Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Kaining Wang, Bo Yang, Yusheng Lei, Zhiwen Yu, Xuelin Cao, George C. Alexandropoulos, Marco Di Renzo, Chau Yuen

TL;DR

The paper addresses spectrum pollution in RIS-enabled wireless networks caused by blind reflection of interference signals. It proposes a trajectory prediction-based dynamical RIS ON-OFF control (TPC) that uses an LSTM at the base station to forecast user trajectories and a codebook-based RIS configuration to pre-emptively switch RISs on or off. By jointly optimizing the RIS activation vector ${\mathbf V}$ and phase shifts ${\mathbf \Phi}$, the method maximizes the SINR ${\gamma_l}$ in mobility scenarios. Simulations with real trajectory data and multiple RISs demonstrate that TPC yields higher SINR than baseline strategies, and that trajectory-prediction accuracy directly influences the control effectiveness and interference mitigation.

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.

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

TL;DR

The paper addresses spectrum pollution in RIS-enabled wireless networks caused by blind reflection of interference signals. It proposes a trajectory prediction-based dynamical RIS ON-OFF control (TPC) that uses an LSTM at the base station to forecast user trajectories and a codebook-based RIS configuration to pre-emptively switch RISs on or off. By jointly optimizing the RIS activation vector and phase shifts , the method maximizes the SINR in mobility scenarios. Simulations with real trajectory data and multiple RISs demonstrate that TPC yields higher SINR than baseline strategies, and that trajectory-prediction accuracy directly influences the control effectiveness and interference mitigation.

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.

Paper Structure

This paper contains 20 sections, 10 equations, 5 figures, 1 algorithm.

Table of Contents

  1. Introduction
  2. System Model and Problem Formulation
  3. RISs-aided Network Scenario
  4. Channel Model
  5. Problem Formulation and Analysis
  6. Proposed TPC Algorithm
  7. LSTM-based Trajectory Prediction
  8. Trajectory collection
  9. Offline training
  10. Online inference
  11. RIS ON-OFF control
  12. Codebook-based phase configuration
  13. RIS binary control algorithm
  14. Frame structure design
  15. Simulation Results
  16. ...and 5 more sections

Figures (5)

  • Figure 1: In the left figure, we show a conventional multi-user uplink RIS-assisted wireless communication system without TPC. Some interfering signals and desired signals are reflected to the BS. In the right figure, interfering signals approach the BS and are predicted by the BS. The BS sends the predicted control signal to the RIS based on the user trajectory. Each RIS controller can receive the control on/off signal and configure the RIS in real-time.
  • Figure 2: The proposed TPC algorithm structure. The input includes the history points of the pedestrian trajectories, and the output is the predicted coordinates.
  • Figure 3: Comparison of real trajectory and predicted trajectory
  • Figure 4: SINR comparison across transmission power
  • Figure 5: SINR comparison across numbers of RIS elements