Machine Learning Techniques to Analyze Network Slicing for 5G Network Management

EasyChair Preprint no. 10697

Abstract

The upcoming fifth-generation (5G) wireless networks are expected to revolutionize the existing fourth-generation network in order to accommodate the massive number of devices that will eventually be linked over the web. 5G networks are going to bring about brand new and enhanced abilities to facilitate high-speed data transmission, improved connectivity, and increased network capacity.  For a network to effectively satisfy demanding application needs, it is imperative for its infrastructure to possess a great degree of flexibility and adaptability. A network's architecture can be enriched with dynamic and flexible attributes through the implementation of network slicing. An existing 5G network can be improved by implementing a network slicing architecture, which will enable better network dynamics and flexibility to cater to contemporary network applications. The expansion of devices, applications, and services has led to an increase in consumer expectations and requirements for network service providers to deliver high-quality service.  An outstanding investigation is currently being carried out by network architecture and top-notch research professionals as more and more devices, services and applications are being increased. To be able to make the preceding paradigm more adaptable, user-centered, and service-centric, the researchers claim that mobility management is now being studied.  Network slicing may be able to meet the demanding application requirements for the network layout now in place if done so efficiently. The traffic and mobility management algorithms developed in the current work employ sophisticated fuzzy logic to provide maximum flexibility and high performance. The development of NFV (Network Function Virtualization) and SDN (Software-Defined Networking) technologies is crucial. An architectural framework for 5G networks called "network slicing" is designed to support a range of different networks.

Keyphrases: 5G network slicing, Fuzzy Logic, Network Function Virtualization, Software Defined Networking

@Booklet{EasyChair:10697,
  author = {Swarna Kamalam Vaddi and Venkata Vara Prasad Padyala},
  title = {Machine Learning Techniques to Analyze Network Slicing for 5G Network Management},
  howpublished = {EasyChair Preprint no. 10697},

  year = {EasyChair, 2023}}