Joint Transmit and Pinching Beamforming for PASS: Optimization-Based or Learning-Based?

2025-02-12

AI Summary

This paper addresses the sum-rate maximization problem in downlink multi-user multiple-input single-output (MU-MISO) systems. We propose a joint beamforming and reconfigurable pincer antenna (PA) placement optimization framework based on the Pincer Antenna System (PASS), dynamically tuning path loss and phase to enhance desired signals and suppress interference. Our contributions include: (i) the first physical implementation of reconfigurable PAs; (ii) a novel KKT-guided dual learning (KDL) paradigm that embeds Karush–Kuhn–Tucker optimality conditions into data-driven modeling; and (iii) a KDL-Transformer architecture capturing high-dimensional couplings among PAs, users, and channel state information (CSI). Furthermore, we develop the MM-PDD optimization algorithm—integrating Lipschitz surrogate functions with penalized dual decomposition—to ensure superior convergence and robustness. Experiments demonstrate that PASS achieves higher sum-rates than conventional massive MIMO using only a few PAs; KDL-Transformer outperforms MM-PDD by over 30% in rate performance while maintaining millisecond-level inference latency.

Technology Category

• Search and Optimization: Mixed Discrete/Continuous Search
• Machine Learning: Optimization
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search

Abstract

A novel pinching antenna system (PASS)-enabled downlink multi-user multiple-input single-output (MISO) framework is proposed. PASS consists of multiple waveguides spanning over thousands of wavelength, which equip numerous low-cost dielectric particles, named pinching antennas (PAs), to radiate signals into free space. The positions of PAs can be reconfigured to change both the large-scale path losses and phases of signals, thus facilitating the novel pinching beamforming design. A sum rate maximization problem is formulated, which jointly optimizes the transmit and pinching beamforming to adaptively achieve constructive signal enhancement and destructive interference mitigation. To solve this highly coupled and nonconvex problem, both optimization-based and learning-based methods are proposed. 1) For the optimization-based method, a majorization-minimization and penalty dual decomposition (MM-PDD) algorithm is developed, which handles the nonconvex complex exponential component using a Lipschitz surrogate function and then invokes PDD for problem decoupling. 2) For the learning-based method, a novel Karush-Kuhn-Tucker (KKT)-guided dual learning (KDL) approach is proposed, which enables KKT solutions to be reconstructed in a data-driven manner by learning dual variables. Following this idea, a KDL-Tranformer algorithm is developed, which captures both inter-PA/inter-user dependencies and channel-state-information (CSI)-beamforming dependencies by attention mechanisms. Simulation results demonstrate that: i) The proposed PASS framework significantly outperforms conventional massive multiple input multiple output (MIMO) system even with a few PAs. ii) The proposed KDL-Transformer can improve over 30% system performance than MM-PDD algorithm, while achieving a millisecond-level response on modern GPUs.

Problem

• Optimizing joint transmit and pinching beamforming for PASS.
• Maximizing sum rate via constructive and destructive signal manipulation.
• Comparing optimization-based and learning-based methods for beamforming.

Innovation

• PASS-enabled downlink MISO framework
• MM-PDD algorithm for optimization
• KDL-Transformer for learning-based solution