WO-2026091123-A1 - MACHINE-LEARNING-MODEL-BASED RADIO FREQUENCY (RF) RESOURCE ALLOCATION IN MULTI-NETWORK DEVICES

Abstract

Certain aspects of the present disclosure provide techniques and apparatus for machine-learning-model-based radio frequency (RF) resource allocation in multi-subscriber identity module (MSIM) devices. An example method generally includes predicting, using a machine learning model, a performance impact on a first radio frequency (RF) chain of a wireless communication device caused by a plurality of actions relative to a second RF chain of the wireless communication device. A performance impact on the second RF chain of the wireless communication device caused by the plurality of actions is predicted. An action of the plurality of actions to perform is selected based on the predicted performance impact on the first RF chain and the predicted performance impact on the second RF chain, and the selected action is executed.

Inventors

• ZHANG, JIANQIANG
• WANG, XINYU
• XIE, LING
• SHAHIDI, REZA
• PARK, CHEOL HEE
• CHEN, QINGXIN
• LI, XIAOYU
• YOUSEFVAND, Mohammad
• MENG, Kuo
• REJ, Rishav

Assignees

• QUALCOMM INCORPORATED

Dates

Publication Date

20260507

Application Date

20241104

Claims (20)

1. A processor-implemented method for wireless communications, comprising: predicting, using a machine learning model, a performance impact on a first radio frequency (RF) chain of a wireless communication device caused by a plurality of actions relative to a second RF chain of the wireless communication device; predicting a performance impact on the second RF chain of the wireless communication device caused by the plurality of actions; selecting an action of the plurality of actions to perform based on the predicted performance impact on the first RF chain and the predicted performance impact on the second RF chain; and executing the selected action.
2. The method of Claim 1, further comprising: measuring the performance impact on the first RF chain based on executing the selected action; and updating the machine learning model based on a difference between the predicted performance impact on the first RF chain for the selected action and the measured performance impact on the first RF chain for the selected action.
3. The method of Claim 2, wherein measuring the performance impact on the first RF chain based on executing the selected action comprises determining a performance impact during one or more time windows after execution of the selected action relative to a baseline performance metric measured during one or more time windows prior to execution of the selected action.
4. The method of Claim 1, wherein the performance impact on the first RF chain is predicted based on one or more operating parameters associated with a current state of the wireless communication device.
5. The method of Claim 1, wherein the performance impact on the first RF chain comprises a spectral efficiency loss.
6. The method of Claim 1, wherein the plurality of actions comprise one or more of: reserving all available RF resources for receiving a downlink channel via the first RF chain; using one of a plurality of subsets of the available RF resources for receiving a downlink channel via the first RF chain and using remaining RF resources for receiving a downlink channel via the second RF chain; or reserving all the available RF resources for receiving the downlink channel via the second RF chain.
7. The method of Claim 1, wherein the machine learning model comprises a multilayer perceptron (MLP) model.
8. The method of Claim 1, wherein predicting the performance impact on the second RF chain comprises predicting a probability of missing a paging message transmitted by a network entity.
9. A processing system for wireless communications, comprising: at least one memory having executable instructions stored thereon; and one or more processors configured to execute the executable instructions to cause the processing system to: predict, using a machine learning model, a performance impact on a first radio frequency (RF) chain of a wireless communication device caused by a plurality of actions relative to a second RF chain of the wireless communication device; predict a performance impact on the second RF chain of the wireless communication device caused by the plurality of actions; select an action of the plurality of actions to perform based on the predicted performance impact on the first RF chain and the predicted performance impact on the second RF chain; and execute the selected action.
10. The processing system of Claim 9, wherein the one or more processors are further configured to cause the processing system to: measure the performance impact on the first RF chain based on executing the selected action; and update the machine learning model based on a difference between the predicted performance impact on the first RF chain for the selected action and the measured performance impact on the first RF chain for the selected action.
11. The processing system of Claim 10, wherein to measure the performance impact on the first RF chain based on executing the selected action, the one or more processors are configured to cause the processing system to determine a performance impact during one or more time windows after execution of the selected action relative to a baseline performance metric measured during one or more time windows prior to execution of the selected action.
12. The processing system of Claim 9, wherein the performance impact on the first RF chain is predicted based on one or more operating parameters associated with a current state of the wireless communication device.
13. The processing system of Claim 9, wherein the performance impact on the first RF chain comprises a spectral efficiency loss.
14. The processing system of Claim 9, wherein the plurality of actions comprise one or more of: reserving all available RF resources for receiving a downlink channel via the first RF chain; using one of a plurality of subsets of the available RF resources for receiving a downlink channel via the first RF chain and using remaining RF resources for receiving a downlink channel via the second RF chain; or reserving all the available RF resources for receiving the downlink channel via the second RF chain.
15. The processing system of Claim 9, wherein the machine learning model comprises a multilayer perceptron (MLP) model.
16. The processing system of Claim 9, wherein to predict the performance impact on the second RF chain, the one or more processors are configured to cause the processing system to predict a probability of missing a paging message transmitted by a network entity.
17. A non-transitory computer-readable medium having executable instructions stored thereon which, when executed by one or more processors, performs an operation for wireless communications, the operation comprising: predicting, using a machine learning model, a performance impact on a first radio frequency (RF) chain of a wireless communication device caused by a plurality of actions relative to a second RF chain of the wireless communication device; predicting a performance impact on the second RF chain of the wireless communication device caused by the plurality of actions; selecting an action of the plurality of actions to perform based on the predicted performance impact on the first RF chain and the predicted performance impact on the second RF chain; and executing the selected action.
18. The computer-readable medium of Claim 17, wherein the operations further comprise: measuring the performance impact on the first RF chain based on executing the selected action; and updating the machine learning model based on a difference between the predicted performance impact on the first RF chain for the selected action and the measured performance impact on the first RF chain for the selected action.
19. The computer-readable medium of Claim 18, wherein measuring the performance impact on the first RF chain based on executing the selected action comprises determining a performance impact during one or more time windows after execution of the selected action relative to a baseline performance metric measured during one or more time windows prior to execution of the selected action.
20. The computer-readable medium of Claim 17, wherein predicting the performance impact on the second RF chain comprises predicting a probability of missing a paging message transmitted by a network entity.

Description

MACHINE-LEARNING-MODEL-BASED RADIO FREQUENCY (RF) RESOURCE ALLOCATION IN MULTI-NETWORK DEVICES BACKGROUND Field of the Disclosure Aspects of the present disclosure relate to wireless communications, and more particularly, to techniques for radio frequency (RF) resource allocation. Description of Related Art Wireless communications systems are widely deployed to provide various telecommunication services such as telephony, video, data, messaging, broadcasts, or other similar types of services. These wireless communications systems may employ multiple-access technologies capable of supporting communications with multiple users by sharing available wireless communications system resources with those users. Although wireless communications systems have made great technological advancements over many years, challenges still exist. For example, complex and dynamic environments can still attenuate or block signals between wireless transmitters and wireless receivers. Accordingly, there is a continuous desire to improve the technical performance of wireless communications systems, including, for example: improving speed and data carrying capacity of communications, improving efficiency of the use of shared communications mediums, reducing power used by transmitters and receivers while performing communications, improving reliability of wireless communications, avoiding redundant transmissions and/or receptions and related processing, improving the coverage area of wireless communications, increasing the number and types of devices that can access wireless communications systems, increasing the ability for different types of devices to intercommunicate, increasing the number and type of wireless communications mediums available for use, and the like. Consequently, further improvements in wireless communications systems to overcome the aforementioned technical challenges and others are desired. SUMMARY Certain aspects of the present disclosure provide a method for wireless communication by a user equipment (UE) . The method includes predicting, using a machine learning model, a performance impact on a first radio frequency (RF) chain of a  wireless communication device caused by a plurality of actions relative to a second RF chain of the wireless communication device. A performance impact on the second RF chain of the wireless communication device caused by the plurality of actions is predicted. An action of the plurality of actions to perform is selected based on the predicted performance impact on the first RF chain and the predicted performance impact on the second RF chain, and the selected action is executed. Other aspects provide: an apparatus operable, configured, or otherwise adapted to perform any one or more of the aforementioned methods and/or those described elsewhere herein; a non-transitory, computer-readable media comprising instructions that, when executed by one or more processors of an apparatus, cause the apparatus to perform the aforementioned methods as well as those described elsewhere herein; a computer program product embodied on a computer-readable storage medium comprising code for performing the aforementioned methods as well as those described elsewhere herein; and/or an apparatus comprising means for performing the aforementioned methods as well as those described elsewhere herein. By way of example, an apparatus may comprise a processing system, a device with a processing system, or processing systems cooperating over one or more networks. The following description and the appended figures set forth certain features for purposes of illustration. BRIEF DESCRIPTION OF DRAWINGS The appended figures depict certain features of the various aspects described herein and are not to be considered limiting of the scope of this disclosure. FIG. 1 depicts an example wireless communications network. FIG. 2 depicts an example disaggregated base station architecture. FIG. 3 depicts aspects of an example base station and an example user equipment. FIGS. 4A, 4B, 4C, and 4D depict various example aspects of data structures for a wireless communications network. FIG. 5 illustrates an example pipeline for selecting actions to perform on a wireless device based on predicted performance losses caused by an action performed on  a first radio frequency (RF) chain to a second RF chain, according to certain aspects of the present disclosure. FIG. 6 illustrates an example of a predicted performance impact on RF chains in a wireless device caused by the execution of various enumerated actions on at least one RF chain, according to certain aspects of the present disclosure. FIG. 7 illustrates an example neural network for predicting a performance impact of an action performed on a first RF chain to a second RF chain, according to certain aspects of the present disclosure. FIG. 8 illustrates example operations performed by a user equipment (UE) to perform an action on a first RF chain based on a pred