Deep-Unfolded Wideband ISAC Beamforming for DMA Under Frequency-Selective Lorentzian Model

2026-07-03

AI Summary

This work addresses the limitations of existing integrated sensing and communication (ISAC) designs based on dynamic metasurface antennas (DMAs), which typically rely on frequency-flat response models ill-suited for wideband scenarios, leading to phase and amplitude mismatches. To overcome this, the study introduces, for the first time, a frequency-selective Lorentzian model to accurately capture the dispersive characteristics of DMA elements and jointly optimizes the signal-to-interference-plus-noise ratio (SINR) for communication users and the signal-to-noise ratio (SNR) for radar targets. An alternating optimization framework based on projected gradient ascent is proposed, augmented with closed-form gradient expressions and embedded within a deep unfolding network featuring learnable hyperparameters. This approach preserves model interpretability while harnessing data-driven advantages. Compared to frequency-flat models, the proposed method improves system performance by approximately 20%, achieves up to a 20× faster convergence than conventional optimization algorithms, and yields a maximum 7% gain in the objective function value.

Abstract

Integrated sensing and communications (ISAC), empowered by dynamic metasurface antennas (DMAs), has emerged as a promising paradigm for next-generation wireless networks. However, existing DMA-based designs commonly rely on the frequency-flat response model for DMA elements, which is accurate only in narrowband scenarios and can cause significant phase and magnitude mismatches in wideband and ultra-wideband systems. This paper investigates a DMA-based wideband ISAC system under a frequency-selective Lorentzian response model, which accurately captures the frequency-dependent behavior of DMA elements. We aim to jointly balance the aggregate signal-to-interference-plus-noise ratio (SINR) of communication users and the signal-to-noise ratio (SNR) of the radar target. To this end, we first develop an alternating optimization framework based on projected gradient ascent (PGA), deriving closed-form gradients of the objective function with respect to the digital beamforming vectors, resonance frequencies, and damping factors under the frequency-selective Lorentzian DMA model. We then propose an unfolded PGA architecture that preserves the interpretability of model-based optimization while learning key hyperparameters to accelerate convergence. Simulation results show that the frequency-selective Lorentzian model improves performance by approximately 20\% over its frequency-flat approximation. Moreover, deep-unfolded PGA achieves up to 20-fold faster convergence and improves the objective value by up to 7\% compared with PGA-based benchmarks.

Problem

• Integrated Sensing and Communications (ISAC)
• Dynamic Metasurface Antennas (DMAs)
• Frequency-Selective Response
• Wideband Systems
• Lorentzian Model

Innovation

• Deep-Unfolded Optimization
• Frequency-Selective Lorentzian Model
• Dynamic Metasurface Antennas (DMAs)
• Wideband ISAC
• Projected Gradient Ascent