Automated Capacity Modeling Using Forecast Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current capacity modeling implementations require numerous manual operations, making it impractical for large organizations with vast IT infrastructure to effectively model virtual resource configuration capacity consumption and headroom, leading to inadequate resource optimization and potential resource unavailability for critical applications.
Innovation Solution
A method that retrieves capacity utilization data, applies linear regression analysis, projects future capacity utilization, and uses a non-linear capacity consumption model to determine deviations from predetermined threshold ranges, automatically selecting resource configurations to prevent deviations and optimize resource allocation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual capacity modeling operations are performed for each resource, then modeling precision can be maintained, but the time and effort required becomes prohibitively large for large organizations with vast IT infrastructure
Solution Approach 1:
The patent segments the capacity modeling process by dividing resources into different categories (virtual computing resources, storage resources, network resources) and applying appropriate modeling techniques to each segment. This allows automated modeling at scale while maintaining precision through category-specific approaches.
Solution Approach 2:
The patent creates capacity models as representations of actual resources without requiring physical manipulation of the resources themselves. These model copies can be analyzed, projected, and optimized independently, enabling automated processing of vast numbers of resources while maintaining modeling precision.
2Productivity
If automated modeling is implemented across vast IT infrastructure, then productivity and scalability improve, but the complexity of managing and maintaining the automated system increases
Solution Approach 1:
The patent implements a universal capacity modeling system that can handle multiple resource types (virtual computing, storage, network) through a single automated platform. This multi-functional approach increases productivity across the entire IT infrastructure while managing complexity through standardized processes.
Solution Approach 2:
The system manages complexity by dynamically adjusting modeling parameters based on resource characteristics, data availability, and organizational needs. This allows the automated system to adapt to different scenarios without requiring complete redesign, maintaining productivity while controlling system complexity.
3Adaptability or versatility
If comprehensive capacity modeling is performed on all resources, then resource optimization improves, but the computational resources and processing time required increase significantly
Solution Approach 1:
The patent applies partial action by focusing capacity modeling efforts on resources that will provide the greatest optimization benefit. Rather than uniformly modeling all resources, the system identifies and prioritizes critical resources for detailed modeling, achieving effective resource optimization while reducing computational overhead.
Solution Approach 2:
The system performs preliminary capacity modeling and analysis to identify resources requiring detailed optimization. This preliminary action filters the dataset before applying more computationally intensive modeling techniques, enabling comprehensive resource optimization while managing computational resource consumption.
Data Source
AI summary
A method includes retrieving capacity utilization data for a plurality of resources and applying a linear regression analysis on the capacity utilization data. The method further includes projecting, using a processor, the capacity utilization data through a future time based on results of the linear regression analysis. The method additionally includes determining a deviation from a predetermined threshold range in the projected capacity utilization data for a first resource, and, in response to determining the deviation, determining, for each of a plurality of resource configurations, future capacity utilization of the first resource based on a non-linear capacity consumption model corresponding to the resource configuration. The method also includes applying a selected resource configuration from the plurality of resource configurations to the first resource to prevent the first resource from deviating from the predetermined threshold range.