A Model-Driven Deep Learning Network for Quantized GFDM Receiver

Low-resolution analog-to-digital converter(ADC)is a promising solution to reduce hardware cost and power consumption in generalized frequency division multiplexing(GFDM)systems.The severe nonlinear distortion of ADCs and the non-orthogonality of GFDM make receiver design a great challenge.In this paper,we propose a novel model-driven receiver architecture for GFDM with low-resolution ADCs.Orthogonal approximate message passing(OAMP)framework is combined with the classical linear estimator in this work to create a robust iterative receiver for GFDM systems with low-precision ADCs.The corresponding model-driven network is organized based on the proposed novel iterative algorithm according to the procedures of the receiver.The network of OAMP can reduce the gap between the approximate algorithm and the Bayesian optimal result due to the information loss of ADCs.The signal flow of the neural network is designed by unfolding the iterative algorithms for channel estimation and data detection.Numerical results are provided to show that the proposed OAMP-based receiver algorithm outperforms traditional receivers and the model-driven network can further improve the system performance on the basis of the corresponding novel algorithm.

Low-Cost Massive MIMO:Pilot Length and ADC Resolution

When designing an energy efficient massive multiple-input multiple-output(MIMO)system where each receiver antenna is equipped with a low-resolution analog-to-digital converter(ADC),the number of base station(BS)antennas and quantization bits are generally two mutually conflicting system parameters.In this paper,we investigate the joint optimization of the number of BS antennas and ADC resolution in quantized massive MIMO systems,assuming imperfect channel state infor-mation(CSI).A tractable approximate expression for the uplink sum spectral efficiency(SE)using maximal ratio combining(MRC)receivers is derived,based on which the pilot length which maximizes the sum SE is put forward.Considering the effect of ADCs,a realistic model of total power consumption is given subsequently.Capitalizing on it,we formulate the optimization problem of selecting the number of BS antennas and ADC resolution to maximize the sum SE under a total power consumption constraint.Our results show that more pilot symbols should be assigned for massive MIMO systems with low-resolution ADCs,especially for the receivers with one-bit quantizers.Moreover,the results show the trade-off between the number of BS antennas and quantization bits.Numer-ical results suggest that there exists an optimal ADC resolution in massive MIMO systems,while lower quan-tization bits may cause a substantial degradation of the SE performance and higher one will consume more power.