IP Library › Granted Patent US 12,316,494

Granted Patent B2

US 12,316,494 · App. 18/023,404 · Granted May 27, 2025

System and method for optimizing the scheduling of O-Cloud nodes in a telecommunications network

Inventors: Manmeet Bhangu (Indore, IN); Jyoti Bose (Tokyo, JP)

Assignee: RAKUTEN SYMPHONY, INC.

H04L41/0816 H04L41/0895 H04L41/16

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 12,316,494
App. No.: 18/023,404
Granted: May 27, 2025
Kind: B2

External Links

USPTO Patent Center↗ Full Patent PDF↗

Abstract

A method for optimizing the scheduling of an O-Cloud node, the method includes: determining a NF hosted on a O-Cloud node to be migrated to another O-Cloud nodes; sending a recommendation to the SMO to migrate the determined NF; sending instructions to implement the migration of the NF via an O2 interface to an O-Cloud management service; controlling the implementation of the migration of the determined NF to the other O-Cloud nodes; upon implementation of the migration, sending a confirmation notice to the SMO via the O2 interface; wherein the determining the one or more network functions NFs to be migrated, includes: obtaining data referring to historical and/or current utilization patterns of a O-Cloud node and/or a NF hosted thereon; inputting the data to an AI/ML model; obtaining a prediction of a utilization scenario; and determining a migration recommendation for the NF.

Claims (100)

1. A system for optimizing the scheduling of one or more open cloud (O-Cloud) nodes within an O-Cloud infrastructure of a telecommunications network, the system comprising:

at least one memory storing instructions; and

at least one processor configured to execute the instructions to:

determine, by a rApp within a service management orchestration framework (SMO), one or more network functions (NFs) hosted on at least one O-Cloud node to be migrated to one or more other O-Cloud nodes;

send, by the rApp, a recommendation to the SMO to migrate the determined one or more NFs;

send, by the SMO, instructions to implement the migration of the determined one or more NFs via an O2 interface to at least one O-Cloud management service;

control, by the SMO, the implementation of the migration for each of the determined one or more NFs to the one or more other O-Cloud nodes;

upon implementation of the migration, send, by the at least one O-Cloud management service, a confirmation notice of the migration implementation to the SMO via the O2 interface;

wherein in determining the one or more network functions NFs to be migrated, the at least one processor is configured to execute the instructions:

obtain, by the rApp, data referring to historical and/or current utilization patterns of at least one O-Cloud node and/or one or more NFs hosted thereon;

input, by the rApp, the data referring to historical and/or current utilization patterns of the at least one O-Cloud node and/or the one or more NFs hosted thereon to an artificial intelligence/machine learning (AI/ML) model;

obtain, by the rApp, a prediction of at least one utilization scenario for the at least one O-Cloud node and/or the one or more NFs hosted thereon; and

determine, by the rApp, based on the prediction of the at least one utilization scenario, a migration recommendation for the one or more NFs hosted on the at least one O-Cloud node.

2. The system as claimed in claim 1 , wherein the at least one processor is further configured to execute the instructions to:

feedback, by the rApp, data referring to the data referring to historical and/or current utilization patterns of at least one O-Cloud node and/or one or more NFs hosted thereon to the AI/ML model,

wherein the AI/ML model is a reinforcement learning model configured to update the data referring to historical and/or current utilization patterns of at least one O-Cloud node and/or one or more NFs hosted thereon based on the feedback; and the feedback comprises

at least one of O-Cloud node related data received over the O2 interface and/or one or more NF related data received over an O1 interface.

3. The system as claimed in claim 1 , wherein the at least one processor is further configured to execute the instructions to:

input, by the rApp, to the AI/ML model, data referring to historical and/or current utilization patterns of at least one O-Cloud node and/or one or more NFs hosted thereon;

apply, by the ML model, the data referring to historical and/or current utilization patterns of at least one O-Cloud node and/or one or more NFs hosted thereon, for training for the AI/ML model based on at least one utilization scenario;

predict, by the ML model, based on at least one utilization scenario trained in the AI/ML model, at least one O-cloud node and/or one or more NFs hosted thereon.

4. The system as claimed in claim 3 , wherein in applying the data referring to historical and/or current utilization patterns of at least one O-Cloud node and/or one or more NFs hosted thereon for training for the AI/ML model, the at least one processor is further configured to execute the instructions to:

predict, by the ML model, future workloads and/or traffic patterns of at least one O-Cloud node and/or one or more NFs hosted thereon; and

identify, by the ML model, an optimal O-Cloud node for hosting the one or more NFs to be migrated based on the trained AI/ML model.

5. The system as claimed in claim 4 , wherein the identifying of the optimal O-Cloud node for hosting the at least one NF to be migrated based on the trained AI/ML model comprises

at least one optimal O-Cloud node predicted based on a location-centric utilization scenario node and/or a power consumption-centric utilization scenario.

6. The system as claimed in claim 1 , wherein in controlling to implement the migration for each of the determined one or more NFs to be migrated the one or more other O-Cloud nodes, the at least one processor is further configured to execute the instructions to:

identify, by the SMO, for each NF to be migrated, one or more O-Cloud nodes to instantiate a new NF;

instantiate, by the SMO, the new NF on the identified one or more O-Cloud nodes;

perform, by the SMO, based on at least one of O-Cloud node data received over the O2 interface and/or NF data received over an O1 interface, a sanity and health check on the new NF;

determine, by the SMO, that the sanity and health check on the new NF is successful;

divert, by the SMO, the traffic from the NF to be migrated to the new NF;

determine, by the SMO, that all traffic from the NF to be migrated is diverted to the new NF; and

terminate, by the SMO, the NF to be migrated.

7. The system as claimed in claim 1 , wherein in confirmation of the migration implementation, the at least one processor is further configured to execute the instructions to:

update, by the SMO, deployment inventory based on the one or more NFs after migration;

send, by the at least one O-Cloud management service, an update status of the migration to at least one of the rApp, a non-real time radio intelligent controller (NRT-RIC) and a Network Function Orchestrator (NFO).

8. The system as claimed in claim 1 , wherein in updating deployment inventory based on the one or more NFs after migration, the at least one processor is further configured to execute the instructions to:

determine, by the SMO, that the migration has not been successful, and

relocate the one or more NFs back to the at least one O-Cloud node prior to the migration recommendation.

9. A method for optimizing the scheduling of one or more open cloud (O-Cloud) nodes within an O-Cloud infrastructure of a telecommunications network, the method comprising:

determining, by a rApp within a service management orchestration framework (SMO), one or more network functions (NFs) hosted on at least one O-Cloud node to be migrated to one or more other O-Cloud nodes;

sending, by the rApp, a recommendation to the SMO to migrate the determined one or more NFs;

sending, by the SMO, instructions to implement the migration of the determined one or more NFs via an O2 interface to at least one O-Cloud management service;

controlling, by the SMO, the implementation of the migration for each of the determined one or more NFs to the one or more other O-Cloud nodes;

upon implementation of the migration, sending, by the at least one O-Cloud management service, a confirmation notice of the migration implementation to the SMO via the O2 interface;

wherein the determining the one or more network functions NFs to be migrated, comprising:

obtaining, by the rApp, data referring to historical and/or current utilization patterns of at least one O-Cloud node and/or one or more NFs hosted thereon;

inputting, by the rApp, the data referring to historical and/or current utilization patterns of the at least one O-Cloud node and/or the one or more NFs hosted thereon to an artificial intelligence/machine learning (AI/ML) model;

obtaining, by the rApp, a prediction of at least one utilization scenario for the at least one O-Cloud node and/or the one or more NFs hosted thereon; and

determining, by the rApp, based on the prediction of the at least one utilization scenario, a migration recommendation for the one or more NFs hosted on the at least one O-Cloud node.

10. The method as claimed in claim 9 , wherein the method comprises:

feeding back, by the rApp, data referring to the data referring to historical and/or current utilization patterns of at least one O-Cloud node and/or one or more NFs hosted thereon to the AI/ML model,

at least one of O-Cloud node related data received over the O2 interface and/or one or more NF related data received over an O1 interface.

11. The method as claimed in claim 9 , wherein the method comprises:

inputting, by the rApp, to the AI/ML model, data referring to historical and/or current utilization patterns of at least one O-Cloud node and/or one or more NFs hosted thereon;

applying, by the ML model, the data referring to historical and/or current utilization patterns of at least one O-Cloud node and/or one or more NFs hosted thereon, for training for the AI/ML model based on at least one utilization scenario;

predicting, by the ML model, based on at least one utilization scenario trained in the AI/ML model, at least one O-cloud node and/or one or more NFs hosted thereon.

12. The method as claimed in claim 9 , wherein the applying the data referring to historical and/or current utilization patterns of at least one O-Cloud node and/or one or more NFs hosted thereon for training for the AI/ML model comprises:

predicting, by the ML model, future workloads and/or traffic patterns of at least one O-Cloud node and/or one or more NFs hosted thereon; and

identifying, by the ML model, an optimal O-Cloud node for hosting the one or more NFs to be migrated based on the trained AI/ML model.

13. The method as claimed in claim 12 , wherein the identifying of the optimal O-Cloud node for hosting the at least one NF to be migrated based on the trained AI/ML model comprises

at least one optimal O-Cloud node predicted based on a location-centric utilization scenario node and/or a power consumption-centric utilization scenario.

14. The method as claimed in claim 9 , wherein the controlling to implement the migration for each of the determined one or more NFs to be migrated the one or more other O-Cloud nodes comprises:

identifying, by the SMO, for each NF to be migrated, one or more O-Cloud nodes to instantiate a new NF;

instantiating, by the SMO, the new NF on the identified one or more O-Cloud nodes;

performing, by the SMO, based on at least one of O-Cloud node data received over the O2 interface and/or NF data received over an O1 interface, a sanity and health check on the new NF;

determining, by the SMO, that the sanity and health check on the new NF is successful;

diverting, by the SMO, the traffic from the NF to be migrated to the new NF;

determining, by the SMO, that all traffic from the NF to be migrated is diverted to the new NF; and

terminating, by the SMO, the NF to be migrated.

15. The method as claimed in claim 9 , wherein the confirmation of the migration implementation comprises:

updating, by the SMO, deployment inventory based on the one or more NFs after migration;

sending, by the at least one O-Cloud management service, an update status of the migration to at least one of the rApp, a non-real time radio intelligent controller (NRT-RIC) and a Network Function Orchestrator (NFO).

16. The method as claimed in claim 9 , wherein the updating deployment inventory based on the one or more NFs after migration comprises:

determining, by the SMO, that the migration has not been successful, and

relocating the one or more NFs back to the at least one O-Cloud node prior to the migration recommendation.

17. A non-transitory computer-readable recording medium having recorded thereon instructions executable by at least one processor configured to perform a for optimizing the scheduling of one or more open cloud (O-Cloud) nodes within an O-Cloud infrastructure of a telecommunications network, the method comprising: