Machine learning algorithms in proactive decision making for handover management from 5G & beyond 5G

Abstract

In recent years, heterogeneous networks (HetNets) have drawn a lot of attention to connecting devices that will enable everything to become smart, efficient, and fast. These networks are made up of many cell types, including macro, micro, pico, and femto that are added to suit customer demand. HetNets requires sophisticated mobility management to handle a variety of inter-frequency technologies. Mobility management needs to be adequately addressed to prevent service degradation caused by high rates of unnecessary handover attempts (HOA), handover ping-pong (HOPP), handover failure (HOF), radio link failure (RLF) and HO delay involved, which necessitates the user to execute the handover (HO) process while moving from one place to another. A well-suited HO management technique is proposed to resolve the issues observed when the user moves. The purpose of this study is to ascertain how the handover control parameter (HCP) involves the functionality of the 5G network. The novel approach taken into consideration in this work for cell selection is proactive decision-making (PDM). The performance of the proposed technique is evaluated through a simulation consisting of 5G Hetnets. Comparisons of evaluations were made in terms of HOA, HOPP, HOF, RLF and HO delay.