Metric-Driven Cloud Traffic Routing Between Serverless and Containers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Switching between serverless and container-based frameworks in a cloud computing environment for tasks is inefficient due to the need for separate codebases, consuming resources and time, and existing load balancers lack the ability to determine the most efficient framework based on metrics.
Innovation Solution
A system that monitors traffic metrics and uses a single deployable codebase to dynamically route traffic to either a serverless or container-based framework based on performance, time, and system metrics, leveraging a machine learning model for prediction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If separate codebases are maintained for serverless and container-based frameworks, then each framework can be optimized independently, but resource consumption and development time increase
Solution Approach 1:
The patent applies universality by creating a single unified codebase that can be deployed to both serverless and container-based frameworks. This multi-functional codebase eliminates the need for maintaining separate codebases while preserving the ability to optimize each framework independently through selective deployment and configuration.
2Productivity
If existing load balancers are used for traffic routing, then basic load distribution is achieved, but the ability to determine the most efficient framework based on metrics is lacking
Solution Approach 1:
The patent implements feedback mechanisms by monitoring performance metrics from both serverless and container-based frameworks and using this information to dynamically determine the most efficient framework for traffic routing. This closed-loop system enables data-driven decisions about framework selection based on actual performance data.
Solution Approach 2:
The patent replaces traditional mechanical load balancing approaches with a more intelligent system that uses machine learning models to predict framework performance. This substitution enables proactive selection of the optimal framework based on predicted metrics rather than reactive load distribution.
3Ease of operation
If manual framework switching is performed, then framework selection can be controlled, but resource consumption and time efficiency decrease
Solution Approach 1:
The patent applies self-service by implementing automated framework switching based on monitored metrics and machine learning predictions. The system automatically determines when to switch between serverless and container-based frameworks without manual intervention, reducing switching time while maintaining operational control through configurable parameters and thresholds.
Data Source
AI summary
In some implementations, a device may obtain a codebase, associated with an application and one or more services of the application, that is deployable via both a first framework of the cloud computing environment and a second framework of the cloud computing environment. The device may receive the traffic associated with the application. The device may monitor one or more metrics associated with the traffic. The device may deploy, based on the one or more metrics, the codebase via the first framework or the second framework in the cloud computing environment. The device may route, based on the one or more metrics, the traffic to the first framework or to the second framework.