RLIS: Resource Limited Improved Security Beyond Fifth-Generation Networks Using Deep Learning Algorithms

Abstract

This study explores the feasibility of allocating finite resources beyond fifth generation networks for extended reality applications through the implementation of enhanced security measures via offloading analysis (RLIS). The quantification of resources is facilitated through the utilization of parameters, namely energy, capacity, and power, which are equipped with proximity constraints. These constraints are then integrated with activation functions in both multilayer perceptron and long short term memory models. Furthermore, the system model has been developed using vision-based computing, which involves managing data queues in terms of waiting periods to minimize congestion for data transmission with limited resources. The major significance of the proposed method is to utilize allocated spectrums for future generation networks by allocating necessary resources and therefore high usage of resources by all users can be avoided. In addition the advantage of the proposed method is secure the networks that operate beyond 5G where more number of users will try to share the allocated resources that needs to be provided with high security conditions.

Keywords

• Deep learning algorithm
• extended reality applications
• fifth generation networks
• limited resource
• visual systems