Two-Timescale Joint Transmit and Pinching Beamforming for Pinching-Antenna Systems

TL;DR

This paper tackles the challenge of optimizing downlink throughput in pinching antenna systems (PASS) by introducing a two-timescale framework that decouples long-term pinching beamforming from short-term transmit beamforming. A primal-dual decomposition (PDD) splits the problem into a long-term subproblem solved via stochastic successive convex approximation (SSCA) and a short-term subproblem addressed with a Karush-Kuhn-Tucker guided dual learning (KDL) based Transformer to predict optimal dual variables, enabling efficient gradient computation. The long-term optimization uses SSCA to adapt pinching positions $\mathbf{X}$ over channel statistics, while the short-term uses a KDL-enhanced MMSE/KKTx solution to compute transmit beams $\mathbf{W}$ for instantaneous CSI. Simulations show significant sum-rate gains over baselines, with rapid convergence of the KDL-based short-term solver and clear advantages of exploiting PASS geometry, highlighting the practical viability of the two-timescale design for scalable PASS deployments in 6G-era networks.

Abstract

Pinching antenna systems (PASS) have been proposed as a revolutionary flexible antenna technology which facilitates line-of-sight links via numerous low-cost pinching antennas with adjustable activation positions over waveguides. This letter proposes a two-timescale joint transmit and pinching beamforming design for the maximization of sum rate of a PASS-based downlink multi-user multiple input single output system. A primal dual decomposition method is developed to decouple the two-timescale problem into two sub-problems: 1) A Karush-Kuhn-Tucker-guided dual learning-based approach is proposed to solve the short-term transmit beamforming design sub-problem; 2) The long-term pinching beamforming design sub-problem is tackled by adopting a stochastic successive convex approximation method. Simulation results demonstrate that the proposed two-timescale algorithm achieves a significant performance gain compared to other baselines.

Figures (4)

• Figure 1: An illustration for the considered PASS-based downlink system.
• Figure 2: Two-timescale scheme for joint transmit and pinching beamforming design.
• Figure 3: Comparison of the convergence performance of different short-term stage algorithms.
• Figure 4: Performance comparison of different algorithms under different $P_{max}$.