Abstract
Unmanned aerial vehicle (UAV) enabled communication system provides flexibility and reliability compared to conventional ones. Millimeter wave and massive MIMO have widely been researched since recent years, which are promising techniques for the next and even the later generation communication system. Hybrid precoding, as a method to reduce the high cost in hardware and power brought by massive antenna array, develops fiercely and is often combined to deep learning, a kind of popular optimization tool, which brings overwhelming performance. On the other hand, there are not so many attentions about the hybrid precoding in time-varying millimeter wave massive MIMO, which is necessary to be considered in a UAV-enabled communication scenario because the performance will degrade seriously if the channel changed while the transmitter and receiver use the precoding matrix corresponding to the expired channel, yet. In this paper, we propose a double-pilot-based hybrid precoding system, which completes analog precoding and digital precoding separately--predicting the previous one using deep learning structure and updating equivalent channel frequently for the post one by enhancing the frequency of equivalent channel estimation.
Deep Learning for Beamspace Channel Estimation in Millimeter-Wave Massive MIMO Systems
