Allocating compute offload resources

Patent metadata

Field	Value
Publication number	US-10628222-B2
Application number	US-201615157183-A
Country	US
Kind code	B2
Filing date	May 17, 2016
Priority date	May 17, 2016
Publication date	Apr 21, 2020
Grant date	Apr 21, 2020

Abstract

Systems, methods, and computer program products to perform an operation comprising receiving, by a fog computing platform, a request from a wireless device to perform a compute task on behalf of the wireless device, determining a first computing resource, of a plurality of computing resources, required to perform the compute task, associating the request with a first level of priority, of a plurality of levels of priority, for accessing the first computing resource, allocating, based at least in part on the first level of priority, a portion of the first computing resource to perform the requested compute task.

First claim

The claims are as follows:

1. A method, comprising:
receiving, by a fog computing platform, a request from a wireless device to perform a compute task on behalf of the wireless device;
determining a first computing resource, of a plurality of computing resources, required to perform the compute task;
determining a sentiment of a text of a first item of content, of a plurality of items of content, published by a user associated with the wireless device on one of a plurality of social media platforms;
determining a level of participation of the user in a loyalty program, wherein the level of participation includes purchase history of the user;
determining a history of requests issued by a plurality of wireless devices associated with the user, wherein the requests comprise requests for the fog computing environment to perform compute tasks on behalf of one or more of the plurality of wireless devices associated with the user;
computing a score for the user based at least in part on the determined sentiment of the text, the determined level of participation in the loyalty program;
associating, based on the score and the history of requests, the request with a first level of priority, of a plurality of levels of priority, for accessing the first computing resource;
allocating, based at least in part on the first level of priority and a first resource requirement to complete the requested compute task, a first portion of the first computing resource to perform the requested compute task, wherein the first portion is insufficient to complete the requested compute task;
associating, based on the score and the history of requests, the request with an updated level of priority of the plurality of levels of priority; and
subsequently to allocating the first portion, allocating, based at least in part on the updated level of priority and a second resource requirement to complete a remainder of the requested compute task, a second portion of the first computing resource to perform the remainder of the requested compute task.

2. The method of claim 1 , wherein the score is further computed based on:
a sentiment expressed by the user in a second item of content of the plurality of items of content published by the user on the plurality of social media platforms, wherein the second item of content comprises an image depicting the user; and
a length of time the user has been a member of the loyalty program.

3. The method of claim 2 , wherein the computed score is associated with the first level of priority, wherein the computed score is relative to a first business that provides the allocated portion of the first computing resource, wherein the user is associated with a plurality of scores, wherein each of the plurality of scores is associated with a respective business that provides respective computing resources, wherein the user is further associated with a composite score, wherein the composite score is based on each of the plurality of scores.

4. The method of claim 1 , further comprising prior to allocating the portion of the first computing resource:
determining a set of attributes of the wireless device;
identifying a set of computing resources required to perform the compute task, wherein the set of computing resources is of the plurality of computing resources and includes the first computing resource;
determining an amount of time required to perform the compute task using the set of compute resources;
determining a cost of performing the compute task using the set of compute resources;
determining a level of use of all compute resources in the fog computing environment;
determining a set of currently pending compute tasks to be performed by the fog computing environment, and
allocating the set of computing resources to the wireless device based on the set of attributes of the wireless device, the set amount of time required to perform of the compute task, the cost of performing the compute task, the level of use of the compute resources in the fog computing environment, and the set of currently pending compute tasks.

5. The method of claim 1 , wherein the wireless device comprises an Internet-of-Things (IOT) device, wherein the plurality of computing resources comprise: (i) a processor, (ii) a storage device, (iii) a memory, (iv) a graphics processor, (v) a field programmable gate array (FPGA), (vi) a coherent accelerator, and (vii) an encryption device.

6. The method of claim 1 , wherein allocating the portion of the first computing resource comprises at least one of: (i) allocating the first computing resource for a predefined amount of time and (ii) allocating at least one unit of the first computing resource.

7. The method of claim 1 , wherein the QoS level is differentiated for each of the plurality of levels of priority.

8. A system, comprising:
a computer processor; and
a memory containing a program which when executed by the processor performs an operation to allocate compute resources in a fog computing platform, the operation comprising:
receiving, by a fog computing platform, a request from a wireless device to perform a compute task on behalf of the wireless device;
determining a first computing resource, of a plurality of computing resources, required to perform the compute task;
determining a sentiment of a text of a first item of content, of a plurality of items of content, published by a user associated with the wireless device on one of a plurality of social media platforms;
determining a level of participation of the user in a loyalty program, wherein the level of participation includes purchase history of the user;
determining a history of requests issued by a plurality of wireless devices associated with the user, wherein the requests comprise requests for the fog computing environment to perform compute tasks on behalf of one or more of the plurality of wireless devices associated with the user;
computing a score for the user based at least in part on the determined sentiment of the text, the determined level of participation in the loyalty program;
associating, based on the score and the history of requests, the request with a first level of priority, of a plurality of levels of priority, for accessing the first computing resource;
allocating, based at least in part on the first level of priority and a first resource requirement to complete the requested compute task, a first portion of the first computing resource to perform the requested compute task, wherein the first portion is insufficient to complete the requested compute task; and
subsequently to allocating the first portion:
associating, based on the score and the history of requests, the request with an updated level of priority of the plurality of levels of priority; and

a second resource requirement to complete a remainder of the requested compute task, a second portion of the first computing resource to perform the remainder of the requested compute task.

9. The system of claim 8 , wherein the score is further computed based on:
a sentiment expressed by the user in a second item of content of the plurality of items of content published by the user on the plurality of social media platforms, wherein the second item of content comprises an image depicting the user; and
a length of time the user has been a member of the loyalty program.

10. The system of claim 9 , wherein the computed score is associated with the first level of priority, wherein the computed score is relative to a first business that provides the allocated portion of the first computing resource, wherein the user is associated with a plurality of scores, wherein each of the plurality of scores is associated with a respective business

Assignees

• IBM

Inventors

• Liu Su
• Rozner Eric J
• Sze Chin Ngai
• Wei Yaoguang

Classifications

• G06F9/5027

  the resource being a machine, e.g. CPUs, Servers, Terminals · CPC title

• G06F9/5038 Primary

  considering the execution order of a plurality of tasks, e.g. taking priority or time dependency constraints into consideration (scheduling strategies G06F9/4881 and subgroups) · CPC title

• G06F9/5061

  Partitioning or combining of resources · CPC title

• G06F2209/509

  Offload · CPC title

• H04W4/21

  for social networking applications · CPC title