Device and method for scheduling a set of jobs for a plurality of machines

A technology for scheduling jobs and machines, applied in neural learning methods, instruments, computer parts, etc.

Pending Publication Date: 2021-10-12
ROBERT BOSCH GMBH
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Another challenge is its online (or dynamic) nature

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
  • Device and method for scheduling a set of jobs for a plurality of machines
  • Device and method for scheduling a set of jobs for a plurality of machines
  • Device and method for scheduling a set of jobs for a plurality of machines

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] In the following, a job scheduler should be disclosed that builds on both reinforcement learning and global search, more specifically by combining graph convolutional DQN with MCTS while allowing one to benefit from the other. The job scheduler is capable of directly computing solutions to scheduling problems represented as graphs without the help of external solvers or simulation environments.

[0036] First, the settings for the problems that the job scheduler can solve should be defined.

[0037] In general, a job scheduler should be able to solve online scheduling, specifically online combinatorial problems. Note that the job scheduler can be easily extended to, for example, other online compositional problems where destinations are added online, such as the traveling salesman problem and the vehicle routing problem. Online combinatorial optimization problems, including online logistics problems (e.g., planning a courier's route through a city, where additional pick-...

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

A device and method for scheduling a set of jobs for a plurality of machines are provided. The method for scheduling the set of jobs for the plurality of machines. Each job is defined by at least one feature which characterizes a processing time of the job. If any of the machines is free, a job from of the set of jobs is selected to be carried out by said machine and scheduled for said machine. The job is selected as follows: a Graph Neural Network receives as input the set of jobs and a current state of at least the machine which is free, the Graph Neural Network outputs a reward for the set of jobs if launched on the machines, which states are inputted into the Graph Neuronal Network, and the job for the free machine is selected depending on the Graph Neural Network output.

Description

technical field [0001] The invention relates to a job scheduler for a machine, in particular a production machine, for continuous selection of jobs via a graph neural network. The invention further relates to computer programs and machine-readable storage media and systems configured to implement a job scheduler. Background technique [0002] prior art [0003] Optimization of throughput or resource utilization is challenging and has great potential for great cost savings in manufacturing plants and great potential for increased productivity. [0004] One challenge lies in the combinatorial nature of the problem. There are many possible schedules, and the problem of finding the best schedule is usually NP-hard. Another challenge is its online (or dynamic) nature. Additional tasks arrive during the execution of the current schedule. The properties of arriving jobs are not known definitively until they arrive. [0005] Mao et al. (https: / / arxiv.org / abs / 1810.01963) used R...

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): G06Q10/06G06Q10/08G06Q50/04G06N3/08
CPCG06Q10/0631G06Q10/0633G06Q10/083G06Q50/04G06N3/08G05B19/41865G05B2219/32335Y02P90/02G06N5/01G06N3/045G06N3/04G06F18/217G06F18/24323
Inventor A·塔特勒C·丹尼尔D·D·卡斯特罗F·M·里赫特J·奥伦M·列法罗夫N·M·迪兹滨Z·费尔德曼
Owner ROBERT BOSCH GMBH
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