Cloud Architecture Scaling via ML Usage Pattern Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing cloud technologies face inefficiencies in scaling cloud architecture components, leading to resource strain and errors due to manual configuration and delayed provisioning in response to usage patterns, which can result in underutilization or overutilization of resources.
Innovation Solution
A computer-implemented method using a machine learning model to monitor and determine usage patterns, identifying periods of excessive and scanty usage, and orchestrating scaling adjustments before subsequent usage iterations, allowing for proactive resource allocation based on pre-defined thresholds.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If cloud architecture scaling is triggered reactively by external stimuli (increased network traffic or CPU utilization), then resource provisioning responds to actual demand, but there is a time delay in provisioning new resources and additional strain on existing resources during the transition period
Solution Approach 1:
The system performs preliminary actions by proactively provisioning cloud resources based on predicted usage patterns before actual demand peaks occur. The machine learning model forecasts future resource needs, and scaling operations are initiated in advance, eliminating the reactive delay and preventing resource strain during transition periods.
2Reliability
If manual configuration and assessment is used for removing assets when peak use fades, then resource removal can be controlled, but the process is time-consuming and requires manual intervention
Solution Approach 1:
The system enables self-service by automatically managing asset removal based on predicted usage patterns. The machine learning model forecasts when resource demand will decrease, and the system autonomously provisions or deprovisions resources without manual intervention, maintaining control while significantly improving management efficiency.
3Adaptability or versatility
If cloud architecture waits for stimulus before scaling, then resources are allocated based on actual usage patterns, but existing resources experience additional strain during the provisioning period
Solution Approach 1:
The system applies preliminary action by predicting resource demand patterns using machine learning and proactively scaling resources before peak usage occurs. This prevents strain on existing resources during provisioning by having capacity ready in advance, while maintaining adaptability through pattern-based predictions rather than fixed thresholds.
Data Source
AI summary
A computer-implemented method is disclosed. The method can comprise: monitoring utilization of a cloud architecture component that is being used by a component utilizer; determining, via a machine learning model, a pattern of usage of the cloud architecture component based on the monitoring; determining, based on the pattern of usage, a first time period when the cloud architecture component is excessively used by the component utilizer and a second time period when the cloud resource is scantily used by the component utilizer; and orchestrating, based on the first and second time periods, a scaling of the cloud architecture immediately before a subsequent iteration of the pattern of usage by the component utilizer.