Deep Learning Optimization of Two-State Pinching Antennas Systems

2025-07-08

AI Summary

This work addresses the problem of maximizing communication rate for dual-state pinching antennas (PAs) fixed at predetermined positions within a waveguide. To enhance robustness against user location uncertainty, the antenna activation strategy is formulated as a combinatorial fractional 0–1 quadratic programming problem. The proposed method introduces a multi-complexity neural network architecture that directly learns optimal antenna subset selection from spatial channel features and signal structure, while jointly optimizing waveguide phase shifts and power allocation in an end-to-end manner. Experimental results demonstrate that the approach consistently achieves significant communication rate gains across diverse waveguide configurations and user distributions. It exhibits strong generalization capability and operational stability, establishing a novel, efficient, and robust intelligent beam control paradigm for reconfigurable waveguide communications.

Technology Category

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

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

The evolution of wireless communication systems requires flexible, energy-efficient, and cost-effective antenna technologies. Pinching antennas (PAs), which can dynamically control electromagnetic wave propagation through binary activation states, have recently emerged as a promising candidate. In this work, we investigate the problem of optimally selecting a subset of fixed-position PAs to activate in a waveguide, when the aim is to maximize the communication rate at a user terminal. Due to the complex interplay between antenna activation, waveguide-induced phase shifts, and power division, this problem is formulated as a combinatorial fractional 0-1 quadratic program. To efficiently solve this challenging problem, we use neural network architectures of varying complexity to learn activation policies directly from data, leveraging spatial features and signal structure. Furthermore, we incorporate user location uncertainty into our training and evaluation pipeline to simulate realistic deployment conditions. Simulation results demonstrate the effectiveness and robustness of the proposed models.

Problem

• Optimize activation of pinching antennas for maximum communication rate
• Solve combinatorial fractional 0-1 quadratic program using deep learning
• Address user location uncertainty in antenna activation policies

Innovation

• Deep learning optimizes pinching antenna activation
• Neural networks learn policies from spatial features
• Models handle user location uncertainty robustly