In this article, we propose a model-driven deep learning (DL) approach that combines DL with the expert knowledge to replace the existing orthogonal frequency-division multiplexing (OFDM) receiver in wireless communications. Different from the data-driven fully connected deep neural network (FC-DNN) method, we adopt the block-by-block signal processing method that divides the receiver into channel estimation subnet and signal detection subnet. Each subnet is constructed by a DNN and uses the existing simple and traditional solution as initialization. The proposed model-driven DL receiver offers more accurate channel estimation comparing with the linear minimum mean-squared error (LMMSE) method and exhibits higher data recovery accuracy comparing with the existing methods and FC-DNN.Simulation results further demonstrate the robustness of the proposed approach in terms of signal-tonoise ratio and its superiority to the FC-DNN approach in the computational complexities or the memory usage.

No abstract

No abstract

The updated physical layer standard of the fifth generation wireless communication suggests the necessity of a rapid prototyping platform. To this end, we develop RaPro, a multi-core general purpose processor-based massive multipleinput-multiple-output (MIMO) prototyping platform. To enhance RaPro, high performance detection and beamforming are needed, whereas both of them request for accurate channel state information (CSI). In this paper, linear minimum mean square error (LMMSE)-based channel estimator is adopted and encapsulated inside RaPro to gain more accurate CSI. Considering the high comlexity and unknown of channel statistics, we design lowcomplexity LMMSE channel estimator to alleviate the rising complexity along with increasing antenna number and set more computational resource aside for massive MIMO uplink detection and downlink beamforming. Simulation results indicate the high mean square error performance and robustness of designed lowcomplexity method. Indoor and corridor scenario tests show prominent improvement in bit error rate performance. Time cost analysis proves the practical use and real-time transmission ability of the implemented uplink receiver on RaPro.Index Terms-Massive MIMO, uplink receiver, channel estimation, prototyping testbed, general purpose processor.

No abstract