CN-122019144-A - Urban rail transit cloud platform resource scheduling method, system, equipment and medium

CN122019144ACN 122019144 ACN122019144 ACN 122019144ACN-122019144-A

Abstract

The method comprises the steps of determining an initial passenger flow peak time period in a target period based on a large data platform passenger flow center, collecting real-time passenger flow data, predicting a predicted passenger flow peak time period in the target period based on the real-time passenger flow data, determining a target passenger flow peak time period based on the initial passenger flow peak time period and the predicted passenger flow peak time period, generating an initial virtual machine allocation strategy based on the target passenger flow peak time period, detecting operation parameters in the operation process of the initial virtual machine allocation strategy in real time, and adjusting the initial virtual machine allocation strategy based on real-time detection results. The cloud computing resource utilization rate is improved.

Inventors

WANG YU
LIU JUN
ZHANG BO
ZHANG WANQIU
CHE WENXUAN

Assignees

北京全路通信信号研究设计院集团有限公司

Dates

Publication Date: 20260512
Application Date: 20260105

Claims (10)

1. A resource scheduling method for urban rail transit cloud platform is characterized in that, The method may include the steps of, Determining an initial passenger flow peak time in a target period based on a passenger flow center of a big data platform; Collecting real-time passenger flow data, and predicting a passenger flow peak time in a target period based on the real-time passenger flow data; Determining a target traffic peak period based on the initial traffic peak period and the predicted traffic peak period; generating an initial virtual machine allocation strategy based on the target passenger flow peak period; And detecting operation parameters in the operation process of the initial virtual machine allocation strategy in real time, and adjusting the initial virtual machine allocation strategy based on a real-time detection result.
2. The method of claim 1, wherein the step of determining the position of the substrate comprises, The method for determining the initial passenger flow peak time based on the large data platform passenger flow center specifically comprises the following steps: receiving passenger flow information, and analyzing the passenger flow information to obtain passenger flow time distribution characteristics; And predicting and obtaining an initial passenger flow peak time in the target period based on passenger flow time distribution characteristics.
3. The method of claim 2, wherein the step of determining the position of the substrate comprises, Predicting a passenger flow peak period in a target period based on real-time passenger flow data specifically comprises the following steps: Acquiring real-time passenger flow data based on the real-time data acquired by the real-time sensing equipment and the real-time data of the service system; and drawing a real-time passenger flow change map based on the real-time passenger flow data, analyzing the real-time passenger flow change map based on a time window, calculating the corresponding passenger flow increase rate and peak fluctuation amplitude, and determining a predicted passenger flow peak time period based on the passenger flow increase rate and the peak fluctuation amplitude.
4. The method of claim 3, wherein the step of, The method for determining the peak period of the target passenger flow specifically comprises the following steps: Comparing the initial passenger flow peak time period with the predicted passenger flow peak time period, and determining the time period coincidence degree and the peak value deviation degree; comparing the time period overlap ratio with a preset overlap ratio to obtain an overlap ratio comparison result; And adjusting preset weights based on the coincidence ratio comparison result, and calculating to obtain the target passenger flow peak period based on a weighted average algorithm.
5. The method of claim 4, wherein the step of determining the position of the first electrode is performed, Generating an initial virtual machine allocation strategy based on the target passenger flow peak period, which specifically comprises the following steps: Judging the distribution density and the peak value average value of the peak period of the target passenger flow in the target period; and determining to call the virtual machine of the cloud platform based on the distribution density and the peak value average value, or adjusting the computing resource of the virtual machine of the cloud platform.
6. The method of claim 5, wherein the step of determining the position of the probe is performed, And determining to call the cloud platform virtual machine based on the distribution density, or adjusting computing resources of the cloud platform virtual machine, wherein the method specifically comprises the following steps of: comparing the distribution density with a preset density to obtain a density comparison result; comparing the peak value average value with a preset average value to obtain a peak value comparison result; when the distribution density is greater than or equal to the preset density or the peak average value is greater than or equal to the preset average value, calling a cloud platform virtual machine in the target passenger flow peak period; and when the distribution density is smaller than the preset density and the peak average value is smaller than the preset average value, adjusting the computing resources of the cloud platform virtual machine in the target passenger flow peak period.
7. The method of claim 6, wherein the step of providing the first layer comprises, The initial virtual machine allocation strategy is adjusted based on a real-time detection result, and specifically comprises the following steps: detecting the running state of the cloud platform virtual machine in a target passenger flow peak period to obtain the real-time CPU utilization rate and the real-time memory occupancy rate; comparing the real-time CPU utilization rate with a preset CPU utilization rate to obtain a CPU comparison result; comparing the real-time memory occupancy rate with a preset memory occupancy rate to obtain a memory occupancy comparison result; and adjusting the initial virtual machine allocation strategy based on the CPU comparison result and the memory occupation comparison result.
8. A resource scheduling system of urban rail transit cloud platform is characterized in that, The system may be comprised of a plurality of devices, The initial determining module is used for determining an initial passenger flow peak time in a target period based on a passenger flow center of the big data platform; The prediction module is used for collecting real-time passenger flow data and predicting a passenger flow peak time period in a target period based on the real-time passenger flow data; A target determination module to determine a target traffic peak period based on the initial traffic peak period and the predicted traffic peak period; The strategy generation module is used for generating an initial virtual machine allocation strategy based on the target passenger flow peak period; the adjusting module is used for detecting the operation parameters in the operation process of the initial virtual machine allocation strategy in real time and adjusting the initial virtual machine allocation strategy based on the real-time detection result.
9. The electronic equipment is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus; a memory for storing a computer program; and the processor is used for realizing the method for scheduling the urban rail transit cloud platform resources according to any one of claims 1-7 when executing the program stored in the memory.
10. A computer storage medium, wherein a computer program is stored in the computer storage medium, and when the computer program is executed by a processor, the method for scheduling resources of the urban rail transit cloud platform according to any one of claims 1 to 7 is implemented.

Description

Urban rail transit cloud platform resource scheduling method, system, equipment and medium Technical Field The disclosure belongs to the technical field of rail transit, and particularly relates to a method, a system, equipment and a medium for scheduling resources of a cloud platform of urban rail transit. Background The urban rail transit cloud platform is a comprehensive digital platform which is manufactured by taking a cloud computing technology as a core and integrating leading edge technologies such as big data, the Internet of things and artificial intelligence. The urban rail transit cloud platform generally comprises a large data platform, collects and analyzes operation data, provides decision basis for passenger flow prediction, equipment operation and maintenance and the like, promotes the cooperative operation of the systems, improves the operation efficiency and the service quality, enhances the safety and the stability of the systems, and promotes the urban rail transit to go forward to wisdom and high efficiency. Elastic computing (Elastic Computing) refers to the ability of a cloud computing platform to automatically increase or decrease computing resources according to changes in load. This means that the cloud platform can quickly expand resources when business needs of the enterprise increase, and the platform can reduce unnecessary resources when the needs decrease, thereby achieving optimal cost effectiveness and resource utilization. Elastic computing involves not only automatic expansion and contraction of computing resources, but also dynamic adjustment of storage and network resources. At present, although the rail transit of each city builds a cloud platform of the city, different service systems such as a signal system, an automatic ticket selling and checking system and the like respectively run in respective virtual machines, each virtual machine executes a fixed task, and although the concept of elastic calculation of the cloud platform exists, the urban rail transit cloud platform does not realize elastic resource allocation. The cloud platform cannot flexibly adjust the number of virtual machines of each service or adjust the configuration of the virtual machines according to the data characteristics of urban rail transit, so that the advantage of cloud computing flexibility cannot be exerted, and waste of cloud computing resources is generated. Disclosure of Invention In order to solve the problems, the present disclosure provides a method, a system, a device and a medium for scheduling resources of an urban rail transit cloud platform, which adopt two-dimensional passenger flow analysis of historical big data and real-time sensor data to accurately identify peak time, and combine a virtual machine elastic expansion strategy to realize resource allocation as required, so that the problem of cloud computing resource waste can be solved. In a first aspect, the present disclosure provides a method for scheduling resources of an urban rail transit cloud platform, The method may include the steps of, Determining an initial passenger flow peak time in a target period based on a passenger flow center of a big data platform; Collecting real-time passenger flow data, and predicting a passenger flow peak time in a target period based on the real-time passenger flow data; Determining a target traffic peak period based on the initial traffic peak period and the predicted traffic peak period; generating an initial virtual machine allocation strategy based on the target passenger flow peak period; And detecting operation parameters in the operation process of the initial virtual machine allocation strategy in real time, and adjusting the initial virtual machine allocation strategy based on a real-time detection result. Further, the method comprises the steps of, The method for determining the initial passenger flow peak time based on the large data platform passenger flow center specifically comprises the following steps: receiving passenger flow information, and analyzing the passenger flow information to obtain passenger flow time distribution characteristics; And predicting and obtaining an initial passenger flow peak time in the target period based on passenger flow time distribution characteristics. Further, the method comprises the steps of, Predicting a passenger flow peak period in a target period based on real-time passenger flow data specifically comprises the following steps: Acquiring real-time passenger flow data based on the real-time data acquired by the real-time sensing equipment and the real-time data of the service system; and drawing a real-time passenger flow change map based on the real-time passenger flow data, analyzing the real-time passenger flow change map based on a time window, calculating the corresponding passenger flow increase rate and peak fluctuation amplitude, and determining a predicted passenger flow peak time period based on the passenger flow incr