IRS-Assisted Ambient Backscatter Communications Utilizing Deep Reinforcement Learning

TL;DR

This paper introduces a deep reinforcement learning framework to optimize IRS-assisted ambient backscatter communication systems without prior channel knowledge, achieving detection performance comparable to systems with full channel information.

Contribution

It presents a novel deep reinforcement learning approach for IRS and beamforming optimization in AmBC systems lacking channel state information.

Findings

Effective AmBC communication achieved without channel knowledge

Detection performance comparable to full channel knowledge benchmarks

Deep reinforcement learning outperforms traditional methods in this context

Abstract

We consider an ambient backscatter communication (AmBC) system aided by an intelligent reflecting surface (IRS). The optimization of the IRS to assist AmBC is extremely difficult when there is no prior channel knowledge, for which no design solutions are currently available. We utilize a deep reinforcement learning-based framework to jointly optimize the IRS and reader beamforming, with no knowledge of the channels or ambient signal. We show that the proposed framework can facilitate effective AmBC communication with a detection performance comparable to several benchmarks under full channel knowledge.