The Network Slicing and Performance Analysis of 6G Networks using Machine Learning

Abstract

6G technology is designed to provide users with faster and more reliable data  transfer as compared to the current 5G technology. 6G is rapidly evolving and provides a large bandwidth, even in underserved areas. This technology is extremely anticipated and is currently booming for its ability to deliver massive network capacity, low latency, and a highly improved user experience. Its scope is immense, and it’s designed to connect everyone and everything in the world. It includes new deployment models and services with extended user capacity. This study proposes a network slicing simulator that uses hardcoded base station coordinates to randomly distribute client locations to help analyse the performance of a particular base station architecture. When a client wants to locate the closest base station, it queries the simulator, which stores base station coordinates in a K-Dimensional tree. Throughout the simulation, the user follows a pattern that continues until the time limit is achieved. It gauges multiple statistics such as client connection ratio, client count per second, Client count per slice, latency, and the new location of the client. The K-D tree handover algorithm proposed here allows the user to connect to the nearest base stations after fulfilling the required criteria. This algorithm ensures the quality requirements and decides among the base stations the user connects to.