Learning to Beamform for Intelligent Reflecting Surface with Implicit Channel Estimate

by   Tao Jiang, et al.

Intelligent reflecting surface (IRS), consisting of massive number of tunable reflective elements, is capable of boosting spectral efficiency between a base station (BS) and a user by intelligently tuning the phase shifters at the IRS according to the channel state information (CSI). However, due to the large number of passive elements which cannot transmit and receive signals, acquisition of CSI for IRS is a practically challenging task. Instead of using the received pilots to estimate the channels explicitly, this paper shows that it is possible to learn the effective IRS reflection pattern and beamforming at the BS directly based on the received pilots. This is achieved by parameterizing the mapping from the received pilots to the optimal configuration of IRS and the beamforming matrix at the BS by properly tuning a deep neural network using unsupervised training. Simulation results indicate that the proposed neural network can efficiently learn to maximize the system sum rate from much fewer received pilots as compared to the traditional channel estimation based solutions.


page 1

page 2

page 3

page 4

page 5

page 6


Intelligent Reflecting Surface-Enhanced OFDM: Channel Estimation and Reflection Optimization

In the intelligent reflecting surface (IRS)-enhanced wireless communicat...

Intelligent Reflecting Surface Enabled Random Rotations Scheme for the MISO Broadcast Channel

The current literature on intelligent reflecting surface (IRS) focuses o...

Anchor-Assisted Intelligent Reflecting Surface Channel Estimation for Multiuser Communications

Due to the passive nature of Intelligent Reflecting Surface (IRS), chann...

On the Effective Capacity of IRS assisted wireless communication

This paper provides the effective capacity (EC)analysis in futuristic in...

Two-Timescale Optimization for Intelligent Reflecting Surface-Assisted MIMO Transmission in Fast-Changing Channels

The application of intelligent reflecting surface (IRS) depends on the k...

Deep Reinforcement Learning-Based Adaptive IRS Control with Limited Feedback Codebooks

Intelligent reflecting surfaces (IRS) consist of configurable meta-atoms...

Configuring Intelligent Reflecting Surface with Performance Guarantees: Blind Beamforming

This work gives a blind beamforming strategy for intelligent reflecting ...