Virtual Machine Migration for Data Center Thermal Balancing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current data center refrigeration methods consume excessive energy due to unbalanced temperature distributions among servers, leading to inefficient cooling processes.

Innovation Solution

A method for migrating virtual machines from servers with the highest temperature to other servers, where the migration is determined based on temperature differences and resource availability, aiming to balance temperature distribution and reduce energy consumption.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Temperature

If refrigeration is used to reduce data center temperature, then temperature is reduced, but energy consumption increases due to unbalanced temperature distribution

Engineering Contradiction:
Improvedata center temperatureVSAvoidrefrigeration energy consumption
Core Design Contradiction:
TemperatureVSUse of energy by moving object

Solution Approach 1:

The system uses virtual machine migration to enable self-regulation of temperature distribution across servers. By automatically moving workloads from hot servers to cooler servers, the system creates a self-balancing mechanism that reduces reliance on energy-intensive refrigeration, allowing the data center to manage its own thermal profile through workload adjustment

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The invention changes the operational parameters of servers by migrating virtual machines between them. This dynamic adjustment of workload distribution modifies the thermal parameters of individual servers, creating a more balanced temperature profile across the data center and reducing the overall refrigeration energy required

Inventive Principle:
Principle #35Parameter changes

2Loss of energy

If virtual machines are migrated to balance temperature distribution, then refrigeration energy consumption is reduced, but system complexity increases

Engineering Contradiction:
Improverefrigeration energy consumptionVSAvoidmigration system complexity
Core Design Contradiction:
Loss of energyVSDevice complexity

Solution Approach 1:

The virtual machine migration system serves multiple functions simultaneously: it balances temperature distribution across servers, optimizes resource utilization, and improves system reliability through failover capabilities. This multi-functionality justifies the added complexity by delivering multiple benefits from a single system

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system implements continuous monitoring of server temperatures and workload distribution, using this feedback to dynamically adjust virtual machine placement. This closed-loop control mechanism automatically responds to changing thermal conditions, reducing the need for complex manual intervention while maintaining optimal temperature balance

Inventive Principle:
Principle #23Feedback

Data Source

PatentEP2950213B1Method, apparatus, and system for migrating virtual machine
Publication Date: 2019.05.29 HUAWEI TECH CO LTD
  • EP2950213B1 patent drawingFigure 1
  • EP2950213B1 patent drawingFigure 2
  • EP2950213B1 patent drawingFigure 3

AI summary

The present invention relates to the field of data center technologies, and in particular, to a method, an apparatus, and a system for migrating a virtual machine. In this solution, a to-be-migrated virtual machine is determined from a server with a largest temperature value at a current time, and the to-be-migrated virtual machine is migrated to a destination server. Because a temperature value of the destination server available after the to-be-migrated virtual machine is migrated to the destination server is less than the largest temperature value of the server with the largest temperature value at the current time available before the virtual machine is migrated out from the server with the largest temperature value at the current time, a largest temperature value of a server in a data center is reduced; in addition, during refrigeration, more energy is consumed if the largest temperature value is larger, and less energy is consumed if the largest temperature value is smaller. Therefore, this solution reduces energy consumed in a refrigeration process.