Deep Learning Based Trainable Approximate Message Passing for Massive MIMO Detection

Zheng，Peicong1; Zeng，Yuan2; Liu，Zhenrong2; Gong，Yi2

10.1109/ICC40277.2020.9148845

2020-06-01

1550-3607

978-1-7281-5090-1

IEEE International Conference on Communications

2020-June

1-6

7-11 June 2020

Dublin, Ireland

In this paper, we present a deep learning based trainable approximate message passing algorithm (TAMP) for signal detection in massive multiple-input multiple-output (MIMO) systems. The TAMP network consists of a preprocessing layer and a fixed number of detection layers, where the preprocessing layer is designed by using a standard fully connected layer, and the structure of each detection layer is derived by unfolding each iteration of the iterative GAMP algorithm. In addition, the proposed TAMP includes trainable parameters controlling prior mean and variance of minimum mean squared error (MMSE) denoiser. The parameters are trained by standard deep learning techniques. We evaluate the signal detection performance of the proposed TAMP under Rayleigh-fading and spatial correlated MIMO channels. Furthermore, we compare TAMP with existing state-of-the-art iterative message passing-based detection algorithms and deep learning based detection algorithms. Computer experiments show that TAMP is applicable under both Rayleigh-fading and spatial correlated channel in massive MIMO systems. Moreover, comparison results demonstrate that TAMP can achieve better detection accuracy and faster convergence.

approximate message passing Deep learning MIMO detection

其他

英语

EI

20203409063856

Message passing ; Deep learning ; Learning algorithms ; Mean square error ; Iterative methods ; MIMO systems ; Learning systems ; Rayleigh fading

Ergonomics and Human Factors Engineering:461.4 ; Information Theory and Signal Processing:716.1 ; Radio Systems and Equipment:716.3 ; Computer Programming:723.1 ; Data Processing and Image Processing:723.2 ; Machine Learning:723.4.2 ; Numerical Methods:921.6 ; Mathematical Statistics:922.2

2-s2.0-85089408712

Scopus

1.Peng Cheng Laboratory,Shenzhen,China
2.Southern University of Science and Technology,Shenzhen,China

Zheng，Peicong,Zeng，Yuan,Liu，Zhenrong,et al. Deep Learning Based Trainable Approximate Message Passing for Massive MIMO Detection[C],2020:1-6.