Dynamic Cloud Request Routing via Edge Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Centralized cloud computing models often result in delayed user experiences due to the distance between compute resources and end-users, as well as limitations in rerouting requests during cloud provider difficulties, leading to suboptimal performance and responsiveness.
Innovation Solution
Implementing edge-based resource spin-up by distributing virtualized instances closer to users, dynamically routing requests to the nearest edge servers, and spinning up resources based on demand to enhance responsiveness and efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If compute resources are centralized in a data center cluster, then resource management is simplified, but user response time and performance deteriorate due to distance
Solution Approach 1:
The patent segments the centralized cloud computing model into multiple distributed edge computing locations. Instead of all compute resources being in one centralized data center, the system creates edge clusters at multiple geographic locations closer to end users. This segmentation allows resource management to remain relatively simple while significantly reducing the distance between users and compute resources, thereby improving response time.
Solution Approach 2:
The patent introduces a new spatial dimension to cloud computing architecture by distributing compute resources across multiple geographic locations rather than concentrating them in a single data center. This dimensional change from centralized to distributed architecture enables the system to maintain resource management simplicity while improving user response time through proximity-based resource allocation.
2Ease of manufacture
If applications are deployed to a single cloud, then deployment simplicity is maintained, but system reliability deteriorates when the cloud provider experiences difficulties
Solution Approach 1:
The patent segments the single-cloud deployment model into multi-cloud deployment across multiple edge locations and cloud providers. Applications are deployed to multiple clouds simultaneously, creating segmented redundancy that maintains deployment simplicity through automated provisioning while significantly improving system reliability by eliminating single-point failures.
Solution Approach 2:
The patent changes the deployment parameter from single-cloud to multi-cloud architecture. By deploying applications to multiple cloud providers and edge locations, the system maintains deployment simplicity through standardized processes while improving reliability through geographic and provider diversification, allowing requests to be routed around failures.
3Loss of energy
If compute resources are located far from users, then infrastructure cost is reduced, but user experience and responsiveness deteriorate
Solution Approach 1:
The patent applies local quality by placing compute resources at edge locations geographically close to specific user groups rather than having all resources centralized. Each edge location is optimized for its local user base, providing fast response times and improved user experience while maintaining cost efficiency through distributed, right-sized infrastructure at each location.
Data Source
AI summary
Aspects of the present invention include a method of dynamically routing requests within multiple cloud computing networks. The method includes receiving a request for an application from a user device, forwarding the request to an edge server within a content delivery network (CDN), and analyzing the request to gather metrics about responsiveness provided by the multiple cloud computing networks running the application. The method further includes analyzing historical data for the multiple cloud computing networks regarding performance of the application, based on the performance metrics and the historical data, determining an optimal cloud computing network within the multiple cloud computing networks to route the request, routing the request to the optimal cloud computing network, andreturning the response from the optimal cloud computing network to the user device.