Metadata Tag-Based Resource Allocation in Distributed Data Centers

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current data center management systems lack efficient automated methods for optimizing resource allocation across multiple data centers based on metadata tags, leading to suboptimal placement and allocation of virtualized compute and storage resources.

Innovation Solution

A global orchestrator uses metadata tags to select the appropriate data center for allocating resources by identifying objects within a resource object model that meet specific criteria, enabling automated management and optimization of resource placement and allocation across multiple data centers.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If automated resource allocation using metadata tags is implemented, then resource allocation efficiency is improved, but system complexity increases

Engineering Contradiction:
Improveresource allocation efficiencyVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent introduces a global orchestrator as an intermediary component that manages resource allocation across multiple data centers. The orchestrator uses metadata tags and resource policies to automatically determine optimal resource placement, reducing manual intervention while maintaining controlled complexity through centralized management rather than distributed complexity across all systems

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system changes the state of resource management by introducing metadata tags with specific criteria (such as location, latency requirements) that transform how resources are identified and allocated. This parameter-based approach enables automated decision-making based on tagged attributes rather than manual configuration, improving efficiency while keeping the underlying system architecture relatively simple

Inventive Principle:
Principle #35Parameter changes

2Device complexity

If manual resource placement methods are used, then system complexity is reduced, but resource allocation efficiency deteriorates

Engineering Contradiction:
Improvesystem complexityVSAvoidresource allocation efficiency
Core Design Contradiction:
Device complexityVSProductivity

Solution Approach 1:

The system enables self-service automated resource allocation where the global orchestrator autonomously evaluates metadata tags, applies resource policies, and determines optimal data center selections without manual intervention. This self-automating mechanism improves allocation efficiency while maintaining manageable complexity through rule-based decision-making rather than complex human coordination

Inventive Principle:
Principle #25Self-service

3Productivity

If multidimensional metadata tag sets are used for resource selection, then resource placement optimization is improved, but measurement and detection difficulty increases

Engineering Contradiction:
Improveresource placement optimizationVSAvoidtag criteria evaluation complexity
Core Design Contradiction:
ProductivityVSDifficulty of detecting and measuring

Solution Approach 1:

The patent segments the resource selection process into distinct evaluable components by using separate metadata tags for different criteria (location, latency, resource type). Each tag represents a discrete attribute that can be independently evaluated and matched against policy requirements, making the multidimensional selection process more manageable through modular tag-based filtering rather than monolithic complex queries

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP3754494B1Using multidimensional metadata tag sets to determine resource allocation in a distributed computing environment
Publication Date: 2024.08.28 JUNIPER NETWORKS INC
  • EP3754494B1 patent drawingFigure 1
  • EP3754494B1 patent drawingFigure 2
  • EP3754494B1 patent drawingFigure 3

AI summary

An example method includes receiving a resource request for at least one compute and/or storage resource from a distributed computing system distributed among multiple data centers, determining a resource policy that is associated with the resource request, wherein the resource policy includes a rule specifying at least one metadata tag and at least one criterion associated with the at least one metadata tag, identifying at least one object included in a resource object model that complies with the rule of the resource policy, wherein the at least one object has an assigned value for the metadata tag that satisfies the at least one criterion, selecting a data center that is associated with the at least one object identified from the resource object model, and deploying, on the selected data center, the at least one compute or storage resource.