Green Learning for STAR-RIS mmWave Systems with Implicit CSI

2025-09-08

AI Summary

To address green communication requirements in STAR-RIS-aided mmWave MIMO broadcast systems, this paper proposes the first Green Learning (GL) precoding framework that operates without explicit Channel State Information (CSI). The method jointly predicts STAR-RIS reflection/transmission coefficients and base station precoding matrices directly from uplink pilot signals, eliminating reliance on perfect CSI or iterative optimization—unlike conventional schemes—and avoiding CSI-labeled data and complex network training—unlike deep learning approaches. Innovatively integrating Subspace approximation and bias-adjustment (Saab), Relevance-based Feature Testing (RFT) for feature selection, and an XGBoost decision model, the framework achieves spectral efficiency comparable to block coordinate descent and deep learning baselines, while reducing floating-point operations by over four orders of magnitude. This yields substantial improvements in energy efficiency and real-time performance, making it particularly suitable for resource-constrained 6G scenarios.

Technology Category

• Machine Learning: Efficient ML / Green AI
• Search and Optimization: Learning to Search
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

In this paper, a green learning (GL)-based precoding framework is proposed for simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS)-aided millimeter-wave (mmWave) MIMO broadcasting systems. Motivated by the growing emphasis on environmental sustainability in future 6G networks, this work adopts a broadcasting transmission architecture for scenarios where multiple users share identical information, improving spectral efficiency and reducing redundant transmissions and power consumption. Different from conventional optimization methods, such as block coordinate descent (BCD) that require perfect channel state information (CSI) and iterative computation, the proposed GL framework operates directly on received uplink pilot signals without explicit CSI estimation. Unlike deep learning (DL) approaches that require CSI-based labels for training, the proposed GL approach also avoids deep neural networks and backpropagation, leading to a more lightweight design. Although the proposed GL framework is trained with supervision generated by BCD under full CSI, inference is performed in a fully CSI-free manner. The proposed GL integrates subspace approximation with adjusted bias (Saab), relevant feature test (RFT)-based supervised feature selection, and eXtreme gradient boosting (XGBoost)-based decision learning to jointly predict the STAR-RIS coefficients and transmit precoder. Simulation results show that the proposed GL approach achieves competitive spectral efficiency compared to BCD and DL-based models, while reducing floating-point operations (FLOPs) by over four orders of magnitude. These advantages make the proposed GL approach highly suitable for real-time deployment in energy- and hardware-constrained broadcasting scenarios.

Problem

• Proposes green learning for STAR-RIS mmWave systems without explicit CSI
• Reduces computational complexity and power consumption in 6G networks
• Enables real-time deployment in hardware-constrained broadcasting scenarios

Innovation

• GL-based precoding without explicit CSI estimation
• Subspace approximation and XGBoost for joint prediction
• Reduces FLOPs by four orders of magnitude