Spectral efficiency prediction with artificial intelligence for enhancing carrier aggregation and proactive radio resource management

1. An apparatus comprising:

at least one processor; and

at least one non-transitory memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to:

transmit an indication of a transformation function to a user equipment, wherein at least one input to the transformation function comprises a location of the user equipment and at least one measurement of a radio channel;

receive a representation from the user equipment, the representation comprising a result of a calculation using the transformation function and the at least one input to the transformation function;

wherein the result of the calculation using the transformation function comprises at least one value different from values associated with the location of the user equipment, and different from values associated with the at least one measurement of the radio channel, wherein the at least one value comprises a transformation of the values associated with the location of the user equipment and the at least one measurement of the radio channel; and

determine, based on the representation and primary cell related measurements, a channel quality of at least one secondary cell or an identity of at least one secondary cell.

2. The apparatus of claim 1 , wherein the channel quality of the at least one secondary cell is determined using a machine learning model trained using data collected from a plurality of user equipments for which the at least one secondary cell has been activated, wherein the data comprises results of calculations using the transformation function, and a previously known channel quality of a secondary cell.

3. The apparatus of claim 1 , wherein the instructions, when executed by the at least one processor, cause the apparatus at least to:

select the at least one secondary cell for the user equipment for carrier aggregation using the determined channel quality of the at least one secondary cell;

wherein the channel quality of the at least one secondary cell is determined using a machine learning model trained at least using results of calculations performed by at least one user equipment using the transformation function, and a previously known channel quality of a secondary cell; and

transmit, to the user equipment, a configuration comprising the selected at least one secondary cell for the user equipment for carrier aggregation.

4. The apparatus of claim 1 , wherein the determined channel quality of the at least one secondary cell is used for radio resource management.

5. The apparatus of claim 1 , wherein the location of the user equipment and the at least one measurement of the radio channel are not within the representation received from the user equipment, the representation comprising the result of the calculation using the transformation function and the at least one input to the transformation function.

6. The apparatus of claim 1 , wherein the instructions, when executed by the at least one processor, cause the apparatus at least to:

transmit an indication of which specific measurement is to be used as the at least one measurement of the radio channel which is to be used as the at least one input to the transformation function.

7. The apparatus of claim 1 , wherein the representation comprising the result of the calculation using the transformation function received from the user equipment comprises an encoded representation having less data than the at least one measurement of the radio channel or the location of the user equipment.

8. The apparatus of claim 1 , wherein the transformation function is a machine learning model.

9. The apparatus of claim 1 , wherein the channel quality of the at least one secondary cell is further determined using at least one of:

a load of the at least one secondary cell;

at least one primary cell measurement of a primary cell made by the apparatus;

activity of neighboring cells of the at least one secondary cell;

activity of neighboring cells of the primary cell; or

locations of transmission points of the primary cell and the at least one secondary cell.

10. The apparatus of claim 1 , wherein the instructions, when executed by the at least one processor, cause the apparatus at least to:

accumulate training data, wherein the training data comprises:

a plurality of representations determined using the transformation function, the transformation function using user equipment location as input, from a plurality of user equipments for which respective secondary cells have been selected;

at least one measurement determined with the radio access network; and

respective spectral efficiencies of the plurality of user equipments on the respective secondary cells, the respective spectral efficiencies being labels for the training data.

11. The apparatus of claim 10 , wherein the instructions, when executed by the at least one processor, cause the apparatus at least to:

train a machine learning model using the training data.

12. The apparatus of claim 10 , wherein the instructions, when executed by the at least one processor, cause the apparatus at least to:

provide the training data to a machine learning training server; and

receive a trained machine learning model from the training server.

13. The apparatus of claim 1 , wherein transmitting the indication of the transformation function comprises transmitting an indication of parameters for the user equipment to use for computing the transformation function.

14. The apparatus of claim 1 , wherein the instructions, when executed by the at least one processor, cause the apparatus at least to;

transmit, from a radio access network node to an inference server, the representation comprising the result of the calculation using the transformation function, wherein the apparatus comprises the radio access network node; and

receive, with the radio access network node from the inference server, based on the representation comprising the result of the calculation using the transformation function, the channel quality of the at least one secondary cell or the identity of the at least one secondary cell.

15. The apparatus of claim 1 , wherein the instructions, when executed by the at least one processor, cause the apparatus at least to:

determine at least one measurement performed with the apparatus or received from cells neighboring the apparatus, wherein the apparatus comprises a radio access network node; and

transmit, to an inference server, the at least one measurement performed with the apparatus or received from cells neighboring the apparatus;

receive, from the inference server, the channel quality of the at least one secondary cell or the identity of the at least one secondary cell;

wherein the r channel quality of the at least one secondary cell or the identity of the at least one secondary cell received from the inference server is based on the at least one measurement performed with the apparatus or received from cells neighboring the apparatus.

16. An apparatus comprising:

at least one processor; and

at least one non-transitory memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to:

receive, from a radio access network, a representation comprising a result of a calculation using a transformation function and at least one input to the transformation function;

wherein at least one input to the transformation function comprises a location of a user equipment and at least one measurement of a radio channel;

wherein the result of the calculation using the transformation function comprises at least one value different from values associated with the location of the user equipment, and different from values associated with the at least one measurement of the radio channel, wherein the at least one value comprises a transformation of the values associated with the location of the user equipment and the at least one measurement of the radio channel;

determine, based on the representation and primary cell related measurements, a channel quality of at least one secondary cell or an identity of at least one secondary cell; and

transmit, to the radio access network, the channel quality of the at least one secondary cell or the identity of the at least one secondary cell.