Artificial-Intelligence-Enhanced Beamforming for Power-Efficient User Targeting in 5G Networks using Reinforcement Learning

Abstract

In the quest for optimizing 5G networks, this study introduces an innovative Artificial Intelligence (A.I.)-based beamforming technique focused on power efficiency and signal integrity. By combining reinforcement learning (RL) and adaptive signal processing, the system achieves optimal beamforming towards the user with the lowest power signature. The system starts at the base station (BS) which conducts an omnidirectional scan to identify and direct beams towards the user equipment (UE) exhibiting the lowest power signature, optimizing the network's performance and efficiency. Extensive simulations conducted using a Uniform Linear Array (ULA) at 28 GHz with QAM modulation to authenticate the process, A.I. algorithm dynamically adjusted the beamforming weights, which were then applied to synthetic user signals to simulate real-world conditions. The results, validated through Bit Error Rate (BER), Throughput, Angle of Arrival (AOA), Direction of Arrival (DOA), and Array Response metrics demonstrated that the A.I.-driven approach not only reduces power consumption but also maintains signal fidelity with high precision. A.I.'s decision-making process was exactly analyzed showing its capability to fine-tune beam direction in the presence of noise and interference. The study concluded that A.I.-based steering towards the least power-intensive user is not only viable but also enhances overall network efficiency and reliability.