Neural network design method and device for channel estimation
A channel estimation and neural network technology, applied in the field of neural network design methods and devices, can solve problems such as unreachable accuracy, and achieve the effects of meeting real-time requirements, reducing delay, and improving performance
Pending Publication Date: 2022-03-25
UNIV OF SCI & TECH BEIJING
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] In view of the lack of a neural network structure designed for wireless channel data characteristics in the prior art, and the problem that the expected accuracy cannot be achieved, the present invention proposes a neural network design method and device for channel estimation
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
[0047] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, the following will describe in detail with reference to the drawings and specific embodiments.
[0048] Such as figure 1 As shown, the embodiment of the present invention provides a neural network design method for channel estimation, including:
[0049] S101: Obtain the CSI change of the channel state estimate value at the current moment through the historical estimate value of the channel state, and model the CSI change as a first-order Markov model;
[0050] S102: Obtain the CSI conditional entropy through the first-order Markov model calculation, and the CSI conditional entropy represents the amount of information required to obtain the channel state information CSI matrix at the current moment;
[0051] S103: Construct a new cyclic neural network structure by using the obtained CSI conditional entropy, and the new cyclic neural network structu...
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 invention provides a neural network design method and device for channel estimation, and relates to the technical field of wireless communication. Comprising the following steps: calculating a current estimation value CSI entropy through a historical estimation value of a channel state; modeling the change of the CSI as a first-order Markov model, and obtaining the information amount required by a channel state information CSI matrix at the current moment; and constructing a new network structure by using the information amount required by the CSI matrix at the current moment, performing off-line training on the new neural network, determining a weight parameter and an offset parameter, and completing the neural network design for channel estimation. The invention provides a neural network structure which is independent of pilot frequency and is used for channel estimation, and strong time correlation characteristics of wireless channel data are evaluated by utilizing an information entropy theory so as to improve the performance of a channel estimation algorithm based on a neural network. According to the neural network structure for channel estimation, the channel estimation precision can be improved, the time delay of channel estimation is reduced, and the real-time requirement of a wireless communication system is met.
Description
technical field [0001] The present invention relates to the technical field of wireless communication, in particular to a neural network design method and device for channel estimation. Background technique [0002] The method and accuracy of channel estimation affect the transmission quality of the mobile communication system. The channel estimation algorithm obtains CSI (Channel State Information, channel state information) by mining and revealing the internal characteristics of the wireless transmission signal, such as inserting pilot signals, approximating the minimum error and nonlinear mapping, etc. At present, commonly used channel estimation methods include LS (Least Square, least squares), MMSE (Minimum Mean Square Error, minimum mean square error), LMMSE (Linear Minimum Mean Square Error, linear minimum mean square error), compressed sensing channel estimation algorithm, Neural network algorithms, etc., cannot obtain accurate results in the case of limited pilots....
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 Applications(China)
IPC IPC(8): G06N3/08G06N3/04G06F17/16
CPCG06N3/04G06N3/084G06F17/16
Inventor 陈月云买智源陈广董家辉杜利平韩双双
Owner UNIV OF SCI & TECH BEIJING