DNN-Based Precoding in RIS-Aided mmWave MIMO Systems With Practical Phase Shift

TL;DR

The paper tackles RIS-aided mmWave MIMO precoding under a practical phase-dependent amplitude model, formulating a non-convex joint optimization of the transmit precoder and RIS phases. It reduces complexity by designing a Kronecker-structured DFT codebook and learning a supervised DNN mapping CSI to near-optimal codewords, incorporating amplitude effects. Results show the DNN achieves about 98–100% of the exhaustive-search performance with two orders of magnitude lower computation time, and remains robust to user-RIS distance variations and practical RIS imperfections. This work demonstrates a viable, low-complexity pathway for real-time RIS control in mmWave systems with realistic RIS behavior.

Abstract

In this paper, the precoding design is investigated for maximizing the throughput of millimeter wave (mmWave) multiple-input multiple-output (MIMO) systems with obstructed direct communication paths. In particular, a reconfigurable intelligent surface (RIS) is employed to enhance MIMO transmissions, considering mmWave characteristics related to line-of-sight (LoS) and multipath effects. The traditional exhaustive search (ES) for optimal codewords in the continuous phase shift is computationally intensive and time-consuming. To reduce computational complexity, permuted discrete Fourier transform (DFT) vectors are used for finding codebook design, incorporating amplitude responses for practical or ideal RIS systems. However, even if the discrete phase shift is adopted in the ES, it results in significant computation and is time-consuming. Instead, the trained deep neural network (DNN) is developed to facilitate faster codeword selection. Simulation results show that the DNN maintains sub-optimal spectral efficiency even as the distance between the end-user and the RIS has variations in the testing phase. These results highlight the potential of DNN in advancing RIS-aided systems.

Figures (4)

• Figure 1: The RIS-aided mmWave MIMO system.
• Figure 2: DNN model training flow chart.
• Figure 3: The spectral efficiency in the different RIS element numbers under the mmWave channel assumption ($K_t = K_r = 10$, $N_{t} = 10$, $N_{r} = 2$, and $L = 2$).
• Figure 4: The spectral efficiency at different distances between the receiver and RIS ($K_t = K_r = 10$, $N_{t} = 10$, $N_{r} = 2$, $N = 45$ and $L = 2$).