Hybrid cluster task scheduling method based on Monte Carlo tree search

A technology of task scheduling and tree search, which is applied in the direction of program startup/switching, resource allocation, program control design, etc. It can solve the problems of long computing time and inapplicability, achieve the balance between performance and overhead, and realize the effect of dynamic scheduling

Pending Publication Date: 2021-12-07
SUN YAT SEN UNIV
View PDF0 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Meta-heuristic algorithms such as particle swarm optimization algorithm, ant colony algorithm, and genetic algorithm are widely used in resource-constrained project scheduling problems. Their calculation time is long, and they are suitable for static scheduling scenarios. It is necessary to determine the execution of all tasks before the task starts. Sequential, so it is not suitable for mixed deployment scenarios that require dynamic scheduling

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 cluster task scheduling method based on Monte Carlo tree search
  • Hybrid cluster task scheduling method based on Monte Carlo tree search
  • Hybrid cluster task scheduling method based on Monte Carlo tree search

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The accompanying drawings are for illustrative purposes only and cannot be construed as limiting the patent;

[0043] For those skilled in the art, it is understandable that some well-known structures and descriptions thereof may be omitted in the drawings.

[0044] The technical solutions of the present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0045] This embodiment proposes a method for scheduling tasks in mixed clusters based on Monte Carlo tree search, such as figure 1 As shown in FIG. 1 , it is a flow chart of the task scheduling method for mixed cluster clusters based on Monte Carlo tree search in this embodiment.

[0046] In the method for scheduling tasks of a mixed cluster cluster based on Monte Carlo tree search proposed in this embodiment, the following steps are included:

[0047] Step 1. Obtain the current system status, task queue, available resources and time series of all machines, build...

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 provides a hybrid cluster task scheduling method based on Monte Carlo tree search in order to overcome the defects that time overhead is large and the method is not suitable for hybrid scenes needing dynamic scheduling; the method comprises the following steps of: acquiring a current system state, a task queue, available resources of all machines and a time sequence to form a Monte Carlo tree by setting a root node; selecting a current optimal node according to a preset in-tree selection strategy, judging whether the current optimal node is a termination node, and if not, directly judging whether a preset search threshold value is reached; if yes, randomly selecting one action from all possible actions in the current optimal node as an expansion node of the current optimal node; on the basis of the state of the expansion node, scheduling the remaining tasks in the task queue to obtain a scheduling plan, and then starting from the termination node, backtracking the nodes on the path upwards to update; and repeatedly executing the steps until a preset search threshold value is reached.

Description

technical field [0001] The present invention relates to the technical field of cluster task scheduling, and more specifically, to a method for scheduling mixed cluster tasks based on Monte Carlo tree search. Background technique [0002] Data centers are an important support for Internet applications, and the cost of data centers and servers is an important part of the cost composition of Internet companies. When an enterprise builds a data center, it usually builds an offline cluster and an online cluster separately. Among them, the online cluster is responsible for processing user requests, such as search, instant messaging, games, e-commerce transactions and other services. In order to meet the quality of service, the online cluster will reserve a large number of servers to ensure its service quality, resulting in relatively low resource utilization. The offline cluster is mainly responsible for processing data-intensive offline tasks, such as data analysis jobs and mach...

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): G06F9/50G06F9/48
CPCG06F9/5027G06F9/4881
Inventor 吴维刚李伟冠
Owner SUN YAT SEN 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