Federated Data Center Resource Allocation for Application Scaling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In a multi-data center environment, when an application requires capacity expansion but the resources in its host data center are exhausted, existing methods fail to efficiently utilize available resources in other data centers, leading to delayed capacity expansion and low resource utilization.
Innovation Solution
An application scaling management method and apparatus that dynamically selects a secondary data center with sufficient resources, creates a virtual machine, establishes a network connection, and registers it with the main control node, allowing the application to expand capacity using the secondary data center's resources, and migrates resources back when necessary.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If capacity expansion is performed on the data center A when resources are exhausted, then the application capacity can be expanded, but new hardware needs to be purchased and the process is time-consuming
Solution Approach 1:
The patent merges multiple data centers into a unified resource pool, allowing the system to combine available resources from data center B with the application requirements from data center A. This enables capacity expansion without waiting for new hardware procurement by utilizing existing resources across the federated data center network.
Solution Approach 2:
The patent creates a universal resource allocation system where data centers can serve multiple functions - acting as both primary and backup resources for different applications. Data center B's remaining resources become universally available to support applications from data center A, eliminating the need for dedicated hardware for each application's capacity expansion.
2Productivity
If capacity expansion is performed on the data center A when resources are exhausted, then the application capacity can be expanded, but resource utilization is low because remaining resources in data center B cannot be utilized
Solution Approach 1:
The patent merges the resource pools of data center A and data center B into a unified federated resource system. This allows the system to combine available resources from data center B with the application requirements from data center A, enabling full utilization of remaining resources across the network rather than leaving them idle.
Solution Approach 2:
The patent introduces a federated resource management system as an intermediary that mediates between applications in data center A and available resources in data center B. This intermediary automatically matches resource demands with available capacity across data centers, ensuring optimal resource utilization without manual intervention.
3Productivity
If resources are allocated from another data center, then resource utilization improves and capacity expansion is faster, but network connection and resource allocation complexity increases
Solution Approach 1:
The patent implements a self-service federated resource allocation system where data centers automatically discover and utilize available resources from other data centers without manual configuration. The system autonomously manages resource provisioning, network connectivity, and load balancing across the federated environment, reducing the perceived complexity for users while enabling rapid capacity expansion.
Data Source
AI summary
An application scaling management method and apparatus are disclosed, so as to perform, in a case in which an application requires capacity expansion and remaining resources of a data center in which the application runs are insufficient, capacity expansion of the application by utilizing remaining resources of another data center, thereby improving resource utilization and capacity expansion efficiency.