CN-122003821-A - Apparatus and method for negotiation and signaling for cooperative control of power amplifier nonlinearity

Abstract

Apparatus and methods for negotiation and signaling of cooperative control of power amplifier nonlinearities are disclosed. At least some example embodiments may allow signaling to support the design and deployment of cooperative control of power amplifier nonlinearities for digital pre-distortion (DPD) applications in user equipment and digital post-distortion (DPoD) applications in network nodes, where digital pre-distortion may be used to control out-of-band emissions (e.g., adjacent Channel Leakage Ratio (ACLR)) and digital post-distortion may be used to control in-band emissions (e.g., error Vector Magnitude (EVM)).

Inventors

• O-e. barb
• FERIDOON JALILI
• D. J. kolpi
• S. Rezai

Assignees

• 诺基亚技术有限公司

Dates

Publication Date

20260508

Application Date

20230926

Claims (20)

1. 1. A user equipment (200), comprising: at least one processor (202), and At least one memory (204) storing instructions that, when executed by the at least one processor (202), cause the user equipment (200) to at least: Performing a negotiation procedure with a network node (210) for cooperative power amplifier nonlinear control with the network node (210), wherein the negotiation procedure comprises negotiating whether the user equipment (200) performs training of a first machine learning model (251) adapted for controlling digital pre-distortion of in-band emissions before or after training of a second machine learning model (252) adapted for controlling digital post-distortion of in-band emissions; In the case that the training of the first machine learning model (251) is performed before the training of the second machine learning model (252): Transmitting information about the training completion of the first machine learning model (251) and information for tagging input data for the training of the second machine learning model (252) to the network node (210), and In the case where the training of the first machine learning model (251) is performed after the training of the second machine learning model (252): Information about output parameters of the training of the second machine learning model (252) is received from the network node (210) and the training of the first machine learning model (251) is performed using the information.
2. 2. The user equipment (200) according to claim 1, wherein the negotiation procedure further comprises sending a request to the network node (210) for the training of the first machine learning model (251) and/or the training of the second machine learning model (252), or receiving a request from the network node (210) for the training of the first machine learning model (251) and/or the training of the second machine learning model (252).
3. 3. The user equipment (200) according to claim 1 or claim 2, wherein the negotiation procedure further comprises coordination signaling for using a common cost function.
4. 4. A user equipment (200) according to any of claims 1 to 3, wherein the negotiation procedure further comprises a control of the duration of the training of the first machine learning model (251) and/or the training of the second machine learning model (252).
5. 5. The user equipment (200) according to any of claims 1 to 4, wherein the first machine learning model (251) is adapted to control an adjacent channel leakage ratio and the second machine learning model (252) is adapted to control an error vector magnitude.
6. 6. The user equipment (200) according to any of claims 1 to 5, wherein the instructions, when executed by the at least one processor (202), further cause the user equipment (200) to: determining to use another first machine learning model; transmitting an indication of the further first machine learning model to the network node (210), and If a training is required, The negotiation process is performed with respect to the further first machine learning model and a second machine learning model associated with the further first machine learning model.
7. 7. A network node (210), comprising: At least one processor (212), and At least one memory (214) storing instructions that, when executed by the at least one processor (212), cause the network node (210) to at least: performing a negotiation procedure with a user equipment (200) for cooperative power amplifier nonlinear control with the user equipment (200), wherein the negotiation procedure comprises negotiating whether the user equipment (200) performs training of a first machine learning model (251) adapted for controlling digital pre-distortion of in-band emissions before or after training of a second machine learning model (252) adapted for controlling digital post-distortion of in-band emissions; In the case that the training of the first machine learning model (251) is performed before the training of the second machine learning model (252): Receiving information about the training completion of the first machine learning model (251) and information for tagging input data for the training of the second machine learning model (252) from the user equipment (200) and performing the training of the second machine learning model (252), and In the case where the training of the first machine learning model (251) is performed after the training of the second machine learning model (252): -sending information about output parameters of the training of the second machine learning model (252) to the user equipment (200) for the training of the first machine learning model (251).
8. 8. The network node (210) of claim 7, wherein the negotiation process further comprises receiving a request from the user equipment (200) for the training of the first machine learning model (251) and/or the training of the second machine learning model (252), or sending a request to the user equipment (200) for the training of the first machine learning model (251) and/or the training of the second machine learning model (252).
9. 9. The network node (210) of claim 7 or claim 8, wherein the negotiation procedure further comprises coordination signaling for using a common cost function.
10. 10. The network node (210) of any one of claims 7 to 9, wherein the negotiation process further comprises control of a duration of the training of the first machine learning model (251) and/or the training of the second machine learning model (252).
11. 11. The network node (210) of any one of claims 7 to 10, wherein the first machine learning model (251) is adapted to control an adjacent channel leakage ratio and the second machine learning model (252) is adapted to control an error vector magnitude.
12. 12. The network node (210) of any one of claims 7 to 11, wherein the instructions, when executed by the at least one processor (212), further cause the network node (210) to: receiving an indication of another first machine learning model determined to be used from the user equipment (200), and If a training is required, The negotiation process is performed with respect to the further first machine learning model and a second machine learning model associated with the further first machine learning model.
13. 13. A method (700), comprising: -performing (701-705) a negotiation procedure with a network node (210) by a user equipment (200) for cooperative power amplifier non-linear control with the network node (210), wherein the negotiation procedure comprises negotiating (705) whether the user equipment (200) performs training of a first machine learning model (251) adapted for controlling digital pre-distortion of an out-of-band transmission before or after training of a second machine learning model (252) adapted for controlling digital post-distortion of an in-band transmission; In the case that the training of the first machine learning model (251) is performed before the training of the second machine learning model (252): Transmitting (707) information from the user equipment (200) to the network node (210) about the training completion of the first machine learning model (251) and information for tagging input data for the training of the second machine learning model (252), and In the case where the training of the first machine learning model (251) is performed after the training of the second machine learning model (252): -receiving (708) information from the network node (210) at the user equipment (200) about output parameters of the training of the second machine learning model (252), and-performing (709) the training of the first machine learning model (251) by the user equipment (200) using the information.
14. 14. The method (700) of claim 13, wherein the negotiating procedure further comprises sending a request from the user equipment (200) to the network node (210) for the training of the first machine learning model (251) and/or the training of the second machine learning model (252), or receiving a request at the user equipment (200) from the network node (210) for the training of the first machine learning model (251) and/or the training of the second machine learning model (252).
15. 15. The method (700) of claim 13 or claim 14, wherein the negotiation procedure further comprises coordination signaling for using a common cost function.
16. 16. The method (700) according to any of claims 13-15, wherein the negotiation procedure further comprises control of a duration of the training of the first machine learning model (251) and/or the training of the second machine learning model (252).
17. 17. The method (700) according to any of claims 13-16, wherein the first machine learning model (251) is adapted to control adjacent channel leakage ratio and the second machine learning model (252) is adapted to control error vector magnitude.
18. 18. The method (700) according to any one of claims 13-17, further comprising: determining (710) by the user device (200) to use another first machine learning model; -transmitting (711) an indication of the further first machine learning model from the user equipment (200) to the network node (210), and If a training is required, -Performing (701-705), by the user equipment (200), the negotiation procedure with respect to the further first machine learning model and a second machine learning model related to the further first machine learning model.
19. 19. A method (800) comprising: -performing (801-805) a negotiation procedure with a user equipment (200) by a network node (210) for cooperative power amplifier non-linear control with the user equipment (200), wherein the negotiation procedure comprises negotiating (805) whether the user equipment (200) performs training of a first machine learning model (251) adapted for controlling digital pre-distortion of in-band emissions before or after training of a second machine learning model (252) adapted for controlling digital post-distortion of in-band emissions; In the case that the training of the first machine learning model (251) is performed before the training of the second machine learning model (252): -receiving (806) information about the training completion of the first machine learning model (251) and information for tagging input data for the training of the second machine learning model (252) from the user equipment (200) at the network node (210), and-performing (807) the training of the second machine learning model (252) by the network node (210), -and In the case where the training of the first machine learning model (251) is performed after the training of the second machine learning model (252): -transmitting (809) information from the network node (210) to the user equipment (200) about output parameters of the training of the second machine learning model (252) for the training of the first machine learning model (251).
20. 20. The method (800) of claim 19, wherein the negotiation process further comprises receiving, at the network node (210), a request from the user device (200) for the training of the first machine learning model (251) and/or the training of the second machine learning model (252), or sending, from the network node (210) to the user device (200), a request for the training of the first machine learning model (251) and/or the training of the second machine learning model (252).

Description

Apparatus and method for negotiation and signaling for cooperative control of power amplifier nonlinearity Technical Field The present disclosure relates generally to communications, and more particularly, but not exclusively, to negotiating and signaling for cooperative control of power amplifier nonlinearities. Background A power amplifier used in a radio transmitter, for example, included in a user equipment such as a mobile phone, may have non-linearities or distortions that need to be controlled to improve power efficiency and overall performance. Furthermore, strict transmission requirements have been introduced for user equipment in fifth generation (5G) and sixth generation (6G) wireless networks, for example. Thus, at least in some cases, it may be desirable to control non-linearities in a power amplifier used in a user equipment radio transmitter in a manner that also takes into account transmission requirements. Disclosure of Invention The scope of protection sought for the various exemplary embodiments of the present invention is set forth in the independent claims. Example embodiments and features (if any) described in this specification that do not fall within the scope of the independent claims are to be construed as examples useful for understanding the various example embodiments of the invention. An example embodiment of a user equipment includes at least one processor and at least one memory storing instructions that, when executed by the at least one processor, cause the user equipment to perform a negotiation process with a network node for at least cooperative power amplifier nonlinear control with the network node, wherein the negotiation process includes negotiating whether the user equipment performs training of a first machine learning model adapted to control digital pre-distortion of in-band transmission before or after training of a second machine learning model adapted to control digital post-distortion of in-band transmission. In the case where the training of the first machine learning model is performed prior to the training of the second machine learning model, the instructions, when executed by the at least one processor, further cause the user equipment to at least send information about the completion of the training of the first machine learning model and information for tagging input data for the training of the second machine learning model to the network node. In the case where the training of the first machine learning model is performed after the training of the second machine learning model, the instructions, when executed by the at least one processor, further cause the user equipment to at least receive information from the network node regarding output parameters of the training of the second machine learning model and perform the training of the first machine learning model with the information. In an example embodiment, the negotiation process further comprises, alternatively or additionally to the above example embodiment, sending a request to the network node for training of the first machine learning model and/or training of the second machine learning model, or receiving a request from the network node for training of the first machine learning model and/or training of the second machine learning model. In an example embodiment, the negotiation process further comprises, alternatively or additionally to the example embodiment described above, coordination signaling for using a common cost function. In one example embodiment, the negotiation process further comprises, alternatively or additionally to the example embodiment described above, control of a duration of training of the first machine learning model and/or training of the second machine learning model. In one example embodiment, instead of, or in addition to, the example embodiment described above, a first machine learning model is adapted to control adjacent channel leakage ratio, and a second machine learning model is adapted to control error vector magnitude. In an example embodiment, the instructions, when executed by the at least one processor, further cause the user equipment to determine to use another first machine learning model in lieu of or in addition to the example embodiments described above. The instructions, when executed by the at least one processor, further cause the user equipment to send an indication of another first machine learning model to a network node. The instructions, if training is required, when executed by the at least one processor, further cause the user equipment to perform a negotiation procedure with respect to the further first machine learning model and a second machine learning model associated with the further first machine learning model. An example embodiment of a network node includes at least one processor and at least one memory storing instructions that, when executed by the at least one processor, cause the network node to perform a negotiation proc