NMBEnet: Efficient Near-field mmWave Beam Training for Multiuser OFDM Systems Using Sub-6 GHz Pilots

TL;DR

This work tackles the high pilot overhead of near-field mmWave beam training in ELAA-enabled 6G by leveraging sub-6 GHz uplink pilots to directly estimate the optimal near-field codeword. It introduces NMBEnet, a dual CNN+GNN architecture that performs a dual mapping from far-field sub-6 GHz pilots to near-field mmWave codewords, exploiting inter-subcarrier and inter-user correlations in multiuser OFDM. Offline training uses exhaustive-search labels, while online inference maps sub-6 GHz pilots to probability vectors over angle and distance indices, enabling rapid construction of the mmWave analog precoder and a ZF digital precoder. WI-based simulations show that NMBEnet achieves high beam-training accuracy, approaches exhaustive-search performance in sum rate, and reduces pilot overhead while being robust to sub-6 GHz BS location. This approach offers a practical, scalable path to efficient near-field beam training for future high-density mmWave systems.

Abstract

Combining millimetre-wave (mmWave) communications with an extremely large-scale antenna array (ELAA) presents a promising avenue for meeting the spectral efficiency demands of the future sixth generation (6G) mobile communications. However, beam training for mmWave ELAA systems is challenged by excessive pilot overheads as well as insufficient accuracy, as the huge near-field codebook has to be accounted for. In this paper, inspired by the similarity between far-field sub-6 GHz channels and near-field mmWave channels, we propose to leverage sub-6 GHz uplink pilot signals to directly estimate the optimal near-field mmWave codeword, which aims to reduce pilot overhead and bypass the channel estimation. Moreover, we adopt deep learning to perform this dual mapping function, i.e., sub-6 GHz to mmWave, far-field to near-field, and a novel neural network structure called NMBEnet is designed to enhance the precision of beam training. Specifically, when considering the orthogonal frequency division multiplexing (OFDM) communication scenarios with high user density, correlations arise both between signals from different users and between signals from different subcarriers. Accordingly, the convolutional neural network (CNN) module and graph neural network (GNN) module included in the proposed NMBEnet can leverage these two correlations to further enhance the precision of beam training.

Figures (17)

• Figure 1: Illustration of the adopted system model.
• Figure 2: Similarity between beam patterns of far-field sub-6 GHz channel and near-field mmWave channel.
• Figure 3: Similarity between the beam patterns of different users' channels.
• Figure 4: Similarity between beam patterns of channels with different subcarriers.
• Figure 5: Overall architecture of the poposed NMBEnet.