Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Power-Measurement-Based Channel Autocorrelation Estimation for IRS-Assisted Wideband Communications

He Sun, Lipeng Zhu, Weidong Mei, Rui Zhang

TL;DR

This work tackles CSI acquisition for IRS-assisted wideband OFDM by introducing a neural-network framework that learns the wideband channel autocorrelation from user power measurements. A single-layer NN with multiple subnetworks represents a rank-K decomposition of the autocorrelation matrix, enabling recovery of $\boldsymbol{R}$ from RSRP data collected under random IRS reflections; a progressive training strategy adapts to the unknown rank to balance accuracy and complexity. With the estimated $\hat{\boldsymbol{R}}$, IRS passive reflection is optimized via SDR and subsequent refinement, achieving near-optimal average channel power gains under discrete phase constraints. The approach yields significant gains over power-measurement benchmarks and remains robust to environmental changes, offering a practical path to IRS integration in wideband systems and multi-user scenarios.

Abstract

Channel state information (CSI) is essential to the performance optimization of intelligent reflecting surface (IRS)-aided wireless communication systems. However, the passive and frequency-flat reflection of IRS, as well as the high-dimensional IRS-reflected channels, have posed practical challenges for efficient IRS channel estimation, especially in wideband communication systems with significant multi-path channel delay spread. To tackle the above challenge, we propose a novel neural network (NN)-empowered IRS channel estimation and passive reflection design framework for the wideband orthogonal frequency division multiplexing (OFDM) communication system based only on the user's reference signal received power (RSRP) measurements with time-varying random IRS training reflections. In particular, we show that the average received signal power over all OFDM subcarriers at the user terminal can be represented as the prediction of a single-layer NN composed of multiple subnetworks with the same structure, such that the autocorrelation matrix of the wideband IRS channel can be recovered as their weights via supervised learning. To exploit the potential sparsity of the channel autocorrelation matrix, a progressive training method is proposed by gradually increasing the number of subnetworks until a desired accuracy is achieved, thus reducing the training complexity. Based on the estimates of IRS channel autocorrelation matrix, the IRS passive reflection is then optimized to maximize the average channel power gain over all subcarriers. Numerical results indicate the effectiveness of the proposed IRS channel autocorrelation matrix estimation and passive reflection design under wideband channels, which can achieve significant performance improvement compared to the existing IRS reflection designs based on user power measurements.

Power-Measurement-Based Channel Autocorrelation Estimation for IRS-Assisted Wideband Communications

TL;DR

This work tackles CSI acquisition for IRS-assisted wideband OFDM by introducing a neural-network framework that learns the wideband channel autocorrelation from user power measurements. A single-layer NN with multiple subnetworks represents a rank-K decomposition of the autocorrelation matrix, enabling recovery of from RSRP data collected under random IRS reflections; a progressive training strategy adapts to the unknown rank to balance accuracy and complexity. With the estimated , IRS passive reflection is optimized via SDR and subsequent refinement, achieving near-optimal average channel power gains under discrete phase constraints. The approach yields significant gains over power-measurement benchmarks and remains robust to environmental changes, offering a practical path to IRS integration in wideband systems and multi-user scenarios.

Abstract

Channel state information (CSI) is essential to the performance optimization of intelligent reflecting surface (IRS)-aided wireless communication systems. However, the passive and frequency-flat reflection of IRS, as well as the high-dimensional IRS-reflected channels, have posed practical challenges for efficient IRS channel estimation, especially in wideband communication systems with significant multi-path channel delay spread. To tackle the above challenge, we propose a novel neural network (NN)-empowered IRS channel estimation and passive reflection design framework for the wideband orthogonal frequency division multiplexing (OFDM) communication system based only on the user's reference signal received power (RSRP) measurements with time-varying random IRS training reflections. In particular, we show that the average received signal power over all OFDM subcarriers at the user terminal can be represented as the prediction of a single-layer NN composed of multiple subnetworks with the same structure, such that the autocorrelation matrix of the wideband IRS channel can be recovered as their weights via supervised learning. To exploit the potential sparsity of the channel autocorrelation matrix, a progressive training method is proposed by gradually increasing the number of subnetworks until a desired accuracy is achieved, thus reducing the training complexity. Based on the estimates of IRS channel autocorrelation matrix, the IRS passive reflection is then optimized to maximize the average channel power gain over all subcarriers. Numerical results indicate the effectiveness of the proposed IRS channel autocorrelation matrix estimation and passive reflection design under wideband channels, which can achieve significant performance improvement compared to the existing IRS reflection designs based on user power measurements.

Paper Structure

This paper contains 18 sections, 3 theorems, 59 equations, 11 figures, 1 algorithm.

Table of Contents

  1. Introduction
  2. System Model
  3. NN-enabled Channel Estimation Based on User Power Measurements
  4. RSRP Measurement
  5. NN-Enabled Channel Autocorrelation Matrix Estimation
  6. NN Training and IRS Reflection Optimization
  7. Progressive NN Training
  8. IRS Reflection Design
  9. Numerical Results
  10. Progressive NN Training
  11. IRS Channel Autocorrelation Matrix Estimation
  12. IRS Passive Reflection Design
  13. Extension to Multi-user Systems
  14. Effect of Channel Power Decaying Factor
  15. Conclusion
  16. ...and 3 more sections

Key Result

Lemma 1

Given $M_0 \geq K$, the RSRP measurement in (Eqs0030101) based on a subset of subcarriers in ${\cal M}_0$ is equal to the ARSP over all the $M$ subcarriers in (Eqs002010), i.e.,

Figures (11)

  • Figure 1: An IRS-aided wideband OFDM system.
  • Figure 2: An example of inserted RSs over OFDM symbols with $Q=2$, $M_0=3$, and $M=9$.
  • Figure 3: Single-layer NN structure for wideband channel autocorrelation matrix estimation.
  • Figure 4: NN training loss versus the number of training iterations.
  • Figure 5: Minimum training MSE of progressive training versus the number of NN subnetworks, $K'$.
  • ...and 6 more figures

Theorems & Definitions (5)

  • Lemma 1
  • Lemma 2
  • Lemma 3
  • Remark 1
  • Remark 2