Cloud Resource Adequacy Scoring for Predictive Allocation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for allocating cloud computing resources rely heavily on user-driven inputs and lack the ability to accurately predict performance, leading to suboptimal resource utilization and unexpected cost overruns due to fluctuations in workload and user behavior.
Innovation Solution
A method using artificial intelligence (AI) and machine learning (ML) techniques, including Simple Linear Regression (SLR) and Multiple Linear Regression (MLR) models, to evaluate cloud computing resource allocation by generating adequacy scores based on historical data, identifying key drivers and interactions among features, and optimizing resource allocation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional user-driven input methods are used for resource allocation, then ease of operation is maintained, but measurement precision of performance prediction deteriorates
Solution Approach 1:
The patent introduces AI/ML models as intermediary components between user inputs and resource allocation decisions. These models process historical data, workload patterns, and performance metrics to generate predictions and recommendations, thereby improving measurement precision without requiring users to directly manage complex allocation parameters.
Solution Approach 2:
The system enables self-service through automated resource allocation where the AI/ML models continuously monitor performance, predict future needs, and adjust resource distribution without constant user intervention. This maintains ease of operation while significantly improving prediction accuracy through data-driven insights.
2Productivity
If more cloud computing resources are allocated, then productivity is improved, but loss of energy increases
Solution Approach 1:
The patent implements dynamic resource allocation where the system continuously adjusts resource distribution based on real-time workload analysis and predictive modeling. Resources are allocated flexibly to match actual demand, improving productivity during peak periods while reducing energy consumption during low-utilization periods through automated scaling decisions.
Solution Approach 2:
The AI/ML models analyze multiple parameters including workload intensity, resource utilization metrics, and performance requirements to dynamically change allocation parameters. This enables optimized resource distribution that maximizes productivity while minimizing energy waste by adjusting allocation based on changing conditions rather than static over-provisioning.
3Reliability
If manual resource allocation methods are used, then device complexity is reduced, but reliability of resource sufficiency deteriorates
Solution Approach 1:
The patent implements feedback mechanisms where the AI/ML models continuously monitor resource utilization, performance metrics, and workload patterns. The system compares actual performance against predicted outcomes, learns from discrepancies, and refines allocation decisions over time, thereby improving reliability of resource adequacy assessments while managing complexity through automated learning processes.
Solution Approach 2:
The system performs preliminary analysis of historical data and workload patterns to predict future resource needs before allocation decisions are made. By proactively identifying potential resource sufficiency issues through predictive modeling, the system improves reliability of adequacy assessments and prevents both overprovisioning and underprovisioning before they occur.
Data Source
AI summary
The present disclosure discloses a computer implemented method and system to evaluate adequacy of cloud computing resources allocation. The method includes extracting a set of features and a set of target variables from a historic dataset stored in a database. Further, the method includes generating a plurality of simple linear regression (SLR) model and a multiple linear regression (MLR) model. Furthermore, a respective value of each target variable of the set of target variables is determined based on the SLR model and MLR model. Thereafter, the method includes calculating a new value of each feature of the set of features followed by generating adequacy score by comparing the new value of each feature of the set of features with a desired value of each feature of the set of features.