EXECUTION ALLOCATION COST ASSESSMENT FOR COMPUTING SYSTEMS AND ENVIRONMENTS INCLUDING ELASTIC COMPUTING SYSTEMS AND ENVIRONMENTS

• US 20110004574A1
• Filed: 02/22/2010
• Published: 01/06/2011
• Est. Priority Date: 07/02/2009
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: ZHANG, Xinwen, GIBBS, Simon J., JEONG, Sangoh, KUNJITHAPATHAM, Anugeetha
• Granted Patent: US 8,560,465 B2
• Time in Patent Office: Days
• US Class Current: 706/12
• CPC Class Codes: G06F 9/5066 Algorithms for mapping a plurality of inter-dependent sub-tasks onto a plurality of physical CPUs mappping at compile time, see G06F8/451
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation

Abstract

Techniques for allocating individually executable portions of executable code for execution in an Elastic computing environment are disclosed. In an Elastic computing environment, scalable and dynamic external computing resources can be used in order to effectively extend the computing capabilities beyond that which can be provided by internal computing resources of a computing system or environment. Machine learning can be used to automatically determine whether to allocate each individual portion of executable code (e.g., a Weblet) for execution to either internal computing resources of a computing system (e.g., a computing device) or external resources of an dynamically scalable computing resource (e.g., a Cloud). By way of example, status and preference data can be used to train a supervised learning mechanism to allow a computing device to automatically allocate executable code to internal and external computing resources of an Elastic computing environment.

Claims

1. A computing system that includes one or more internal computing resources, wherein the computing system is operable to:

determine, based on machine learning, how to allocate a plurality of individually executable portions of executable computer code for execution between the internal computing resources and one or more external computing resources, including at least one dynamically scalable computing resource external to the computing system.

2. The computing system of claim 1, wherein the computing system is further operable to use the machine learning to automatically allocate the plurality of executable portions of the executable computer code.

3. The computing system of claim 1, wherein the computing system is further operable to automatically allocate, without requiring user input, each one of the plurality of executable portions of executable computer code to either the internal computing resources or to the external computing resources.

4. The computing system of claim 1, wherein the computing system is further operable to determine, during the runtime of the executable computer code, how to allocate the plurality of executable portions for execution between the one or more internal computing resources and one or more external resources.

5. The computing system of claim 1, wherein the computing system is further operable to determine how to allocate the plurality of executable portions when one or more of the following occurs:

one or more of the plurality of the executable portions are to be loaded for execution;

one or more of the plurality of the executable portions are loaded for execution; and

one or more of the plurality of the executable portions of executable computer code are being executed by the internal or external computing resources.

6. The computing system of claim 1, wherein the machine learning is a form of supervised machine learning.

7. The computing system of claim 6, wherein the supervised machine learning uses a Naï

ve Bayesian classification.

8. The computing system of claim 6, wherein the supervised machine learning is based on one or more of the following:

preference data, and

status and/or system data.

9. The computing system of claim 8, wherein the preference data is indicative of one or more preferences of one or more users of the computing system, and wherein the status and/or system data is indicative of one or more states of the computing system and/or its computing environment.

10. The computing system of claim 1, wherein the computing system is further operable to collect allocation data pertaining to actual allocation of portions of executable computer code for execution between the one or more internal computing resources and one or more external resources.

11. The computing system of claim 10, wherein the allocation data includes status data pertaining to status of the computing system and/or user preference data indicative of user preference data corresponding to the actual allocation of portions of executable computer code.

12. The computing system of claim 11, wherein the computing system is further operable to provide the allocation data as training data for supervised machine learning.

13. The computing system of claim 1, wherein the computing system is further operable to:

determine prior and/or conditional probabilities, wherein the conditional probabilities are associated with one or more conditional components; and

determine, based on the prior and/or conditional probabilities the allocation of the executable code portions.

14. The computing system of claim 13, wherein the conditional components include one or more preference components and one or more system status components that are represented in a vector form.

15. The computing system of claim 1, wherein the computing system is further operable to:

receive current data indicative of current status and/or current preferences as input; and

select an execution allocation configuration, based on the current data and conditional probabilities associated with the current data for at least a plurality of possible execution allocation configurations.

18. The computer implemented method of claim 1,

wherein the executable computer code includes a web-based applications and the plurality of individually executable portions are Weblets of the web-based application, and

wherein the machine learning is a form of supervised machine learning.

16. A computer implemented method, comprising:

determining, based on machine learning, how to allocate a plurality of individually executable portions of executable computer code for execution between one or more internal computing resources of a computing system and one or more external computing resources, including at least one dynamically scalable computing resource external to the computing system.

17. The computer implemented method of claim 16, further comprising:

using the machine learning to automatically allocate the plurality of executable portions of the executable computer code either to the internal computing resources or to the external computing resources.

19. A computer readable storage medium storing computer executable instructions that when executed:

determines, based on machine learning, how to allocate a plurality of individually executable portions of executable computer code for execution between one or more internal computing resources of a computing system and one or more external computing resources, including at least one dynamically scalable computing resource external to the computing system.

20. The computer readable storage medium of claim 19, wherein the computer executable instructions when executed also use the machine learning to automatically allocate the plurality of executable portions of the executable computer code either to the internal computing resources or to the external computing resources.

21. A computing system, wherein the computing system is operable to:

determine, based on machine learning, how to allocate a plurality of individually executable portions of executable computer code for execution between internal computing resources of a second computing system and one or more external computing resources, including at least one dynamically scalable computing resource external to the computing system.

22. The computing system of claim 21, wherein the computing system is a server that effectively servers the second computing system as a client.

23. The computing system of claim 21, wherein the computing system is provided as a part of the at least one dynamically scalable computing resource.