Millimeter wave sparse array plane channel estimation method based on deep learning network

Abstract

The invention discloses a millimeter wave sparse array plane channel estimation method based on a deep learning network, which takes millimeter wave channel sparse characteristics as priori information to train a designed full-connection deep neural network for millimeter wave array plane communication channel estimation. Firstly, a full-connection phase shifter network is adopted, and isotropic analog transceivers are designed by configuring phase uniform distribution of phase shifters; and the obtained channel sparse information and the designed optimal digital estimator are taken as training data of the full-connection deep learning network. For the sparse channel under each signal-to-noise ratio, the sparse information of the channel is input into a network to obtain a corresponding digital estimator, thereby obtaining a channel estimation result. The sparse channel estimator provided by the invention can reduce errors caused by nonlinear quantization of a low-precision analog-to-digital converter, and is realized by using a deep learning network, so that the channel estimation complexity is reduced, and the performance of the sparse channel estimator can approach to a theoretically optimal channel estimation method.

Description

technical field [0001] The present invention relates to the field of communication, to a channel estimation method, and more specifically to a millimeter-wave sparse front channel estimation method based on a deep learning network. Background technique [0002] In recent years, communication technology has made a breakthrough and gradually matured, and the mobile communication industry has developed rapidly worldwide. Multiple Input Multiple Output (MIMO) technology is one of the key technologies in the development of communication technology, which improves the data transmission rate of the system. The transmitting end and the receiving end of the system are equipped with multiple antennas, and multiple antennas at the transmitting and receiving ends are used to form diversity, which can improve system stability. At the same time, due to the large increase in the number of independent channels between the antennas at the transmitting and receiving ends, the amount of data ...

AI Technical Summary

Problems solved by technology

Channel estimation in traditional large-scale multi-antenna technology systems is a big challenge in itself. The use of low-precision analog-to-digital converters in hybrid architectures makes channel estimation more difficult while

Images