A Channel Information Compression Feedback Method Using Bit-Level Optimal Network

Abstract

The invention discloses a channel information compression feedback method using a bit-level optimization network. First, the channel matrix in the frequency domain is transformed into the angle-time delay domain by using two-dimensional Fourier transform, and then the complex matrix is ​​split into two real The sub-matrix is ​​counted and spliced; the encoding network extracts channel features through a composite residual network, and compresses the channel feature dimension through a fully connected network, and finally quantizes each real number into a 4-bit binary symbol through a quantizer; the decoding network converts the received The binary bit stream is mapped into a real code word, and then the dimension is expanded through a fully connected network, and finally the channel information is recovered through two composite residual networks; the method of the present invention introduces a composite residual network and provides a bit-level optimized The network training method effectively improves the compression and recovery performance of channel information. The trained bit-level optimized neural network can perform channel compression feedback more efficiently and has obvious performance advantages.

Description

technical field [0001] The invention belongs to the technical field of compressed sensing and channel information recovery, relates to a channel information compression feedback network method, in particular to a channel information compression feedback method using a bit-level optimized network. Background technique [0002] In massive MIMO, the base station is equipped with a large number of antennas, so that the uplink channel information feedback needs to consume a lot of resources. Usually, the channel information matrix of massive MIMO is very sparse, and its efficient compression can well reduce the cost of feedback. However, the traditional codebook-based method cannot be used when the channel matrix is ​​very large due to the exponential relationship between its calculation and storage costs and the number of feedback bits; the method based on compressed sensing is difficult to recover when the feedback bits are small. However, the current neural network-based comp...

AI Technical Summary

Problems solved by technology

[0003] In order to solve the above problems, the present invention discloses a channel information compression feedback method using a bit-level optimized network, designs a more efficient convolution structure, and adopts a bit-level optimized network design, thereby greatly improving network performance , which can solve the problem of low feedback accuracy of existing methods on the channel compression feedback problem

Images