Transmission mode adaptation in new radio with AI/ML assistance

1 . A base station (BS) comprising:

a transceiver configured to receive a set of input metrics, wherein the set of input metrics comprises at least one metric derived from a channel state information (CSI) report; and

a processor operably coupled to the transceiver, the processor configured to:

determine, based on the set of input metrics, a first multiple-input multiple-output (MIMO) mode throughput prediction and a second MIMO mode throughput prediction;

generate, based on the first MIMO mode throughput prediction, a predicted first MIMO mode throughput result;

generate, based on the second MIMO mode throughput prediction, a predicted second MIMO mode throughput result; and

select a MIMO mode from among a precoding matrix indicator (PMI) mode and a transmit antenna selection (TAS) mode based on the predicted first MIMO mode throughput result and the predicted second MIMO mode throughput result.

2 . The BS of claim 1 , wherein,

the MIMO mode is selected based on one of a deterministic selection procedure and a probabilistic selection procedure,

the first MIMO mode is a precoding matrix indicator (PMI) mode, and

the second MIMO mode is a transmit antenna selection (TAS) mode.

3 . The BS of claim 1 , wherein the set of input metrics further comprises at least one metric derived from a sounding reference signal (SRS).

4 . The BS of claim 1 , wherein the processor is further configured to:

select a first MIMO mode throughput prediction model based on a first MIMO mode throughput prediction error history and a first MIMO mode throughput prediction model selection history, wherein the first MIMO mode throughput prediction is determined based on the selected first MIMO mode throughput prediction model; and

select a second MIMO mode throughput prediction model based on a second MIMO mode throughput prediction error history and a second MIMO mode throughput prediction model selection history, wherein the second MIMO mode throughput prediction is determined based on the selected second MIMO mode throughput prediction model,

wherein the MIMO mode is selected based on the predicted first MIMO mode throughput result given the selected first MIMO mode throughput prediction model, the predicted second MIMO mode throughput result given the selected second MIMO mode throughput prediction model, and a corresponding model uncertainty.

5 . The BS of claim 4 , wherein the processor is further configured to update parameters related to the first and second MIMO mode throughput prediction models.

6 . The BS of claim 4 , wherein the first and second MIMO mode throughput prediction models are selected based on a condition of a communications channel.

7 . The base station of claim 1 , wherein the processor is further configured to:

determine, from a set of first MIMO mode throughput prediction models, a subset of first MIMO mode throughput prediction models based on a first MIMO mode throughput prediction error history and a first MIMO mode throughput prediction model selection history, wherein the first MIMO mode throughput prediction is determined based on a first combination result from the determined subset of first MIMO mode throughput prediction models; and

determine, from a set of second MIMO mode throughput prediction models, a subset of second MIMO mode prediction models based on a second MIMO mode throughput prediction error history and a second MIMO mode throughput model selection history, wherein the second MIMO mode throughput prediction is determined based on a second combination result from the determined subset of second MIMO mode throughput prediction models,

wherein the MIMO mode is selected based on the predicted first MIMO mode throughput result given the first combination result, the predicted second MIMO mode throughput result given the second combination result, and a corresponding model uncertainty.

8 . A method of operating a base station (BS) comprising:

receiving a set of input metrics, wherein the set of input metrics comprises at least one metric derived from a channel state information (CSI) report;

determining, based on the set of input metrics, a first multiple-input multiple-output (MIMO) mode throughput prediction and a second MIMO mode throughput prediction;

generating, based on the first MIMO mode throughput prediction, a predicted first MIMO mode throughput result;

generating, based on the second MIMO mode throughput prediction, a predicted second MIMO mode throughput result; and

selecting a MIMO mode from among a precoding matrix indicator (PMI) mode and a transmit antenna selection (TAS) mode based on the predicted first MIMO mode throughput result and the predicted second MIMO mode throughput result.

9 . The method of claim 8 , wherein,

the MIMO mode is selected based on one of a deterministic selection procedure and a probabilistic selection procedure,

the first MIMO mode is a precoding matrix indicator (PMI) mode, and

the second MIMO mode is a transmit antenna selection (TAS) mode.

10 . The method of claim 8 , wherein the set of input metrics further comprises at least one metric derived from a sounding reference signal (SRS).

11 . The method of claim 8 , further comprising:

selecting a first MIMO mode throughput prediction model based on a first MIMO mode throughput prediction error history and a first MIMO mode throughput prediction model selection history, wherein the first MIMO mode throughput prediction is determined based on the selected first MIMO mode throughput prediction model; and

selecting a second MIMO mode throughput prediction model based on a second MIMO mode throughput prediction error history and a second MIMO mode throughput prediction model selection history, wherein the second MIMO mode throughput prediction is determined based on the selected second MIMO mode throughput prediction model,

wherein the MIMO mode is selected based on the predicted first MIMO mode throughput result given the selected first MIMO mode throughput prediction model, the predicted second MIMO mode throughput result given the selected second MIMO mode throughput prediction model, and a corresponding model uncertainty.

12 . The method of claim 11 , further comprising updating parameters related to the first and second MIMO mode throughput prediction models.

13 . The method of claim 11 , wherein the first and second MIMO mode throughput prediction models are selected based on a condition of a communications channel.

14 . The method of claim 8 , further comprising:

determining, from a set of first MIMO mode throughput prediction models, a subset of first MIMO mode throughput prediction models based on a first MIMO mode throughput prediction error history and a first MIMO mode throughput prediction model selection history, wherein the first MIMO mode throughput prediction is determined based on a first combination result from the determined subset of first MIMO mode throughput prediction models; and

determining, from a set of second MIMO mode throughput prediction models, a subset of second MIMO mode prediction models based on a second MIMO mode throughput prediction error history and a second MIMO mode throughput model selection history, wherein the second MIMO mode throughput prediction is determined based on a second combination result from the determined subset of second MIMO mode throughput prediction models,

wherein the MIMO mode is selected based on the predicted first MIMO mode throughput result given the first combination result, the predicted second MIMO mode throughput result given the second combination result, and a corresponding model uncertainty.

15 . A non-transitory computer readable medium embodying a computer program, the computer program comprising program code that, when executed by a processor of a device, causes the device to:

receive a set of input metrics, wherein the set of input metrics comprises at least one metric derived from a channel state information (CSI) report;

determine, based on the set of input metrics, a first multiple-input multiple-output (MIMO) mode throughput prediction and a second MIMO mode throughput prediction;

generate, based on the first MIMO mode throughput prediction, a predicted first MIMO mode throughput result;

generate, based on the second MIMO mode throughput prediction, a predicted second MIMO mode throughput result; and

select a MIMO mode from among a precoding matrix indicator (PMI) mode and a transmit antenna selection (TAS) mode based on the predicted first MIMO mode throughput result and the predicted second MIMO mode throughput result.

16 . The non-transitory computer readable medium of claim 15 , wherein:

the MIMO mode is selected based on one of a deterministic selection procedure and a probabilistic selection procedure,

the first MIMO mode is a precoding matrix indicator (PMI) mode, and

the second MIMO mode is a transmit antenna selection (TAS) mode.

17 . The non-transitory computer readable medium of claim 15 , wherein the set of input metrics further comprises at least one metric derived from a sounding reference signal (SRS).

18 . The non-transitory computer readable medium of claim 15 , wherein the computer program further comprises computer readable program code that, when executed by the processor, causes the device to:

select a first MIMO mode throughput prediction model based on a first MIMO mode throughput prediction error history and a first MIMO mode throughput prediction model selection history, wherein the first MIMO mode throughput prediction is determined based on the selected first MIMO mode throughput prediction model; and

select a second MIMO mode throughput prediction model based on a second MIMO mode throughput prediction error history and a second MIMO mode throughput prediction model selection history, wherein the second MIMO mode throughput prediction is determined based on the selected second MIMO mode throughput prediction model,

wherein the MIMO mode is selected based on the predicted first MIMO mode throughput result given the selected first MIMO mode throughput prediction model, the predicted second MIMO mode throughput result given the selected second MIMO mode throughput prediction model, and a corresponding model uncertainty.

19 . The non-transitory computer readable medium of claim 18 , wherein the first and second MIMO mode throughput prediction models are selected based on a condition of a communications channel, and the computer program further comprises computer readable program code that when executed by the processor causes the device to update parameters related to the first and second MIMO mode throughput prediction models.

20 . The non-transitory computer readable medium of claim 15 , wherein the computer program further comprises computer readable program code that when executed by the processor causes the device to:

determine, from a set of first MIMO mode throughput prediction models, a subset of first MIMO mode throughput prediction models based on a first MIMO mode throughput prediction error history and a first MIMO mode throughput prediction model selection history, wherein the first MIMO mode throughput prediction is determined based on a first combination result from the determined subset of first MIMO mode throughput prediction models; and

determine, from a set of second MIMO mode throughput prediction models, a subset of second MIMO mode prediction models based on a second MIMO mode throughput prediction error history and a second MIMO mode throughput model selection history, wherein the second MIMO mode throughput prediction is determined based on a second combination result from the determined subset of second MIMO mode throughput prediction models,

wherein the MIMO mode is selected based on the predicted first MIMO mode throughput result given the first combination result, the predicted second MIMO mode throughput result given the second combination result, and a corresponding model uncertainty.