University of Wales Trinity Saint David

Year dc:date.issued

2024

Author dc:creator

• Tu, Lingzhuo

• TK Peirianneg drydanol. Peirianneg Niwclear Electronig

Dc Identifier Grantnumber

UWTSD

OAI identifier oai:identifier

oai:repository.uwtsd.ac.uk:3310