Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Deep Unfolding for SIM-Assisted Multiband MU-MISO Downlink Systems

Muhammad Ibrahim, Amine Mezghani, Ekram Hossain

Abstract

To improve the efficiency of scarce radio-frequency (RF) resources in next-generation wireless systems, an intelligent transceiver architecture based on stacked intelligent metasurfaces (SIM) has recently emerged, where multiple programmable metasurface layers are cascaded and each layer comprises passive meta-atoms that perform beamforming directly in the wave domain. In parallel, inter-band carrier aggregation enables multi-band transmission with high spectral efficiency. Their integration in multi-band multiuser downlink transmission is challenging because a single SIM phase configuration must remain effective across all subcarriers, while user scheduling and power allocation vary across scheduling intervals. To address these challenges, we propose an alternating-optimization framework that decomposes the joint design into a power-constrained precoder update and a SIM phase update. For the SIM phase subproblem, we develop a physically consistent multi-band deep-unfolding network (MBDU-Net) that unrolls projected-gradient phase updates into a compact trainable architecture. Each stage computes an analytic gradient from the cascaded SIM channel model and learns lightweight parameters, including per-stage step sizes and band-aware scaling, enabling fast convergence. Numerical results for multi-band multiuser downlink scenarios demonstrate reliable convergence and consistent sum-rate gains on unseen channel realizations.

Deep Unfolding for SIM-Assisted Multiband MU-MISO Downlink Systems

Abstract

To improve the efficiency of scarce radio-frequency (RF) resources in next-generation wireless systems, an intelligent transceiver architecture based on stacked intelligent metasurfaces (SIM) has recently emerged, where multiple programmable metasurface layers are cascaded and each layer comprises passive meta-atoms that perform beamforming directly in the wave domain. In parallel, inter-band carrier aggregation enables multi-band transmission with high spectral efficiency. Their integration in multi-band multiuser downlink transmission is challenging because a single SIM phase configuration must remain effective across all subcarriers, while user scheduling and power allocation vary across scheduling intervals. To address these challenges, we propose an alternating-optimization framework that decomposes the joint design into a power-constrained precoder update and a SIM phase update. For the SIM phase subproblem, we develop a physically consistent multi-band deep-unfolding network (MBDU-Net) that unrolls projected-gradient phase updates into a compact trainable architecture. Each stage computes an analytic gradient from the cascaded SIM channel model and learns lightweight parameters, including per-stage step sizes and band-aware scaling, enabling fast convergence. Numerical results for multi-band multiuser downlink scenarios demonstrate reliable convergence and consistent sum-rate gains on unseen channel realizations.
Paper Structure (11 sections, 12 equations, 3 figures, 1 algorithm)

This paper contains 11 sections, 12 equations, 3 figures, 1 algorithm.

Table of Contents

  1. Introduction
  2. System Model and Assumptions
  3. Physically-Consistent SIM Model
  4. Signal Transmission Model
  5. Formulation of Optimization Problem and Solution
  6. Problem Formulation
  7. Proposed Solution of the Optimization Problem
  8. Power Allocation and Beamforming Optimization
  9. Multi-band Deep Unfolding for Phase Shift Optimization
  10. Simulation Results and Discussion
  11. Conclusion

Figures (3)

  • Figure 1: SIM-aided multi-user MISO system
  • Figure 2: Sum rate versus the number of iterations: (a) Varying the number of inner iterations for $I_{\max}=1$, (b) Varying the number of outer iterations for $T=6$.
  • Figure 3: Sum-rate versus the number of subcarriers per band.