To support the ever increasing number of devices in massive multiple-input multiple-output systems, an excessive amount of overhead is required for conventional orthogonal pilot based channel estimation (CE) schemes. To relax this stringent constraint, we design a machine learning (ML)-based time division duplex scheme in which channel state information (CSI) can be obtained by leveraging the temporal channel correlation. The proposed ML-based predictors involve a pattern extraction and CSI predictor, which are implemented via a convolutional neural network (CNN) and autoregressive (AR) predictor or an autoregressive network with exogenous inputs recurrent neural network (NARX-RNN), respectively. Numerical results demonstrate that ML-based predictors can remarkably improve the prediction quality, and the optimal CE overhead is provided for practical reference.
|Title of host publication||20th IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC 2019): Proceedings |
|Publisher|| IEEE |
|Number of pages||5|
|Publication status||Published - 29 Aug 2019|
|Name||International Workshop on Signal Processing Advances in Wireless Communications (SPAWC): Proceedings|