An Evaluation and Examination of Software-Defined Networks and Its Routing Enhancements

Main Article Content

Kalaivani S
Dr. A. Sumathi

Abstract

Software-Defined Networking (SDN) has enabled the creation of sophisticated, adaptable, and customizable network management solutions. It enables the centralized management and flexible adjustment of routing by utilizing its decoupled architecture. Therefore, efficient routing is essential in SDN to improve network performance, scalability, and efficiency. While conventional models primarily emphasize heuristic and metaheuristic methods, recent progress has incorporated Machine Learning (ML) techniques into some of these models providing adaptive and intelligent solutions to routing challenges. These ML-enhanced models specifically target problems related to delay, traffic congestion and efficient use of resources. This survey provides a comprehensive analysis of different routing strategies in SDN with a specific emphasis on the subset of approaches that incorporate ML techniques. We evaluate the influence of ML on network performance, emphasizing their benefits and constraints, and examine the difficulties and future prospects in using ML for SDN routing. The survey concludes with suggestions for enhancing routing efficiency and network performance by employing advanced techniques selectively

Downloads

Download data is not yet available.

Article Details

Section
Articles