Workflow scheduling method and system based on graph convolutional neural network

A convolutional neural network and scheduling method technology, applied in the field of deep reinforcement learning and workflow scheduling, can solve problems such as inability to deal with resource allocation in dynamic and reproducible environments, and achieve good generalization, high scheduling quality, and strong adaptability Effect
CN112711475AActive Publication Date: 2021-04-27SHANGHAI JIAO TONG UNIV
5 Cites 6 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
SHANGHAI JIAO TONG UNIV
Publication Date
2021-04-27

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention provides a workflow scheduling method and system based on a graph convolutional neural network. The method comprises the steps: 1, processing the features of task nodes and a complex dependence relation based on a graph convolutional neural network model, and extracting a high-dimensional abstract feature representation; 2, the strategy network inputs the high-dimensional abstract features into a full connection layer neural network to be processed, and a Softmax layer is used for selecting a next task node to be executed; 3, according to the selected task node, a DEFT heuristic algorithm is used to calculate whether to copy the father node of the task node, which father node is copied and which resource is allocated for execution; and 4, executing allocation according to the scheme calculated in the step 3, updating the task information and the resource information after the task nodes are allocated, and repeating the step 1 to enter the next allocation until all the arrived task nodes are allocated. The method can adapt to a dynamic workflow environment, and the algorithm scheduling quality is higher.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The present invention relates to the technical field of deep reinforcement learning and workflow scheduling, in particular to a workflow scheduling method and system based on a graph convolutional neural network. Background technique

[0002] With the rapid development of cloud computing, cloud computing has gradually become an indispensable key resource. The efficiency of workflow scheduling in cloud computing has also become very critical, and it can have a great impact on the efficiency of cloud computing task execution. Therefore, we need an efficient workflow scheduling algorithm to handle complex task dependencies and reasonably match tasks and resources. Workflow scheduling based on list scheduling can generally be divided into two stages: node sorting and resource allocation.

[0003] For the sorting phase, it is necessary to deal with the dependencies between tasks and give a reasonable execution sequence of task nodes. The traditional heur...

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