AI Resource Provisioning for Multitenant Capacity Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional capacity planning methods for cloud services are laborious, ineffective, and expensive, often leading to inaccurate resource allocation that can result in system overloads, poor performance, or underutilized resources, straining efficiency and increasing costs.
Innovation Solution
Utilizing artificial intelligence models, particularly gradient boost classifiers, to predict and automate computing resource requirements for potential tenants in multitenant computing platforms by analyzing historical data and current tenant patterns, enabling precise resource provisioning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional manual capacity planning methods are used, then resource allocation can be adjusted flexibly, but the process becomes laborious, expensive, and inaccurate leading to system overloads or underutilization
Solution Approach 1:
The patent replaces manual mechanical capacity planning processes with an AI-based predictive system. The machine learning model automatically analyzes historical data, tenant patterns, and resource usage metrics to generate accurate resource allocation predictions, eliminating the need for laborious manual planning while improving accuracy.
Solution Approach 2:
The system enables self-service capacity planning by allowing the AI model to autonomously predict resource requirements and generate provisioning recommendations without human intervention. The model continuously learns from data and automatically adjusts predictions, making the planning process independent and efficient.
2Reliability
If more computing resources are provisioned to potential tenants, then system reliability improves, but resource underutilization increases leading to wasted capacity and higher costs
Solution Approach 1:
The patent applies preliminary action by using the AI model to predict future resource requirements before actual demand occurs. The system analyzes historical patterns and tenant growth trajectories to proactively provision resources in advance, ensuring system reliability while avoiding over-provisioning through data-driven predictions.
Solution Approach 2:
The system implements feedback mechanisms where the AI model continuously monitors actual resource usage against predictions, learns from discrepancies, and refines future predictions. This closed-loop approach ensures resources are allocated based on actual demand patterns, preventing both over-provisioning and under-provisioning.
3Productivity
If manual capacity planning is performed, then resource allocation can be customized, but the process is time-consuming and leads to poor performance
Solution Approach 1:
The patent replaces time-consuming manual capacity planning with automated AI-driven predictions. The machine learning model processes historical data and generates resource allocation recommendations instantly, reducing planning time from days or weeks to minutes while improving accuracy and enabling faster tenant onboarding.
Solution Approach 2:
The system uses copying by analyzing patterns from existing successful tenant deployments and replicating those resource allocation strategies for similar potential tenants. The AI model creates predictive copies of successful allocation patterns, accelerating the planning process while maintaining effectiveness.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A disclosed computer-implemented method may include providing, by a processor, an artificial intelligence model ("predictive model") pre-configured to infer, via a plurality of features included in the predictive model trained using data representative of computing resource requirements of current tenants of a multitenant computing platform, computing resource requirements for potential tenants of the multitenant computing platform. The method may also include receiving, by the processor, at least one query comprising data that describes an attribute of a potential tenant of the multitenant computing platform, and determining, by the processor, based on an inference of the predictive model generated based on the at least one query, an output comprising an estimated computing resource requirement of the potential tenant. Various other methods, systems, and computer-readable media are also disclosed.