PUAL-DBSCP: Personalized Ubiquitous Adaptive Learning for Density-Based Splitting Controller Placement in software-defined networks

Abstract

In the field of personalized and adaptive education, ubiquitous adaptive learning (PUAL), which aims to give students customized learning experiences to improve their educational achievements, has grown in importance. The difficulties of implementing PUAL in the setting of Software Defined Networks (SDN) are addressed in this study. Using a capacity-based switch-splitting technique, DBSCP separates the SDN into several sub-networks. One controller is thoughtfully positioned within each of the sub-networks, which are each thought of as separate domains. This study examines the creation and use of DBSCP, emphasizing how it could revolutionize how educational content is distributed and personalized in software-defined networks. This research introduces a novel method for individualized ubiquitous adaptive learning called Density-Based Splitting Controller Placement (PAUL-DBSCP). The size of each sub-network in the proposed technique can be determined by the controller’s bandwidth and density-based splitting results based on identifying the ideal number of controllers. On a collection of 262 network topologies that are available to the public, the performance is accessed for the proposed technique. The performance evaluation of $ method, CNPA and SAPKM state-of-the-art approaches has been analyzed with the proposed approach and it has been observed that the results achieve 4.2% worst-case delay with regard to the number of controllers.