Non-codebook-based precoding based on downlink channel predictions

1 . A user equipment (UE), comprising:

one or more memories storing processor-executable code; and

one or more processors coupled with the one or more memories and individually or collectively operable to execute the code to cause the UE to:

receive control signaling indicating a channel state information reference signal resource and a sounding reference signal resource, the control signaling instructing the UE to transmit a sounding reference signal via the sounding reference signal resource;

receive, via the channel state information reference signal resource, a channel state information reference signal;

transmit, via the sounding reference signal resource, the sounding reference signal that is precoded based at least in part on predicted channel state information for a wireless channel resource that occurs in time after the sounding reference signal resource, wherein the predicted channel state information is based at least in part on the channel state information reference signal; and

transmit a control message indicating one or more differential values, wherein each of the one or more differential values indicates a respective time after the sounding reference signal resource at which the UE is to predict channel state information, and wherein each of the one or more differential values correspond to a respective sounding reference signal.

2 . The UE of claim 1 , wherein the one or more processors are individually or collectively further operable to execute the code to cause the UE to:

receive a request to indicate a capability of the UE to support channel state information prediction; and

transmit a capability message indicating the capability of the UE to support the channel state information prediction based at least in part on the request.

3 . The UE of claim 2 , wherein the capability message includes an indication of a maximum duration of time after the sounding reference signal resource at which the UE is to predict channel state information, a quantity of time durations for which the UE is to predict the channel state information, or any combination thereof.

4 . The UE of claim 1 , wherein, to transmit the sounding reference signal, the one or more processors are individually or collectively operable to execute the code to cause the UE to:

transmit the sounding reference signal that is precoded according to the predicted channel state information that is predicted at a first time after the sounding reference signal resource, and a second sounding reference signal that is precoded according to the predicted channel state information that is predicted at a second time after the sounding reference signal resource.

5 . The UE of claim 4 , wherein the one or more processors are individually or collectively further operable to execute the code to cause the UE to:

transmit an indication of the first time and the second time after the sounding reference signal resource.

6 . The UE of claim 1 , wherein the sounding reference signal is precoded based at least in part on the predicted channel state information corresponding to a time associated with the one or more differential values.

7 . The UE of claim 1 , wherein the control signaling instructs the UE to precode the sounding reference signal based at least in part on the predicted channel state information.

8 . A network entity, comprising:

one or more memories storing processor-executable code; and

one or more processors coupled with the one or more memories and individually or collectively operable to execute the code to cause the network entity to:

transmit control signaling indicating a channel state information reference signal resource and a sounding reference signal resource, the control signaling instructing a user equipment (UE) to transmit a sounding reference signal via the sounding reference signal resource;

transmit, via the channel state information reference signal resource, a channel state information reference signal;

receive, via the sounding reference signal resource, the sounding reference signal that is precoded based at least in part on predicted channel state information for a wireless channel resource that occurs in time after the sounding reference signal resource, wherein the predicted channel state information is based at least in part on the channel state information reference signal; and

receive a control message indicating one or more differential values, wherein each of the one or more differential values indicates a respective time after the sounding reference signal resource at which the UE is to predict channel state information, and wherein each for the one or more differential values correspond to a respective sounding reference signal.

9 . The network entity of claim 8 , wherein the one or more processors are individually or collectively further operable to execute the code to cause the network entity to:

transmit a request to indicate a capability of the UE to support channel state information prediction; and

receive a capability message indicating the capability of the UE to support the channel state information prediction based at least in part on the request.

10 . The network entity of claim 9 , wherein the capability message includes an indication of a maximum duration of time after the sounding reference signal resource at which the UE is to predict channel state information, a quantity of time durations at which the UE is to predict the channel state information, or any combination thereof.

11 . The network entity of claim 8 , wherein, to receive the sounding reference signal, the one or more processors are individually or collectively operable to execute the code to cause the network entity to:

receive the sounding reference signal that is precoded according to the predicted channel state information that is predicted at a first time after the sounding reference signal resource, and a second sounding reference signal that is precoded according to the predicted channel state information that is predicted at a second time after the sounding reference signal resource.

12 . The network entity of claim 11 , wherein the one or more processors are individually or collectively further operable to execute the code to cause the network entity to:

receive an indication of the first time and the second time after the sounding reference signal resource at which channel state information is predicted.

13 . The network entity of claim 8 , wherein the sounding reference signal is precoded based at least in part on the predicted channel state information corresponding to a time associated with the one or more differential values.

14 . The network entity of claim 8 , wherein the control signaling instructs the UE to precode the sounding reference signal based at least in part on the predicted channel state information.

15 . A method for wireless communications at a user equipment (UE), comprising:

receiving control signaling indicating a channel state information reference signal resource and a sounding reference signal resource, the control signaling instructing the UE to transmit a sounding reference signal via the sounding reference signal resource;

receiving, via the channel state information reference signal resource, a channel state information reference signal;

transmitting, via the sounding reference signal resource, the sounding reference signal that is precoded based at least in part on predicted channel state information for a wireless channel resource that occurs in time after the sounding reference signal resource, wherein the predicted channel state information is based at least in part on the channel state information reference signal; and

transmitting a control message indicating one or more differential values, wherein each of the one or more differential values indicates a respective time after the sounding reference signal resource at which the UE is to predict channel state information, and wherein each of the one or more differential values correspond to a respective sounding reference signal.

16 . A method for wireless communications at a network entity, comprising:

transmitting control signaling indicating a channel state information reference signal resource and a sounding reference signal resource, the control signaling instructing a user equipment (UE) to transmit a sounding reference signal via the sounding reference signal resource;

transmitting, via the channel state information reference signal resource, a channel state information reference signal;

receiving, via the sounding reference signal resource, the sounding reference signal that is precoded based at least in part on predicted channel state information for a wireless channel resource that occurs in time after the sounding reference signal resource, wherein the predicted channel state information is based at least in part on the channel state information reference signal; and

receiving a control message indicating one or more differential values, wherein each of the one or more differential values indicates a respective time after the sounding reference signal resource at which the UE is to predict channel state information, and wherein each for the one or more differential values correspond to a respective sounding reference signal.

17 . The method of claim 15 , further comprising:

receiving a request to indicate a capability of the UE to support channel state information prediction; and

transmitting a capability message indicating the capability of the UE to support the channel state information prediction based at least in part on the request.

18 . The method of claim 17 , wherein the capability message includes an indication of a maximum duration of time after the sounding reference signal resource at which the UE is to predict channel state information, a quantity of time durations for which the UE is to predict the channel state information, or any combination thereof.

19 . The method of claim 15 , wherein, transmitting the sounding reference signal includes:

transmitting the sounding reference signal that is precoded according to the predicted channel state information that is predicted at a first time after the sounding reference signal resource, and a second sounding reference signal that is precoded according to the predicted channel state information that is predicted at a second time after the sounding reference signal resource.

20 . The method of claim 19 , further comprising:

transmitting an indication of the first time and the second time after the sounding reference signal resource.

21 . The method of claim 15 , wherein the sounding reference signal is precoded based at least in part on the predicted channel state information corresponding to a time associated with the one or more differential values.

22 . The method of claim 15 , wherein the control signaling instructs the UE to precode the sounding reference signal based at least in part on the predicted channel state information.

23 . The method of claim 16 , further comprising:

transmitting a request to indicate a capability of the UE to support channel state information prediction; and

receiving a capability message indicating the capability of the UE to support the channel state information prediction based at least in part on the request.

24 . The method of claim 23 , wherein the capability message includes an indication of a maximum duration of time after the sounding reference signal resource at which the UE is to predict channel state information, a quantity of time durations at which the UE is to predict the channel state information, or any combination thereof.

25 . The method of claim 16 , wherein receiving the sounding reference signal includes:

receiving the sounding reference signal that is precoded according to the predicted channel state information that is predicted at a first time after the sounding reference signal resource, and a second sounding reference signal that is precoded according to the predicted channel state information that is predicted at a second time after the sounding reference signal resource.

26 . The method of claim 25 , further comprising:

receive an indication of the first time and the second time after the sounding reference signal resource at which channel state information is predicted.

27 . The method of claim 16 , wherein the sounding reference signal is precoded based at least in part on the predicted channel state information corresponding to a time associated with the one or more differential values.

28 . The method of claim 16 , wherein the control signaling instructs the UE to precode the sounding reference signal based at least in part on the predicted channel state information.