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

arXiv: https://arxiv.org/abs/2309.09840 · HTML: https://mlsanity.com/paper/2309.09840/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Sep 2023.

## Built on by (most cited first, 2 of 2)

- [CHOMET: Conditional Handovers via Meta-Learning](https://mlsanity.com/paper/2507.07581/) (2025)
- [Meta-Learning-Based Handover Management in NextG O-RAN](https://mlsanity.com/paper/2512.22022/) (2025)

## Abstract (arXiv)

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.