Dynamical ON-OFF Control with Trajectory Prediction for Multi-RIS Wireless Networks

2025-05-27

AI Summary

In multi-RIS large-scale wireless networks, reconfigurable intelligent surfaces (RISs) cannot distinguish desired signals from interference, leading to spectral pollution and degraded SINR. To address this, this paper proposes a dynamic ON-OFF cooperative control mechanism leveraging user trajectory prediction. Specifically, it innovatively integrates LSTM-based mobility prediction with binary RIS activation/deactivation control, coupled with a codebook-driven adaptive coordination strategy—overcoming the inherent limitation of passive RISs’ indistinguishable signal sources. Furthermore, a joint optimization algorithm is designed to maximize SINR by jointly determining RIS activation states and reflection configurations. Simulation results demonstrate that the proposed method significantly suppresses inter-RIS interference across diverse scenarios, yielding an average SINR improvement of 3.2–5.8 dB at the receiver and effectively mitigating spectral pollution.

Technology Category

• Intelligent Robots: Multi-Robot Systems
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Multiagent Systems: Coordination and Collaboration

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

Abstract

Reconfigurable intelligent surfaces (RISs) have demonstrated an unparalleled ability to reconfigure wireless environments by dynamically controlling the phase, amplitude, and polarization of impinging waves. However, as nearly passive reflective metasurfaces, RISs may not distinguish between desired and interference signals, which can lead to severe spectrum pollution and even affect performance negatively. In particular, in large-scale networks, the signal-to-interference-plus-noise ratio (SINR) at the receiving node can be degraded due to excessive interference reflected from the RIS. To overcome this fundamental limitation, we propose in this paper a trajectory prediction-based dynamical control algorithm (TPC) for anticipating RIS ON-OFF states sequence, integrating a long-short-term-memory (LSTM) scheme to predict user trajectories. In particular, through a codebook-based algorithm, the RIS controller adaptively coordinates the configuration of the RIS elements to maximize the received SINR. Our simulation results demonstrate the superiority of the proposed TPC method over various system settings.

Problem

• Control RIS interference in multi-RIS wireless networks
• Predict user trajectories to optimize RIS ON-OFF states
• Maximize received SINR via adaptive RIS configuration

Innovation

• LSTM-based trajectory prediction for RIS control
• Codebook algorithm for adaptive RIS configuration
• Dynamic ON-OFF control to maximize SINR