Superposition coding csi feedback method based on deep learning
A technology of superposition coding and deep learning, which is applied in the field of superposition feedback of massive MIMO systems, can solve problems such as difficult to apply, large codebook dimension, and occupying spectrum resources, so as to improve detection performance, improve recovery accuracy, and simplify system architecture. Effect
Active Publication Date: 2021-06-04
XIHUA UNIV
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] The traditional codebook-based CSI scheme has a large number of antennas and requires a huge codebook dimension, which makes it difficult to apply; and the compressed sensing (CS, compressed sensing) feedback technology that utilizes the signal sparsity can reduce the feedback of the system to a certain extent. Overhead, but occupy a certain spectrum resources in the feedback process
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0049] The technical solution of the present invention will be further described in detail below in conjunction with the accompanying drawings, but the protection scope of the present invention is not limited to the following description.
[0050] Such as figure 1 As shown, the superposition coding CSI feedback method based on deep learning includes:
[0051] a: Client:
[0052] (a1) The user end reads the channel state information H with a length of N and the "uplink user sequence" D with a length of M;
[0053] (a2) Perform spread spectrum processing on the channel state information H to obtain a spread spectrum sequence H with a length of M spread ;
[0054] The matrix P is a Walsh spreading matrix, which satisfies P T P=MI N , the superscript "T" means the transpose operation, I N Represents the N-order identity matrix;
[0055] In this embodiment, the example of step a2) is as follows:
[0056] Assumption: N=4, M=8, H=(0.2+0.3j, 0.4+0.5j, 0.6+0.7j, 0.8+0.9j),
[...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The present invention discloses a deep learning-based superposition coding CSI feedback method, including: a: user end: (a1) the user end reads channel state information and uplink user sequence; (a2) performs spread spectrum processing on the channel state information, Obtaining the spread spectrum sequence; (a3) performing weighted superposition of the spread spectrum sequence and the uplink user sequence to obtain the superposition sequence; (a4) transmitting the superposition sequence by the user end. b: Base station side: (b1) The base station receives the received sequence; (b2) The base station recovers the channel state information and the uplink user sequence by using the trained multi-task neural network. Compared with non-superimposed coded CSI feedback, the present invention completely avoids uplink bandwidth resource occupation; compared with superimposed coded CSI feedback, the present invention can improve CSI recovery accuracy and improve uplink user sequence detection performance; at the same time, the present invention can also simplify the system architecture to reduce the processing complexity of the system.
Description
technical field [0001] The present invention relates to the technical field of superposition feedback of massive MIMO (multiple input multiple output) systems, in particular to a superposition coding CSI (Channel State Information) feedback method based on deep learning. Background technique [0002] As a key technology to meet the high spectral efficiency and energy efficiency of the future 5G (the fifth generation) network, the massive MIMO system can provide more power without increasing the transmission power and system bandwidth through hundreds of antennas deployed at the base station. The user provides wireless data service. At the same time, many performance-improving operations in massive MIMO systems (such as multi-user scheduling, rate allocation, and precoding at the transmitter, etc.) depend on the acquisition of accurate downlink channel state information (CSI, channel state information). In a frequency division duplex (FDD, frequency division duplex) massive ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): H04B7/0417H04B7/06H04B7/0413
CPCH04B7/0413H04B7/0417H04B7/0626
Inventor 卿朝进蔡斌阳庆瑶万东琴张岷涛郭奕
Owner XIHUA UNIV