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

Information non-perception Coflow scheduling system capable of automatically adjusting queue threshold and scheduling method thereof

An automatic adjustment and scheduling system technology, applied in the field of communication, can solve the problem of long overall cycle time of heuristic

Active Publication Date: 2020-01-17
JIANGSU FUTURE NETWORKS INNOVATION +1
View PDF8 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] Although the DHS algorithm improves the average completion time of Coflow, the overall cycle time of the design heuristic is very long, usually several weeks or longer

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
  • Information non-perception Coflow scheduling system capable of automatically adjusting queue threshold and scheduling method thereof
  • Information non-perception Coflow scheduling system capable of automatically adjusting queue threshold and scheduling method thereof
  • Information non-perception Coflow scheduling system capable of automatically adjusting queue threshold and scheduling method thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The technical solutions of the embodiments of the present invention will be described below with reference to the drawings of the embodiments of the present invention. Apparently, the described embodiments are only some of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0033] The present invention improves the Aalo mechanism and proposes an information-insensitive Coflow scheduling mechanism DeepAalo, which minimizes the completion time of Coflow by automatically adjusting the threshold of the priority queue. DeepAalo utilizes deep reinforcement learning techniques to transform the design of thresholds into a continuous learning process. Specifically, DeepAalo trains the neural network model, and automatically updates the degraded threshold of ...

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 an information imperceptible Coflow scheduling system capable of automatically adjusting a queue threshold and a scheduling method thereof. The scheduling system comprises a monitoring system (MS) and a central controller (CC), wherein the monitoring system and the CC are distributed on a terminal host; the monitoring system is used for collecting Coflow information on a terminal host. And the central controller adjusts a set of degradation thresholds according to the information of the Coflow, observes a scheduling result of the Coflow as an award of a reinforcement learning algorithm, and further optimizes the degradation threshold of the queue through the award.

Description

technical field [0001] The invention relates to an information-insensitive Coflow scheduling system and a scheduling method for automatically adjusting queue thresholds, and relates to the technical field of communications. Background technique [0002] In the Data Center network (DCN), parallel computing modes such as MapReduce, Spark, and Dryad have been widely used to support commercial applications and scientific research. These different computing frameworks have a common feature: they all have continuous computing stages between machine clusters, and when all the data in one stage has been sent, the task can start to execute the next data processing process. Specifically, Coflow is defined as a set of flows between two sets of machines. An example of Coflow is the Shuffle process between Mapper and Reducer in MapReduce. Related work shows that the completion time of Coflow exceeds 33% of the total computing task completion time, even up to 50% in some cases. Therefo...

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): H04L12/865G06N3/08G06N3/04H04L47/6275
CPCH04L47/6275G06N3/08G06N3/045
Inventor 汪硕王速黄韬霍如刘韵洁
Owner JIANGSU FUTURE NETWORKS INNOVATION
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