Machine Learning Based on Handover Decision in 5G/6G Cellular Networks: Survey

Sejma Hasak, Bilal Saoud, Leila Rzayeva, Дина Сатыбалдина, Сакен Тлеубердин, Gulsipat Abisheva

2025

Closed access Metadata (CSL-JSON)
DOI 10.1109/snpd65828.2025.11252998
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

During the last century the term mobile communication developed at a high speed. From 1G with availability for only phone calls at the strict routes, to 6G with variety of applications available at any certain position. The goal of the 5G and 6G network is to provide services worldwide for the users. 5G and 6G coming with new challenges such as Handover Decision. Handover Decision is one of the most important aspects of cellular communications. With new technologies, Handover Decision is starting to be more challenging in terms of Handover Management. Handover Management implies seamless handover of users within a certain path. Seamless handover gives the connection of user to base station through radio link. For establishing seamless handover over 5G and 6G Network can be very challenging. The reason is new technologies provide small coverage of the base stations which immediately implies frequent handovers. Handover parameters that decide a lot in handover management are time-to-trigger, handover margin, handover control parameters. The need for 5G and 6G Network arose from the increasing number of devices. With new technologies bandwidth increases, which gives the opportunity for connectivity of numerous numbers of devices. There are also different environments such as mmWave Network, Heterogeneous Network, Ultra Dense Network, etc. This paper will give the overall summary of machine learning based on handover decision in 5G and 6G cellular networks. The focus will be on related studies from previous research, discussion on the various ML algorithms.