A distributed computing resource scheduling method for a GNSS subsidence monitoring platform

Abstract

This invention relates to the field of distributed computing resource scheduling, and more particularly to a distributed computing resource scheduling method for a GNSS settlement monitoring platform. The method includes: collecting monitoring data in the GNSS settlement monitoring platform, introducing a non-uniform sampling optimization scheduling algorithm to calculate the processing time of tasks on nodes; performing resource scheduling based on the processing time of tasks on nodes, and optimizing the node selection for tasks. This solves the technical problems of traditional distributed computing resource scheduling methods, such as the inability to dynamically adjust the sampling frequency, inaccurate estimation of task processing time, and insufficient intelligence in task scheduling decisions.

Description

Technical Field

[0001] This invention relates to the field of distributed computing resource scheduling, and in particular to a distributed computing resource scheduling method for a GNSS settlement monitoring platform. Background Technology

[0002] With the acceleration of urbanization, land subsidence is becoming an increasingly prominent problem, especially in mining areas, urban construction, and infrastructure development, where the need for subsidence monitoring is becoming more urgent. GNSS subsidence monitoring utilizes the Global Navigation Satellite System to accurately locate ground targets, combining three-dimensional coordinate data and timestamp information to provide precise subsidence rate and displacement data. It can monitor the dynamic changes of land subsidence in real time, providing decision support for engineering safety and environmental protection.

[0003] However, GNSS settlement monitoring platforms face challenges in computing resource scheduling during practical applications. Due to the complexity of the platform's monitoring tasks and the need to process massive amounts of data, how to efficiently and accurately allocate computing resources becomes a key issue, and a reasonable computing resource scheduling method is crucial to ensuring the platform's efficient operation.

[0004] However, traditional distributed computing resource scheduling methods still suffer from problems such as the inability to dynamically adjust sampling frequency, inaccurate estimation of task processing time, and insufficient intelligence in task scheduling decisions. Therefore, there is an urgent need for a distributed computing resource scheduling method for GNSS settlement monitoring platforms to improve their processing efficiency, resource utilization, and real-time response capabilities, providing solid technical support for settlement monitoring in complex engineering environments. Summary of the Invention

[0005] This invention provides a distributed computing resource scheduling method for GNSS settlement monitoring platforms to solve the technical problems of traditional distributed computing resource scheduling methods, such as the inability to dynamically adjust the sampling frequency, inaccurate estimation of task processing time, and insufficient intelligence in task scheduling decisions.

[0006] The present invention provides a distributed computing resource scheduling method for a GNSS settlement monitoring platform, comprising the following steps:

[0007] S1. Collect monitoring data in the GNSS settlement monitoring platform and introduce a non-uniform sampling optimization scheduling algorithm to calculate the processing time of the task on the node;

[0008] S2. Based on the processing time of tasks on nodes, perform resource scheduling and optimize the selection of task nodes.

[0009] Preferably, S1 specifically includes:

[0010] The monitoring data includes three-dimensional coordinates, data volume, and timestamps; based on the three-dimensional coordinates, the settlement rate and settlement acceleration are calculated.

[0011] Preferably, S1 specifically includes:

[0012] In the implementation of the non-uniform sampling optimization scheduling algorithm, a sampling frequency function is constructed based on the settlement acceleration and combined with a preset settlement acceleration threshold, and the sampling frequency is dynamically adjusted.

[0013] Preferably, S1 specifically includes:

[0014] In the sampling frequency function, when the settlement acceleration is greater than the settlement acceleration threshold, a dynamic factor is introduced to reflect the nonlinear relationship between the settlement acceleration and the sampling frequency.

[0015] Preferably, S1 specifically includes:

[0016] In the implementation of the non-uniform sampling optimization scheduling algorithm, a scheduling period is introduced, and the sampling frequency function is integrated to calculate the number of samples within the scheduling period.

[0017] Preferably, S1 specifically includes:

[0018] In the implementation of the non-uniform sampling optimization scheduling algorithm, the processing time of the task on the node is obtained based on the number of samplings, data volume and processing capacity of all monitoring locations in the task within the scheduling period; the processing capacity of the node is quantified by the processing time per byte.

[0019] Preferably, S2 specifically includes:

[0020] Based on the processing time of tasks on nodes, decision variables for tasks are introduced for resource scheduling; the goal of resource scheduling is to minimize the total processing time of all tasks.

[0021] Preferably, S2 specifically includes:

[0022] During resource scheduling, the decision variables for task allocation are solved by combining constraints to optimize the node selection of tasks. The constraints are: each task can only be assigned to one node for processing, each node can handle two or more tasks, and the maximum processing time of each node is less than or equal to the preset maximum processing time threshold of the node.

[0023] The beneficial effects of the technical solution of the present invention are:

[0024] 1. By introducing a non-uniform sampling optimization scheduling algorithm, the resource scheduling efficiency of the GNSS settlement monitoring platform is significantly improved. The sampling frequency is dynamically adjusted based on the settlement acceleration at the monitoring location, and the data acquisition density can be flexibly adjusted according to the intensity of settlement activity, thereby achieving rapid response and accurate capture of settlement activity and ensuring the real-time performance and accuracy of monitoring data.

[0025] 2. By calculating the number of samples within the scheduling cycle and combining it with the processing capacity of the nodes, the processing time of the task on each node can be accurately estimated. It takes into account the size of the task, the processing capacity of the nodes, and the changes in the sampling frequency within the scheduling cycle, which can achieve more accurate scheduling, thereby avoiding overload or waste of resources and ensuring the efficient use of computing resources.

[0026] 3. By solving the decision variables of task allocation using classic mathematical optimization methods, the total processing time of all tasks can be minimized, ensuring maximum utilization of resources and timely completion of tasks. Considering the sustainability and stability of the monitoring platform, reasonable constraints are set while ensuring the processing capacity of nodes, avoiding system crashes and performance degradation caused by improper task allocation or excessive consumption of node resources, effectively ensuring the stable operation of the monitoring platform. Attached Figure Description

[0027] Figure 1 This is a flowchart of a distributed computing resource scheduling method for a GNSS settlement monitoring platform as described in this invention. Detailed Implementation

[0028] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0029] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0030] The following description, in conjunction with the accompanying drawings, details a specific scheme for a distributed computing resource scheduling method for a GNSS settlement monitoring platform provided by the present invention.

[0031] See attached document Figure 1 The diagram illustrates a distributed computing resource scheduling method for a GNSS settlement monitoring platform according to an embodiment of the present invention. The method includes the following steps:

[0032] S1. Collect monitoring data in the GNSS settlement monitoring platform and introduce a non-uniform sampling optimization scheduling algorithm to calculate the processing time of the task on the node;

[0033] In the GNSS settlement monitoring platform, there are GNSS reference stations, each reference station monitor There are 10 monitoring locations, where each monitoring location is 10 ... The collected monitoring data includes three-dimensional coordinates, data volume, and timestamps. The settlement is determined by subtracting the vertical component of the three-dimensional coordinates at the current moment from the vertical component of the three-dimensional coordinates at the previous moment. The first derivative of the settlement with respect to time is calculated to obtain the settlement rate. The rate of change of the settlement rate with respect to time is calculated to obtain the settlement acceleration.

[0034] To improve the real-time performance and processing accuracy of resource scheduling, a non-uniform sampling optimization scheduling algorithm is introduced to obtain the processing time of tasks on nodes; the specific implementation process is as follows:

[0035] The sampling frequency is dynamically adjusted based on the settlement acceleration at the monitoring location. The greater the settlement acceleration, the more obvious the settlement activity, and the sampling frequency should be increased accordingly to capture more dynamic change information. Specifically, the relationship between the sampling frequency and settlement acceleration at the monitoring location is achieved by setting a baseline sampling frequency and a settlement acceleration threshold. When the settlement acceleration exceeds the settlement acceleration threshold, the dynamic factor will increase exponentially with the increase of settlement acceleration, thereby increasing the sampling frequency accordingly. This adjustment method is more adaptable to changes in settlement acceleration than linear increase, especially when the settlement acceleration is large, and can more sensitively reflect rapid changes in settlement activity.

[0036] The formula for the sampling frequency function is expressed as follows:

[0037]

[0038] in, Indicates the base station Monitoring location The sampling frequency is dynamically adjusted based on the settlement acceleration. The reference sampling frequency is set by professional technicians according to actual needs, and its value range is [range missing]. ; Indicates the base station Monitoring location Settlement acceleration at a certain moment; The settlement acceleration threshold is set based on geological activity and monitoring requirements, with a range of values. ; This represents a dynamic factor used to reflect the nonlinear relationship between settlement acceleration and sampling frequency;

[0039] In the case of non-uniform sampling, the sampling frequency at each monitoring location changes, which leads to a change in the number of samples within a given scheduling period. The number of samples within the scheduling period is calculated by integrating the dynamically adjusted sampling frequency function. The calculation formula is as follows:

[0040]

[0041] in, Indicates the base station Monitoring location The number of samples taken within the scheduling period; The scheduling cycle is defined by technical personnel based on actual needs, and its value range is [value range missing]. ; Indicates the base station Monitoring location At any time Settlement acceleration;

[0042] Each task contains data from multiple monitoring locations. The size of the task is determined by the amount of data from each monitoring location. The higher the sampling frequency, the larger the amount of data the task needs to process. The processing capacity of each node is one of the key factors affecting the task processing time. The processing capacity of a node is quantified by the processing time per byte.

[0043] Multiply the number of samples, the amount of data, and the processing capacity of each node for all monitoring locations within the scheduling period to obtain the processing time of the task on the node. The calculation formula is as follows:

[0044]

[0045] in, Indicates task At the node Processing time; Indicates the first Monitoring locations of each base station The data at this location belongs to the task. , This indicates that it belongs to a task. The set of monitoring locations; Indicates the base station Monitoring location The amount of data at the location; Represents a node The time required to process each byte of data is determined by the node's hardware performance.

[0046] S2. Based on the processing time of tasks on nodes, perform resource scheduling and optimize the selection of task nodes.

[0047] Since each task involves processing data from one or more monitoring locations, a task allocation decision variable is introduced to indicate whether a task is assigned to a particular node for processing. The task allocation decision variable takes the value 0 or 1, where 0 indicates no allocation and 1 indicates allocation. During resource scheduling, the most suitable node must be selected from all nodes for task processing. The goal of resource scheduling is to minimize the total processing time of all tasks, expressed by the formula:

[0048]

[0049] in, This indicates finding the minimum value; Indicates the total number of tasks; Indicates the total number of nodes; The decision variable representing task assignment is used to represent the task. Is it assigned to a node? If the task Assigned to a node ,but ,otherwise ;

[0050] To ensure the effective operation of the monitoring platform, various constraints are imposed on the scheduling process: each task can only be assigned to one node for processing, each node can handle multiple tasks, and the maximum processing time of each node is less than or equal to a node's maximum processing time threshold, where the node's maximum processing time threshold is taken as the scheduling period. ;

[0051] By employing classic mathematical optimization methods, such as integer programming, we can solve for the decision variables assigned to each task, optimize the node selection for the task, and thus minimize latency and waste of computing resources.

[0052] In the above scheme, the units of all frequency-related data (such as the reference sampling frequency) are uniformly converted to Hertz (Hz), the units of all time-related data (such as scheduling cycle and processing time) are uniformly converted to seconds (s), and the units of all data volume are converted to bytes (B). This aims to eliminate the multi-dimensional problem and ensure that all physical quantities have a consistent numerical scale in subsequent analysis.

[0053] In summary, a distributed computing resource scheduling method for a GNSS settlement monitoring platform has been developed.

[0054] The order of the embodiments is for illustrative purposes only and does not represent the superiority or inferiority of the embodiments. The processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0055] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0056] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A distributed computing resource scheduling method for a GNSS settlement monitoring platform, characterized in that, Includes the following steps: S1. Collect monitoring data in the GNSS settlement monitoring platform and introduce a non-uniform sampling optimization scheduling algorithm to calculate the processing time of the task on the node; S2. Based on the processing time of tasks on nodes, perform resource scheduling and optimize the selection of task nodes.

2. The distributed computing resource scheduling method for a GNSS settlement monitoring platform according to claim 1, characterized in that, S1 specifically includes: The monitoring data includes three-dimensional coordinates, data volume, and timestamps; based on the three-dimensional coordinates, the settlement rate and settlement acceleration are calculated.

3. The distributed computing resource scheduling method for a GNSS settlement monitoring platform according to claim 2, characterized in that, S1 specifically includes: In the implementation of the non-uniform sampling optimization scheduling algorithm, a sampling frequency function is constructed based on the settlement acceleration and combined with a preset settlement acceleration threshold, and the sampling frequency is dynamically adjusted.

4. A distributed computing resource scheduling method for a GNSS settlement monitoring platform according to claim 3, characterized in that, S1 specifically includes: In the sampling frequency function, when the settlement acceleration is greater than the settlement acceleration threshold, a dynamic factor is introduced to reflect the nonlinear relationship between the settlement acceleration and the sampling frequency.

5. A distributed computing resource scheduling method for a GNSS settlement monitoring platform according to claim 3, characterized in that, S1 specifically includes: In the implementation of the non-uniform sampling optimization scheduling algorithm, a scheduling period is introduced, and the sampling frequency function is integrated to calculate the number of samples within the scheduling period.

6. A distributed computing resource scheduling method for a GNSS settlement monitoring platform according to claim 5, characterized in that, S1 specifically includes: In the implementation of the non-uniform sampling optimization scheduling algorithm, the processing time of the task on the node is obtained based on the number of samplings, data volume and processing capacity of all monitoring locations in the task within the scheduling period; the processing capacity of the node is quantified by the processing time per byte.

7. A distributed computing resource scheduling method for a GNSS settlement monitoring platform according to claim 1, characterized in that, S2 specifically includes: Based on the processing time of tasks on nodes, decision variables for tasks are introduced for resource scheduling; the goal of resource scheduling is to minimize the total processing time of all tasks.

8. A distributed computing resource scheduling method for a GNSS settlement monitoring platform according to claim 7, characterized in that, S2 specifically includes: During resource scheduling, the decision variables for task allocation are solved by combining constraints to optimize the node selection of tasks. The constraints are: each task can only be assigned to one node for processing, each node can handle two or more tasks, and the maximum processing time of each node is less than or equal to the preset maximum processing time threshold of the node.

Images