SIGMAML: SNR-Guided 5G Mobility Management using Machine Learning Algorithms

In the realm of 5G technology, seamless mobility relies heavily on efficient mobility management, particularly handovers (HOs). Our study investigates the parameters of A3 event and their impact on the mean edge signal-to-noise ratio (SNR), a vital but often overlooked metric. Using Deep Neural Networks (DNNs), we establish a detailed connection between A3 parameters and key performance indicators (KPIs). Our analysis highlights the dominance of A3-offset over A3-time to trigger (TTT) in influencing mean edge SNR. While DNNs offer complexity, decision tree provide a balanced trade-off between RMSE and complexity, aiding in optimizing mobility management for enhanced 5G network performance.