AI Batch Job Scheduling for Cloud Resource Optimization

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional application management techniques in multi-tenant cloud hosting environments lead to resource limitations, resulting in reduced application performance due to inefficient batch job processing.

Innovation Solution

The use of artificial intelligence techniques to predict execution outcomes and estimate temporal durations for batch jobs by processing historical job execution and resource utilization data, enabling automated actions to optimize resource allocation and scheduling.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If conventional application management techniques are used in multi-tenant cloud hosting environments, then resource sharing is enabled to reduce costs, but resource limitations occur resulting in application performance reductions

Engineering Contradiction:

Improveresource sharingVSAvoidapplication performance

Core Design Contradiction:

Quantity of substanceVSProductivity

Solution Approach 1:

The system performs preliminary actions by predicting batch job execution outcomes and temporal durations before actual execution using AI techniques. Historical job execution data and resource utilization data are processed in advance to forecast outcomes, enabling proactive resource allocation and scheduling decisions that prevent performance degradation before it occurs.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements dynamic resource allocation by continuously adjusting resource assignment based on predicted job outcomes and durations. The AI model processes historical and current data to dynamically determine optimal resource allocation strategies, allowing the system to adapt resource distribution in real-time rather than using static allocation methods.

Inventive Principle:

Principle #15Dynamics

2Productivity

If batch jobs are processed in multi-tenant cloud environments, then resource utilization efficiency improves, but execution outcome uncertainty increases making scheduling difficult

Engineering Contradiction:

Improveresource utilization efficiencyVSAvoidexecution outcome predictability

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The system implements feedback mechanisms by using historical job execution data to train AI models that predict future execution outcomes. The system continuously learns from past performance data, resource utilization patterns, and actual execution results, refining its predictions over time. This feedback loop enables the system to reliably forecast job outcomes and adjust scheduling decisions accordingly.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system replaces traditional mechanical scheduling approaches with AI-based predictive modeling. Instead of using fixed scheduling rules or manual allocation methods, the system employs machine learning algorithms that process historical execution data and resource utilization patterns to intelligently predict job outcomes and optimize scheduling decisions.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Device complexity

If traditional scheduling methods are used for batch jobs, then system complexity remains low, but scheduling optimization and performance improvement are limited

Engineering Contradiction:

Improvescheduling system complexityVSAvoidscheduling optimization

Core Design Contradiction:

Device complexityVSProductivity

Solution Approach 1:

The system introduces an intermediary AI-based prediction layer between job submission and execution scheduling. This intermediary component processes historical execution data and resource utilization information to generate predicted outcomes and temporal durations, which then inform scheduling decisions. The intermediary enables optimized scheduling without requiring complete system redesign.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS20240264868A1Automatically processing batch jobs in cloud environments using artificial intelligence techniques

Publication Date: 2024.08.08 DELL PROD LP

AI summary

Methods, apparatus, and processor-readable storage media for automatically processing batch jobs in cloud environments using artificial intelligence techniques are provided herein. An example computer-implemented method includes obtaining historical job execution-related data for previous batch jobs in at least one cloud environment and resource utilization-related data for one or more pending batch jobs in the at least one cloud environment; predicting execution outcome(s) for the pending batch job(s) by processing at least a portion of the historical job execution-related data and at least a portion of the resource utilization-related data using artificial intelligence techniques; estimating temporal duration(s) associated with executing the pending batch job(s) by processing the at least a portion of the historical job execution-related data and the at least a portion of the resource utilization-related data using the artificial intelligence techniques; and performing automated actions based on the predicted execution outcome(s) and the estimated temporal duration(s).