CPU temperature forecasting method and device for virtual machine

A technology of CPU temperature and prediction method, which is used in data processing power supply, instrumentation, electrical digital data processing, etc.

Active Publication Date: 2014-03-26
ZHEJIANG UNIV
View PDF1 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the previous work was based on task scheduling or computer operating status adjustment, and there was no temperature model, temperature-aware scheduling technology, and temperature management system for virtual machines.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • CPU temperature forecasting method and device for virtual machine
  • CPU temperature forecasting method and device for virtual machine
  • CPU temperature forecasting method and device for virtual machine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0060] A virtual machine-oriented CPU temperature prediction method, such as Figure 2-4 shown, including the following specific steps:

[0061] Node deployment step 110: build the experiment node 201, the environment temperature monitoring node 202 and the control node 203 respectively;

[0062] Data collection step 120: the experimental node (201) runs a certain number of configured virtual machines and sends the monitoring data of this node to the control node (203), while the ambient temperature monitoring node (202) collects the ambient temperature and sends it to the control node ( 203);

[0063] Temperature analysis step 130: analyzing the data collected by the management and control node 203, including feature extraction, extracting the physical machine configuration, virtual machine configuration, ambient temperature, initial CPU temperature of the experimental node 201, and CPU peak temperature as feature values, and using the feature values Input the training mode...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a CPU temperature forecasting method for a virtual machine. The method comprises the steps of node deployment, data collection, temperature analysis and forecasting. Different running nodes comprising test nodes, environment temperature nodes and control nodes are built, a training model of a support vector machine is used for training output characteristics of the test nodes, a piecewise function is built on the basis of an output value of the training model, and a correct value is added to the piecewise function to obtain final forecasting data; in addition, the invention further discloses a CPU temperature forecasting device using the CPU temperature forecasting method for the virtual machine. The CPU temperature forecasting method and device for the virtual machine have the advantages of being high in forecasting precision, fast in modeling, small in calculated amount, and convenient to monitor remotely, supporting node separation and on-line forecasting, and having high application value.

Description

technical field [0001] The invention relates to a virtual machine-oriented CPU temperature prediction method and a virtual machine-oriented CPU temperature prediction device. Background technique [0002] With the advent of the era of cloud computing and big data, energy consumption and environmental issues in data centers have become increasingly prominent. Traditional energy-saving methods generally aim at reducing the computing energy consumption of nodes. In fact, due to the reliability requirements of equipment and the large temperature distribution of data center nodes, cooling energy consumption has become the most important part of data center energy consumption, and its energy consumption is close to 50% of all energy consumption. Therefore, establishing a temperature management system for data centers and comprehensively considering computing energy consumption and cooling energy consumption provide a new idea for energy saving. The temperature management of the ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F1/20G06F1/32G06F11/34
Inventor 吴朝晖李翔姜晓红陈英芝
Owner ZHEJIANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products