Reinforcement learning-based inter-data center multi-target disaster backup method and system

A data center and disaster backup technology, applied in digital transmission systems, transmission systems, data exchange networks, etc., can solve problems such as unconsidered network link load balancing problems, data center daily service impact, etc., to alleviate the maximum link congestion , slow down the maximum link congestion, reduce the effect of bandwidth waste

Active Publication Date: 2020-11-24
SHANDONG UNIV
View PDF15 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] At present, for redundant disaster backup, most studies use multicast routing to reduce backup bandwidth consumpt

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
  • Reinforcement learning-based inter-data center multi-target disaster backup method and system
  • Reinforcement learning-based inter-data center multi-target disaster backup method and system
  • Reinforcement learning-based inter-data center multi-target disaster backup method and system

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0029] Example 1

[0030] At present, for redundant disaster backup, most studies have adopted multicast routing to reduce backup bandwidth consumption, but most of them have not considered the load balancing problem of network links. This easily makes the data center Daily services will also be severely affected. However, applying the store-and-forward mechanism in the time expansion network can better solve the problem of link congestion and achieve link load balance. Due to the rise of software-defined networks, explicit routing and scheduling of traffic can be performed in software-defined networks, which allows us to perform traffic scheduling more flexibly.

[0031] In this embodiment, a multi-objective disaster backup method between data centers based on reinforcement learning is disclosed. In the time expansion network after expanding the network between data centers, multicast routing and store-and-forward mechanisms are used to transmit backup data to achieve Minimal to...

Example Embodiment

[0072] Example 2

[0073] In this embodiment, a multi-target disaster backup system between data centers based on reinforcement learning is disclosed, including:

[0074] Acquisition module to obtain data to be backed up;

[0075] Storage module, storage time expansion network and backup routing selection model. The backup routing selection model includes the fitness function of each link in the multicast tree in the time expansion network to the multicast tree and the congestion factor function of each link, with minimum Targeting backup costs and link load balancing, solve the problem of obtaining the optimal backup routing scheme;

[0076] The calculation module inputs the data to be backed up into the backup route selection model to obtain the optimal backup route plan.

Example Embodiment

[0077] Example 3

[0078] In this embodiment, a computer-readable storage medium is disclosed for storing computer instructions that, when executed by a processor, complete the multi-objective disaster between data centers based on reinforcement learning described in Example 1. Steps of the backup method.

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 reinforcement learning-based inter-data center multi-target disaster backup method and a system. The method comprises the steps of expanding an inter-data center network to obtain a time expansion network; acquiring to-be-backed-up data in the time expansion network; inputting the to-be-backed-up data into a backup route selection model to obtain an optimal backup route scheme; transmitting and backing up the to-be-backed-up data in the time expansion network according to the optimal backup routing scheme; wherein the backup route selection model comprises a fitness function of each link in a multicast tree in the time expansion network to the multicast tree and a congestion factor function of each link, and solving to obtain an optimal backup route scheme by taking minimization of backup cost and link load balance as a target. When disaster backup is carried out, factors in two aspects of backup cost and load balancing are fully considered, a backup routing scheme which is relatively good in the two aspects of backup cost and load balancing at the same time is obtained through a backup routing selection model, and on the basis of reducing broadband waste,maximum link congestion is relieved.

Description

Technical field [0001] The present disclosure relates to a method and system for multi-target disaster backup between data centers based on reinforcement learning. Background technique [0002] The statements in this section merely provide background technical information related to the present disclosure, and do not necessarily constitute prior art. [0003] In recent years, many large enterprises, such as Amazon, Google, and Microsoft, have deployed large data centers in multiple geographic locations to provide various services to millions of users around the world. Due to natural disasters and man-made sabotage, data security has also attracted more and more attention. In order to achieve data redundancy and ensure data security, it is necessary to regularly replicate TB to PB of data in the inter-data center network and distribute it to three or more other remote data centers. This is disaster backup. [0004] At present, for redundant disaster backup, most studies have adopted...

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
IPC IPC(8): H04L12/707H04L12/703H04L12/801H04L12/803H04L45/24H04L45/28
CPCH04L45/22H04L45/28H04L45/24H04L47/12H04L47/125
Inventor 王华燕嘉鑫伊善文
Owner SHANDONG 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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap