VM Placement via Temperature-Aware Prediction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing virtual machine placement methods do not consider the performance degradation of physical servers, particularly due to temperature, leading to inefficient resource management and potential data loss during live migration in data centers.

Innovation Solution

A virtual machine placement system that calculates a placement schedule based on predicted workload and temperature, using a workload calculation module, prediction module, and migration module to efficiently distribute virtual machines across physical servers, minimizing performance degradation and migration costs.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If virtual machine placement methods are used to balance physical servers, then load distribution is improved, but temperature-related performance degradation is not considered

Engineering Contradiction:

Improveload distributionVSAvoidperformance degradation

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The patent applies preliminary action by predicting future temperature and workload before placing virtual machines. The system calculates predicted temperatures and workloads for physical servers in advance, then uses this information to make placement decisions that prevent performance degradation before it occurs, rather than reacting after degradation has happened.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent changes the parameters considered in placement decisions from only workload metrics to include both workload and temperature predictions. By incorporating temperature as a key parameter alongside workload, the system selects physical servers that will maintain optimal performance under predicted conditions, resolving the contradiction between load balancing and performance reliability.

Inventive Principle:

Principle #35Parameter changes

2Productivity

If live migration is performed to balance load, then resource utilization is improved, but data loss risk and resource occupation increase

Engineering Contradiction:

Improveresource utilizationVSAvoiddata loss risk

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The patent performs preliminary temperature and workload prediction before triggering migration decisions. By having this information ready in advance, the system can make informed migration choices that minimize data loss risk and resource occupation, rather than performing migrations reactively without adequate preparation.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system uses feedback from temperature sensors and workload monitors to continuously update placement decisions. This feedback mechanism allows the system to adjust migration timing and target selection based on actual server conditions, reducing unnecessary migrations and their associated risks while maintaining optimal resource utilization.

Inventive Principle:

Principle #23Feedback

3Ease of operation

If existing placement methods are used, then migration is performed based on load threshold, but temperature impact on performance is ignored

Engineering Contradiction:

Improvemigration automationVSAvoidperformance prediction accuracy

Core Design Contradiction:

Ease of operationVSReliability

Solution Approach 1:

The patent fundamentally changes the parameters used in placement decisions by incorporating temperature predictions alongside workload metrics. This transforms the system from considering only load thresholds to evaluating both thermal and computational conditions, thereby improving performance prediction accuracy while maintaining automated operation.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The system performs preliminary temperature and workload calculations before making placement decisions. This advance preparation provides accurate performance predictions that guide automated migration choices, resolving the contradiction between ease of automation and prediction accuracy by having both elements ready before execution.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS12190170B2Virtual machine placement system and virtual machine placement method for implementing prediction management of virtual machines considering performance degration of physical server

Publication Date: 2025.01.07 OKESTRO CO LTD

AI summary

A virtual machine placement system for placing a plurality of virtual machines on a first physical server and a second physical server in order to efficiently operate a physical server in which the plurality of virtual machines are installed is disclosed. The physical server includes the first physical server and the second physical server, the virtual machine placement system contains a workload calculation module, a prediction module, a temperature prediction module, a schedule module, and a migration module, wherein the schedule module calculates a placement schedule considering predicted temperature of the physical server.