| CPC H04B 17/391 (2015.01) [H04L 5/0051 (2013.01); H04L 5/0064 (2013.01)] | 1 Claim |
|
1. A first device comprising:
at least one processor; and
at least one memory
storing instructions that, when executed by the at least one processor, cause the first device at least to:
receive from a second device a reference signal on an uplink channel, wherein the second device comprises a terminal device, and wherein the first device is caused to receive the reference signal by monitoring the uplink channel for receiving the reference signal during a predetermined period;
determine first channel information on the uplink channel based at least in part on the received reference signal, wherein the first device comprises a network device, and wherein the first device is caused to determine the first uplink channel information by:
determining an original reference signal transmitted by the second device; and
determining the first uplink channel information based on the original reference signal and the received reference signal;
extract second channel information on the uplink channel from the first channel information, the second channel information being generated based on the first channel information, wherein the first device is caused to extract the second channel information by compressing the first channel information to obtain the second channel information, wherein the second channel information has less information than the first channel information, and wherein the first channel information is quantized to obtain the second channel information;
train, based on the first channel information and the second channel information, a data processing model to be used for recovering channel information on a downlink channel between the first device and the second device, wherein the model includes a clustered model which is written as
 where MT is an array at the first device, MR is an array at the second device, Nc denotes a number of clusters, Np denotes a number of rays and/or paths within one cluster, αil denotes a complex channel gain of an i-th cluster and an 1-th path and follows a complex normal distribution CN(0,1), φil and θil are uniformly distributed within [0, 2π] and denote an angle of arrival and an angle of departure, respectively, and aR(ϕil) and aT(θil) are array response vectors of the second device and the first device at angles of ϕil, θil, respectively, wherein the first device is caused to train the data processing model by iteratively performing the following:
recovering the second channel information using the data processing model;
comparing the recovered second channel information with the first channel information by applying a loss function, where in the loss function is a Mean Squared Error (MSE) of a channel estimation; and
updating the data processing model based on the comparison, until a difference between the recovered second channel information and the first channel information being less than a threshold value;
determining a compensation parameter based on a first frequency of the uplink channel and a second frequency of the downlink channel;
compensating a phase of the received reference signal based on the compensation parameter;
transmitting a further reference signal on the downlink channel to the second device;
receiving from the second device a feedback to the further reference signal, the feedback comprising extracted channel information on the downlink channel; and
recovering the extracted channel information on the downlink channel from the feedback using the data processing model.
|