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

Hybrid cloud scientific workflow scheduling strategy based on task probability clustering and multi-constraint workflow division

A scheduling strategy and workflow technology, applied in the direction of instruments, data processing applications, resources, etc., can solve problems such as scientific workflow scheduling problems that cannot be solved well, and achieve the goal of reducing execution costs, execution time, and system overhead Effect

Inactive Publication Date: 2016-10-26
SICHUAN UNIV
View PDF3 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The above algorithm cannot solve the scientific workflow scheduling problem in the actual hybrid cloud environment.

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
  • Hybrid cloud scientific workflow scheduling strategy based on task probability clustering and multi-constraint workflow division
  • Hybrid cloud scientific workflow scheduling strategy based on task probability clustering and multi-constraint workflow division
  • Hybrid cloud scientific workflow scheduling strategy based on task probability clustering and multi-constraint workflow division

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] attached figure 1 It is a schematic flow chart of the strategy of the present invention.

[0043] The implementation process is attached figure 1 Shown:

[0044] (1) Calculate the number of task clusters in each layer according to the resource requirements and dependency characteristics of the workflow. For each layer of tasks, calculate its clustering probability, and select tasks with high clustering probability to merge, such as figure 2 shown. In this way, resource allocation and task scheduling granularity of tasks are improved, and execution time is shortened.

[0045] (2) Adopting the private cloud scheduling strategy, firstly only using the private cloud resources for resource allocation and task scheduling of the workflow, and calculating the completion time.

[0046] (3) If the deadline cannot be met by using only private cloud resources, a multi-constraint workflow is used for division, such as image 3 As shown, balance the resource requirements of ea...

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 relates to a strategy of scientific workflow scheduling under a hybrid cloud. The strategy is based on the idea of task probability clustering and multi-constraint workflow division, effectively reduces system overhead, shortens execution time, reduces execution cost of a public cloud, and improves execution efficiency of a research organization. The strategy comprises the steps of: firstly, utilizing the task probability clustering idea, carrying out task probability clustering on a scientific workflow, increasing task scheduling granularity and reducing system overhead; secondly, utilizing the multi-constraint workflow division idea, adopting multi-constraint workflow division when a private cloud cannot meet time demand required by the research institution, balancing resource demand of each child workflow, and reducing communication traffic among the child workflows; thirdly, and allocating appropriate cloud resource for each child workflow according to a deadline, increasing resource utilization rate of the private cloud, and reducing cost of the public cloud.

Description

technical field [0001] The invention belongs to the field of scientific workflow scheduling, and in particular relates to a strategy for scientific workflow scheduling in a hybrid cloud environment. Background technique [0002] Scientific workflow represents a large-scale complex application in the field of scientific computing, which consists of multiple data-dependent tasks and can be represented by a directed acyclic graph DAG. Research institutions will establish private clouds to ensure the security of data and task execution. Due to the limited private cloud resources, it is impossible to handle the sudden increase in data volume or urgent time requirements. Therefore, elastic public cloud resources are needed to assist in the completion. Private cloud and public cloud form a hybrid cloud. The hybrid cloud can help complete scientific workflow execution, effectively reduce public cloud execution costs, and promote scientific development. [0003] The cloud scientific...

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): G06Q10/06
CPCG06Q10/06316G06Q10/0633
Inventor 彭舰王彬黎红友李梦诗宁黎苗陈瑜刘唐黄飞虎徐文政
Owner SICHUAN UNIV
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