US 11,910,238 B2Granted

Dynamic uplink data split threshold

AssigneeQUALCOMM Incorporated

InventorsVishal Dalmiya, Vaishakh Rao, Sathish Kumar Nallamanti, Krishna Chaitanya Bellam, Gautham Kumar Reddy Adireddy, Leena Zacharias, Kuo-Chun Lee, Vanitha Aravamudhan Kumar

Life of this patent

Estimating the term…

patentgrep

Loading patent…

Abstract

Certain aspects of the present disclosure provide techniques for dynamically determining an uplink data split threshold for communicating using one or more radio link control (RLC) entities of a split bearer configuration. A method that may be performed by a user equipment (UE) includes inputting a first set of parameters to a machine learning algorithm, obtaining, as an output of the machine learning algorithm based at least in part on the inputted first set of parameters, a value for a data split threshold, and transmitting the data using at least one of a first RLC entity or the second RLC entity based on the value for the data split threshold and the amount of data the apparatus has to transmit.

Claims27

Dependent claims

An apparatus for wireless communication, comprising:

one or more processors individually or collectively configured to execute instructions stored on one or more memories and to cause the apparatus to:
periodically input a first set of parameters to a machine learning algorithm;
periodically obtain, as an output of the machine learning algorithm based at least in part on the inputted first set of parameters, a threshold amount of data for split bearer communication, wherein:
when an amount of data the apparatus has to transmit is less than the threshold amount of data, the one or more processors are further configured to cause the apparatus to transmit data using a first radio link control (RLC) entity of a split-bearer configuration;
and
when the amount of data the apparatus has to transmit is equal to or greater than the threshold amount of data, one or more processors are further configured to cause the apparatus to transmit the data using the first RLC entity and a second RLC entity of the split-bearer configuration;
and
transmit the data using at least one of the first RLC entity or the second RLC entity based on the threshold amount of data and the amount of data the apparatus has to transmit;
detect a decrease in throughput associated with at least one of the first RLC entity or the second RLC entity when transmitting the data based on the periodically-obtained threshold amount of data;
and
in response to detecting the decrease in throughput, stop periodically inputting the first set of parameters to the machine learning algorithm to periodically obtain the threshold amount of data.

8 more elements

A method for wireless communication by an apparatus, comprising:

periodically inputting a first set of parameters to a machine learning algorithm;
periodically obtaining, as an output of the machine learning algorithm based at least in part on the inputted first set of parameters, a threshold amount of data, wherein:
when an amount of data the apparatus has to transmit is less than the threshold amount of data, the apparatus is configured to transmit data using a first radio link control (RLC) entity of a split-bearer configuration;
and
when the amount of data the apparatus has to transmit is equal to or greater than the threshold amount of data, the apparatus is configured to transmit the data using the first RLC entity and a second RLC entity of the split-bearer configuration;
and
transmitting the data using at least one of the first RLC entity or the second RLC entity based on the threshold amount of data and the amount of data the apparatus has to transmit;
detecting a decrease in throughput associated with at least one of the first RLC entity or the second RLC entity when transmitting the data based on the periodically-obtained threshold amount of data;
and
in response to detecting the decrease in throughput, stop the periodically inputting of the first set of parameters to the machine learning algorithm to periodically obtain the threshold amount of data.

7 more elements

An apparatus for wireless communication, comprising:

means for periodically inputting a first set of parameters to a machine learning algorithm;
means for periodically obtaining, as an output of the machine learning algorithm based at least in part on the inputted first set of parameters, a threshold amount of data, wherein:
when an amount of data the apparatus has to transmit is less than the threshold amount of data, the apparatus is configured to transmit data using a first radio link control (RLC) entity of a split-bearer configuration;
and
when the amount of data the apparatus has to transmit is equal to or greater than the threshold amount of data, the apparatus is configured to transmit the data using the first RLC entity and a second RLC entity of the split-bearer configuration;
and
means for transmitting the data using at least one of the first RLC entity or the second RLC entity based on the threshold amount of data and the amount of data the apparatus has to transmit;
means for detecting a decrease in throughput associated with at least one of the first RLC entity or the second RLC entity when transmitting the data based on the periodically-obtained threshold amount of data;
and
means for stopping the periodically inputting of the first set of parameters to the machine learning algorithm in response to detecting the decrease in throughput.

7 more elements

A non-transitory computer-readable medium comprising executable instructions that, when executed by one or more processors of an apparatus, cause the apparatus to:

periodically input a first set of parameters to a machine learning algorithm;
periodically obtain, as an output of the machine learning algorithm based at least in part on the inputted first set of parameters, a threshold amount of data, wherein:
when an amount of data the apparatus has to transmit is less than the threshold amount of data, the apparatus is configured to transmit data using a first radio link control (RLC) entity of a split-bearer configuration;
and
when the amount of data the apparatus has to transmit is equal to or greater than the threshold amount of data, the apparatus is configured to transmit the data using the first RLC entity and a second RLC entity of the split-bearer configuration;
and
transmit the data using at least one of the first RLC entity or the second RLC entity based on the threshold amount of data and the amount of data the apparatus has to transmit;
detect a decrease in throughput associated with at least one of the first RLC entity or the second RLC entity when transmitting the data based on the periodically-obtained threshold amount of data;
and
in response to detecting the decrease in throughput, stop periodically inputting the first set of parameters to the machine learning algorithm to periodically obtain the threshold amount of data.

7 more elements

Dependencies are inferred from the claim text.

Facts

Application: 17/371,012Filed 8 Jul 2021
Published: US 2023/0012050 A112 Jan 2023
Granted: 20 Feb 2024
Term ends: Not estimatedThe source records don’t support an estimate.

Classification7 codes

H04W 28/0864
Between base stations: of different hierarchy levels, e.g. Master Evolved Node B [MeNB] or Secondary Evolved node B [SeNB]
H04L 1/1819
Hybrid protocols; Hybrid automatic repeat request [HARQ]: with retransmission of additional or different redundancy
H04L 1/1896
Arrangements specially adapted for the transmitter end: aRQ related signaling
H04W 28/08
Traffic management, e.g. flow control or congestion control: load balancing or load distribution

Family

US 2023/0012050 A1Pre-grant publication · published 12 Jan 2023
US 11,910,238 B2This patent

From the US filing history. Foreign family members aren’t listed.

Timeline

Citations

Open elsewhere

Building an agent or pulling many patents? Use the API or MCP server instead of scraping pages. Get an API key