Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Computing and unloading method for stateful data stream applications

A technology of computing offloading and data flow, applied in the research field of computing segmentation, which can solve problems such as increasing the total completion time and network congestion.

Active Publication Date: 2019-10-22
SOUTH CHINA UNIV OF TECH
View PDF14 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition, because migrating too much state volume in the network will increase the possibility of network congestion and further increase the total completion time, how to reduce the number of state volumes when updating the calculation splitting scheme? Transmission is also a problem that needs to be solved

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
  • Computing and unloading method for stateful data stream applications
  • Computing and unloading method for stateful data stream applications
  • Computing and unloading method for stateful data stream applications

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0066] A computational offloading method for stateful data flow applications to achieve a trade-off between minimizing the total completion time of the application and reducing the amount of state, such as figure 1 shown, including the following steps:

[0067] figure 1 It is the optimized target application program model in the present invention, that is, a stateful data flow application program model, which can be seen in optical flow applications and object tracking applications in actual applications, such as STC (Spatio-Temporal Context) algorithm and improved STC algorithm.

[0068] In the present invention, considering the dependencies between the modules and the influence of the state quantity on the split decision, we abstract the application program into a weighted directed acyclic graph G= (such as figure 2 shown). Wherein V={i|1,2,...,n} is a vertex set, which is a set of functional modules, if module i is executed on the mobile device at time n, then make If...

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 computing and unloading method for stateful data stream applications. The computing and unloading method comprises the following steps: selecting a research scene; obtaininga research object; setting a network environment according to the time dynamic change; formulating an optimization target, minimizing the total completion time, and reducing the transmission of the state quantity; according to constraint conditions, constructing a stateful data stream application program model, wherein the constraint conditions include inter-module dependency constraint, state quantity migration constraint and network bandwidth constraint; judging a problem through the stateful data stream application program model, and if the problem is an offline problem, executing an offline problem method; if the problem is an online problem, executing an online problem method; and solving the problem to realize computing and unloading of the stateful data stream application program.

Description

technical field [0001] The invention relates to the research field of computing segmentation, in particular to a computing unloading method for stateful data flow applications. Background technique [0002] With the development and application of technologies such as the Internet of Things, virtual reality, and augmented reality, there will be a data explosion in the future. Relying entirely on cloud computing for data transmission and processing will cause huge network delays. Moreover, the data stream generated from smart devices is also growing continuously. Streaming data processing requires fast and real-time features. Streaming processing frameworks such as Hadoop and Storm can handle traditional streaming applications very well. However, the research on the computing segmentation problem of stateful streaming applications such as object tracking in the edge cloud environment still needs to be effectively solved. [0003] Computing segmentation is an important techno...

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): H04W28/16H04W72/12H04L12/24G06N3/12
CPCH04W28/16G06N3/126H04L41/145H04W72/12
Inventor 丁绍帅杨磊
Owner SOUTH CHINA UNIV OF TECH
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
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