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

2026-03-02

AI Summary

This work addresses the joint optimization challenge in multi-band multi-user MISO downlink systems assisted by a stacked intelligent metasurface (SIM), where a single phase configuration must serve all subcarriers despite dynamic user scheduling and power allocation. To tackle this, the authors propose an alternating optimization framework that decouples the problem into precoder updates and SIM phase design. For the latter, they introduce, for the first time, a deep unfolding approach tailored to SIM-aided multi-band systems, developing a Multi-Band Deep Unfolding Network (MBDU-Net). By unfolding the projected gradient method, MBDU-Net enables trainable, lightweight beamforming with band-aware scaling and learnable step sizes per unfolding stage, ensuring physical consistency while maintaining interpretability and rapid convergence. Experiments demonstrate that MBDU-Net consistently converges on unseen channels and significantly improves system sum-rate.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Multiagent Systems: Multiagent Learning
• Machine Learning: Multi-instance/Multi-view Learning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

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.

Problem

• SIM
• multi-band
• MU-MISO
• downlink
• phase configuration

Innovation

• Deep Unfolding
• Stacked Intelligent Metasurfaces
• Multi-band MU-MISO
• Projected Gradient
• Carrier Aggregation