Hybrid Precoding Optimization Based on Quantum Neural Network for Multi-User MISO Systems

Hybrid precoding emerges as a promising solution for minimizing hardware costs and power consumption while maintaining near-optimal performance for multi-user (MU) multiple-input-single-output (MISO) communication. It leverages an extensive array of phase shifters to execute high-dimensional analog precoding, addressing significant path loss, alongside a limited number of radio frequency chains for low-dimensional digital precoding. This paper introduces a novel approach to hybrid precoding optimization employing Quantum Neural Networks (QNN) and an unsupervised learning technique, with the objective to maximize spectral efficiency and reducing the complexity. The QNN is utilized to obtain optimal analog precoding matrix, which is then utilized to calculate digital precoding using zero-forcing criteria. Simulation results demonstrate the spectral efficiency of QNN-based hybrid precoding gain improvement compared to other hybrid precoding solutions with low complexity.