Virtual Machine Resource Right-Sizing Using Usage Time-Series
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Hyperscalers face challenges in optimizing resource commissioning to balance performance and cost, as customers are charged based on commissioned resources rather than actual usage, leading to potential waste or performance issues.
Innovation Solution
Analyzing historic time-series data of resource consumption on virtual machines to recommend service tier adjustments, such as downsizing or upsizing, to align resource commissioning with actual usage patterns.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If more resources are commissioned to ensure performance, then performance is improved, but cost increases
Solution Approach 1:
The system performs preliminary analysis of historic time-series data to predict future resource usage patterns before making commissioning decisions. This allows the system to proactively commission or de-commission resources based on predicted demand, ensuring performance requirements are met while avoiding unnecessary resource commissioning and associated costs.
Solution Approach 2:
The system continuously monitors actual resource usage and compares it with commissioned resources, using this feedback to dynamically adjust resource commissioning decisions. By analyzing the correlation between historic usage patterns and performance requirements, the system optimizes the balance between maintaining adequate performance and minimizing resource commissioning costs.
2Loss of energy
If fewer resources are commissioned to reduce cost, then cost is reduced, but performance deteriorates
Solution Approach 1:
The system analyzes historic time-series data in advance to identify patterns and predict future resource requirements. This preliminary analysis enables the system to de-commission resources safely before actual demand decreases, ensuring cost reduction without compromising performance when demand is still high.
Solution Approach 2:
The system continuously monitors actual resource usage and performance metrics, using this feedback to make informed decisions about resource commissioning. By comparing actual usage against commissioned resources and predicting future needs, the system ensures that resource de-commissioning does not lead to performance deterioration.
3Reliability
If resources are commissioned without analyzing actual usage patterns, then resource availability is ensured, but resource waste occurs
Solution Approach 1:
The system performs preliminary analysis of historic time-series data to understand actual usage patterns before making resource commissioning decisions. This data-driven approach ensures that resources are commissioned based on actual needs rather than estimates, preventing both resource waste and availability issues.
Solution Approach 2:
The system continuously monitors actual resource usage and uses this feedback to optimize resource commissioning decisions. By analyzing the correlation between usage patterns and commissioned resources, the system ensures that resource availability is maintained while minimizing waste through data-driven commissioning decisions.
Data Source
AI summary
Described herein are techniques for analyzing historic time-series data to determine right-size commissioned resources from a software provider such as a hyperscaler. The historic time-series data may be analyzed to determine whether a commissioned resource should be upsized or downsized based on historical usage of the resource. Advantages to right-sizing a commissioned resource include improved performance and reduced spending.