A proposed mobility and resource prediction method for seamless handover and service continuity in 5G small cell networks

Abstract

Developments in 5G New Radio (NR) aim to provide the best possible user experience, but barred and resource-depleted cells in dense small cell networks can cause service interruptions and increase handover latency. To address these challenges, we propose a proactive mitigation framework that applies the unified Autoregressive Recurrent Neural Network (AR-RNN). This framework simultaneously predicts a user’s future cell trajectory and their resource requirements by learning from historical data. By integrating these predictive forecasts with standard network-monitoring alerts (e.g., from an Intrusion Detection System (IDS), a Network Management System (NMS), or Operations, Administration, and Maintenance (OAM) systems), the system preemptively reroutes users to avoid flagged or unavailable cells. Applying the algorithm to both Homogeneous and Heterogeneous networks, our simulations demonstrate that this proactive approach yields substantial and quantifiable improvements in network performance across both topologies. The AR-RNN model achieves a next-cell prediction accuracy of up to 95.8%, establishing high dependability. This accuracy directly translates to enhanced Quality of Service (QoS) by reducing handover latency even to as low as nearly 5 ms. Furthermore, the framework significantly improves network reliability, reducing the network outage probability by up to 50% compared to standard reactive handover procedures. These results demonstrate a concrete and effective method for creating a more seamless and efficient telecommunications experience in dense 5G environments.