CLOUD AWARE COMPUTING DISTRIBUTION TO IMPROVE PERFORMANCE AND ENERGY FOR MOBILE DEVICES

• US 20140095695A1
• Filed: 09/28/2012
• Published: 04/03/2014
• Est. Priority Date: 09/28/2012
• Status: Abandoned Application

• Current Assignee: Intel Corporation
• Original Assignee: Intel Corporation
• Inventors: Wang, Ren, Tsai, Jr-Shian (James), Tai, Tsung-Yuan C., Min, Alexander W., Ergin, Mesut
• Application Number:
  US13/631,415
• Publication Number:
  US 20140095695A1
• Time in Patent Office: Days
• US Class Current: 709/224
• CPC Class Codes: G06F 9/5088 involving task migration
• CPC Class Codes: G06F 9/5094 where the allocation takes into account power or heat criteria power management in computers in general G06F1/3203; thermal management in computers in general G06F1/206
• CPC Class Codes: Y02D 10/00 Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

An intelligent cloud aware computing distribution architecture for a device. A network conditions monitor is to observe and identify decision impact factors of tasks in a runtime environment. A dynamic profiler, coupled to the network conditions monitor, is to receive runtime information regarding the decision impact factors identified by the network conditions monitor and produce a profile based on the decision impact factors. Runtime offload decision making logic is to process the profile produced by the dynamic profiler based on the received decision impact factors according a predetermined policy and to determine final offloading decisions based on the predetermined policy and the processed decision impact factors. The runtime offload decision making logic is to provide the final offloading decisions to the applications on the device for executing the tasks locally or remotely based on the determined final offloading decision.

Claims

1. A mobile device, comprising:

a network conditions monitor for observing and for identifying decision impact factors of tasks in a runtime environment;

a dynamic profiler, coupled to the network conditions monitor, for receiving runtime information regarding the decision impact factors identified by the network conditions monitor and for producing a profile based on the decision impact factors;

runtime offload decision making logic, coupled to the dynamic profiler, for processing the profile produced by the dynamic profiler based on the received decision impact factors according a predetermined policy and determining final offloading decisions based on the predetermined policy and the processed decision impact factors;

wherein the runtime offload decision making logic is to provide the final offloading decisions to the applications on the device for executing the tasks locally or remotely based on the determined final offloading decision.

2. The device of claim 1, wherein the dynamic profiler is to convert the received decision impact factors to parameters used as input to runtime offload decision making logic.

3. The device of claim 1, wherein the dynamic profiler is to continuously monitor and collect comprehensive runtime information to produce a profile and the runtime offload decision making logic is to make optimal offloading decision based on multiple considerations associated with the profile.

4. The device of claim 1, wherein the network conditions monitor is to observe network availability and channel conditions and to identify energy impact factors, performance impact factors, user preference impact factors and cost impact factors.

5. The device of claim 1, wherein the runtime offload decision making logic is to consider a subset of the decision impact factors provided in the profile according to the predetermined policy.

6. The device of claim 1, wherein the decision impact factors are associated with network availability and channel conditions.

7. The device of claim 1, wherein the architecture further includes a client interface for communicating with a server interface at the remote cloud server to offload a task by moving the execution of the task from the local device to the remote server.

8. The device of claim 1, wherein the runtime offload decision making logic is disposed at the mobile device.

9. The device of claim 1, wherein the runtime offload decision making logic is disposed at the remote cloud server.

10. The device of claim 1, wherein the dynamic profiler is to process the runtime information by determining a cost and a benefit of executing tasks locally and at a remote cloud server.

11. A method for providing intelligent cloud aware computing distribution, comprising:

starting an application;

obtaining an action for the application preferred by a user;

determining whether the user prefers local execution;

gathering runtime information for a task when the user is determined to prefer remote execution;

obtaining the preferred policy and a decided weight on the runtime information based on the preferred policy;

calculating a final combination of weights for the runtime information; and

executing the offloading of the task based on the calculated final combination of weights for the runtime information.

12. The method of claim 11, wherein the runtime information comprises energy impact factors, performance impact factors, user preference impact factors and cost impact factors.

13. The method of claim 11 further comprising executing the process locally when the user is determined to prefer local execution.

14. The method of claim 11 further comprising continuously monitoring and collecting comprehensive runtime information to produce a profile and making an optimal offloading decision based on multiple considerations associated with the profile.

15. The method of claim 11, wherein the gathering runtime information comprises observing network availability and channel conditions.

16. The method of claim 11, wherein the executing the offloading of the task further comprises considering only a subset of the runtime information according to the preferred policy.

17. The method of claim 11, wherein the calculating a final combination of weights for the runtime information comprises determining a cost and a benefit of executing tasks locally and at a remote cloud server.

18. At least one machine readable storage medium comprising instructions that, when executed by the machine, cause the machine to perform operations for intelligent cloud aware computing distribution, the operations comprising:

starting an application;

obtaining an action for the application preferred by a user;

determining whether the user prefers local execution;

gathering runtime information for a task when the user is determined to prefer remote execution;

obtaining the preferred policy and a decided weight on the runtime information based on the preferred policy;

calculating a final combination of weights for the runtime information; and

executing the offloading of the task based on the calculated final combination of weights for the runtime information.

19. The machine readable medium of claim 18, wherein the runtime information comprises energy impact factors, performance impact factors, user preference impact factors and cost impact factors.

20. The machine readable medium of claim 18 further comprising executing the process locally when the user is determined to prefer local execution.

21. The machine readable medium of claim 18 further comprising continuously monitoring and collecting comprehensive runtime information to produce a profile and making an optimal offloading decision based on multiple considerations associated with the profile.

22. The machine readable medium of claim 18, wherein the gathering runtime information comprises Observing network availability and channel conditions.

23. The machine readable medium of claim 18, wherein the executing the offloading of the task further comprises considering only a subset of the runtime information according to the preferred policy.

24. The machine readable medium of claim 18, wherein the calculating a final combination of weights for the runtime information comprises determining a cost and a benefit of executing tasks locally and at a remote cloud server.

25. A system for providing cloud aware computing distribution to improve performance and energy for mobile devices, comprising:

a mobile device coupled to a server through a network,

wherein the mobile device comprises;

a network conditions monitor for observing and for identifying decision impact factors of tasks in a runtime environment;

a dynamic profiler, coupled to the network conditions monitor, for receiving runtime information regarding the decision impact factors identified by the network conditions monitor and for producing a profile based on the decision impact factors;

runtime offload decision making logic, coupled to the dynamic profiler, for processing the profile produced by the dynamic profiler based on the received decision impact factors according a predetermined policy and determining final offloading decisions based on the predetermined policy and the processed decision impact factors;

wherein the runtime offload decision making logic is to provide the final offloading decisions to the applications on the device for executing the tasks locally at the mobile device or remotely at the server based on the determined final offloading decision; and

wherein the server comprises;

at least one application for executing the at least one task offloaded from the mobile device; and

a server interface for processing data associated with the at least one task communicated between the mobile device and the server.

26. The system of claim 25, wherein the dynamic profiler is further to continuously monitor and collect comprehensive runtime information to produce a profile and to convert the received decision impact factors to parameters used as input to the runtime offload decision making logic, the dynamic profiler is to further process the runtime information by determining a cost and a benefit of executing tasks locally and at a remote cloud server, the dynamic profiler.

27. The system of claim 25, wherein the runtime offload decision making logic is to further make optimal offloading decision based on multiple considerations associated with the profile including considering a subset of the decision impact factors provided in the profile according to the predetermined policy.

28. The system of claim 25, wherein the network conditions monitor is to observe network availability and channel conditions and to identify energy impact factors, performance impact factors, user preference impact factors and cost impact factors.

29. The system of claim 25, wherein the decision impact factors are associated with network availability and channel conditions.

30. The system of claim 25, wherein the architecture further includes a client interface tier communicating with a server interface at the remote cloud server to offload a task by moving the execution of the task from the local device to the remote server.