Designing hybrid beamforming transceivers in millimeter wave (mmWave) MIMO-OFDM systems with satisfactory performance and acceptable complexity is a challenging problem. The well-known weighted minimum mean square error manifold optimization (WMMSE-MO) algorithm offers desired performance but has high computational complexity. In this paper, we propose to apply the deep unfolding technique to the WMMSE-MO algorithm. The proposed deep unfolding model yields faster convergence to better solutions as compared to the original algorithm. Simulation results demonstrate remarkable spectral efficiency performance with reduced computational time complexity for the proposed scheme, under different hardware (RF chains) and algorithmic (inner/outer iterations) settings for a massive MIMO-OFDM system.
Hybrid Beamforming in mmWave MIMO-OFDM Systems via Deep Unfolding
2022-06-01
996137 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch