IP Library Granted Patent US 11,496,550
Granted Patent B2
US 11,496,550 · App. 17/105,030 · Granted Nov 8, 2022

Method, system, and computer program product for deploying application

Inventors: Jinpeng Liu (Shanghai, CN); Jin Li (Shanghai, CN)
Assignee: EMC IP Holding Company LLC
H04L67/10G06N5/04G06N20/00H04L41/12
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,496,550
App. No.
17/105,030
Granted
Nov 8, 2022
Kind
B2
Abstract

Methods, systems, and computer program products for deploying an application. One method includes acquiring a computational graph corresponding to an application. The computational graph includes a plurality of nodes corresponding to operations performed by the application, the nodes including at least one input node for exchanging data with at least one terminal device and at least one computational node for processing data. The at least one input node is deployed to a first group of edge nodes co-located with a first base station serving the at least one terminal device, and the at least one computational node is deployed to a second group of edge nodes co-located with an area data center. Illustrative embodiments of the present disclosure enable an input node to be as close to a user as possible, thereby achieving low response delays while meeting the requirements of a computational node for storage and computational resources.

Claims (46)

1. A method for deploying an application, comprising:

acquiring a computational graph corresponding to an application, the computational graph comprising a plurality of nodes corresponding to operations performed by the application, and the plurality of nodes comprising at least one input node for exchanging data with at least one terminal device and at least one computational node for processing data;

deploying the at least one input node to a first group of edge nodes co-located with a first base station serving the at least one terminal device; and

deploying the at least one computational node to a second group of edge nodes co-located with an area data center.

2. The method according to claim 1 , further comprising:

based on an association relationship between the at least one input node and the at least one terminal device, establishing a first data path between the at least one terminal device and the first group of edge nodes; and

based on an association relationship between the at least one input node and the at least one computational node, establishing a second data path between the first group of edge nodes and the second group of edge nodes.

3. The method according to claim 1 , further comprising:

in response to a movement of the at least one terminal device from a first cell provided by the first base station to a second cell provided by a second base station, migrating the at least one input node from the first group of edge nodes to a third group of edge nodes co-located with the second base station.

4. The method according to claim 3 , further comprising:

based on the association relationship between the at least one input node and the at least one terminal device, establishing a third data path between the at least one terminal device and the third group of edge nodes; and

based on the association relationship between the at least one input node and the at least one computational node, establishing a fourth data path between the third group of edge nodes and the second group of edge nodes.

5. The method according to claim 1 , wherein the first group of edge nodes and the second group of edge nodes are devices that implement a multi-access edge computing system.

6. The method according to claim 3 , wherein the third group of edge nodes are devices that implement a multi-access edge computing system.

7. The method according to claim 1 , wherein the application performs inference tasks by using a machine learning model and based on data from the at least one terminal device.

8. A system for deploying an application, comprising:

at least one processing unit; and

at least one memory which is coupled to the at least one processing unit and stores instructions for execution by the at least one processing unit, wherein the instructions, when executed by the at least one processing unit, cause the system to perform actions comprising:

acquiring a computational graph corresponding to an application, the computational graph comprising a plurality of nodes corresponding to operations performed by the application, and the plurality of nodes comprising at least one input node for exchanging data with at least one terminal device and at least one computational node for processing data;

deploying the at least one input node to a first group of edge nodes co-located with a first base station serving the at least one terminal device; and

deploying the at least one computational node to a second group of edge nodes co-located with an area data center.

9. The system according to claim 8 , wherein the actions further comprise:

based on an association relationship between the at least one input node and the at least one terminal device, establishing a first data path between the at least one terminal device and the first group of edge nodes; and

based on an association relationship between the at least one input node and the at least one computational node, establishing a second data path between the first group of edge nodes and the second group of edge nodes.

10. The system according to claim 8 , wherein the actions further comprise:

in response to a movement of the at least one terminal device from a first cell provided by the first base station to a second cell provided by a second base station, migrating the at least one input node from the first group of edge nodes to a third group of edge nodes co-located with the second base station.

11. The system according to claim 10 , wherein the actions further comprise:

based on the association relationship between the at least one input node and the at least one terminal device, establishing a third data path between the at least one terminal device and the third group of edge nodes; and

based on the association relationship between the at least one input node and the at least one computational node, establishing a fourth data path between the third group of edge nodes and the second group of edge nodes.

12. The system according to claim 8 , wherein the first group of edge nodes and the second group of edge nodes are devices that implement a multi-access edge computing system.

13. The system according to claim 10 , wherein the third group of edge nodes are devices that implement a multi-access edge computing system.

14. The system according to claim 8 , wherein the application performs inference tasks by using a machine learning model and based on data from the at least one terminal device.

15. A computer program product tangibly stored in a non-transitory computer storage medium and comprising machine-executable instructions that, when executed by a device, cause the device to perform a method for deploying an application, the method comprising:

acquiring a computational graph corresponding to an application, the computational graph comprising a plurality of nodes corresponding to operations performed by the application, and the plurality of nodes comprising at least one input node for exchanging data with at least one terminal device and at least one computational node for processing data;

deploying the at least one input node to a first group of edge nodes co-located with a first base station serving the at least one terminal device; and

deploying the at least one computational node to a second group of edge nodes co-located with an area data center.

16. The computer program product according to claim 15 , further comprising:

based on an association relationship between the at least one input node and the at least one terminal device, establishing a first data path between the at least one terminal device and the first group of edge nodes; and

based on an association relationship between the at least one input node and the at least one computational node, establishing a second data path between the first group of edge nodes and the second group of edge nodes.

17. The computer program product according to claim 15 , further comprising:

in response to a movement of the at least one terminal device from a first cell provided by the first base station to a second cell provided by a second base station, migrating the at least one input node from the first group of edge nodes to a third group of edge nodes co-located with the second base station.

18. The computer program product according to claim 17 , further comprising:

based on the association relationship between the at least one input node and the at least one terminal device, establishing a third data path between the at least one terminal device and the third group of edge nodes; and

based on the association relationship between the at least one input node and the at least one computational node, establishing a fourth data path between the third group of edge nodes and the second group of edge nodes.

19. The computer program product according to claim 15 , wherein the first group of edge nodes and the second group of edge nodes are devices that implement a multi-access edge computing system.

20. The computer program product according to claim 17 , wherein the third group of edge nodes are devices that implement a multi-access edge computing system.

Assignments (9)
RELEASE OF SECURITY INTEREST IN PATENTS PREVIOUSLY RECORDED AT REEL/FRAME (055479/0342) Recorded Jun 10, 2022
From: THE BANK OF NEW YORK MELLON TRUST COMPANY, N.A., AS NOTES COLLATERAL AGENT
To: EMC IP HOLDING COMPANY LLC; DELL PRODUCTS L.P.
Reel/Frame 062021/0460 →
RELEASE OF SECURITY INTEREST IN PATENTS PREVIOUSLY RECORDED AT REEL/FRAME (055479/0051) Recorded Jun 10, 2022
From: THE BANK OF NEW YORK MELLON TRUST COMPANY, N.A., AS NOTES COLLATERAL AGENT
To: EMC IP HOLDING COMPANY LLC; DELL PRODUCTS L.P.
Reel/Frame 062021/0663 →
RELEASE OF SECURITY INTEREST IN PATENTS PREVIOUSLY RECORDED AT REEL/FRAME (056136/0752) Recorded Jun 10, 2022
From: THE BANK OF NEW YORK MELLON TRUST COMPANY, N.A., AS NOTES COLLATERAL AGENT
To: EMC IP HOLDING COMPANY LLC; DELL PRODUCTS L.P.
Reel/Frame 062021/0771 →
RELEASE OF SECURITY INTEREST AT REEL 055408 FRAME 0697 Recorded Nov 2, 2021
From: CREDIT SUISSE AG, CAYMAN ISLANDS BRANCH
To: DELL PRODUCTS L.P.; EMC IP HOLDING COMPANY LLC
Reel/Frame 058001/0553 →
SECURITY INTEREST Recorded Mar 3, 2021
From: EMC IP HOLDING COMPANY LLC; DELL PRODUCTS L.P.
To: THE BANK OF NEW YORK MELLON TRUST COMPANY, N.A., AS NOTES COLLATERAL AGENT
Reel/Frame 056136/0752 →
SECURITY INTEREST Recorded Mar 3, 2021
From: EMC IP HOLDING COMPANY LLC; DELL PRODUCTS L.P.
To: THE BANK OF NEW YORK MELLON TRUST COMPANY, N.A., AS NOTES COLLATERAL AGENT
Reel/Frame 055479/0051 →
SECURITY INTEREST Recorded Mar 3, 2021
From: EMC IP HOLDING COMPANY LLC; DELL PRODUCTS L.P.
To: THE BANK OF NEW YORK MELLON TRUST COMPANY, N.A., AS NOTES COLLATERAL AGENT
Reel/Frame 055479/0342 →
SECURITY AGREEMENT Recorded Feb 25, 2021
From: EMC IP HOLDING COMPANY LLC; DELL PRODUCTS L.P.
To: CREDIT SUISSE AG, CAYMAN ISLANDS BRANCH
Reel/Frame 055408/0697 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 25, 2020
From: LIU, JINPENG; LI, JIN
To: EMC IP HOLDING COMPANY LLC
Reel/Frame 054472/0029 →
Priority Claims (1)
CN 202011182682.4 · Oct 29, 2020 · national
Continuity (1)
Related Publication 20220141282A1 · May 5, 2022