Multi-level resource pool intelligent scheduling method for urban rail cloud platform, and device

By dividing the urban rail cloud platform into multi-level resource pools and combining them with application models for dynamic scheduling, the problem of low resource utilization in the rail transit system has been solved, achieving reasonable allocation and maximum utilization of resources and improving memory usage efficiency.

WO2026137970A1PCT designated stage Publication Date: 2026-07-02CASCO SIGNAL LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
CASCO SIGNAL LTD
Filing Date
2025-09-05
Publication Date
2026-07-02

AI Technical Summary

Technical Problem

When existing technologies are applied to the cloud in rail transit systems, resource utilization is low, memory utilization is high, and CPU utilization is low, resulting in uneven hardware resource utilization and an inability to effectively adapt to the specific business needs of rail transit systems.

Method used

By dividing the resource pool into multiple levels, and based on the CPU over-allocation ratio, memory over-allocation ratio, and whether KSM is disabled, combined with the application system operation behavior model and health status analysis model, business modules are dynamically scheduled to different levels of resource pools to optimize resource allocation. By utilizing the characteristics of business modules and peak running times, reasonable allocation and dynamic scheduling of resources can be achieved.

Benefits of technology

It improved the effective utilization of memory, reduced the overall hardware resource requirements, ensured the normal operation of each business module, maximized resource utilization and flexibility, and avoided virtual machine performance degradation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2025119354_02072026_PF_FP_ABST
    Figure CN2025119354_02072026_PF_FP_ABST
Patent Text Reader

Abstract

The present invention relates to a multi-level resource pool intelligent scheduling method for an urban rail cloud platform, and a device, which are applied to a rail transit service system. The method comprises: on the basis of a CPU overcommit ratio, a memory overcommit ratio, and whether KSM is disabled, automatically defining resource pools of different levels by using an application system operating behavior model and an application health status analysis model; on the basis of the importance and characteristics of each service module, a virtual machine live migration capability, and a current time period, using the application health status analysis model and an application peak operation time analysis model to respectively schedule the service modules to resource pools of different levels; and receiving system operation condition feedback data, and, on the basis of the feedback data, optimizing the application system operating behavior model and the application health status analysis model. Compared with the prior art, the present invention reduces memory resource requirements and improves effective memory utilization while ensuring that allocated virtual machines can meet actual system operation requirements.
Need to check novelty before this filing date? Find Prior Art