IP Library › Granted Patent US 12,652,615
Granted Patent B2
US 12,652,615 · App. 18/270,741 · Granted Jun 9, 2026

System and method for carrier and/or cell switch off/on optimization based on an A1 policy in a telecommunications network

Inventors: Pankaj Tanaji Shete (Tokyo, JP); Awn Muhammad (Tokyo, JP)
Assignee: RAKUTEN MOBILE, INC.
H04W52/0203G06N20/00H04L41/16H04W16/24H04W24/02
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,652,615
App. No.
18/270,741
Granted
Jun 9, 2026
Kind
B2
Abstract

A method for implementing a carrier and/or cell switch off/on optimization in an O-RAN based on an A1 policy, the method includes: deploying, by the NRT-RIC framework, a AI/ML model to the nRT-RIC; providing, by the rApp, an A1 policy to prepare and execute the cell and/or carrier switch off/on optimization through the NRT-RIC framework to the nRT-RIC; collecting, by the nRT-RIC, data to perform the cell and/or carrier switch off/on via the E2-interface from the O-RU via the E2 node; evaluating, by nRT-RIC, the collected data; generating, by the nRT-RIC, an E2 message and send, by the nRT-RIC, the E2 message to the O-RU via the E2 node; implementing, by the E2 node and the O-RU, the cell and/or carrier switch off/on optimization within the O-RAN; receiving, by the rApp, an A1 policy feedback through an NRT-RIC framework from the O-RU via the E2 node and the nRT-RIC.

Claims (107)

1 . A system for implementing at least one of carrier or cell switch off/on optimization in an open radio access network (O-RAN) based on an A1 policy, the system comprising:

a memory storing instructions; and

at least one processor configured to implement a service management and orchestration (SMO) framework, a near-real-time radio intelligent controller (nRT-RIC), a non-real-time radio intelligent controller (NRT-RIC), a NRT-RIC framework and an application (rApp), the at least one processor configured to execute the instructions to:

collect, by the application (rApp), data to perform at least one of cell or carrier switch off/on optimization through at least one of the NRT-RIC framework or the SMO framework via the nRT-RIC from an open radio unit (O-RU);

based on the collected optimization data, by the SMO, re-train at least one artificial intelligence/machine learning (AI/ML) model;

among the at least one re-trained AI/ML, deploy, by the NRT-RIC framework, a re-trained AI/ML model to the nRT-RIC;

provide, by the application (rApp), an A1 policy to prepare and execute the at least one of cell or carrier switch off/on optimization through the NRT-RIC framework to the nRT-RIC;

based on the provided A1 policy, by the nRT-RIC, collect data to perform the at least one of cell or carrier switch off/on from the O-RU via an E2 node;

based on the deployed AI/ML model and the provided A1 policy, evaluate, by nRT-RIC, the collected data to perform the at least one of cell or carrier switch off/on;

based on the evaluating, generate, by the nRT-RIC, at least one E2 message to prepare and execute the at least one of cell or carrier switch off/on optimization and send, by the nRT-RIC, the at least one E2 message to the O-RU via the E2 node;

based on the at least one E2 message, implement, by the E2 node and the O-RU, the at least one of cell or carrier switch off/on optimization within the O-RAN;

based on the implementing, receive, by the application (rApp), an A1 policy feedback through an NRT-RIC framework from the O-RU via the E2 node and the nRT-RIC.

2 . The system as claimed in claim 1 , wherein while collecting the data to perform the at least one of cell or carrier switch off/on by the nRT-RIC, the at least one processor is configured to:

interpret, by the nRT-RIC, the provided A1 policy for at least one of cell or carrier switch off/on;

based on the interpretation of the provided A1 policy, send, by the nRT-RIC, a data collection request via an E2 interface to the E2 node;

receive, by the E2 node, the data collection request from the nRT-RIC;

collect, by the E2 node, the data to perform the at least one of cell or carrier switch off/on from the O-RU via an open FH M-Plane interface; and

send, by the E2 node, the collected data to perform the at least one of cell or carrier switch off/on via the E2 interface to the nRT-RIC.

3 . The system as claimed in claim 2 , wherein while evaluating the collected data to perform the at least one of cell or carrier switch off/on, the at least one processor is configured to:

receive, by the nRT-RIC, the collected data to perform the at least one of cell or carrier switch off/on from the E2 node via the E2 interface; and

based on the collected data to perform the at least one of cell or carrier switch off/on, apply, by the nRT-RIC, AI/ML model inference to evaluate the at least one E2 message.

4 . The system as claimed in claim 3 , wherein while generating the at least one E2 message to prepare and execute the at least one of cell or carrier switch off/on optimization, the at least one processor is configured to:

based on the AI/ML model inference, generate, by the nRT-RIC, at least one of an E2 control command or an E2 policy command for the E2 node that corresponds to the O-RU's capabilities; and

send, by the nRT-RIC, the at least one of the E2 control command or the at least one E2 policy command to the E2 node via the E2 interface.

5 . The system as claimed in claim 1 , wherein while receiving the A1 policy feedback from the O-RU, the at least one processor is further configured to:

notify, by the nRT-RIC, the A1 policy feedback based on feedback on the at least one E2 message from the O-RU towards the application (rApp) through the at least one of the NRT-RIC framework or the SMO framework;

based on the notified A1 policy feedback, monitor, by the application (rApp), at least one performance objective;

determine that at least one predetermined performance objective is not achieved based on the notified A1 policy feedback; and

initiate a fallback mechanism to pertain to the at least one predetermined performance objective.

6 . The system as claimed in claim 5 , wherein while initiating the fallback mechanism the at least one processor is further configured to:

based on the initiation, modify, by the application (rApp), the provided A1 policy to prepare and execute the at least one of cell or carrier switch off/on optimization based on the at least one predetermined performance objective; and

request, by the application (rApp), the NRT-RIC to deploy the modified A1 policy from the NRT-RIC framework to the nRT-RIC.

7 . The system as claimed in claim 6 , wherein while initiating the fallback mechanism the at least one processor is further configured to:

based on the initiation, by the application (rApp), initiates at least one of an AI/ML model update or an AI/ML model retraining based on the at least one predetermined performance objective;

update, by the application (rApp), an AI/ML model, by:

sending, by the application (rApp), an initiation request for re-training the AI/ML model to the NRT-RIC framework;

re-training, by the NRT-RIC, the AI/ML model by the NRT-RIC framework;

monitoring, by the application (rApp), re-trained AI/ML model parameters and

based on the re-trained AI/ML model parameters, by the application (rApp), determining to request the NRT-RIC to deploy the re-trained AI/ML model from the NRT-RIC framework to the nRT-RIC.

8 . A method for implementing at least one of carrier or cell switch off/on optimization in an open radio access network (O-RAN) based on an A1 policy, the method comprising:

collecting, by an application (rApp), data to perform at least one of cell or carrier switch off/on optimization through at least one of a non-real-time radio intelligent controller (NRT-RIC) framework or a service management and orchestration (SMO) framework via a near-real-time radio intelligent controller (nRT-RIC) from an open radio unit (O-RU) via an E2 node;

based on the collected optimization data, by the SMO, re-training at least one artificial intelligence/machine learning (AI/ML) model and,

among the at least one re-trained AI/ML, deploying, by the NRT-RIC framework, one re-trained AI/ML model to the nRT-RIC;

providing, by an application (rApp), an A1 policy to prepare and execute the at least one of cell or carrier switch off/on optimization through the NRT-RIC framework to the nRT-RIC;

based on the provided A1 policy, by the nRT-RIC, collecting data to perform the at least one of cell or carrier switch off/on from the O-RU via an E2 node;

based on the deployed AI/ML model and the provided A1 policy, evaluating, by nRT-RIC, the collected data to perform the at least one of cell or carrier switch off/on;

based on the evaluating, generating, by the nRT-RIC, at least one E2 message to prepare and execute the at least one of cell or carrier switch off/on optimization and

sending, by the nRT-RIC, the at least one E2 message to the O-RU via the E2 node;

based on the at least one E2 message, implementing, by the E2 node and the O-RU, the at least one of cell or carrier switch off/on optimization within the O-RAN;

based on the implementing, receiving, by the application (rApp), an A1 policy feedback through an NRT-RIC framework from the O-RU via the E2 node and the nRT-RIC.

9 . The method as claimed in claim 8 , wherein the collecting the data to perform the at least one of cell or carrier switch off/on by the nRT-RIC comprises:

interpreting, by the nRT-RIC, the provided A1 policy for at least one of cell or carrier switch off/on;

based on the interpretation of the provided A1 policy, sending, by the nRT-RIC, a data collection request via an E2 interface to the E2 node;

receiving, by the E2 node, the data collection request from the nRT-RIC;

collecting, by the E2 node, the data to perform the at least one of cell or carrier switch off/on from the O-RU via an open FH M-Plane interface; and

sending, by the E2 node, the collected data to perform the at least one of cell or carrier switch off/on via the E2 interface to the nRT-RIC.

10 . The method as claimed in claim 9 , wherein the evaluating the collected data to perform the at least one of cell or carrier switch off/on comprises:

receiving, by the nRT-RIC, the collected data to perform the at least one of cell or carrier switch off/on from the E2 node via the E2 interface; and

based on the collected data to perform the at least one of cell or carrier switch off/on, applying, by the nRT-RIC, AI/ML model inference to evaluate the at least one E2 message.

11 . The method as claimed in claim 10 , wherein the generating the at least one E2 message to prepare and execute the at least one of cell or carrier switch off/on optimization comprises:

based on the AI/ML model inference, generating, by the nRT-RIC, at least one of an E2 control command or an E2 policy command for the E2 node that corresponds to the O-RU's capabilities; and

sending, by the nRT-RIC, the at least one of the E2 control command or the E2 policy command to the E2 node via the E2 interface.

12 . The method as claimed in claim 8 , wherein the receiving of the A1 policy feedback through an NRT-RIC framework from the O-RU via the E2 node and the nRT-RIC comprises:

notifying, by the nRT-RIC, the A1 policy feedback based on feedback on the at least one E2 message from the O-RU towards the application (rApp) through the at least one of the NRT-RIC framework or the SMO framework;

based on the notified A1 policy feedback, monitoring, by the application (rApp), at least one performance objective;

determining that at least one predetermined performance objective is not achieved based on the notified A1 policy feedback; and

initiating a fallback mechanism to pertain to the at least one predetermined performance objective.

13 . The method as claimed in claim 12 , wherein the initiating the fallback mechanism comprises:

based on the initiation, modifying, by the application (rApp), the provided A1 policy to prepare and execute the at least one of cell or carrier switch off/on optimization based on the at least one predetermined performance objective; and

requesting, by the application (rApp), the NRT-RIC to deploy the modified A1 policy from the NRT-RIC framework to the nRT-RIC.

14 . The method as claimed in claim 12 , wherein the initiating the fallback mechanism comprises:

based on the initiation, by the application (rApp), initiating at least one of an AI/ML model update or an AI/ML model retraining based on the at least one predetermined performance objective;

updating, by the application (rApp), an AI/ML model, wherein the updating comprises:

sending, by the application (rApp), an initiation request for re-training the AI/ML model to the NRT-RIC framework;

re-training, by the NRT-RIC, the AI/ML model by the NRT-RIC framework; and

based on the re-trained AI/ML model parameters, by the application (rApp), determining to request the NRT-RIC to deploy the re-trained AI/ML model from the NRT-RIC framework to the nRT-RIC.

15 . A non-transitory computer-readable recording medium having recorded thereon instructions executable by at least one processor, the at least one processor further configured to perform a method for implementing at least one of carrier or cell switch off/on optimization in an open radio access network (O-RAN) based on an A1 policy, the method comprising:

collecting, by an application (rApp), data to perform at least one of a cell or carrier switch off/on optimization through at least one of a non-real-time radio intelligent controller (NRT-RIC) framework or a service management and orchestration (SMO) framework via a near-real-time radio intelligent controller (nRT-RIC) from an open radio unit (O-RU) via an E2 node;

based on the collected optimization data, by the SMO, re-training at least one artificial intelligence/machine learning (AI/ML) model and,

among the at least one re-trained AI/ML, deploying, by the NRT-RIC framework, one re-trained AI/ML model to the nRT-RIC;

providing, by an application (rApp), an A1 policy to prepare and execute the at least one of cell or carrier switch off/on optimization through the NRT-RIC framework to the nRT-RIC;

based on the provided A1 policy, by the nRT-RIC, collecting data to perform the at least one of cell or carrier switch off/on from the O-RU via an E2 node;

based on the deployed AI/ML model and the provided A1 policy, evaluating, by nRT-RIC, the collected data to perform the at least one of cell or carrier switch off/on;

based on the evaluating, generating, by the nRT-RIC, at least one E2 message to prepare and execute the at least one of cell or carrier switch off/on optimization and

sending, by the nRT-RIC, the at least one E2 message to the O-RU via the E2 node;

based on the at least one E2 message, implementing, by the E2 node and the O-RU, the at least one of cell or carrier switch off/on optimization within the O-RAN;

based on the implementing, receiving, by the application (rApp), an A1 policy feedback through an NRT-RIC framework from the O-RU via the E2 node and the nRT-RIC.

16 . The non-transitory computer-readable recording medium as claimed in claim 15 , wherein the collecting the data to perform the at least one of cell or carrier switch off/on by the nRT-RIC comprises:

interpreting, by the nRT-RIC, the provided A1 policy for at least one of cell or carrier switch off/on;

based on the interpretation of the provided A1 policy, sending, by the nRT-RIC, a data collection request via an E2 interface to the E2 node;

receiving, by the E2 node, the data collection request from the nRT-RIC;

collecting, by the E2 node, the data to perform the at least one of cell or carrier switch off/on from the O-RU via an open FH M-Plane interface; and

sending, by the E2 node, the collected data to perform the at least one of cell or carrier switch off/on via the E2 interface to the nRT-RIC.

17 . The non-transitory computer-readable recording medium as claimed in claim 16 , wherein the evaluating the collected data to perform the at least one of cell or carrier switch off/on comprises:

receiving, by the nRT-RIC, the collected data to perform the at least one of cell or carrier switch off/on from the E2 node via the E2 interface; and

based on the collected data to perform the at least one of cell or carrier switch off/on, applying, by the nRT-RIC, AI/ML model inference to evaluate the at least one E2 message.

18 . The non-transitory computer-readable recording medium as claimed in claim 17 , wherein the generating the at least one E2 message to prepare and execute the at least one of cell or carrier switch off/on optimization comprises:

based on the AI/ML model inference, generating, by the nRT-RIC, at least one of an E2 control command or an E2 policy command for the E2 node that corresponds to the O-RU's capabilities; and

sending, by the nRT-RIC, the at least one of the E2 control command or the E2 policy command to the E2 node via the E2 interface.

19 . The non-transitory computer-readable recording medium as claimed in claim 15 , wherein the receiving of the A1 policy feedback through an NRT-RIC framework from the O-RU via the E2 node and the nRT-RIC comprises:

notifying, by the nRT-RIC, the A1 policy feedback based on feedback on the at least one E2 message from the O-RU towards the application (rApp) through the at least one of the NRT-RIC framework or the SMO framework;

based on the notified A1 policy feedback, monitoring, by the application (rApp), at least one performance objective;

determining that at least one predetermined performance objective is not achieved based on the notified A1 policy feedback; and

initiating a fallback mechanism to pertain to the at least one predetermined performance objective.

20 . The non-transitory computer-readable recording medium as claimed in claim 19 , wherein the initiating the fallback mechanism comprises:

based on the initiation, modifying, by the application (rApp), the provided A1 policy to prepare and execute the at least one of cell or carrier switch off/on optimization based on the at least one predetermined performance objective; and

requesting, by the application (rApp), the NRT-RIC to deploy the modified A1 policy from the NRT-RIC framework to the nRT-RIC.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 3, 2023
From: SHETE, PANKAJ TANAJI; MUHAMMAD, AWN
To: RAKUTEN MOBILE, INC.
Reel/Frame 064137/0086 →
Continuity (1)
Related Publication 20250048251A1 · Feb 6, 2025
References Cited (27)
US 20230362809A1 · Dixit · 2023 [cited by examiner]
US 20230370959A1 · Rajendran · 2023 [cited by examiner]
US 20240098629A1 · Rajendran · 2024 [cited by examiner]
US 20240162955A1 · Whinnett · 2024 [cited by examiner]
US 20240187317A1 · Cui · 2024 [cited by examiner]
US 20240196177A1 · Parasher · 2024 [cited by examiner]
US 20240196178A1 · Ying · 2024 [cited by examiner]
US 20240214272A1 · Ying · 2024 [cited by examiner]
US 20240236766A1 · Shete · 2024 [cited by examiner]
US 20240250875A1 · Luthra · 2024 [cited by examiner]
US 20240250878A1 · Luthra · 2024 [cited by examiner]
US 20240250904A1 · Shete · 2024 [cited by examiner]
US 20240251254A1 · Luthra · 2024 [cited by examiner]
US 20240251292A1 · Forenza · 2024 [cited by examiner]
US 20240259836A1 · Shete · 2024 [cited by examiner]
US 20240259873A1 · Shete · 2024 [cited by examiner]
US 20240267752A1 · Shete · 2024 [cited by examiner]
US 20240267753A1 · Shete · 2024 [cited by examiner]
US 20240276187A1 · Shete · 2024 [cited by examiner]
US 20240276188A1 · Shete · 2024 [cited by examiner]
US 20240276580A1 · Shete · 2024 [cited by examiner]
US 20250063429A1 · Hegde · 2025 [cited by examiner]
US 20250097285A1 · Reddy · 2025 [cited by examiner]
US 20250097732A1 · Hegde · 2025 [cited by examiner]
US 20250133419A1 · Shete · 2025 [cited by examiner]
International Search Report issued Jul. 19, 2023 in Application No. PCT/US2023/017362. [cited by applicant]
Written Opinion issued Jul. 19, 2023 in Application No. PCT/US2023/017362. [cited by applicant]