# US 12,225,571 B2 · 5G link selection in non-standalone network

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 12,225,571 B2
- Document ID: US12225571B2
- Status: Granted
- Kind: B2
- Application number: 17/804,167
- Filed: 2022-05-26
- Published: 2023-12-21
- Granted: 2025-02-11
- Earliest claimed: 2022-05-26
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Sagar Tayal
- Web page: https://patentgrep.com/patent/US12225571B2

## CPC

- H04W 72/542: using measured or perceived quality
- H04W 24/02: Arrangements for optimising operational condition
- H04W 24/10: Scheduling measurement reports {; Arrangements for measurement reports}
- H04W 28/26: Resource reservation
- H04W 76/15: Setup of multiple wireless link connections
- H04W 72/54: based on quality criteria
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)

## Abstract

A method, a system, and a computer program product for optimal link selection between user equipment and new radio stations in a non-standalone network. The method includes detecting a connection attempt by a user equipment to a non-standalone network that includes at least one base station and NR stations. The method also includes receiving connection data from the UE and connecting the UE to the base station. The method further includes determining an NR station from the NR stations based on channel quality measurements relating to the NR stations and the connection data of the UE using a prediction module that uses a machine learning model to predict the NR station. The channel quality measurements include cell range, uplink performance, cell capacity, and link quality. The method also includes connecting the UE to the NR station determined by the machine learning model.

## Claims

### Claim 1

A method of wireless connectivity of a user equipment (UE), the method comprising:
detecting a connection attempt by the UE to a non-standalone (NSA) network including at least one base station and new radio (NR) stations;
receiving connection data from the UE;
connecting the UE to the base station;
determining, by a prediction module, an NR station from the NR stations based on channel quality measurements relating to the NR stations and the connection data of the UE; and
connecting the UE to the NR station determined by the prediction module.

### Claim 2 (depends on 1)

The method of claim 1, wherein the channel quality measurements of the NR stations include cell range, uplink performance, cell capacity, link quality, and other quality aspects.

### Claim 3 (depends on 1)

The method of claim 1, wherein the prediction module utilizes a machine learning model trained using channel quality measurements of the NR stations.

### Claim 4 (depends on 1)

The method of claim 1, further comprising:
receiving periodically, via a measurement module, updated channel quality measurements of the NR stations;
evaluating the updated channel quality measurements by the prediction module using a machine learning model; and
determining, by the prediction module, which of the NR stations to connect the UE to at a particular time of day.

### Claim 5 (depends on 1)

The method of claim 1, further comprising:
receiving periodically, via a measurement module, a timing advance from the UE;
evaluating the timing advance by the prediction module using a machine learning model; and
determining, by the prediction module, which of the NR stations to connect the UE to.

### Claim 6 (depends on 1)

The method of claim 1, wherein timing advance is used to control an uplink transmission timing of the UE.

### Claim 7 (depends on 1)

The method of claim 1, wherein the prediction module maintains a blacklist of other NR stations that should not be used when establishing the connection with the UE.

### Claim 8

A system for link selection in a non-standalone (NSA) network including a base station and new radio (NR) stations, the system comprising:
a memory;
a processor;
local data storage having stored thereon computer executable code, wherein the computer executable code includes program instruction executable by a processor to cause the processor to perform a method;
a measurement module configured to obtain channel quality measurements of the NR stations in the NSA network;
a training module configured to train a machine learning model using the channel quality measurements obtained by the measurement module; and
a prediction module configured to deploy the machine learning model onto the NSA network for connecting user equipment (UE) to the NR stations.

### Claim 9 (depends on 8)

The system of claim 8, wherein the prediction module is further configured to periodically receive updated channel quality measurements from the measurement module to retrain the machine learning model and continuously monitor the NR stations.

### Claim 10 (depends on 8)

The system of claim 8, wherein the channel quality measurements include cell range, uplink performance, cell capacity, and link quality.

### Claim 11 (depends on 8)

The system of claim 8, wherein the prediction module maintains a blacklist of other NR stations that should not be used when establishing the connection with the UE.

### Claim 12 (depends on 11)

The system of claim 11, wherein other NR stations of the NR stations collocated with the base station are blacklisted based on a distance between the other NR stations and the UE being beyond a predetermined allowed distance.

### Claim 13 (depends on 11)

The system of claim 11, wherein other NR stations of the NR stations non-collocated with the base station are blacklisted based on a distance between the other NR stations and the UE being beyond a predetermined allowed distance.

### Claim 14

A computer program product including computer readable storage media of mitigating unauthorized encryptions, having computer executable instructions that when executed by at least one computer cause the at least one computer to execute the instructions to:
detect, on a non-standalone (NSA) network including a base station and new radio (NR) stations, a connection attempt by the UE;
receive connection data from the UE;
connect the UE to the base station;
determine, by a prediction module, an NR station from the NR stations based on channel quality measurements relating to the NR stations and the connection data of the UE; and
connect the UE to the NR station determined by the prediction module.

### Claim 15 (depends on 14)

The computer program product of claim 14, wherein the channel quality measurements of the NR stations include cell range, uplink performance, cell capacity, and link quality.

### Claim 16 (depends on 14)

The computer program product of claim 14, wherein the prediction module utilizes a machine learning model trained using channel quality measurements of the NR stations.

### Claim 17 (depends on 14)

The computer program product of claim 14, further comprising:
receiving periodically, via a measurement module, updated channel quality measurements of the NR stations;
evaluating the updated channel quality measurements by the prediction module using a machine learning model; and
determining, by the prediction module, which of the NR stations to connect the UE to at a particular time of day.

### Claim 18 (depends on 14)

The computer program product of claim 14, further comprising:
receiving periodically, via a measurement module, a timing advance from the UE;
evaluating the timing advance by the prediction module using a machine learning model; and
determining, by the prediction module, which of the NR stations to connect the UE to at a particular time of day.

### Claim 19 (depends on 14)

The computer program product of claim 14, wherein timing advance is used to control an uplink transmission timing of the UE.

### Claim 20 (depends on 14)

The computer program product of claim 14, wherein the prediction module maintains a blacklist of other NR stations that should not be used when establishing the connection with the UE.