Adaptive deployment of applications

Patent metadata

Field	Value
Publication number	US-11296902-B2
Application number	US-201716478591-A
Country	US
Kind code	B2
Filing date	Jun 27, 2017
Priority date	Feb 5, 2017
Publication date	Apr 5, 2022
Grant date	Apr 5, 2022

Abstract

An Internet of Things (IoT) system that includes an orchestration device is provided. The orchestration device receives resource requirements and accesses a device/capability map to produce a task deployment map.

First claim

What is claimed is:

1. An Internet of Things (IoT) system, comprising hardware to implement an orchestration device, to receive resource requirements and access a device/capability map of a plurality of onboarded devices in the IoT system to produce a task deployment map, and communicate the task deployment map to a controller in each of the plurality of onboarded devices in the IoT system.

2. The IoT system of claim 1 , comprising the device/capability map comprising identities, properties, and utilization of an IoT device.

3. The IoT system of claim 1 , comprising a monitoring/telemetry tool to obtain current device state and metrics from an IoT device.

4. The IoT system of claim 3 , wherein the monitoring/telemetry tool is to provide the current device state and metrics for the IoT device to the device/capability map.

5. The IoT system of claim 1 , comprising a task image repository comprising containerized tasks.

6. The IoT system of claim 1 , comprising a build factory to package tasks in containers for different operating environments.

7. The IoT system of claim 1 , comprising a device onboarding tool to identify an IoT device and its capabilities, and to provide that information to the device/capability map.

8. The IoT system of claim 1 , comprising an IoT device, comprising a containerized task to implement a portion of an application.

9. The IoT system of claim 1 , comprising an IoT device, comprising a functional block.

10. The IoT system of claim 9 , wherein the functional block comprises a containerized task.

11. A method for orchestrating the deployment of applications in an Interpret of Things (IoT) system, comprising:
creating a device/capability map of a plurality of onboarded devices in the IoT system;
matching application requirements to the device/capability map;
producing a task deployment map; and
communicating the task deployment map to a controller in each of the plurality of onboarded devices in the IoT system.

12. The method of claim 11 , comprising:
receiving a request from a controller for a task image; and
sending the task image from a task image repository to the controller if the task image is available.

13. The method of claim 11 , comprising:
receiving a request from a controller for a task image;
building the task image if the task image is not present in a task imager repository;
saving the task image to the task image repository; and
sending the task image from the task image repository to the controller.

14. The method of claim 11 , comprising:
receiving node metrics from each of the plurality of onboarded devices in the IoT system, wherein the node metrics comprise CPU utilization, network utilization, or memory utilization, or any combinations thereof; and
saving the node metrics to the device/capability map.

15. The method of claim 11 , comprising building a task image, comprising packaging a task in a container, wherein the container is a code segment designed to allow the task to function in a target environment.

16. The method of claim 11 , comprising building a task image, comprising compiling a task to run as a code segment in a target environment.

17. The method of claim 11 , comprising linking the inputs, outputs, or both, of a local containerized task to another containerized task based, at least in part, on the task deployment map.

18. The method of claim 11 , comprising launching a plurality of tasks to start an application.

19. The method of claim 11 , comprising moving a containerized task from a first IoT device to a second IoT device based, at least in part, on metrics reported by the first IoT device.

20. A non-transitory, machine readable medium comprising code that, when executed, directs a processor to:
create a device/capability map of a plurality of onboarded devices;
match application requirements to the device/capability map;
produce a task deployment map; and
communicate the task deployment map to a controller in each of the plurality of onboarded devices.

21. The non-transitory, machine readable medium of claim 20 , comprising code that, when executed, directs a processor to:
receive a request from a controller for a task image; and
send the task image from a task image repository to the controller if the task image is available.

22. The non-transitory, machine readable medium of claim 20 , comprising code that, when executed, directs a processor to:
receive a request from a controller for a task image;
build the task image if the task image is not present in a task image repository;
save the task image to the task image repository; and
send the task image from the task image repository to the controller.

23. The non-transitory, machine readable medium of claim 20 , comprising code that, when executed, directs a processor to build a task image, comprising packaging a task in a container, wherein the container is a code segment designed to allow the task to function in a target environment.

24. The non-transitory, machine readable medium of claim 20 , comprising code that, when executed, directs a processor to launch a task.

25. The non-transitory, machine readable medium of claim 20 , comprising code that, when executed, directs a processor to move a containerized task from a first IoT device to a second IoT device based, at least in part, on metrics reported by the first IoT device.

Assignees

• Intel Corp

Inventors

• Yarvis Mark D
• Berck Aaron R
• Garg Sharad K
• Rathbone Casey T
• Shirtz Andrew G
• Thomas Ron Kuruvilla
• Zhang Xubo

Classifications

• H04L67/60

  Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources (admission control or resource allocation H04L47/70) · CPC title

• H04L67/125

  involving control of end-device applications over a network · CPC title

• H04L67/10 Primary

  in which an application is distributed across nodes in the network (software deployment G06F8/60; multiprogramming arrangements G06F9/46) · CPC title

• G06F9/5066

  Algorithms for mapping a plurality of inter-dependent sub-tasks onto a plurality of physical CPUs (mappping at compile time, see G06F8/451) · CPC title

• H04L67/34

  involving the movement of software or configuration parameters  (network booting or remote initial program loading [RIPL] G06F9/4416) · CPC title