Edge Network Cluster Management With Selective Service Updates

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing virtual computing systems face challenges in efficiently updating configurations of specific services within clusters due to slow and resource-intensive bundle upgrades, and issues with communication and processing of cluster state changes between edge networks and servers.

Innovation Solution

A telemetry platform with intelligent edge processing units that dynamically push and rollback configurations from a cloud server, identify missed configuration state changes, and manage data processing to reduce false positives and enhance flexibility in hyper-converged environments.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If bundle upgrades are used to update configurations in virtual computing systems, then configuration updates can be applied, but the process becomes slow and resource-intensive

Engineering Contradiction:
Improveconfiguration update speedVSAvoidresource consumption
Core Design Contradiction:
ProductivityVSLoss of energy

Solution Approach 1:

The patent segments the monolithic bundle upgrade process into individual service configuration updates. Instead of upgrading entire bundles, the system updates configurations of specific services independently, allowing faster and more resource-efficient configuration changes. This is achieved by parsing configuration data into service-specific segments and applying them selectively.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent extracts the configuration update process from the bundle upgrade mechanism. By separating configuration management from bundle deployment, the system can apply configuration changes without triggering full bundle upgrades, thereby reducing resource consumption and update time while maintaining the ability to apply necessary configuration changes.

Inventive Principle:
Principle #2Taking out (Extraction)

2Extent of automation

If configuration state changes are communicated between edge networks and servers, then centralized control is maintained, but communication overhead and processing delays increase

Engineering Contradiction:
Improvecentralized configuration controlVSAvoidconfiguration propagation delay
Core Design Contradiction:
Extent of automationVSLoss of time

Solution Approach 1:

The patent implements preliminary action by having edge processing units detect and handle configuration state changes locally before server communication is required. The system preemptively identifies configuration changes at the edge, processes them locally when possible, and only communicates with the server when centralized coordination is necessary, thereby reducing communication overhead and propagation delays.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent introduces dynamics by enabling the configuration management system to adapt its communication pattern based on the situation. The system dynamically determines whether to communicate configuration changes to the server or handle them locally at the edge, optimizing the balance between centralized control and response time based on the specific configuration change and system state.

Inventive Principle:
Principle #15Dynamics

3Stability of the object's composition

If all nodes in a cluster apply the same configuration, then consistency is maintained, but flexibility to handle node-specific issues is reduced

Engineering Contradiction:
Improveconfiguration consistencyVSAvoidnode-specific configuration flexibility
Core Design Contradiction:
Stability of the object's compositionVSAdaptability or versatility

Solution Approach 1:

The patent applies local quality by allowing different configuration parameters to be applied to different nodes based on their specific needs and states. Instead of uniform configuration application, the system evaluates each node's configuration state individually and applies configurations selectively, enabling node-specific customization while maintaining overall system consistency through controlled propagation of configuration changes.

Inventive Principle:
Principle #3Local quality

4Productivity

If configuration updates are pushed to edge devices, then rapid deployment is achieved, but false positives and erroneous updates may occur

Engineering Contradiction:
Improveconfiguration deployment speedVSAvoidconfiguration update accuracy
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The patent implements feedback mechanisms where edge processing units monitor the results of configuration updates and communicate status information back to the system. This feedback loop allows the system to detect false positives, identify erroneous updates, and correct issues promptly, thereby maintaining high deployment speed while improving update accuracy through continuous verification and adjustment based on actual system responses.

Inventive Principle:
Principle #23Feedback

Data Source

PatentEP3993353B1System and method for managing clusters in an edge network
Publication Date: 2025.10.29 NUTANIX INC
  • EP3993353B1 patent drawingFigure 1
  • EP3993353B1 patent drawingFigure 2
  • EP3993353B1 patent drawingFigure 3

AI summary

Various embodiments disclosed herein are related to an apparatus. In some embodiments, the apparatus includes a processor and a memory. In some embodiments, the memory includes instructions that, when executed by the processor, cause the apparatus to collect, at a cloud server, service data from a collector framework service of an edge network. In some embodiments, the memory includes instructions that, when executed by the processor, cause the apparatus to provide a configuration to the collector framework service based on the service data.