Deep Learning Based Channel Estimation for Massive MIMO With Mixed-Resolution ADCs

Gao, Shen; Dong, Peihao; Pan, Zhiwen; Li, Geoffrey Ye

doi:10.1109/lcomm.2019.2936393

Cited by 93 publications

(59 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is worth pointing out that the slope of the DNN curve decreases as the SNR increases after 15 dB for the compression ratio ρ = 0.25. We can find a reasonable explanation in [24] that the NMSE performance is not only affected by the SNR but also related to the number of training set samples and the setting of hyper-parameters. Note that the effectiveness of the proposed DNN-based channel estimation scheme for OFDM systems is based on the multi-carrier channel samples, which consist of the channels of all subcarriers from different channel realizations.…”

Section: B Mmwave Massive Mimo Over Cluster Sparse Channel Modelmentioning

confidence: 64%

Data-Driven Deep Learning to Design Pilot and Channel Estimator for Massive MIMO

Gao

2020

IEEE Trans. Veh. Technol.

115

View full text Add to dashboard Cite

In this paper, we propose a data-driven deep learning (DL) approach to jointly design the pilot signals and channel estimator for wideband massive multiple-input multiple-output (MIMO) systems. By exploiting the angular-domain compressibility of massive MIMO channels, the conceived DL framework can reliably reconstruct the high-dimensional channels from the under-determined measurements. Specifically, we design an endto-end deep neural network (DNN) architecture composed of dimensionality reduction network and reconstruction network to respectively mimic the pilot signals and channel estimator, which can be acquired by data-driven deep learning. For the dimensionality reduction network, we design a fully-connected layer by compressing the high-dimensional massive MIMO channel vector as input to low-dimensional received measurements, where the weights are regarded as the pilot signals. For the reconstruction network, we design a fully-connected layer followed by multiple cascaded convolutional layers, which will reconstruct the highdimensional channel as the output. By defining the mean square error between input and output as loss function, we leverage Adam algorithm to train the end-to-end DNN aforementioned with extensive channel samples. In this way, both the pilot signals and channel estimator can be simultaneously obtained. The simulation results demonstrate that the superiority of the proposed solution over state-of-the-art compressive sensing approaches.

show abstract

Section: B Mmwave Massive Mimo Over Cluster Sparse Channel Modelmentioning

confidence: 64%

Data-Driven Deep Learning to Design Pilot and Channel Estimator for Massive MIMO

Gao

2020

IEEE Trans. Veh. Technol.

115

View full text Add to dashboard Cite

show abstract

“…For wideband mmWave massive MIMO systems in time-varying channels, channel correlation has been exploited by deep convolutional neural network (CNN) in [24] to improve the accuracy and accelerate the computation for the channel estimation. Deep neural network (DNN) has been utilized in [25] to model the mapping relationship among antennas for reliable channel estimation in massive MIMO systems with mixed-resolution ADCs. An autoencoder-like DNN has been developed in [26] to reduce the overhead for channel state information (CSI) feedback in the frequency duplex division massive MIMO system.…”

Section: A Related Workmentioning

confidence: 99%

Framework on Deep Learning-Based Joint Hybrid Processing for mmWave Massive MIMO Systems

Dong

Zhang

2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

For millimeter wave (mmWave) massive multiple-input multiple-output (MIMO) systems, hybrid processing architecture is essential to significantly reduce the complexity and cost but is quite challenging to be jointly optimized over the transmitter and receiver. In this paper, deep learning (DL) is applied to design a novel joint hybrid processing framework (JHPF) that allows end-to-end optimization by using back propagation. The proposed framework includes three parts: hybrid processing designer, signal flow simulator, and signal demodulator, which outputs the hybrid processing matrices for the transceiver by using neural networks (NNs), simulates the signal transmission over the air, and maps the detected symbols to the original bits by using the NN, respectively. By minimizing the cross-entropy loss between the recovered and original bits, the proposed framework optimizes the analog and digital processing matrices at the transceiver jointly and implicitly instead of approximating pre-designed label matrices, and its trainability is proved theoretically. It can be also directly applied to orthogonal frequency division multiplexing systems by simply modifying the structure of the training data. Simulation results show the proposed DL-JHPF outperforms the existing hybrid processing schemes and is robust to the mismatched channel state information and channel scenarios with the significantly reduced runtime. INDEX TERMS mmWave massive MIMO, deep learning, hybrid processing design, end-to-end optimization.

show abstract

“…The initial results reported in 31,32 show that a simple fully-connected network trained in a supervised setting to estimate the channel directly from sign measurements can reduce the required pilot length roughly by an order of magnitude, while achieving similar reconstruction performance in comparison with previous sparse or low-rank based techniques. In 33 , the authors consider a mixed-ADC scenario, where several BS antennas are equipped with high resolution ADCs and others with few-bit ADCs to achieve a trade-off between the performance and power (6) Y q = Q(HX + Z), consumption. They input an initial least square (LS) channel estimate to a 5-layer fully-connected NN, and show that the NN can learn to utilize the correlation between antennas to improve the estimation performance for the low-resolution branches.…”

Section: Mimo Channel Estimation By DLmentioning

confidence: 99%

Deep Learning for Massive MIMO Channel State Acquisition and Feedback

Mashhadi

Gündüz

2020

J Indian Inst Sci

View full text Add to dashboard Cite

Introduction Massive multiple-input multiple-output (MIMO) systems are an important component of 5G and future generation wireless networks due to their ability to serve many users simultaneously with high spectral and energy efficiency. The main idea in massive MIMO is to equip base stations (BSs) in wireless networks with large arrays of cooperating antennas to facilitate spatial multiplexing of many user equipments (UEs) within the same time-frequency resources. Since the number of antennas at the BS is typically assumed to be significantly more than the number of users, a large number of degrees of freedom are available in the downlink, which can be used to shape the transmitted signals in a specific direction or to null interference. This yields a beamforming gain that translates into increased energy efficiency, reduced interference, or improved coverage. In the uplink, each single-antenna user in a massive MIMO system can scale down its transmit power proportionally to the number of antennas at the

show abstract

Deep Learning Based Channel Estimation for Massive MIMO With Mixed-Resolution ADCs

Cited by 93 publications

References 18 publications

Data-Driven Deep Learning to Design Pilot and Channel Estimator for Massive MIMO

Data-Driven Deep Learning to Design Pilot and Channel Estimator for Massive MIMO

Framework on Deep Learning-Based Joint Hybrid Processing for mmWave Massive MIMO Systems

Deep Learning for Massive MIMO Channel State Acquisition and Feedback

Contact Info

Product

Resources

About