Method and system for predicting and optimizing resource utilization of AI applications in an embedded computing system
Disclosed herein is a method and an optimization unit for optimizing and/or improving efficiency of resource utilization in an embedded computing system executing Artificial Intelligence (AI) applications. The method includes: detecting, by an optimization unit comprising processing circuitry and/or executable program instructions configured in the embedded computing system, a launch of an AI application on the embedded computing system; retrieving a runtime profile corresponding to the AI application, the runtime profile indicating resource requirements for executing the AI application; and configuring a runtime environment of the embedded computing system for the AI application based on the runtime profile corresponding to the AI application.
1. A method of improving efficiency of resource utilization in an embedded computing system executing Artificial Intelligence (AI) applications, the method comprising:
detecting launch of an AI application;
retrieving, by an optimization unit comprising processing circuitry and/or executable program instructions configured in the embedded computing system, runtime profiles corresponding to the AI application and one or more related AI applications,
wherein the one or more related AI applications are related to the AI application based on historical usage preferences,
wherein the runtime profiles indicates resource requirements for executing the AI application and the one or more related AI applications, wherein the runtime profiles for the AI application and the one or more related AI applications are based on one or more system state parameters-related to the AI application,
wherein the one or more system state parameters include at least one of power consumption, performance mode chosen by a user of the AI application, or assessment of Random Access Memory (RAM) availability in the embedded computing system;
determining, by the optimization unit, whether the retrieved runtime profiles match current runtime profiles for the AI application and the one or more related AI applications;
based on a match being determined, configuring, by the optimization unit, a runtime environment of the embedded computing system by allocating resources for executing the AI application and the one or more related the AI applications based on the retrieved runtime profiles;
identifying, by an optimization unit, a runtime status of the AI application, wherein the runtime status includes at least one of a foreground instance, a background instance, or closed;
based on the runtime status of the AI application being the background instance or closed, detecting, by the optimization unit, that the AI application is predicted to be launched;
identifying, by the optimization unit, a performance status of the AI application, wherein the performance status is categorized according to resource usage levels; and
holding or releasing resources for the AI application according to the identified the performance status.
2. The method of claim 1 , wherein the retrieved runtime profiles are updated based on real-time usage of the AI application on the embedded computing system.
3. The method of claim 1 , wherein one or more resources required for executing the one or more related AI applications are loaded and maintained in the runtime environment, until completion of execution of the one or more related AI applications.
4. The method of claim 3 , wherein the one or more related AI applications includes AI applications executing concurrently in the runtime environment and one or more AI applications predicted to be executed subsequent to the AI application being executed on the runtime environment.
5. The method of claim 1 , wherein a predefined time period for holding the one or more resources is determined based on a performance status of the AI application.
6. The method of claim 1 , wherein a low-level runtime profile of the AI application is configured on the runtime environment based on the embedded computing system having a constrained resource availability.
7. An optimization unit configured to improve efficiency of resource utilization in an embedded computing system executing Artificial Intelligence (AI) applications, the optimization unit comprising:
a processor comprising processing circuitry; and
a memory, communicatively coupled to the processor, wherein the memory stores processor-executable instructions, which on execution, cause the processor to:
detect launch of an AI application;
retrieve runtime profiles corresponding to the AI application and one or more related AI applications,
wherein the one or more related AI applications are related to the AI application based on historical usage preferences,
wherein the runtime profiles indicates resource requirements for executing the AI application and the one or more related AI applications, wherein the runtime profiles for the AI application and the one or more related the AI applications are based on one or more system state parameters,
wherein the one or more system state parameters include at least one of power consumption, performance mode chosen by a user of the AI application, or assessment of Random Access Memory (RAM) availability in the embedded computing system;
determine whether the retrieved the runtime profiles match current runtime profiles for the AI application and the one or more related AI applications;
based on a match being determined, configure a runtime environment of the embedded computing system by allocating resources for executing the AI application and the one or more related the AI applications based on the retrieved runtime profiles;
identify a runtime status of the AI application, wherein the runtime status includes at least one of a foreground instance, a background instance, or closed;
based on the runtime status of the AI application being the background instance or closed, detect that the AI application is predicted to be launched;
identify a performance status of the AI application, wherein the performance status is categorized according to resource usage levels; and
hold or release resources for the AI application according to the identified the performance status.
8. The optimization unit of claim 7 , wherein the retrieved runtime profiles are updated based on real-time usage of the AI application on the embedded computing system.
9. The optimization unit of claim 7 , wherein one or more resources required for executing of the one or more related AI applications are loaded and maintained in the runtime environment, until completion of execution of the one or more related AI applications.
10. The optimization unit of claim 7 , wherein a predefined time period for holding the one or more resources is determined based on a performance status of the AI application.
11. The optimization unit of claim 7 , wherein a low-level runtime profile of the AI application is configured on the runtime environment based on the embedded computing system having a constrained resource availability.