# US 2025/0159592 A1 · Radio exposure function for telecommunications networks

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

- Number: US 2025/0159592 A1
- Document ID: US20250159592A1
- Status: Published application
- Kind: A1
- Application number: 18/979,251
- Filed: 2024-12-12
- Published: 2025-05-15
- Earliest claimed: 2023-11-10
- Assignees: T-Mobile USA, Inc.
- Applicants: T-Mobile USA, Inc.
- Inventors: Marouane Balmakhtar; Lyle Walter Paczkowski
- Web page: https://patentgrep.com/patent/US20250159592A1

## CPC

- H04W 48/16: Discovering, processing access restriction or access information
- H04W 48/18: Selecting a network or a communication service
- H04W 88/12: Access point controller devices
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)

## Abstract

Methods for resource and slice allocation for multi-mode operation in Open RAN architectures are described. A programmable radio exposure function switches between real-time and near-real-time modes of operation for a radio access network (RAN) intelligent controller of a telecommunications system. An application programming interface is exposed by the radio exposure function and performs radio resource management for the telecommunications system. The application programming interface communicates with services and/or applications to control RAN functions, and allocates RAN resources of the telecommunications system to a user equipment for the services and/or applications. A machine learning module is embedded within the radio exposure function and trained to identify network slices of the telecommunications system for the services and/or applications.

## Claims

### Claim 1

A computer-implemented method performed by a computer system, the method comprising:
receiving a mode selection request from a highly distributed Internet of things (HDIoT) application executing on multiple IoT devices;
selecting, based on the request, an operational mode from real-time and near-real-time modes of operation of a radio access network (RAN);
allocating, by an application programming interface, multiple RAN resources to the multiple IoT devices based on the operational mode;
creating multiple virtual networks associated with the RAN for the IoT devices to send telemetry data to the computer system; and
providing, to the HDIoT application, access to a RAN function based on the RAN resource to execute the HDIoT application using the telemetry data.

### Claim 2 (depends on 1)

The method of claim 1, comprising:
analyzing, by a machine learning module, operational data received from at least one network function.

### Claim 3 (depends on 1)

The method of claim 1, comprising:
training, based on historical network data, a machine learning module to operate the RAN resources based on operational data.

### Claim 4 (depends on 1)

The method of claim 1, comprising:
training, based on historical network data, a machine learning module to allocate the RAN resources to the IoT devices.

### Claim 5 (depends on 1)

The method of claim 1, comprising:
selecting, by a network slicing selection function, a network slice for executing the HDIoT application.

### Claim 6 (depends on 1)

The method of claim 1, comprising:
enabling the HDIoT application to access the computer system using a network slice.

### Claim 7 (depends on 1)

The method of claim 1, comprising:
detecting that an IoT device has violated a security constraint; and
preventing the IoT device from accessing the computer system.

### Claim 8

A computer system comprising:
at least one hardware processor; and
at least one non-transitory computer-readable storage medium storing instructions, which, when executed by the at least one hardware processor, cause the computer system to:
receive a mode selection request from a highly distributed Internet of things (HDIoT) application executing on multiple IoT devices;
select, based on the request, an operational mode from real-time and near-real-time modes of operation of a radio access network (RAN);
allocate, by an application programming interface, multiple RAN resources to the multiple IoT devices based on the operational mode;
create multiple virtual networks associated with the RAN for the IoT devices to send telemetry data to the computer system; and
provide, to the HDIoT application, access to a RAN function based on the RAN resource to execute the HDIoT application using the telemetry data.

### Claim 9 (depends on 8)

The computer system of claim 8, wherein the computer system is caused to:
select, by a network slicing selection function, a network slice for executing the HDIoT application.

### Claim 10 (depends on 8)

The computer system of claim 8, wherein the computer system is caused to:
operate, by a radio exposure function, a network slice in accordance with a parameter defined by a service level agreement.

### Claim 11 (depends on 8)

The computer system of claim 8, wherein the computer system is caused to:
enable the HDIoT application to access the computer system using a network slice.

### Claim 12 (depends on 8)

The computer system of claim 8, wherein the computer system is caused to:
receive, by a network data analytics function, operational data from the IoT devices; and
analyze, by a machine learning module, the operational data for operating the RAN resources.

### Claim 13 (depends on 8)

The computer system of claim 8, wherein the computer system is caused to:
detect that an IoT device has violated a security constraint; and
prevent the IoT device from accessing the computer system.

### Claim 14 (depends on 8)

The computer system of claim 8, wherein the computer system is caused to:
train, based on historical network data, a machine learning module to allocate the RAN resources to the IoT devices.

### Claim 15

At least one non-transitory computer-readable storage medium storing instructions, which, when executed by at least one data processor of a computer system, cause the computer system to:
receive a mode selection request from a highly distributed Internet of things (HDIoT) application executing on multiple IoT devices;
select, based on the request, an operational mode from real-time and near-real-time modes of operation of a radio access network (RAN);
allocate, by an application programming interface, multiple RAN resources to the multiple IoT devices based on the operational mode;
create multiple virtual networks associated with the RAN for the IoT devices to send telemetry data to the computer system; and
provide, to the HDIoT application, access to a RAN function based on the RAN resource to execute the HDIoT application using the telemetry data.

### Claim 16 (depends on 15)

The non-transitory computer-readable storage medium of claim 15, wherein the computer system is caused to:
train, based on historical network data, a machine learning module to allocate the RAN resources to the IoT devices.

### Claim 17 (depends on 15)

The non-transitory computer-readable storage medium of claim 15, wherein the computer system is caused to:
identify, by a machine learning module, a network slice for the HDIoT application to access the computer system.

### Claim 18 (depends on 15)

The non-transitory computer-readable storage medium of claim 15, wherein the computer system is caused to:
select, by a network slicing selection function, a network slice for executing the HDIoT application.

### Claim 19 (depends on 15)

The non-transitory computer-readable storage medium of claim 15, wherein the computer system is caused to:
enable the HDIoT application to access the computer system using a network slice.

### Claim 20 (depends on 15)

The non-transitory computer-readable storage medium of claim 15, wherein the computer system is caused to:
operate, by a radio exposure function, a network slice in accordance with a parameter defined by a service level agreement.
