Data Center Resource Composition via Network Topology Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional data center management software lacks the ability to efficiently compose and allocate resources to meet the dynamic demands of users, particularly in terms of network topology and resource availability, leading to suboptimal performance and resource utilization.

Innovation Solution

A management application that communicates with data center management software to collect and analyze connection status between nodes and switches, generating a network topology and allocating resources based on user requests, including patching Ethernet interfaces for MLAG and LAG functionality, to ensure resource matching and efficient resource utilization.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If conventional data center management software is used to manage resources, then basic resource allocation is possible, but the ability to efficiently compose and allocate resources to meet dynamic user demands is insufficient

Engineering Contradiction:
Improveresource composition capabilityVSAvoidresource allocation efficiency
Core Design Contradiction:
Adaptability or versatilityVSProductivity

Solution Approach 1:

The system dynamically discovers network topology and continuously updates the matched node database based on real-time connection status changes. The management application automatically adapts to topology changes by re-evaluating connection status and updating the matched nodes database, enabling flexible resource composition that responds to dynamic user demands without manual reconfiguration

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The management application autonomously composes resources by automatically discovering network topology, identifying matched nodes based on connection status, and allocating resources without human intervention. The system self-manages the entire resource composition process from topology discovery to resource allocation and decomposition, improving both adaptability and productivity

Inventive Principle:
Principle #25Self-service

2Ease of operation

If manual resource allocation is performed, then resource composition can be controlled, but the process is time-consuming and inefficient for dynamic demands

Engineering Contradiction:
Improveresource allocation automationVSAvoidresource composition time
Core Design Contradiction:
Ease of operationVSLoss of time

Solution Approach 1:

The system performs preliminary discovery of network topology and pre-identifies matched nodes by evaluating connection status before user requests arrive. The management application continuously monitors and updates the matched nodes database in advance, so when resource allocation is needed, the system can immediately compose resources without time-consuming manual evaluation

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The management application automatically performs resource composition by querying the pre-updated matched nodes database and allocating resources based on user requirements. This automated self-service approach eliminates manual intervention entirely, making resource allocation both easier to operate and significantly faster

Inventive Principle:
Principle #25Self-service

3Measurement precision

If network topology information is not maintained, then system complexity is reduced, but resource matching and allocation accuracy deteriorates

Engineering Contradiction:
Improveresource matching accuracyVSAvoidnetwork topology management
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system implements continuous feedback by monitoring connection status changes in real-time and automatically updating the matched nodes database. When topology changes occur, the management application receives notifications, re-evaluates connection status, and updates the database accordingly, ensuring resource matching accuracy is maintained without requiring complex manual topology management

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The management application autonomously maintains network topology information by automatically discovering connections, evaluating matched nodes, and updating its internal database without external intervention. This self-maintaining approach improves measurement precision for resource matching while the automation actually reduces the operational complexity for users

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP3442166B1Composing by network attributes
Publication Date: 2020.06.24 QUANTA COMPUTER INC
  • EP3442166B1 patent drawingFigure 1A
  • EP3442166B1 patent drawingFigure 1B
  • EP3442166B1 patent drawingFigure 1C

AI summary

The present disclosure provides a system and method for automatically composing resources in a data center using a management application. The management application can communicate with a data center management software to collect information of computer resource, storage resource, and network resource of the data center. Based at least upon the network resource information of the data center, the management application can generate a network topology of the data center. In response to receiving a request from a specific user, the management application can compose suitable resources of the data center to match the request.