Optimized Dual-Attention Convolutional Neural Networks for Hybrid Beamforming and High-Precision Channel Estimation in 5G Massive MIMO Wireless Communications Systems

Abstract

Beamforming and channel estimation are fundamental components of 5G massive MIMO (multiple-input–multiple-output) systems, particularly in the millimeter-wave (mmWave) spectrum, where high-frequency transmissions are susceptible to path loss and signal degradation. The growing demand for ultrareliable low-latency communication (URLLC) and high-quality services necessitates advanced, adaptive techniques to manage the highly dynamic nature of mmWave channels. This study proposes a novel framework that integrates dual-attention convolutional neural networks (DSCN-PAN) with reformed poplar optimization (RePO) to enhance beamforming accuracy and channel estimation efficiency in 5G massive MIMO systems. Compared to conventional methods, the proposed model demonstrates significant performance gains, including over 90% improvement in spectral efficiency, 99.41% beam alignment precision, a 99.5% enhancement in Channel State Information (CSI) estimation, and a 99.2% reduction in bit error rate (BER). The DSCN-PAN-RePO architecture effectively supports dynamic and complex communication environments, offering a scalable and energy-efficient solution for next-generation wireless networks.