Offset Learning Based Channel Estimation for Intelligent Reflecting Surface-Assisted Indoor Communication

Abstract

The emerging intelligent reflecting surface (IRS) can significantly improve the system capacity, and it has been regarded as a promising technology for the beyond fifth-generation (B5G) communications. For IRS-assisted multiple input multiple output (MIMO) systems, accurate channel estimation is a critical challenge. This severely restricts practical applications, particularly for resource-limited indoor scenario as it contains numerous scatterers and parameters to be estimated, while the number of pilots is limited. Prior art tackles these issues and associated optimization using mathematical-based statistical approaches, but are difficult to solve as the number of scatterers increase. To estimate the indoor channels with an affordable piloting overhead, we propose an offset learning (OL)-based neural network for channel estimation. The proposed OL-based estimator can dynamically trace the channel state information (CSI) without any prior knowledge of the IRS-assisted channel structure as well as indoor statistics. In addition, inspired by the powerful learning capability of convolutional neural network (CNN), CNN-based inversion blocks are developed in the offset estimation module to build the offset estimation operator. Numerical results show that the proposed OL-based estimator can achieve more accurate indoor

Reconfigurable-Intelligent-Surface-Assisted B5G/6G Wireless Communications: Challenges, Solution, and Future Opportunities

“…In light of this, we focus on passive RIS in this article. By adjusting the phase shifters (PSs) of passive RIS reflective elements, the incident signals can be dynamically adjusted to support diverse user requirements, without deploying additional mobile stations (MSs) or in-cell relay stations [4], [5]. As a result, it has ultra-low power consuming and low-cost hardware as compared to that of the amplify-andforward (AF) relay-assisted systems relying on active transmission devices or base stations (BSs).…”

Phase retrieval for block sparsity based on adaptive coupled variational Bayesian learning

“…Since the appearance of compressed sensing [15], a huge amount of applications has been proposed [16][17][18][19]. With the booming compressed sensing, the sparse PR has been exploited to obtain robust retrieval without requiring massive measurements.…”

Robust Hybrid Beamforming Design for Multi-RIS Assisted MIMO System With Imperfect CSI

“…It is worth noting that the RIS only consists of low-cost passive reflecting elements, which differs significantly from the conventional amplify-and-forward relay [4]. More importantly, low hardware footprints of RIS structures promote low implementation cost, high-flexibility, and hence they can be easily deployed and integrated into existing wireless communication systems without changing the existing infrastructure and operating standards [5]. Therefore, the design of RIS in assisting wireless communications has attracted extensive attention in both industrial and academia.…”