An Artificial Intelligence-based Handover Triggering and Management Mechanism for 5G Ultra-dense Networks to Improve Handover Authentication

he emergence of5G ultra-dense networks hasgained considerable attention, as solutions of this kind enablerapid and intelligent device connectivity, thus ushering in a newera of high-speed communications. Nevertheless, the processof managing mobility across varying inter-frequency strategiesincreases interference and complexity. The development of a re-liable handover algorithm is crucial for high-quality service,especially in ultra-dense networks with small cells. However, fre-quent handovers, ping-pong effects, and load-balancing issuesarise due to the random and dense deployment of small cells.Additionally, ensuring secure and smooth handover authentica-tion is critical, due to an increased risk of frequent transitionsof users across different networks. In such a context, this re-search focuses on triggering handovers and managing5G mobilenetworks, all while protecting sensitive data. We introduce an ar-tificial intelligence-based approach aimed at improving handoverinitiation and management processes, leveraging Boruta ran-dom forest optimization (BRFO) to fine-tune handover marginsand identify optimal trigger points for handovers. In addition,an impulsive graph neural network (IGNN) is utilized as a deci-sion framework to predict and minimize unnecessary handovers,thus improving stability in small cell environments. Simulationresults demonstrate that the proposed methodology significant-ly enhances handover management, strengthens authentication,and effectively mitigates a variety of attacks in5G ultra-densenetworks