AI-Enhanced ۵G-R Architecture for Adaptive Connectivity and Security in High-Mobility Rail Environments

Modern high-speed rail systems require ultra-reliable, low-latency, and secure wireless connectivity to ensure operational safety and high-quality passenger services at velocities exceeding ۳۰۰ km/h. Existing technologies such as Global System for Mobile communications-Railway (GSM-R) and Long Term Evolution-Railway (LTE-R) fail to maintain seamless handovers, adaptive resource management, and adequate protection against dynamic threats. This paper proposes an AI-enhanced and security-aware fifth generation for Railway (۵G-R) architecture that integrates recurrent neural network (RNN)-based mobility prediction, dynamic resource partitioning, Multi-access Edge Computing (MEC), and a Secure Connectivity Layer (SCL) for real-time optimization. The system continuously predicts train velocity and signal variations to proactively allocate network slices and pre-configure handovers across edge nodes. Federated learning synchronizes local MEC models with a global cloud controller, enabling continual adaptation to changing conditions. Simulation and field evaluations conducted along a ۱۷۴ km railway segment achieved throughput up to ۲۴۰ Mbps, latency below ۲۰ ms, and ۹۴% handover success, while introducing only ۳.۷% security overhead. Results confirm that Artificial intelligence (AI)-driven resource control and MEC-assisted execution significantly enhance the reliability, continuity, and resilience of ۵G-R communications under high mobility.

کلیدواژه ها:

AI-based mobility prediction ، MEC ، dynamic resource allocation ، network slicing ، secure ۵G-R connectivity