Source Coding Based Millimeter-Wave Channel Estimation with Deep Learning Based Decoding

Abstract

mmWave technology is set to become a main feature of next generation wireless networks, e.g., 5G mobile and WiFi 802.11ad/ay. Among the basic and most fundamental challenges facing mmWave is the ability to overcome its unfavorable propagation characteristics using energy efficient solutions. This has been addressed using innovative transceiver architectures. However, these architectures have their own limitations when it comes to channel estimation. This paper focuses on channel estimation and poses it as a source compression problem, where channel measurements are designed to mimic an encoded (compressed) version of the channel. We show that linear source codes can significantly reduce the number of channel measurements required to discover all channel paths. We also propose a deeplearning-based approach for decoding the obtained measurements, which enables high-speed and efficient channel discovery.

How Long to Estimate Sparse MIMO Channels

“…This lower bound is achievable with equality for specific examples as shown in [19]. However, it is not immediately clear how this bound compares to our bound in Eq.…”

“…Then, using Theorem 2, we will derive an asymptotic lower bound on the number of rows of G v and deduce its asymptotic behavior. We will finally show the tightness of our derived asymptotic bound using the solution framework in [19].…”

“…To argue that the measurement lower bound in Theorem 5 is tight, we will show that there exists a solution, based on [19], which yields sensing matrices that satisfy 2k−RIP with constants ∈ (0, 1) and with m ∈ Θ k 2 log nt k log nr k . We briefly discuss the measurement framework of [19] next.…”

“…In [19], a source-coding-based framework for the sparse MIMO channel estimation problem is developed. This solution proposes a method for obtaining a small number of measurements that are sufficient to estimate the channel.…”

“…Lemma 7. The number of measurements achievable using BCH codes in the framework of [19] is asymptotically bounded as m = O k 2 log nt k log nr k .…”