Automatic driving reasoning task workflow scheduling method for time delay optimization of edge environment

A technology of automatic driving and scheduling method, applied in the direction of program startup/switching, electrical digital data processing, program control design, etc., to achieve the effect of optimizing scheduling delay

Active Publication Date: 2020-06-30
FUJIAN NORMAL UNIV
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, the current research work has not yet formed a complete and effective solution to the delay-optimized automatic driving inference task workflow scheduling method in the edge 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
  • Automatic driving reasoning task workflow scheduling method for time delay optimization of edge environment
  • Automatic driving reasoning task workflow scheduling method for time delay optimization of edge environment
  • Automatic driving reasoning task workflow scheduling method for time delay optimization of edge environment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] like Figure 1 to Figure 5 As shown, the edge environment of the present invention is oriented to delay-optimized automatic driving reasoning task workflow scheduling method, which includes the following steps:

[0057] Step 1, obtain the upper limit number of rounds, the number of iterations per round, the initial state and the initial temperature;

[0058] Step 2, randomly select an action, execute the action in the initial state, and after multiple iterations, make the initial state meet the feasible solution condition and become a feasible solution;

[0059] Step 3, select an action according to the Metropolis criterion, and the state transferred by the action must be a feasible solution state;

[0060] Step 4, execute the action and transfer the state;

[0061] Step 5, calculate the completion time of the transferred state by the optimal scheduling algorithm, and get the instant reward by (1 / completion time);

[0062] Step 6, update the value function according ...

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 automatic driving reasoning task workflow scheduling method for time delay optimization of an edge environment, and the method considers the difference of reasoning tasks generated by an automatic driving vehicle in different time slices and the dynamic change condition of edge nodes in the edge environment, and optimizes the transmission time delay of a scientific workflow in combination with edge calculation. According to the method, the difference of reasoning tasks generated by automatic driving vehicles in different time slices and the influence of edge nodes inan edge environment on scheduling processing time delay are considered; by introducing a Metropolis criterion, exploration and development of an algorithm are balanced. And the automatic driving reasoning task scheduling time delay in the edge environment is effectively reduced.

Description

technical field [0001] The invention belongs to the field of parallel and distributed high-performance computing and a workflow scheduling method for autonomous driving inference tasks, and specifically relates to an edge environment considering the differences in inference tasks generated by autonomous vehicles in different time slices and the dynamics of edge nodes in the edge environment A workflow scheduling method for inference tasks in autonomous driving based on latency optimization. Background technique [0002] As the number of vehicles in the world increases, problems such as traffic safety, road congestion, and environmental pollution follow. The development of autonomous driving technology provides a new solution to these problems. Highly automated vehicle driving can not only improve the convenience and comfort of driving, but also greatly reduce traffic accidents caused by human error, improve driving safety, improve the overall traffic efficiency of the road ...

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): G06F9/48
CPCG06F9/4881Y02D10/00
Inventor 林兵林凯黄志高卢宇
Owner FUJIAN NORMAL 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