Mobility Performance Analysis of RACH Optimization Based on Decision Tree Supervised Learning for Conditional Handover in 5G Beamformed Networks

TL;DR

This paper analyzes mobility performance in 5G FR2 beamformed networks, proposing a decision tree supervised learning method to optimize conditional handover and reduce mobility failures.

Contribution

It introduces a decision tree-based supervised learning approach to minimize handover failures and enhances resource efficiency in 5G beamformed networks with conditional handover.

Findings

Optimal random access operation point achieved with the proposed algorithm

Conditional handover reduces total mobility failures despite more handover failures

Tradeoff identified between contention-free access and handover failures

Abstract

In 5G cellular networks, frequency range 2 (FR2) introduces higher frequencies that cause rapid signal degradation and challenge user mobility. In recent studies, a conditional handover procedure has been adopted as an enhancement to baseline handover to enhance user mobility robustness. In this article, the mobility performance of conditional handover is analyzed for a 5G mm-wave network in FR2 that employs beamforming. In addition, a resource-efficient random access procedure is proposed that increases the probability of contention-free random access during a handover. Moreover, a simple yet effective decision tree-based supervised learning method is proposed to minimize the handover failures that are caused by the beam preparation phase of the random access procedure. Results have shown that a tradeoff exists between contention-free random access and handover failures. It is also seen that the optimum operation point of random access is achievable with the proposed learning algorithm for conditional handover. Moreover, a mobility performance comparison of conditional handover with baseline handover is also carried out. Results have shown that while baseline handover causes fewer handover failures than conditional handover, the total number of mobility failures in the latter is less due to the decoupling of the handover preparation and execution phases.