Cloud Data Center Architecture for High Availability and Utilization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current cloud computing models face challenges in achieving high availability and high utilization simultaneously, particularly in telecommunications services, due to low resource utilization and high latency issues, which increase capital and operational expenditures.
Innovation Solution
A high availability and high utilization cloud data center architecture is implemented, utilizing multiple geo-sites with availability zones and regions, enabling geo-redundancy and local redundancy models to manage failures while maintaining real-time performance requirements, such as the 4-site and 3-site models that achieve 37.5%, 66%, and 75% resource utilization with five 9s availability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If cloud computing resources are increased to meet demand, then service availability is improved, but resource utilization deteriorates
Solution Approach 1:
The system segments cloud resources into multiple availability zones (AZs) and regions (ARs) across different geo-sites. This segmentation allows independent failure containment while maintaining resource sharing opportunities, resolving the contradiction by enabling high availability through geographic distribution without requiring complete resource isolation that would reduce utilization.
Solution Approach 2:
The patent introduces a hierarchical geographic dimension (geo-sites → availability zones → availability regions) to resource organization. This additional spatial dimension enables resources to be both isolated for availability and shared across regions for utilization, transforming the traditional single-level resource management approach.
2Reliability
If resources are distributed across multiple availability zones to achieve high availability, then system reliability is improved, but latency increases
Solution Approach 1:
The system implements local redundancy within each availability zone, where resources are replicated only where needed. This local quality approach maintains low latency for local operations while providing availability through the broader geographic distribution, resolving the contradiction between immediate performance and system reliability.
Solution Approach 2:
The patent implements partial redundancy at the availability zone level rather than complete replication across all regions. This partial action provides sufficient availability protection while minimizing the latency penalty, as resources remain accessible within the same AZ for real-time operations.
3Reliability
If geo-redundancy is implemented across multiple sites, then availability is improved, but capital and operational expenditures increase
Solution Approach 1:
The availability zones and regions serve multiple functions: they provide failure isolation, enable resource sharing, support load balancing, and facilitate coordinated failures. This multi-functionality reduces the need for separate dedicated redundancy infrastructure, lowering capital and operational expenditures while maintaining high availability.
Solution Approach 2:
The system dynamically adjusts resource allocation parameters based on demand and failure conditions. Resources can be shifted between availability zones and regions as needed, optimizing the balance between availability protection and cost efficiency, thereby reducing unnecessary expenditures on over-provisioned redundancy.
Data Source
AI summary
The concepts and technologies disclosed herein provide high availability and high utilization cloud data center architecture for supporting telecommunications services. According to one aspect of the concepts and technologies disclosed herein, a 4-site model of application placement within the cloud computing environment provides 37.5% resource utilization with site availability of five 9s (99.999%) and virtual machine availability of five 9s. According to another aspect of the concepts and technologies disclosed herein, a 3-site model of application placement within the cloud computing environment provides 66% resource utilization with site availability of five 9s and virtual machine availability of five 9s. According to another aspect of the concepts and technologies disclosed herein, a 4-site model of application placement within the cloud computing environment provides 75% resource utilization with site availability of five 9s and virtual machine availability of five 9s.