Granted Patent B2

US 12,267,783 · App. 17/929,605 · Granted Apr 1, 2025

Inventors: Vutha Va (Plano, TX); Boon Loong Ng (Plano, TX)

Assignee: Samsung Electronics Co., Ltd.

H04W52/0248H04W52/0258

Abstract

Claims (99)

1. A method performed by a user equipment (UE), the method comprising:

obtaining UE side information;

based on the obtained UE side information, detecting a service type of an application executing on the UE and estimating a supportable throughput;

determining a UE-preferred configuration based on the detected service type and the estimated supportable throughput;

determining whether the UE-preferred configuration is different from a current UE configuration;

controlling transmission of the UE-preferred configuration to an external network device, based on a result of the determination of whether the UE-preferred configuration is different from the current UE configuration.

2. The method of claim 1 , wherein:

the UE side information includes internet protocol (IP) traffic history, network status, and UE status;

the detecting of the service type is based on the IP traffic history; and

the estimating of the supportable throughput is based on the network status and the UE status.

3. The method of claim 1 , further comprising:

determining a state of a UE operational constraint, the state of the UE operational constraint being an ON state or an OFF state based on at least some of the UE side information, the ON state in which UE power saving features degrades a user experience of the application,

wherein determining the UE-preferred configuration comprises determining the UE-preferred configuration based on the state of the UE operational constraint.

4. The method of claim 3 , wherein determining the UE-preferred configuration comprises:

calculating a margin between the estimated supportable throughput and an application-specified throughput;

comparing the margin to a threshold that is greater than or equal to the application-specified throughput;

selecting a UE-power saving configuration as the UE-preferred configuration, in response to a determination that the margin exceeds the threshold; and

selecting a throughput-increasing configuration as the UE-preferred configuration, in response to a determination that the margin does not exceed the threshold.

5. The method of claim 4 , wherein determining the UE-preferred configuration comprises:

determining the UE-preferred configuration based on a selected service type, wherein the selected service type is one selected from the detected service type and a modified service type that is different from the detected service type; and

selecting the selected service type based on the determined state of the UE operational constraint by:

in response to determining that UE operational constraint is in the OFF state, selecting the detected service type as the selected service type, the selected service type being a first service type that corresponds to a first quality of user experience that corresponds to the application-specified throughput; and

in response to determining that UE operational constraint is in the ON state:

selecting the modified service type as the selected service type, wherein the modified service type is a second service type that corresponds to a second quality of user experience that is a less quality of user experience than the first quality, the second quality of user experience corresponding to a reduced throughput that prioritizes power savings; and

modifying the application-specified throughput to be the reduced throughput,

wherein calculating the margin comprises calculating the margin between the estimated supportable throughput and the modified application-specified throughput that is the reduced throughput.

6. The method of claim 1 , wherein the UE-preferred configuration comprises a recommendation that includes at least one of an RRC-inactive state and a DRX parameter.

7. The method of claim 1 , further comprising:

generating a prediction of a UE configuration that is likely to be accepted by the external network device, the predicted UE configuration being a result of executing a multi-arm bandit (MAB) reinforcement-learning algorithm on an MAB database, the UE-preferred configuration, and at least one of:

a current location of the UE, and

a time of day at the UE; and

in response to determining that the UE-preferred configuration is different from the predicted UE configuration,

not transmitting the UE-preferred configuration, and

transmitting the UE-preferred configuration to the external network device in response to a determination that the predicted UE configuration is different from the current UE configuration.

8. A user equipment (UE) comprising:

a transceiver;

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

obtain UE side information;

based on the obtained UE side information, detect a service type of an application executing on the UE and estimate a supportable throughput;

determine a UE-preferred configuration based on the detected service type and the estimated supportable throughput;

determine whether the UE-preferred configuration is different from a current UE configuration;

control transmission of the UE-preferred configuration to an external network device, based on a result of the determination of whether the UE-preferred configuration is different from the current UE configuration.

9. The UE of claim 8 , wherein:

the UE side information includes internet protocol (IP) traffic history, network status, and UE status; and

the processor is further configured to:

detect the service type based on the IP traffic history; and

estimate the supportable throughput based on the network status and the UE status.

10. The UE of claim 8 , wherein the processor is further configured to:

determine a state of a UE operational constraint, the state of the UE operational constraint being an ON state or an OFF state based on at least some of the UE side information, the ON state in which UE power saving features degrades a user experience of the application; and

determine the UE-preferred configuration based on the state of the UE operational constraint.

11. The UE of claim 10 , wherein to determine the UE-preferred configuration, the processor is configured to:

calculate a margin between the estimated supportable throughput and an application-specified throughput;

compare the margin to a threshold;

select a UE-power saving configuration as the UE-preferred configuration, in response to a determination that the margin exceeds or is equal to the threshold; and

select a throughput-increasing configuration as the UE-preferred configuration, in response to a determination that the margin does not exceed the threshold.

12. The UE of claim 11 , wherein the processor is further configured to determine the UE-preferred configuration by:

determining the UE-preferred configuration based on a selected service type, wherein the selected service type is one selected from the detected service type and a modified service type that is different from the detected service type; and

selecting the selected service type based on the determined state of the UE operational constraint by:

in response to determining that UE operational constraint is in the OFF state, selecting the detected service type as the selected service type, the selected service type being a first service type that corresponds to a first quality of user experience that corresponds to the application-specified throughput; and

in response to determining that UE operational constraint is in the ON state:

selecting the modified service type as the selected service type, wherein the modified service type is a second service type that corresponds to a second quality of user experience that is a less quality of user experience than the first quality, the second quality of user experience corresponding to a reduced throughput that prioritizes power savings; and

modifying the application-specified throughput to be the reduced throughput,

wherein calculating the margin comprises calculating the margin between the estimated supportable throughput and the modified application-specified throughput that is the reduced throughput.

13. The UE of claim 8 , wherein the UE-preferred configuration comprises a recommendation that includes at least one of an RRC-inactive state and a DRX parameter.

14. The UE of claim 8 , wherein the processor is further configured to:

generate a prediction of a UE configuration that is likely to be accepted by the external network device, the predicted UE configuration being a result of executing a multi-arm bandit (MAB) reinforcement-learning algorithm on an MAB database, the UE-preferred configuration, and at least one of:

a current location of the UE, and

a time of day at the UE; and

in response to determining that the UE-preferred configuration is different from the predicted UE configuration,

not transmit the UE-preferred configuration, and

transmit the UE-preferred configuration to the external network device in response to a determination that the predicted UE configuration is different from the current UE configuration.

15. A non-transitory computer readable medium comprising program code that, when executed by a processor of a user equipment (UE), causes the UE to:

obtain UE side information;

based on the obtained UE side information, detect a service type of an application executing on the UE and estimate a supportable throughput;

determine a UE-preferred configuration based on the detected service type and the estimated supportable throughput;

determine whether the UE-preferred configuration is different from a current UE configuration;

control transmission of the UE-preferred configuration to an external network device, based on a result of the determination of whether the UE-preferred configuration is different from the current UE configuration.

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

the UE side information includes internet protocol (IP) traffic history, network status, and UE status;

non-transitory computer readable medium further comprises program code that, when executed by the processor of the UE, causes the UE to:

detect the service type based on the IP traffic history; and

estimate the supportable throughput based on the network status and the UE status.

17. The non-transitory computer readable medium of claim 15 , further comprising program code that, when executed by the processor of the UE, causes the UE to:

determine a state of a UE operational constraint, the state of the UE operational constraint being an ON state or an OFF state based on at least some of the UE side information, the ON state in which UE power saving features degrades a user experience of the application; and

determine the UE-preferred configuration based on the state of the UE operational constraint.

18. The non-transitory computer readable medium of claim 17 , wherein the program code that, when executed by the processor of the UE, causes the UE to:

calculate a margin between the estimated supportable throughput and an application-specified throughput;

compare the margin to a threshold;

select a UE-power saving configuration as the UE-preferred configuration, in response to a determination that the margin exceeds or is equal to the threshold; and

select a throughput-increasing configuration as the UE-preferred configuration, in response to a determination that the margin does not exceed the threshold.

19. The non-transitory computer readable medium of claim 18 , further comprising program code that, when executed by the processor, causes the UE to determine the UE-preferred configuration by:

determining the UE-preferred configuration based on a selected service type, wherein the selected service type is one selected from the detected service type and a modified service type that is different from the detected service type; and

selecting the selected service type based on the determined state of the UE operational constraint by:

in response to determining that UE operational constraint is in the OFF state, selecting the detected service type as the selected service type, the selected service type being a first service type that corresponds to a first quality of user experience that corresponds to the application-specified throughput; and

in response to determining that UE operational constraint is in the ON state:

selecting the modified service type as the selected service type, wherein the modified service type is a second service type that corresponds to a second quality of user experience that is a less quality of user experience than the first quality, the second quality of user experience corresponding to a reduced throughput that prioritizes power savings; and

modifying the application-specified throughput to be the reduced throughput,

wherein calculating the margin comprises calculating the margin between the estimated supportable throughput and the modified application-specified throughput that is the reduced throughput.

20. The non-transitory computer readable medium of claim 15 , wherein the UE-preferred configuration comprises a recommendation that includes at least one of an RRC-inactive state and a DRX parameter.

Assignments (1)

Continuity (2)

References Cited (22)

Cited By (1)

US 12,701,436