AI Tenant Resource Provisioning for Cloud 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, resulting in system overloads, poor performance, or underutilized resources, which strain resources and increase costs.
Innovation Solution
Utilizing artificial intelligence models, particularly gradient boost classifiers, to predict and automate computing resource requirements for new tenants in multitenant computing platforms, incorporating features like active and terminated users, tenant age, and transaction volumes for precise resource estimation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If traditional manual capacity planning methods are used, then resource allocation can be adjusted flexibly, but the process becomes laborious, time-consuming, and expensive
Solution Approach 1:
The patent replaces manual mechanical capacity planning processes with an automated machine learning system. The ML model automatically predicts resource requirements by analyzing tenant characteristics and historical data, eliminating the need for labor-intensive manual comparison and adjustment processes while maintaining allocation flexibility through adaptive predictions.
Solution Approach 2:
The system enables self-service capacity planning where the ML model autonomously performs resource requirement predictions without human intervention. The model automatically processes tenant data, generates predictions, and can trigger provisioning actions, allowing the system to serve itself in the capacity planning process while reducing manual effort.
2Reliability
If traditional capacity planning methods are used, then resource allocation can be manually adjusted, but accuracy decreases leading to system overloads or underutilized resources
Solution Approach 1:
The patent replaces manual resource allocation judgment with automated machine learning predictions. The ML model analyzes multiple tenant characteristics and historical performance data to generate accurate resource requirement predictions, eliminating human error and inconsistency while improving both allocation accuracy and system efficiency through data-driven decisions.
Solution Approach 2:
The system incorporates feedback mechanisms where the ML model continuously learns from actual resource usage patterns and performance data. This feedback loop enables the model to refine its predictions over time, improving accuracy by adjusting to real-world outcomes and preventing both overloads and underutilization through adaptive resource allocation.
3Reliability
If more computing resources are provisioned to ensure adequate capacity, then system performance is maintained, but resource wastage and costs increase
Solution Approach 1:
The patent uses parameter changes in the form of dynamic resource allocation based on ML predictions. Instead of provisioning fixed excessive resources, the system adjusts resource allocation parameters according to predicted tenant requirements, maintaining performance stability only where needed while reducing resource wastage through precise, data-driven allocation decisions.
Data Source
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.