Highly Secure and Accurate Deep Slicing in 5G Wireless Networks for Efficient Resource Utilization

Abstract

Both the current cellular network and the planned 5G mobile network need to meet high dependability standards, very low latency requirements, larger capacity, better security and fast user communication. In order to support multiple independent tenants on the same physical infrastructure, mobile carriers are working towards end-to-end network resource allocation in 5G networks. Future communication networks will require data-driven decision making due to the increase in traffic and the accelerated performance of 5G networks. With the use of in-network deep learning and prediction, a "deep slice" model was built in this study to control network load efficiency and network availability. Even in the event of a network outage, the suggested model is capable of making wise selections and choosing the best network slice.