Source Coding Based Millimeter-Wave Channel Estimation with Deep Learning Based Decoding
This work addresses the critical need for efficient channel estimation in mmWave communications, which is essential for practical adoption, though it appears incremental by combining source coding with deep learning.
The paper tackles the problem of reducing measurement overhead for millimeter-wave channel estimation by framing it as a source compression task and using deep learning for decoding, achieving performance superior to compressed sensing methods and determining a lower bound on required measurements.
The speed at which millimeter-Wave (mmWave) channel estimation can be carried out is critical for the adoption of mmWave technologies. This is particularly crucial because mmWave transceivers are equipped with large antenna arrays to combat severe path losses, which consequently creates large channel matrices, whose estimation may incur significant overhead. This paper focuses on the mmWave channel estimation problem. Our objective is to reduce the number of measurements required to reliably estimate the channel. Specifically, channel estimation is posed as a "source compression" problem in which measurements mimic an encoded (compressed) version of the channel. Decoding the observed measurements, a task which is traditionally computationally intensive, is performed using a deep-learning-based approach, facilitating a high-performance channel discovery. Our solution not only outperforms state-of-the-art compressed sensing methods, but it also determines the lower bound on the number of measurements required for reliable channel discovery.