Resource scheduling method and system based on deep reinforcement learning

A technology of resource scheduling and reinforcement learning, which is applied in the field of deep learning, can solve problems such as not being equal, achieve high performance, improve performance, and improve performance

Inactive Publication Date: 2018-09-28
CHONGQING INST OF GREEN & INTELLIGENT TECH CHINESE ACADEMY OF SCI
View PDF5 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Statistics show that about 60% of the cost of data centers comes from energy consumption, and the long-term environmental impacts such as temperature and smog caused by high energy consumption of a large number of distributed data centers are not measurable as direct costs

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
  • Resource scheduling method and system based on deep reinforcement learning
  • Resource scheduling method and system based on deep reinforcement learning
  • Resource scheduling method and system based on deep reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0037] The invention establishes a cloud resource scheduling algorithm model based on deep reinforcement learning. The computing resource scheduling management of the data center is the core technology of big data and cloud computing, and the core algorithm belongs to the field of machine learning technology. Big data platform scheduling, that is, cluster resource scheduling, is an abstraction of the underlying hardware (mainly for CPU, disk, memory, IO, etc.). This invention focuses on using the idea of ​​deep reinforcement learning to schedule these resources, aiming to improve resource utilization. Higher efficiency, lower operation and maintenance costs, and disaster recovery.

[0038]Resource management problems are ubiquitous in computer systems and networks, including job scheduling in computing clusters, bitrate adaptation in video ...

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 resource scheduling method and system based on deep reinforcement learning, and belongs to the technical field of deep learning. The method comprises the following steps that: obtaining user behavior data; carrying out training according to the task of a user to obtain a proper scheduling algorithm to serve as the initial scheduling algorithm of the user for generating acorresponding scheduling result; and evaluating the scheduling result returned by the user at present, and making a choice to decide whether a current scheduling strategy is received or not. The system comprises a user input module, a data processing module, a resource scheduling system module and a resource scheduling process display module. By use of the method and the system, the average timeand the response speed of the task are improved, and performance indexes, including system time consumption and energy consumption and the like can be reduced.

Description

technical field [0001] The invention belongs to the technical field of deep learning, and relates to a resource scheduling method and system based on deep reinforcement learning. Background technique [0002] The scheduling and management of computing resources in data centers is the core technology of big data and cloud computing, and is the key to improving performance, saving energy and reducing emissions, prolonging service life and supporting sustainable and green large-scale applications. Statistics show that about 60% of the cost of data centers comes from energy consumption, and the long-term environmental impacts such as temperature and smog caused by high energy consumption of a large number of distributed data centers are not measurable as direct costs. Advanced energy-saving scheduling management technology is of great significance for improving the utilization efficiency of computing resources in schools, governments, research institutions and enterprises, savin...

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): G06F9/50
CPCG06F9/5027Y02D10/00
Inventor 田文洪王金何博叶宇飞尚明生史晓雨
Owner CHONGQING INST OF GREEN & INTELLIGENT TECH CHINESE ACADEMY OF SCI
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