Proxy-Based Hybrid Cloud ML Routing for Volume Forecasting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies face challenges in efficiently performing volume prediction and anomaly detection in hybrid cloud environments, particularly in managing data volume and ensuring operational resiliency without the need for complex network management and IP range management.
Innovation Solution
A method and system for applying machine learning in a hybrid cloud computing environment, where a proxy routes requests from a private cloud to a trained machine learning model in a public cloud, optimizing based on speed, accuracy, and cost constraints, and eliminating the need for direct integration of public cloud resources into the private cloud.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If public cloud resources are directly integrated into the private cloud, then machine learning model accessibility is improved, but network management complexity and IP conflict risks increase
Solution Approach 1:
The patent introduces a proxy server as an intermediary component that sits between the private cloud endpoint and public cloud machine learning models. The proxy receives requests from the private cloud, forwards them to appropriate public cloud models, and returns results. This mediator approach enables ML model accessibility without requiring direct integration, thus avoiding IP conflict management and network complexity while maintaining system adaptability.
2Measurement precision
If multiple trained machine learning models are deployed, then forecasting accuracy is improved, but model selection complexity increases
Solution Approach 1:
The proxy server implements automatic model selection capabilities that autonomously evaluate incoming requests and select the most appropriate trained machine learning model based on request characteristics, model performance metrics, and current system state. This self-service approach eliminates the need for manual model selection and reduces selection complexity while maintaining high forecasting accuracy through optimal model matching.
Solution Approach 2:
The system incorporates feedback mechanisms where the proxy server continuously monitors the performance of multiple trained models and uses this feedback to improve model selection decisions. By analyzing model performance data and request outcomes, the system dynamically adjusts model selection strategies, enabling accurate forecasting while simplifying the selection process through data-driven automation.
3Reliability
If health check operations are performed on public cloud endpoints, then system reliability is improved, but operational overhead increases
Solution Approach 1:
The proxy server autonomously performs health check operations on public cloud endpoints without requiring manual intervention or additional operational processes. The system automatically monitors endpoint availability and performance, adjusting its behavior based on health status. This self-service health monitoring maintains system reliability while minimizing operational overhead by eliminating the need for separate manual checking procedures.
Data Source
AI summary
Methods, systems, and techniques for applying machine learning in a hybrid cloud computing environment. A request to perform a forecasting task is received at a private cloud endpoint. The task may be, for example, a sequential forecasting task such as volume forecasting or anomaly detection based on historical log data. A proxy is used to route the request to a trained machine learning model running in a public cloud by connecting the private cloud endpoint to the public cloud endpoint. The proxy can also select one of multiple public clouds and one of multiple trained machine learning models to which the request is routed.