Deep Learning-Based Beamspace Channel Estimation in mmWave Massive MIMO Systems
Yinghui Zhang, Yifan Mu, Yang Liu, Tiankui Zhang, Yi Qian
Abstract
In this letter, fully convolutional denoising approximate message passing (FCDAMP) algorithm is proposed by combining fully convolutional denoising networks with learned approximate message passing networks in millimeter-wave massive MIMO system. In particular, an asymmetric neural network architecture is considered that can learn channel structure and extract noise characteristics. Simulation and analysis show that the proposed FCDAMP algorithm satisfies the lower estimation error and the higher achievable sum rate especially in the low SNR. Moreover, the performance can be further improved by increasing the antenna array in massive MIMO system.
Topics & Concepts
MIMOComputer scienceConvolutional neural networkMessage passingChannel (broadcasting)Extremely high frequencyAntenna (radio)Noise reductionAlgorithmAntenna arrayBit error rateNoise (video)Reduction (mathematics)Communications systemDeep learningArtificial neural networkTelecommunicationsArtificial intelligenceDistributed computingMathematicsImage (mathematics)GeometryMillimeter-Wave Propagation and ModelingWireless Signal Modulation ClassificationAdvanced MIMO Systems Optimization