Deep learning improves mmWave MIMO wireless signal decoding accuracy

Practical Deep Learning-Based Block Demapping for mmWave MIMO Systems

Hardware Architecture

Summary

Signals sent over mmWave wireless systems can be harder to decode because of interference and hardware quirks. The authors design a new way to process these signals by looking at blocks of data all at once, using a kind of deep learning called convolutional neural networks. This method helps fix errors much better than traditional approaches. They tested their method with real wireless signals and found it made big improvements in accuracy, and they also showed it can run very fast on special low-power hardware.

What this means in practice

  • For wireless system engineers: Implement more accurate signal decoding in mmWave MIMO radios to reduce bit errors under real-world conditions using block-wise deep learning demapping.
  • For edge hardware developers: Deploy efficient deep learning demappers on resource-limited radio hardware by using fixed-point and reconfigurable CNN engines for faster processing.

Authors

Syed Asrar ul haq, Jesus O. Lacruz, Joerg Widmer, Sumit J. Darak

Abstract

Deep learning is expected to play a central role in 6G systems, by enabling data-driven physical layer designs that can adapt to practical wireless impairments. This is particularly important for millimetre-wave (mmWave) multiple-input multiple-output (MIMO) systems, which are strongly affected by residual channel distortions, interference, and hardware non-idealities that are difficult to capture with analytical models. In this paper, we propose a deep learning-based soft demapper that performs block-wise processing of received symbols instead of conventional symbol-wise detection. The demapper employs a one-dimensional convolutional neural network to learn temporal structure induced by practical propagation and hardware effects, while producing soft bit outputs compatible with soft-decision decoding stages. The proposed approach is trained and evaluated for a 4$\times$4 wideband mmWave MIMO system at 60~GHz, using an over-the-air dataset collected across multiple days and settings. Experimental results demonstrate consistent improvements over a conventional soft-decision demapper, including up to a 2.6$\times$ reduction in bit error rate for 16QAM and up to a 17.6$\times$ reduction for 64QAM under real over-the-air mmWave MIMO conditions. The proposed demapper is further implemented on a Zynq RFSoC platform using a reconfigurable convolution engine and fixed-point arithmetic, achieving an approximately 34.3$\times$ speedup compared to a processor-based implementation, and demonstrating that learning-based demapping can be deployed efficiently on resource-constrained edge hardware.