US 12,706,646 B2 · Artificial intelligence-enabled link adaptation

Abstract

Signaling resource overhead associated with current communication link adaptation mechanisms can be quite large and such mechanisms typically rely upon a channel state information (CSI) feedback process that can result in poor scheduling performance. Embodiments are disclosed in which a first device channel state information characterizing a wireless communication channel between the first device and a second device, and trains a machine learning (ML) module of the first device using the CSI as an ML module input and one or more modulation and coding scheme (MCS) parameters as an ML module output to satisfy a training target. By applying the concepts disclosed herein, overhead associated with feedback for MCS selection may be reduced compared to conventional link adaptation procedures, because, once ML modules at a pair of devices have been trained, the MCS selection by the ML modules can be done without requiring the ongoing feedback of CSI.

Claims20

Dependent claims

A method in a first device in a wireless communication network, the method comprising:

obtaining channel state information characterizing a wireless communication channel between the first device and a second device in the wireless communication network;
training a machine learning (ML) module of the first device using the channel state information as an ML module input and one or more modulation and coding scheme (MCS) parameters as an ML module output to satisfy a training target, the one or more MCS parameters including a predicted modulation order, a predicted coding rate or both, wherein the ML module of the first device and a further ML module of the second device are trained to predict the same one or more MCS parameters.

A method in a first device in a wireless communication network, the method comprising:

obtaining channel state information characterizing a wireless communication channel between the first device and a second device in the wireless communication network;
and
obtaining, based on the channel state information as an input to a machine learning (ML) module of the first device that has been trained using channel state information characterizing a wireless communication channel between the first device and the second device in the wireless communication network as an ML module input and one or more modulation and coding scheme (MCS) parameters as an ML module output, one or more MCS parameters for communication between the first device and the second device, the one or more MCS parameters including a predicted modulation order, a predicted coding rate or both;
and
transmitting to or receiving from the second device over the wireless communication channel using the one or more MCS parameters, wherein the ML module of the first device and a further ML module of the second device are trained to predict the same one or more MCS parameters.

2 more elements

A device comprising:

a memory storing processor-executable instructions;
and
a processor for executing the processor-executable instructions to cause the device to:
obtain channel state information characterizing a wireless communication channel between the device and a second device in a wireless communication network;
and
obtain, based on the channel state information as an input to a machine learning (ML) module of the device that has been trained using channel state information characterizing a wireless communication channel between the device and the second device in the wireless communication network as an ML module input and one or more modulation and coding scheme (MCS) parameters as an ML module output, one or more MCS parameters for communication between the device and the second device, the one or more MCS parameters including a predicted modulation order, a predicted coding rate or both;
and
transmit to or receive from the second device over the wireless communication channel using the one or more MCS parameters, wherein the ML module of the device and a further ML module of the second device are trained to predict the same one or more MCS parameters.

5 more elements

Dependencies are inferred from the claim text.

Artificial intelligence-enabled link adaptation

Life of this patent

Artificial intelligence-enabled link adaptation

Life of this patent

Abstract

Claims20