AI-Driven Optimization of Wave-Controlled Reconfigurable Intelligent Surfaces

2025-05-11

AI Summary

This work addresses the low reflection-coefficient control accuracy of bias-controlled standing-wave (BSW)-based reconfigurable intelligent surfaces (RISs), caused by physical model mismatch. We propose a data-driven, end-to-end optimization framework that bypasses conventional physics-based modeling: instead, a neural network is trained on measured radiation patterns to learn the nonlinear mapping from BSW amplitude distributions to far-field radiation responses. Subsequently, a hybrid stochastic optimizer—integrating genetic algorithms and simulated annealing—jointly optimizes the BSW bias parameters. We introduce the first “standing-wave excitation–neural network–stochastic optimization” closed-loop paradigm, enabling high-fidelity black-box characterization and real-time configuration of strongly coupled, nonlinear RISs. Experiments demonstrate over 40% reduction in radiation-pattern prediction error, millisecond-scale dynamic reconfiguration, and generation of a lookup-table-ready optimal configuration set, yielding significant improvement in signal-to-leakage-and-noise ratio (SLNR).

Technology Category

• Intelligent Robots: Learning & Optimization for ROB
• Search and Optimization: Learning to Search
• Machine Learning: Optimization

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• 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

Abstract

A promising type of Reconfigurable Intelligent Surface (RIS) employs tunable control of its varactors using biasing transmission lines below the RIS reflecting elements. Biasing standing waves (BSWs) are excited by a time-periodic signal and sampled at each RIS element to create a desired biasing voltage and control the reflection coefficients of the elements. A simple rectifier can be used to sample the voltages and capture the peaks of the BSWs over time. Like other types of RIS, attempting to model and accurately configure a wave-controlled RIS is extremely challenging due to factors such as device non-linearities, frequency dependence, element coupling, etc., and thus significant differences will arise between the actual and assumed performance. An alternative approach to solving this problem is data-driven: Using training data obtained by sampling the reflected radiation pattern of the RIS for a set of BSWs, a neural network (NN) is designed to create an input-output map between the BSW amplitudes and the resulting sampled radiation pattern. This is the approach discussed in this paper. In the proposed approach, the NN is optimized using a genetic algorithm (GA) to minimize the error between the predicted and measured radiation patterns. The BSW amplitudes are then designed via Simulated Annealing (SA) to optimize a signal-to-leakage-plus-noise ratio measure by iteratively forward-propagating the BSW amplitudes through the NN and using its output as feedback to determine convergence. The resulting optimal solutions are stored in a lookup table to be used both as settings to instantly configure the RIS and as a basis for determining more complex radiation patterns.

Problem

• Optimizing wave-controlled RIS performance using AI
• Modeling RIS reflection coefficients with neural networks
• Minimizing error in radiation pattern prediction

Innovation

• AI-driven optimization for RIS configuration
• Genetic algorithm optimizes neural network performance
• Simulated annealing designs optimal BSW amplitudes