Virtual machine scheduling method and device, electronic equipment, storage medium and computer program product

By encoding and decoding the computing resource data of computing nodes using a diffraction deep neural network model to generate optical signals, the problem of complex processes in virtual machine scheduling is solved, and efficient virtual machine creation and data transmission are achieved.

CN122285177APending Publication Date: 2026-06-26CHINA MOBILE (SUZHOU) SOFTWARE TECH CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202610214822.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-02-13
Publication Date
2026-06-26

AI Technical Summary

Technical Problem

In the existing virtual machine scheduling process, the increased number of filters and weights in the scheduler leads to a more complex scheduling process, affecting efficiency and making it difficult to find a balance between high accuracy and reasonable resource allocation.

Method used

A diffraction deep neural network model is used to encode and decode the computing resource data of computing nodes to generate optical signals. The creation node of the virtual machine is determined by the optical imaging plane, which simplifies the scheduling process and improves efficiency.

Benefits of technology

It simplifies the virtual machine scheduling process, improves the efficiency of virtual machine creation and the reliability of data transmission, and enhances the intelligence level of the cloud computing platform.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122285177A_ABST
    Figure CN122285177A_ABST
Patent Text Reader

Abstract

This application provides a virtual machine scheduling method, apparatus, electronic device, storage medium, and computer program product. The method includes: generating a first optical signal based on the computing resource data of each of a plurality of computing nodes; processing the first optical signal by calling a diffraction deep neural network model to obtain a second optical signal; and determining a first computing node for creating a virtual machine among the plurality of computing nodes based on the position of the second optical signal projected on a set imaging plane.
Need to check novelty before this filing date? Find Prior Art