Prescriptive Analytics Compute Sizing Correction Stack

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Cloud computing systems face inefficiencies due to over-provisioning or under-provisioning of computing resources, leading to performance degradation and inefficient hardware deployment, as virtual machines may be underutilized or overwhelmed, resulting in sporadic or non-responsive performance.

Innovation Solution

A prescriptive analytics-based compute sizing correction (CSC) stack that analyzes historical utilization data, tagging data, and consumption metrics to predict future resource needs and provide precise sizing recommendations, adjusting resource allocation dynamically to match demand, thereby optimizing resource utilization and efficiency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If computing resources are over-provisioned to ensure availability, then system reliability is improved, but resource utilization efficiency deteriorates

Engineering Contradiction:
Improvesystem availabilityVSAvoidresource utilization efficiency
Core Design Contradiction:
ReliabilityVSLoss of energy

Solution Approach 1:

The system dynamically adjusts computing resource allocation based on real-time workload demands and historical patterns. The compute sizing correction stack continuously monitors resource utilization metrics and automatically provisions or de-provisions virtual machine instances, transforming static over-provisioning into dynamic adaptive provisioning that maintains reliability while optimizing efficiency.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system implements feedback loops that monitor resource utilization metrics, performance indicators, and workload patterns. This feedback drives automated decisions about resource provisioning, allowing the system to learn from historical data and adjust resource allocation to match actual demand, thereby resolving the contradiction between maintaining availability and avoiding waste.

Inventive Principle:
Principle #23Feedback

2Loss of energy

If computing resources are under-provisioned to optimize efficiency, then resource utilization efficiency is improved, but system reliability deteriorates

Engineering Contradiction:
Improveresource utilization efficiencyVSAvoidsystem availability
Core Design Contradiction:
Loss of energyVSReliability

Solution Approach 1:

The system performs preliminary actions by pre-warming compute clusters and pre-positioning resources based on predicted workload patterns. By analyzing historical utilization data and forecasting future demands, the system proactively provisions resources before peak loads occur, ensuring reliability is maintained while avoiding chronic over-provisioning.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system enables rapid dynamic scaling of computing resources to respond to changing workload conditions. When demand increases, resources are quickly provisioned; when demand decreases, resources are released. This dynamic responsiveness allows the system to operate efficiently at low utilization during off-peak times while maintaining reliability during peak periods.

Inventive Principle:
Principle #15Dynamics

3Reliability

If virtual machine sizes are increased to handle peak loads, then system reliability is improved, but hardware deployment efficiency deteriorates

Engineering Contradiction:
Improvepeak load handling capabilityVSAvoidhardware deployment efficiency
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The system segments computing workloads into discrete virtual machine instances that can be independently provisioned and scaled. Rather than deploying large monolithic systems, the stack creates modular VM units that can be granularly allocated to match specific workload requirements, improving both hardware utilization efficiency and the ability to handle varying load levels.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system dynamically changes resource allocation parameters such as CPU cores, memory, and storage capacity based on actual workload demands. By adjusting these parameters in response to monitored performance metrics and predicted future loads, the system optimizes hardware deployment efficiency while maintaining the capability to handle peak loads through parameter optimization rather than static over-provisioning.

Inventive Principle:
Principle #35Parameter changes

4Ease of operation

If compute sizing is statically determined to simplify deployment, then ease of operation is improved, but resource utilization efficiency deteriorates

Engineering Contradiction:
Improvedeployment simplicityVSAvoidresource utilization efficiency
Core Design Contradiction:
Ease of operationVSLoss of energy

Solution Approach 1:

The compute sizing correction stack implements self-service capabilities that automatically monitor workload demands, analyze utilization patterns, and adjust resource allocation without manual intervention. This automated self-adjustment maintains deployment simplicity while achieving high resource utilization efficiency, as the system serves itself by making intelligent provisioning decisions based on real-time and historical data.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system incorporates continuous feedback mechanisms that monitor resource utilization and automatically adjust compute sizing decisions. This feedback-driven automation eliminates the need for manual sizing optimization while maintaining simplicity of operation, as the system learns from historical patterns and adapts resource allocation to match actual demand over time.

Inventive Principle:
Principle #23Feedback

Data Source

PatentEP3508976B1Prescriptive analytics based compute sizing correction stack for cloud computing resource scheduling
Publication Date: 2023.09.20 ACCENTURE GLOBAL SOLUTIONS LTD
  • EP3508976B1 patent drawingFigure 1
  • EP3508976B1 patent drawingFigure 2
  • EP3508976B1 patent drawingFigure 3

AI summary

A multi-layer compute sizing correction stack may generate prescriptive compute sizing correction tokens for controlling sizing adjustments for computing resources. The input layer of the compute sizing correction stack may generate cleansed utilization data based on historical utilization data received via network connection. A prescriptive engine layer may generate a compute sizing correction trajectory detailing adjustments to sizing for the computing resources. Based on the compute sizing correction trajectory, the prescriptive engine layer may generate the compute sizing correction tokens that that may be used to control compute sizing adjustments prescriptively.