Zone-Based Workload Scheduling for Data Center Thermal Management

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional data center cooling systems are inefficient as they are provisioned for peak load scenarios, leading to excessive energy consumption and inadequate cooling management, especially when workloads are randomly distributed or not considering the thermal interactions between electronic devices.

Innovation Solution

Implementing a zone-based workload scheduling and thermal management system that partitions electronic devices into zones, calculates zone-based cooling efficiencies accounting for neighboring devices, and adjusts cooling management based on environmental conditions and device states to optimize energy usage.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If cooling units are provisioned for worst-case or peak load scenarios, then adequate cooling capacity is ensured, but energy consumption increases significantly

Engineering Contradiction:

Improvecooling capacityVSAvoidenergy consumption

Core Design Contradiction:

ReliabilityVSUse of energy by moving object

Solution Approach 1:

The cooling system transitions from static provisioning to dynamic operation. Cooling units continuously adjust their operation levels based on real-time thermal conditions and workload changes, allowing the system to match cooling capacity precisely to actual needs rather than maintaining peak capacity continuously

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system changes operational parameters of cooling units dynamically. By adjusting cooling unit operation levels, temperature setpoints, and airflow rates based on monitored thermal conditions and workload, the system optimizes the balance between maintaining adequate cooling capacity and reducing energy consumption

Inventive Principle:

Principle #35Parameter changes

2Ease of operation

If workloads are placed randomly or based on device availability, then workload distribution is simple, but cooling efficiency decreases

Engineering Contradiction:

Improveworkload placement simplicityVSAvoidcooling efficiency

Core Design Contradiction:

Ease of operationVSLoss of energy

Solution Approach 1:

The system assigns different workload placement criteria to different locations based on their thermal characteristics. By calculating thermal zones and considering local heat generation patterns, the system places workloads in locations that optimize both cooling efficiency and operational simplicity for each specific area

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The system continuously monitors thermal conditions and workload distribution, using this feedback to dynamically adjust workload placement decisions. This closed-loop approach ensures that workload placement remains simple while continuously improving cooling efficiency based on actual system behavior

Inventive Principle:

Principle #23Feedback

3Ease of operation

If cooling units operate based on temperature changes in airflow, then cooling response is reactive, but energy consumption exceeds actual needs

Engineering Contradiction:

Improvecooling responseVSAvoidenergy consumption

Core Design Contradiction:

Ease of operationVSUse of energy by moving object

Solution Approach 1:

The system performs preliminary assessment of thermal conditions and workload patterns to proactively adjust cooling unit operation before temperature excursions occur. By anticipating thermal conditions based on workload predictions and historical data, the system avoids reactive cooling adjustments that waste energy

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The cooling system uses its own monitored thermal data and workload information to autonomously optimize its operation. The system serves itself by automatically adjusting cooling unit parameters based on real-time conditions, eliminating the need for external control that would require additional energy-intensive monitoring and adjustment cycles

Inventive Principle:

Principle #25Self-service

4Productivity

If workload is removed from one electronic device, then that device's cooling demand decreases, but surrounding devices continue high cooling demand

Engineering Contradiction:

Improveworkload flexibilityVSAvoidcooling demand

Core Design Contradiction:

ProductivityVSLoss of energy

Solution Approach 1:

The system segments the data center into thermal zones that group nearby electronic devices together. By considering thermal interactions between devices within zones, the system can independently manage cooling for each zone, allowing workload removal from one device to have limited impact on surrounding devices' cooling requirements

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system merges the cooling management of multiple electronic devices into unified thermal zone management. By treating nearby devices as a combined thermal unit rather than individually, the system optimizes cooling demand across the entire zone, recognizing that workload changes in one device affect the collective cooling needs of the zone

Inventive Principle:

Principle #5Merging (Combining)

Data Source

PatentUS8677365B2Performing zone-based workload scheduling according to environmental conditions

Publication Date: 2014.03.18 VALTRUS INNOVATIONS LTD

AI summary

To perform zone-based workload scheduling according to environmental conditions in a system having electronic devices, indicators of cooling efficiencies of the electronic devices in corresponding zones are aggregated to form aggregated indicators for respective zones, where the zones include respective subsets of electronic devices. Workload is assigned to the electronic devices according to the aggregated indicators.