Distributed Data Center Resource Pooling via Virtualization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional data center architectures face issues such as low resource utilization, complex administration and maintenance, and high occurrence probabilities of network connection faults or traffic congestion due to tight coupling of software applications with physical devices and lack of unified resource management across data centers.
Innovation Solution
A resource provisioning method is introduced that creates a distributed data center system with a cross-data-center scheduler, intelligent resource routing module, and network controllers to dynamically allocate resources, create virtual networks and machines, and synchronize them across multiple data centers, transforming physical resources into a unified 'logical resource pool' for flexible scheduling.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a physical hierarchical architecture is adopted with multiple data center layers, then service quality requirements can be met, but resource utilization decreases and administration becomes complex
Solution Approach 1:
The patent segments the physical hierarchical architecture into multiple independent data centers (first data center, second data center, third data center) that can be independently managed and utilized. Each data center operates as a separate entity with its own resources, allowing flexible allocation and improved overall resource utilization while maintaining service quality through distributed architecture.
2Ease of manufacture
If software applications are bound to physical computing and storage devices, then deployment is straightforward, but capacity expansion and upgrades become complex
Solution Approach 1:
The patent extracts the binding between software applications and physical devices by introducing virtualization technology. Software applications are deployed on virtual machines that can be dynamically allocated across physical computing and storage devices in different data centers, decoupling the software from specific hardware while simplifying deployment and expansion operations.
Solution Approach 2:
The patent creates a universal resource pool where computing and storage resources from multiple data centers can be dynamically allocated to serve different software applications. This multi-functional resource pool allows the same physical infrastructure to support diverse workloads, simplifying capacity expansion and upgrades without requiring application-specific hardware configurations.
3Reliability
If data centers are distributed across multiple locations, then service quality improves, but network connection faults and traffic congestion increase
Solution Approach 1:
The patent merges the resource pools of multiple geographically distributed data centers into a unified virtual resource pool. By combining computing and storage resources from the first, second, and third data centers, the system achieves load balancing and failover capabilities that reduce network connection faults and traffic congestion while maintaining the benefits of distributed architecture.
Data Source
AI summary
Embodiments of the present invention provides a resource provisioning method, including: receiving, by a first data center, a resource request message, where the first data center is any data center that receives the resource request message in the system; obtaining, by the first data center and by analyzing the resource request message, at least two destination data centers that provision resources; creating a virtual network; creating a virtual machine for the at least two destination data centers; and adding the virtual machine to the virtual network. By implementing the method, the resource utilization of a data center is improved, administration, maintenance, and operation are simplified, and an occurrence probability of network connection fault or traffic congestion is reduced.