ReQuestNet: A Foundational Learning model for Channel Estimation

TL;DR

ReQuestNet is a novel neural network architecture for channel estimation in 5G that simplifies the process, handles various practical system configurations, and significantly outperforms traditional methods across diverse conditions.

Contribution

The paper introduces ReQuestNet, a unified neural model that addresses limitations of linear MMSE solutions by jointly processing MIMO layers and unknown precoding, with improved accuracy and adaptability.

Findings

ReQuestNet achieves up to 10dB gain over genie MMSE at high SNRs.

It generalizes well to unseen channel profiles and dynamic system configurations.

Significantly outperforms traditional linear MMSE channel estimation methods.

Abstract

In this paper, we present a novel neural architecture for channel estimation (CE) in 5G and beyond, the Recurrent Equivariant UERS Estimation Network (ReQuestNet). It incorporates several practical considerations in wireless communication systems, such as ability to handle variable number of resource block (RB), dynamic number of transmit layers, physical resource block groups (PRGs) bundling size (BS), demodulation reference signal (DMRS) patterns with a single unified model, thereby, drastically simplifying the CE pipeline. Besides it addresses several limitations of the legacy linear MMSE solutions, for example, by being independent of other reference signals and particularly by jointly processing MIMO layers and differently precoded channels with unknown precoding at the receiver. ReQuestNet comprises of two sub-units, CoarseNet followed by RefinementNet. CoarseNet performs per PRG, per transmit-receive (Tx-Rx) stream channel estimation, while RefinementNet refines the CoarseNet channel estimate by incorporating correlations across differently precoded PRGs, and correlation across multiple input multiple output (MIMO) channel spatial dimensions (cross-MIMO). Simulation results demonstrate that ReQuestNet significantly outperforms genie minimum mean squared error (MMSE) CE across a wide range of channel conditions, delay-Doppler profiles, achieving up to 10dB gain at high SNRs. Notably, ReQuestNet generalizes effectively to unseen channel profiles, efficiently exploiting inter-PRG and cross-MIMO correlations under dynamic PRG BS and varying transmit layer allocations.