ML-to-ML orchestration system and method for system wide information handling system (IHS) optimization

Patent metadata

Field	Value
Publication number	US-11593178-B2
Application number	US-202117148291-A
Country	US
Kind code	B2
Filing date	Jan 13, 2021
Priority date	Jan 13, 2021
Publication date	Feb 28, 2023
Grant date	Feb 28, 2023

Abstract

Embodiments of systems and methods for managing performance optimization of applications executed by an Information Handling System (IHS) are described. In an illustrative, non-limiting embodiment, an IHS may include computer-executable instructions to, for each of multiple resources used to execute a target application, receive one or more machine learning (ML)-based hints associated with each resource that have been generated by a ML-based optimization service, and generate one or more augmented hints for at least one of the resources using a ML-to-ML orchestration service. The ML-to-ML orchestration service then transmits the augmented hints to the ML-based optimization service that combines the augmented ML-based hints with the one or more internally generated hints to generate augmented profile recommendations that are, in turn, used to adjust one or more settings of the resource to optimize a performance of the target application executed by the resource.

First claim

The invention claimed is:

1. An Information Handling System (IHS) orchestration system, comprising:
at least one processor; and
at least one memory coupled to the at least one processor, the at least one memory having program instructions stored thereon that, upon execution by the at least one processor, cause the IHS to:
for each of a plurality of resources used to execute a target application on the IHS, receive one or more machine learning (ML)-based hints associated with the resource that have been generated by a one of a plurality of ML-based optimization services associated with the resource;
generate, using the ML-based hints received from each of the ML-based optimization services, one or more augmented hints for at least one of the plurality of resources using a ML-to-ML orchestration service; and
transmit the augmented hints to at least one of the ML-based optimization services associated with the at least one resource,
wherein the at least one ML-based optimization service combines the ML-based hints with the one or more augmented hints generated by the at least one ML-based optimization service to generate one or more augmented profile recommendations, and
wherein the at least one ML-based optimization service uses the augmented profile recommendations to adjust one or more settings of the at least one resource to optimize a performance of the target application.

2. The IHS orchestration system of claim 1 , wherein at least one of the plurality of resources comprises at least one of a hardware resource, a software resource, or a platform resource of the IHS.

3. The IHS orchestration system of claim 1 , wherein each of the ML-based hints comprises at least one of a profile recommendation, a resource performance feature, classification information, and raw telemetry data.

4. The IHS orchestration system of claim 1 , wherein the ML-to-ML orchestration service is provided as a cloud-based service.

5. The IHS orchestration system of claim 1 , wherein the instructions are further executed to perform a discovery operation to identify the resources of the IHS.

6. The IHS orchestration system of claim 1 , wherein each of the plurality of resources comprises a device management layer having an application program interface (API) for communicating with the instructions via a secure login session with administrative rights.

7. The IHS orchestration system of claim 6 , wherein the instructions are further executed to perform a registration operation during an initial secure login session with the device management layer, the instructions being further executed to perform the registration operation by at least one of verifying one or more policies or one or more compatibility criteria associated with the resource.

8. The IHS orchestration system of claim 6 , wherein the instructions are further executed to perform the registration operation by transmitting a type of parametric data to be obtained by the device management layer and a frequency at which the type of parametric data is to be sent to the instructions.

9. The IHS orchestration system of claim 1 , wherein the at least one resource is void of any ML-based optimization service, the instructions are further executed to receive telemetry data associated with operation of the resource, and determine the profile recommendations for the at least one resource using the telemetry data.

10. The IHS orchestration system of claim 1 , wherein the instructions are further executed to generate the one or more augmented hints according to a priority level indicator associated with each of the ML-based hints.

11. An Information Handling System (IHS) orchestration method, comprising:
for each of a plurality of resources used to execute a target application on the IHS, receiving one or more machine learning (ML)-based hints associated with the resource that have been generated by a one of a plurality of ML-based optimization services associated with the resource;
generating, using the ML-based hints received from each of the ML-based optimization services, one or more augmented hints for at least one of the plurality of resources using a ML-to-ML orchestration service; and
transmitting the augmented hints to at least one of the ML-based optimization services associated with the at least one resource,
wherein the at least one ML-based optimization service combines the ML-based hints with the one or more augmented hints generated by the at least one ML-based optimization service to generate one or more augmented profile recommendations, and
wherein the at least one ML-based optimization service uses the augmented profile recommendations to adjust one or more settings of the at least one resource to optimize a performance of the target application.

12. The IHS orchestration method of claim 11 , wherein at least one of the plurality of resources comprises at least one of a hardware resource, a software resource, or a platform resource of the IHS.

13. The IHS orchestration method of claim 11 , wherein the ML-to-ML orchestration service is provided as a cloud-based service.

14. The IHS orchestration method of claim 11 , further comprising performing a discovery operation to identify the resources of the IHS.

15. The IHS orchestration method of claim 11 , wherein each of the plurality of resources comprises a device management layer having an application program interface (API) for communicating with the instructions via a secure login session with administrative rights.

16. The IHS orchestration method of claim 15 , further comprising performing a registration operation during an initial secure login session with the device management layer, the instructions being further executed to perform the registration operation by at least one of verifying one or more policies or one or more compatibility criteria associated with the resource.

17. The IHS orchestration method of claim 15 , further comprising performing the registration operation by transmitting a type of parametric data to be obtained by the device management layer and a frequency at which the type of parametric data is to be sent to the instructions.

18. The IHS orchestration method of claim 11 , wherein the resource is void of any ML-based optimization service, the method further comprising receiving telemetry data associated with operation of the resource, and determining the profile recommendations for the at least one resource using the telemetry data.

19. The IHS orchestration method of claim 11 , further comprising generating the one or more augmented hints according to a priority level indicator associated with each of the ML-based hints.

20. A memory storage device having program instructions stored thereon that, upon execution by one or more processors of an Information Handling System (IHS), cause the IHS to:
for each of a plurality of resources used to execute a target application on the IHS, receive one or more machine learning (ML)-based hints associated with the resource that have been generated by a one of a plurality of ML-based optimization services associated with the resource;
generate, using the ML-based hints received from each of the ML-based optimization services, one or more augmented hints for at least one of the plurality of resources using a ML-to-ML orchestration service; and
transmit the augmented hints to at least one of the ML-based optimization services associated with the at least one resource,
wherein the at least one ML-based optimization service combines the ML-based hints with the one

Assignees

• Dell Products Lp

Inventors

• Khosrowpour Farzad
• Markow Mitchell Anthony

Classifications

• G06N20/00

  Machine learning · CPC title

• G06F9/44505 Primary

  Configuring for program initiating, e.g. using registry, configuration files · CPC title

• G06N20/20

  Ensemble learning · CPC title

• G06F9/5005 Primary

  to service a request · CPC title

• G06F21/31

  User authentication · CPC title