INTELLIGENT VERTICAL HANDOVER DECISION FRAMEWORK FOR 5G NETWORKS VIA DATA MINING

Abstract

Seamless vertical handover (VHO) is essential for ensuring continuous connectivity and high Quality of Service (QoS) in 5G heterogeneous networks. However, variations in network behaviors and protocols complicate VHO decision-making, often resulting in higher latency and service disruptions. This paper proposes a data mining-based VHO decision framework for 5G networks that leverages historical handover data to optimize mobility management. Using multivariate regression and Analysis of Variance (ANOVA), the framework identifies critical parameters such as signal strength, bandwidth, jitter, latency, packet loss, and coverage. Simulations conducted in the NetNeuman environment demonstrate that the proposed approach outperforms baseline algorithms by reducing latency, improving handover success rates, and enhancing overall network performance. Real-time decision-making, supported by historical insights, enables the framework to better meet user demands, thereby improving both reliability and user experience. The study also highlights the potential of integrating advanced machine learning methods for adaptive and predictive mobility management in future 6G networks. This work contributes to the development of intelligent, data-driven handover mechanisms vital for achieving ultra-reliable low-latency communication and seamless mobility in next-generation wireless systems.