Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A method for energy saving of servers in a large-scale cloud data center

A cloud data center, large-scale technology, applied in the direction of data processing power supply, biological neural network model, electrical components, etc., can solve the problems of analysis and consideration, poor energy saving effect, and high overall system power consumption, and achieve the improvement of single setting, Effect of high-efficiency energy-saving method and device

Active Publication Date: 2016-10-26
SHANDONG YINGXIN COMP TECH CO LTD
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In a large-scale cloud data center built on the basis of a cloud computing operating system, the number of devices is huge, and the monitoring and management process is complex. How to effectively realize the high efficiency and energy saving of the cloud data center is a problem worth studying.
[0003] At present, most energy-saving strategies only consider temperature trigger or power trigger when setting, without comprehensive analysis and consideration of real-time server load information such as CPU, memory, network bandwidth, disk IO, etc. OK, the overall power consumption of the system is too high

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
  • A method for energy saving of servers in a large-scale cloud data center
  • A method for energy saving of servers in a large-scale cloud data center

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] Such as figure 1 As shown, a server energy-saving device in a large-scale cloud data center is characterized in that: the energy-saving method and device mainly include the following six modules: (1) BP neural network energy-saving strategy training module (2) monitoring data storage module ( 3) Energy-saving strategy storage module (4) System overall monitoring and control module (5) Energy-saving strategy configuration management module (6) Energy-saving strategy implementation module; the six modules are divided into three parts, energy-saving strategy training part, data storage part and control part ,in:

[0026] Energy-saving strategy training part: mainly based on large-scale monitoring data to train the BP neural network, this part is carried out offline (not when the system is running); the main modules include: (1) BP neural network energy-saving strategy training module, based on Monitor sample data to train and learn energy-saving strategies;

[0027] Dat...

Embodiment 2

[0030] A server energy-saving method in a large-scale cloud data center. When monitoring and managing data center server groups, the BP neural network energy-saving strategy model based on large-scale monitoring data sample training is set for the server group for timing association, which is automatic and efficient. The power consumption of the server group can be adjusted in a timely manner, which has achieved the goal of overall energy saving of the cloud data center.

Embodiment 3

[0032] On the basis of Embodiment 2, the method described in this embodiment first uses the BP neural network energy-saving strategy training module to train and analyze large-scale server monitoring data samples, and obtains several neural network energy-saving strategy models and stores them in the system; Then, through the overall monitoring and control module of the system, the real-time monitoring data (monitoring data storage module) is obtained at a certain time interval (autonomous setting) during the operation of the cloud data center server group, and it is used as a new input of the BP neural network algorithm model The energy-saving strategy (energy-saving strategy configuration management module) adopted at this time point is obtained through sample learning, and then the energy-saving strategy model is implemented to automatically and efficiently adjust the power consumption of the server group to achieve the overall energy-saving goal of the cloud data center.

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 server energy-saving method in a large-scale cloud data center, including a BP neural network energy-saving strategy training module, a monitoring data storage module, an energy-saving strategy storage module, a system overall monitoring and control module, an energy-saving strategy configuration management module, and an energy-saving strategy implementation The module automatically and efficiently adjusts the power consumption of the server group by setting the BP neural network energy-saving strategy model based on large-scale monitoring data sample training for the server group to achieve the overall energy-saving goal of the cloud data center. The present invention proposes an all-round, accurate and efficient energy-saving method and device for a cloud data center server group by associating a BP neural network energy-saving strategy model based on large-scale server load sample data training for the cloud data center server group. It has effectively improved the problem that most energy-saving policy settings are single, not accurate and reasonable, and cannot well adjust the energy consumption of the data center.

Description

technical field [0001] The invention relates to a management and monitoring module in a cloud computing operating system, in particular to an energy-saving method and device for a cloud data center. technical background [0002] At present, cloud computing is gradually recognized by the industry, and cloud data center operating systems are gradually realized and put into practice, playing an increasingly important role in social production and life. In the large-scale cloud data center based on the cloud computing operating system, the number of devices is huge, and the monitoring and management process is complex. How to effectively realize the high efficiency and energy saving of the cloud data center is a problem worth studying. [0003] At present, most energy-saving strategies only consider temperature trigger or power trigger when setting, and do not comprehensively analyze and consider the real-time load information of the server, such as CPU, memory, network bandwidt...

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 Patents(China)
IPC IPC(8): G06F1/32G06N3/02H04L29/08
Inventor 于辉刘俊朋李新虎
Owner SHANDONG YINGXIN COMP TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com