Improving wireless signals with smart surface and learning algorithms
A Particle-Swarm-Assisted Gradient Meta-Learning Algorithm for Joint Transmit Precoding and STAR-RIS Coefficient Optimization
Machine LearningInformation Theory
Summary
Wireless communication often faces challenges in sending strong signals to multiple users at the same time. This paper looks at how to better control both the transmitter and a special smart surface that can bounce and pass signals to improve overall connection quality. The authors create a new algorithm that uses a mix of clever searching and machine learning to set the best settings, making the signals stronger and more reliable. Their method performs better than traditional approaches and works well even in challenging situations without extra tuning.
What this means in practice
- •For wireless communication engineers: Optimize signal transmission and surface control jointly to increase multi-user network throughput in downlink scenarios.
- •For smart antenna designers: Use learned update rules to refine antenna and surface parameters without manual tuning, saving design time.
Authors
Kang Zhou
Abstract
This paper investigates the joint optimization of the transmit precoder and the transmission/reflection coefficients of a simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) to maximize the weighted sum rate (WSR) in a multi-user downlink. We propose a particle-swarm-assisted gradient meta-learning (PSA-GML) algorithm for this non-convex problem. The original problem is first equivalently transformed via an amplitude-split parameterization and a collapsed precoder representation, which automatically satisfy the energy-conservation constraint and reduce the search dimension. Particle swarm optimization (PSO) then performs a global search over the STAR-RIS coefficients to yield a high-quality, initialization-robust warm start, with the transmit precoder obtained in closed form. Departing from conventional alternating optimization (AO), a coordinate-wise long short-term memory (LSTM) meta-optimizer trained by first-order gradient meta-learning further refines the coefficients and precoder jointly, learning per-coordinate adaptive update rules from data. The meta-optimizer is trained offline and applied to unseen channels without further adaptation. Numerical results show that PSA-GML attains an 11.06 bits/s/Hz WSR at 10 dB with N=32 elements and K=4 users, exceeding AO by 13.1% (and by 6.2% even with multiple random restarts) and the random-phase scheme by 35.1%. In the interference-limited regime it reaches 83.9% of the hand-designed Adam refinement without manual hyper-parameter tuning, and it transfers zero-shot across regimes, indicating that the learned update rule captures the intrinsic WSR landscape structure.