A Beamforming‐Aided DRX Mechanism for Traffic‐Aware Energy Optimization in 5G NR‐U

ABSTRACT The rise in demand for higher data rates and more subscribers is fueling mobile data traffic. The limited availability of channel access for data transmission requires user equipment (UE) to wait, which subsequently compromises its energy efficiency. To mitigate power consumption and improve quality of service (QoS) in UE, the discontinuous reception (DRX) mechanism over fifth generation (5G) new radio unlicensed (NR‐U) offers a viable solution. Our current work explores this by leveraging DRX within NR‐U for standalone (SA) and non‐standalone (NSA) deployment modes. We have modeled our approach by introducing a traffic‐based analyzer state within our system, which is mathematically investigated by subjecting the analyzed traffic to machine learning (ML)‐based beamforming techniques. Furthermore, Q‐learning‐based reinforcement learning (RL) is implemented in this model to determine optimal DRX strategies under dynamic and stochastic traffic conditions, effectively balancing energy efficiency, delay, and QoS requirements.