Granted Patent B2

US 12,519,696 · App. 18/311,156 · Granted Jan 6, 2026

Inventors: Roger William Lucas (England, GB); Clint Smith (New York, NY)

Assignee: Veea Inc.

H04L41/0893H04L41/0813

Abstract

Claims (122)

1 . A method of dynamically grouping edge nodes within an elastic edge computing system that includes a container orchestration service and a mesh of edge nodes that communicate over wired or wireless links, the method comprising:

collecting, by a processor in an edge node, information about the edge nodes and associated end devices within the elastic edge computing system;

using, by the processor, the collected information to determine characteristics of the edge nodes and end devices;

determining, by the processor, a group objective for each of a plurality of available groups based on group configurations and the determined characteristics;

requesting, by the processor, membership to one or more of the plurality of available groups based on the determined group objectives;

clustering, by the processor, the edge nodes based on the determined characteristics and group memberships; and

dynamically adjusting, by the processor, group configurations or the group memberships in response to changes in conditions in the elastic edge computing system,

wherein the dynamic adjustments include at least one of:

instantiating a container on a selected edge node,

reassigning an application instance or an end device to the selected edge node, and

defining a packet route between the selected edge node and a prior edge node, an end device, or a cloud service.

2 . The method of claim 1 , wherein determining the group objective for each of the plurality of available groups based on the group configurations and the characteristics of the edge node comprises one or more of:

determining a specific set of device capabilities or resources for each group;

determining an intended function or service to be provided by the edge nodes within each group;

determining a specific communication protocol or network architecture to be used by the edge nodes within each group;

determining a desired level of redundancy or resiliency for each group;

determining a specific geographic coverage area or proximity for each group;

determining a specific set of security or privacy requirements for each group;

determining a specific set of performance metrics or quality of service (QOS) criteria for each group;

determining a specific set of energy consumption or power management requirements for each group;

determining a specific set of device management or maintenance requirements for each group;

determining a specific set of data storage or processing requirements for each group; or

determining a distribution of containers within the edge nodes, between edge nodes, within end devices, between end devices, or between edge nodes and end devices.

3 . The method of claim 1 , wherein:

the edge nodes and end devices run containers; and

the method further comprises dynamically allocating container groups:

within the edge nodes,

between edge nodes,

within end devices,

between end devices, or

between edge nodes and end devices.

4 . The method of claim 1 , further comprising:

determining relationships among the edge nodes and end devices across multiple dimensions;

determining a set of common criteria representing similarities among the edge nodes and end devices for forming logical groups;

automatically forming logical groups of edge nodes and end devices based on the determined common criteria, wherein each group consists of devices sharing similar characteristics or devices configured to implement a corresponding group objective;

allocating each edge node and end device to an appropriate logical group based on the identified relationships and common criteria;

monitoring a performance or status of the edge nodes and end devices within each group and changes in the overall elastic edge computing system; and

dynamically adjusting group memberships and configurations based on a result of the monitoring.

5 . The method of claim 1 , further comprising dynamically forming, by the processor, a group based on two or more of a unique identifier parameter, edge node capability parameter, an edge node location parameter, a subnet parameter, an application parameter, a classification parameter, or an amount of time one or more of the edge nodes or associated end devices have been active and connected to the elastic edge computing system.

6 . The method of claim 1 , further comprising:

generating, by the processor, an N-dimensional correlation for edge nodes and end devices based on their relationships across multiple dimensions; and

automatically forming, by the processor, logical groups of edge nodes and end devices based on the N-dimensional correlation, wherein the logical groups may include overlapping groupings and multiple group memberships.

7 . The method of claim 6 , wherein generating the N-dimensional correlation for edge nodes and end devices across multiple dimensions comprise one or more of:

generating the N-dimensional correlation for edge nodes and end devices based on collected information, the collected information identifying at least one or more of device capabilities, scalability, device location, network parameters, application requirements, device classification, power consumption, security requirements, privacy requirements, device reliability, resource availability, or device interoperability information; or

using machine learning or clustering to generate the N-dimensional correlation for edge nodes and end devices.

8 . An edge node, comprising:

a processor configured to:

collect information about edge nodes and associated end devices within an elastic edge computing system that includes a container orchestration service and a mesh of edge nodes that communicate over wired or wireless links;

use the collected information to determine characteristics of the edge nodes and end devices;

determine a group objective for each of a plurality of available groups based on group configurations and the determined characteristics;

request membership to one or more of the plurality of available groups based on the determined group objectives;

cluster the edge nodes based on the determined characteristics and group memberships; and

dynamically adjust group configurations or the group memberships in response to changes in conditions in the elastic edge computing system,

wherein the dynamic adjustments include at least one of:

instantiating a container on a selected edge node,

reassigning an application instance or an end device to the selected edge node, and

defining a packet route between the selected edge node and a prior edge node, an end device, or a cloud service.

9 . The edge node of claim 8 , wherein the processor is configured to determine the group objective for each of the plurality of available groups based on the group configurations and the characteristics of the edge node by determining one or more of:

a specific set of device capabilities or resources for each group;

an intended function or service to be provided by the edge nodes within each group;

a specific communication protocol or network architecture to be used by the edge nodes within each group;

a desired level of redundancy or resiliency for each group;

a specific geographic coverage area or proximity for each group;

a specific set of security or privacy requirements for each group;

a specific set of performance metrics or quality of service (QOS) criteria for each group;

a specific set of energy consumption or power management requirements for each group;

a specific set of device management or maintenance requirements for each group;

a specific set of data storage or processing requirements for each group; or

a distribution of containers within the edge nodes, between edge nodes, within end devices, between end devices, or between edge nodes and end devices.

10 . The edge node of claim 8 , wherein the edge nodes and end devices run containers, and wherein the processor is configured to dynamically allocate container groups within the edge nodes, between edge nodes, within end devices, between end devices, or between edge nodes and end devices.

11 . The edge node of claim 8 , wherein the processor is further configured to:

determine relationships among the edge nodes and end devices across multiple dimensions;

determine a set of common criteria representing similarities among the edge nodes and end devices for forming logical groups;

automatically form logical groups of edge nodes and end devices based on the determined common criteria, wherein each group consists of devices sharing similar characteristics or devices configured to implement a corresponding group objective;

allocate each edge node and end device to an appropriate logical group based on the identified relationships and common criteria;

monitor a performance or status of the edge nodes and end devices within each group and changes in the overall elastic edge computing system; and

dynamically adjust group memberships and configurations based on a result of the monitoring.

12 . The edge node of claim 8 , wherein the processor is further configured to dynamically form a group based on two or more of a unique identifier parameter, edge node capability parameter, an edge node location parameter, a subnet parameter, an application parameter, a classification parameter, or an amount of time one or more of the edge nodes or associated end devices have been active and connected to the elastic edge computing system.

13 . The edge node of claim 8 , wherein the processor is further configured to:

generate an N-dimensional correlation for edge nodes and end devices based on their relationships across multiple dimensions; and

automatically form logical groups of edge nodes and end devices based on the N-dimensional correlation, wherein the logical groups may include overlapping groupings and multiple group memberships.

14 . The edge node of claim 13 , wherein the processor is configured to generate the N-dimensional correlation for edge nodes and end devices across multiple dimensions by:

generating the N-dimensional correlation for edge nodes and end devices based on collected information, the collected information identifying at least one or more of device capabilities, scalability, device location, network parameters, application requirements, device classification, power consumption, security requirements, privacy requirements, device reliability, resource availability, or device interoperability information; or

using machine learning or clustering to generate the N-dimensional correlation for edge nodes and end devices.

15 . A non-transitory computer readable storage medium having stored thereon processor-executable software instructions configured to cause a processor to perform operations for dynamically grouping edge nodes within an elastic edge computing system that includes a container orchestration service and a mesh of edge nodes that communicate over wired or wireless links, the operations comprising:

collecting information about edge nodes and associated end devices within the elastic edge computing system;

using the collected information to determine characteristics of the edge nodes and end devices;

determining a group objective for each of a plurality of available groups based on group configurations and the determined characteristics;

requesting membership to one or more of the plurality of available groups based on the determined group objectives;

clustering the edge nodes based on the determined characteristics and group memberships; and

dynamically adjusting the group configurations or group memberships in response to changes in conditions in the elastic edge computing system,

wherein the dynamic adjustments include at least one of:

instantiating a container on a selected edge node,

reassigning an application instance or an end device to the selected edge node, and

defining a packet route between the selected edge node and a prior edge node, an end device, or a cloud service.

16 . The non-transitory computer readable storage medium of claim 15 , wherein the stored processor-executable software instructions are configured to cause a processor to perform operations such that determining the group objective for each of the plurality of available groups based on the group configurations and the characteristics of the edge node comprises one or more of:

determining a specific set of device capabilities or resources for each group;

determining an intended function or service to be provided by the edge nodes within each group;

determining a specific communication protocol or network architecture to be used by the edge nodes within each group;

determining a desired level of redundancy or resiliency for each group;

determining a specific geographic coverage area or proximity for each group;

determining a specific set of security or privacy requirements for each group;

determining a specific set of performance metrics or quality of service (QOS) criteria for each group;

determining a specific set of energy consumption or power management requirements for each group;

determining a specific set of device management or maintenance requirements for each group;

determining a specific set of data storage or processing requirements for each group; or

determining a distribution of containers within the edge nodes, between edge nodes, within end devices, between end devices, or between edge nodes and end devices.

17 . The non-transitory computer readable storage medium of claim 15 , wherein the stored processor-executable software instructions are configured to cause a processor to perform operations such that the edge nodes and end devices run containers, the method further comprising dynamically allocating container groups within the edge nodes, between edge nodes, within end devices, between end devices, or between edge nodes and end devices.

18 . The non-transitory computer readable storage medium of claim 15 , wherein the stored processor-executable software instructions are configured to cause a processor to perform operations further comprising:

determining relationships among the edge nodes and end devices across multiple dimensions;

determining a set of common criteria representing similarities among the edge nodes and end devices for forming logical groups;

automatically forming logical groups of edge nodes and end devices based on the determined common criteria, wherein each group consists of devices sharing similar characteristics or devices configured to implement a corresponding group objective;

allocating each edge node and end device to an appropriate logical group based on the identified relationships and common criteria;

monitoring a performance or status of the edge nodes and end devices within each group and changes in the overall elastic edge computing system; and

dynamically adjusting group memberships and configurations based on a result of the monitoring.

19 . The non-transitory computer readable storage medium of claim 15 , wherein the stored processor-executable software instructions are configured to cause a processor to perform operations further comprising dynamically forming, by the processor, a group based on two or more of a unique identifier parameter, edge node capability parameter, an edge node location parameter, a subnet parameter, an application parameter, a classification parameter, or an amount of time one or more of the edge nodes or associated end devices have been active and connected to the elastic edge computing system.

20 . The non-transitory computer readable storage medium of claim 15 , wherein the stored processor-executable software instructions are configured to cause a processor to perform operations further comprising:

generating, by the processor, an N-dimensional correlation for edge nodes and end devices based on their relationships across multiple dimensions; and

automatically forming, by the processor, logical groups of edge nodes and end devices based on the N-dimensional correlation, wherein the logical groups may include overlapping groupings and multiple group memberships,

wherein generating the N-dimensional correlation for edge nodes and end devices across multiple dimensions comprise one or more of:

generating the N-dimensional correlation for edge nodes and end devices based on collected information, the collected information identifying at least one or more of device capabilities, scalability, device location, network parameters, application requirements, device classification, power consumption, security requirements, privacy requirements, device reliability, resource availability, or device interoperability information; or

using machine learning or clustering to generate the N-dimensional correlation for edge nodes and end devices.

Assignments (1)

Continuity (2)

References Cited (16)