Optimized network resource management using SDN architecture by hybrid fuzzy neural-grey wolf algorithms in cloud environments

Abstract

This thesis looks at how Dynamic Resource Management in the Cloud using Software Defined Network Architecture can be achieved. The complexity and demand for cloud services are increasing, and traditional network sources’ management is confronting problems with efficiency and adaptability. To address these difficulties, we present an original solution in this research by implementing both hybrid Fuzzy Neural Network and Grey Wolf Optimizer (GWO) algorithms in the SDN framework. The hybrid algorithm enhances load-balancing and resource distribution in the clouds based on the network’s contextual changes. We can thus compare the results achieved by the proposed method with the conventional techniques to show the potential benefits in terms of greater satisfaction, less congestion on the network, higher resource efficiency, and minimizing error resolution time. This research fits into the line of work in SDN by addressing the challenge of resource management and load balancing to real-time network enhancements and optimization that concerns issues such as cloud computing, IoT, and 5G.

Date	9 Jan 2025
Original language	American English
Awarding Institution	École de technologie supérieure
Supervisor	Michel Kadoch (Supervisor)