LU508576B1 - A real-time update management system for measuring control points based on digital campus - Google Patents

A real-time update management system for measuring control points based on digital campus Download PDF

Info

Publication number
LU508576B1
LU508576B1 LU508576A LU508576A LU508576B1 LU 508576 B1 LU508576 B1 LU 508576B1 LU 508576 A LU508576 A LU 508576A LU 508576 A LU508576 A LU 508576A LU 508576 B1 LU508576 B1 LU 508576B1
Authority
LU
Luxembourg
Prior art keywords
task
node
resource
allocation
submodule
Prior art date
Application number
LU508576A
Other languages
German (de)
Inventor
Shibao Zhao
Original Assignee
Chongqing Vocational Inst Eng
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Chongqing Vocational Inst Eng filed Critical Chongqing Vocational Inst Eng
Priority to LU508576A priority Critical patent/LU508576B1/en
Application granted granted Critical
Publication of LU508576B1 publication Critical patent/LU508576B1/en

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/06—Management of faults, events, alarms or notifications
    • H04L41/0631—Management of faults, events, alarms or notifications using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/48—Program initiating; Program switching, e.g. by interrupt
    • G06F9/4806—Task transfer initiation or dispatching
    • G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/48—Program initiating; Program switching, e.g. by interrupt
    • G06F9/4806—Task transfer initiation or dispatching
    • G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
    • G06F9/4881—Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/48—Program initiating; Program switching, e.g. by interrupt
    • G06F9/4806—Task transfer initiation or dispatching
    • G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
    • G06F9/4881—Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
    • G06F9/4893—Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues taking into account power or heat criteria
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
    • G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
    • G06F9/5038—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals considering the execution order of a plurality of tasks, e.g. taking priority or time dependency constraints into consideration
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5061—Partitioning or combining of resources
    • G06F9/5066—Algorithms for mapping a plurality of inter-dependent sub-tasks onto a plurality of physical CPUs
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5083—Techniques for rebalancing the load in a distributed system
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5094—Allocation of resources, e.g. of the central processing unit [CPU] where the allocation takes into account power or heat criteria
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/54—Interprogram communication
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/06—Management of faults, events, alarms or notifications
    • H04L41/0654—Management of faults, events, alarms or notifications using network fault recovery
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/10—Protocols in which an application is distributed across nodes in the network
    • H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
    • H04L67/1004—Server selection for load balancing
    • H04L67/1012—Server selection for load balancing based on compliance of requirements or conditions with available server resources
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/50—Network services
    • H04L67/56—Provisioning of proxy services

Landscapes

  • Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Debugging And Monitoring (AREA)

Abstract

The present invention relates to the field of computer control technology, specifically to a real-time update management system of measurement control points based on digital campus. In the present invention, through the reasonable allocation of high-priority tasks, to ensure that urgent tasks can be processed in a timely manner, by matching node computing power, load state and task complexity, to ensure that complex tasks are assigned to high-performance nodes, to improve task processing efficiency, through the monitoring of node resource usage, to ensure the balanced distribution of tasks, to avoid resource waste and task conflicts, through real-time monitoring of node CPU, memory resources, timely adjustment of resource allocation according to task processing progress, and to optimize the overall resource utilization, It ensures the efficiency, stability and scalability in the process of task scheduling and execution, and improves the overall task processing ability and resource management efficiency.

Description

A real-time update management system for measuring control points LU508576 based on digital campus
Technical fields
The present invention relates to the field of computer control technology, and in particular relates to a real-time update management system for measurement control points based on a digital campus.
Background technology
The field of computer control technology aims to automate the control and management of various types of equipment through computer systems, realizing real-time monitoring, control and regulation of the external environment or objects, improving the efficiency, accuracy and safety of the system, and forming an integrated, automated and efficient control system.
The purpose of the real-time update management system of measurement control points based on digital campus is to monitor and update the status and location information of measurement control points on campus in real time in the digital campus environment, to ensure the accuracy and real-time information, to improve the efficiency and accuracy of the campus management, and to support the intelligent and refined management of the digital campus.
The traditional system relies on static task allocation, which is unable to consider the urgency of the task and the dynamic performance of the nodes, resulting in high-priority tasks may not be able to be processed in a timely manner, the lack of real-time monitoring of the use of node resources and dynamic adjustments, resulting in overloading of nodes in the peak period of the task, other node resources are idle, and the allocation of resources is imbalanced, which reduces the overall efficiency of the system and increases the system's operating costs.
Invention content
The purpose of the present invention is to solve the shortcomings existing in the prior art, and a real-time update management system of measurement control points based on digital campus is proposed.
In order to realize the above purpose, the present invention adopts the following technical solution: a real-time update management system for measurement control points based on a digital campus comprises:
Task decomposition module: based on the real-time data flow of the measurement control points, extract the geographic coordinates of the control points and the measurement data, analyze the data attributes of the control points, divide the region, time and signal type, and assign them according to the node load, and correlate the related measurement data to generate the control task list;
Task scheduling module: based on the list of control tasks, using the earliest deadline priority scheduling algorithm, by extracting the task priority LU508576 and control region, analyzing the task complexity and node status, combining the regional parameters and time conditions to match the judgment, the high-priority task is assigned to the corresponding node, and based on the urgency of the task to adjust to generate the task allocation plan;
Node allocation module: based on the task allocation scheme, by obtaining the computing power, load status and processing speed of each node, matching the task complexity with the node performance parameters, assigning tasks with high complexity to high-performance nodes, and balancing the rest of the tasks to the lighter-loaded nodes, generating a node task allocation table;
Parallel computing module: based on the node task allocation table, select the task with high priority to be executed in parallel on multiple nodes, analyze the resource usage of the nodes to determine whether the task needs to be reallocated to prevent task conflicts, and optimize the distribution of tasks among nodes to generate parallel processing task records;
Resource dynamic adjustment module: based on the parallel processing task record, by monitoring the consumption of CPU, memory and other resources of each node, analyze the progress of task processing, judge whether it is necessary to dynamically adjust resource allocation, reduce the resource pressure of high load nodes, adjust thread allocation, optimize resource use, and generate dynamic resource adjustment results;
Failure detection and recovery module: based on the results of the dynamic resource adjustment, monitor the task execution status of each node, analyze the task progress and node status, determine whether a failure or resource abnormality occurs, such as detecting the problem, switch the task to the backup node, restore the task progress and keep the node stable, and generate fault switching records and recovery programs;
Data Transmission and Optimization Module: Based on the mentioned failover recording and recovery scheme, it monitors the data transmission status between task nodes, analyzes the priority of the task and the transmission path bandwidth, determines the transmission priority order of the data flow, adjusts the data transmission path, reduces the transmission delay, and generates the transmission path scheme;
As a further solution of the present invention, said control task list includes task type, execution region, data collection time point, said task allocation scheme includes node allocation of priority tasks, execution time window, node load allocation, said node task allocation table includes node resource utilization rate, task processing time, task priority allocation, said parallel processing task record includes task execution order, node parallel load, computational resource occupancy, said dynamic resource adjustment results include adjusted memory allocation, number of processing threads, node resource optimization parameters, said failover record and recovery scheme includes a list of faulty nodes, standby node task assignments, task recovery progress status, and said transmission path scheme includes bandwidth LU508576 optimization, data priority order, and path delay parameter adjustment.
As a further solution of the present invention, said task decomposition module includes a coordinate extraction submodule, a data division submodule, and a task assignment submodule, wherein:
Coordinate extraction submodule: based on the real-time data flow of the measurement control point, extract the geographic coordinate data of the said measurement point, carry out the preliminary organization of the said coordinate data by identifying the position information of each measurement point, and arrange and calibrate the position information according to the coordinate system to generate the geographic coordinate set of the control point;
Data division submodule: based on the set of geographic coordinates of the said control points, analyze the data attributes of each measurement point, combine the said position information with the measurement attributes such as time parameter, signal type and other measurement attributes, carry out the regional division, and generate the regional time signal classification set by matching the region of the said control points with the data type and organizing the classification information;
Task allocation submodule: based on the regional time signal classification set, according to the load state of each node in the system and the task allocation rules, extract the control point information and node state, assign the task to the most suitable node in turn, and generate the control task list.
As a further solution of the present invention, said task scheduling module includes a priority analysis submodule, a time condition judgment submodule, and a node allocation submodule, wherein:
Priority analysis submodule: based on the list of said control tasks, adopting the earliest deadline priority scheduling algorithm, extracting the priority parameters of said tasks, identifying the importance and urgency of said tasks, and, by comparing the said control area and task requirements, carrying out the priority ranking, and gradually establishing the execution sequence of said tasks, generating the results of prioritized task ranking;
Time condition judgment submodule: based on the said prioritized task sorting results, extract the execution time window of the said task, analyze the time constraints of the said task, compare the execution time of the said task with the current system time and complete the time matching judgment by selecting the most suitable time node to generate the time matching judgment results:
Node allocation submodule: based on the results of the time matching judgment, extract the load state information of the node, analyze the current processing capacity of the node, and assign the high priority task to the node with lower load, and generate the task allocation scheme.
As a further embodiment of the present invention, said earliest deadline priority scheduling algorithm, according to the formula: LU508576
P = a(D, —C op J+ i i Xi — yu,
E,
Of which:P,for the mandateiThe combined priority value of theD;for the mandateithe deadline, theC;for the mandateiof the projected completion date of the project, andR;for the mandateiresource requirements, andE;is the total amount of resources currently available, theU;for the mandateithe task utilization rate, thea. B, yis the weighting factor.
As a further solution of the present invention, said node allocation module comprises a computational capacity evaluation submodule, a task complexity matching submodule, and a load balancing allocation submodule, wherein:
Computing capability evaluation sub module: based on the task allocation scheme, obtain the CPU and memory usage of each node, extract the real-time processing speed of the node, evaluate the node resource status by analyzing the node resource usage, record the resource parameters of each node to the table, and generate the node performance evaluation table;
Task complexity matching submodule: based on the node performance evaluation table, obtain the complexity information of each task, by comparing the task complexity and node processing capacity, select the node with sufficient resources for task allocation, assign the high complexity task to the high-performance node, and generate the task complexity matching table;
Load balancing allocation submodule: based on the task complexity matching table, extract the remaining unallocated tasks, analyze the low-complexity tasks and the node load state, select the nodes with lighter loads, and monitor the node load changes to generate the node task allocation table.
As a further solution of the present invention, said parallel computing module comprises a task parallel allocation submodule, a resource usage analysis submodule, and a task conflict optimization submodule, wherein:
Task parallel allocation submodule: based on the node task allocation table, extract high-priority tasks, simultaneously allocated to multiple computing nodes, detect the node parallel execution state, ensure the parallel execution of high-priority tasks, generate parallel task execution records;
Resource utilization analysis sub module: based on the parallel task execution record, obtain the resource utilization rate of each node, analyze whether there is insufficient node resources by monitoring the real-time utilization of CPU and memory, extract and compare the resource utilization, record data, and generate the resource utilization analysis results;
Task conflict optimization submodule: based on the results of the resource usage analysis, extract the nodes with task conflicts, analyze the reasons for the conflicts, determine whether it is necessary to re-adjust the order of task allocation, select the idle resource nodes to optimize the execution process,
and generate parallel processing task records. LU508576
As a further solution of the present invention, said resource dynamic adjustment module includes a resource monitoring submodule, a dynamic allocation submodule, and a load balancing submodule, wherein: 5 Resource monitoring sub module: extract the CPU and memory utilization of each node based on the parallel processing task record, obtain the current resource consumption data of the node by monitoring the resource utilization of each node, analyze the change of resource consumption, record the resource consumption rate, and generate the resource consumption status of the node;
Dynamic allocation submodule: based on the state of resource consumption of said node, extract the resource load of said node, analyze whether the processing thread of said task needs to be adjusted by comparing the occupancy rate of said resource with the rate of consumption, reallocate the resources to said high-load node or reduce the occupancy, and generate the result of the adjustment of the allocation of said resource;
Load balancing submodule: based on the said resource allocation adjustment result, extract the said high load node information, analyze the resource occupancy and task allocation status of the said node, and generate the said dynamic resource adjustment result by transferring part of the task to the low load node and assigning the said task to other nodes in a balanced manner.
As a further embodiment of the present invention, said fault detection and recovery module includes a task monitoring sub-module, a fault detection sub-module, and a task recovery sub-module, wherein:
Task monitoring submodule: based on the results of said dynamic resource adjustment, extract the task execution status of said nodes, monitor the task processing progress of each node, identify the nodes with processing abnormalities by comparing the progress of said tasks with the resource utilization, and record the processing progress of said tasks to generate a record of the task execution status of said nodes;
Fault detection submodule: based on the node task execution state record, extract the state information of said node, analyze the processing progress of said task and node load, determine whether there is a fault, by checking the response time of said node and the task is not completed state, extract the fault information, generate the fault detection results;
Task recovery submodule: based on said fault detection results, extract said faulty node information, transfer the task to the standby node, restore the latest progress of said task by accessing the task snapshot of said node, and reassign the uncompleted task to the available node, and generate said failover record and recovery program.
As a further solution of the present invention, said data transmission and optimization module comprises a transmission state monitoring submodule, a priority analysis submodule, and a path optimization submodule, wherein:
Transmission status monitoring submodule: based on the mentioned LU508576 failover recording and recovery scheme, extract the data transmission status of each task node, monitor the real-time data flow by obtaining the data transmission rate and delay between each node, analyze the data bandwidth usage between the nodes, and record the transmission delay and data loss rate, and generate the transmission status record;
Priority analysis submodule: based on the said transmission status record, extract the priority of each task, determine the transmission order by comparing the importance parameter of the task with the data bandwidth occupancy of the current node, select the task with higher priority for bandwidth allocation, and adjust the transmission order of the low-priority task to generate the data transmission priority ordering;
Path optimization submodule: based on the data transmission priority ranking, extract the bandwidth and latency information of the current transmission path, adjust the data transmission path by comparing the transmission load of each path, optimize the task data transmission by selecting the path with high bandwidth utilization and low latency, and generate the transmission path scheme.
The advantages and positive effects of the present invention over the prior artare:
In the invention, by adopting the earliest deadline priority scheduling algorithm, high priority tasks can be reasonably allocated based on the priority of tasks and the conditions of the control area, so as to ensure that urgent tasks can be processed in time. By matching the computing capacity, load status and task complexity of nodes, complex tasks can be allocated to high-performance nodes, and task processing efficiency can be improved, By monitoring the use of node resources, we can ensure the balanced distribution of tasks and avoid resource waste and task conflicts. Through real-time monitoring of node CPU and memory resources, we can timely adjust resource allocation according to task processing progress, optimize the overall resource utilization, and ensure the efficiency, stability and scalability in task scheduling and execution, It improves the overall task processing ability and resource management efficiency.
The accompanying illustration
Figure 1 shows a flowchart of the system of the present invention;
Figure 2 shows a schematic diagram of the system framework of the present invention.
Specific implementations
In order to make the purpose, technical solutions and advantages of the present invention more clear and understandable, the following combines the accompanying drawings and embodiments, the present invention is further described in detail. It should be understood that the specific embodiments described herein are only for the purpose of explaining the present invention, and are not intended to limit the present invention.
Example one LU508576
Referring to FIG. 1, the present invention provides a technical solution: a real-time update management system for measurement control points based on a digital campus comprising:
Task decomposition module: based on the real-time data flow of the measurement control points, extract the geographic coordinates of the control points and the measurement data, analyze the data attributes of the control points, divide the region, time and signal type, and assign them according to the node load, and correlate the related measurement data to generate the control task list;
Task scheduling module: based on the list of control tasks, using the earliest deadline priority scheduling algorithm, through the extraction of task priorities and control regions, analyzing the complexity of the task and the state of the node, combined with the regional parameters and the time conditions of the matching judgement, the high-priority tasks will be assigned to the corresponding node, and based on the degree of urgency of the task adjustments to generate the task allocation scheme;
Node allocation module: based on the task allocation scheme, by obtaining the computational capacity, load status and processing speed of each node, matching the task complexity with the node performance parameters, assigning tasks with high complexity to the high-performance nodes, and balancing the rest of the tasks to the lighter-loaded nodes, and generating the node task allocation table;
Parallel computing module: based on the node task allocation table, select high priority tasks to be executed in parallel on multiple nodes, analyze the resource usage of the nodes to determine whether the tasks need to be reallocated to prevent task conflicts, and optimize the distribution of tasks among nodes to generate parallel processing task records;
Dynamic resource adjustment module: based on parallel processing task records, by monitoring the consumption of CPU, memory and other resources of each node, analyze the progress of task processing, judge whether it is necessary to dynamically adjust resource allocation, reduce resource pressure on high load nodes, adjust thread allocation, optimize resource use, and generate dynamic resource adjustment results;
Failure detection and recovery module: based on the dynamic resource adjustment results, monitor the task execution status of each node, analyze the task progress and node status, determine whether a failure or resource abnormality occurs, if a problem is detected, switch the task to a standby node, restore the task progress and maintain node stability, and generate a failure switching record and recovery plan;
Data Transmission and Optimization Module: Based on the failover record and recovery scheme, it monitors the data transmission status between task nodes, analyzes the priority of tasks and the bandwidth of the transmission path, determines the transmission priority order of the data flow, adjusts the data transmission path, reduces the transmission delay, and generates the LU508576 transmission path scheme.
Control task list includes task type, execution region, data collection time point, task allocation scheme includes node allocation of priority tasks, execution time window, node load allocation, node task allocation table includes node resource utilization, task processing time, task priority allocation, parallel processing task record includes task execution order, node parallel load, computational resource occupancy rate, dynamic resource adjustment result The dynamic resource adjustment results include adjusted memory allocation, number of processing threads, and node resource optimization parameters, the failover record and recovery scheme include the list of failed nodes, task allocation of standby nodes, and task recovery progress status, and the transmission path scheme include bandwidth optimization, data priority order, and path delay parameter adjustment.
Referring to Fig. 2,the task decomposition module includes a coordinate extraction sub-module, a data division sub-module, and a task assignment sub-module, wherein:
Coordinate extraction submodule: based on the real-time data flow of the measurement control points, the geographic coordinate data of the measurement points are extracted, and by identifying the position information of each measurement point, the coordinate data are preliminarily organized, and the position information is arranged and calibrated in accordance with the coordinate system, so as to generate a set of geographic coordinates of the control points;
Data division submodule: based on the geographic coordinate set of the control points, analyze the data attributes of each measurement point, combine the position information with the measurement attributes such as time parameter, signal type, etc., carry out the regional division, and generate the regional time signal classification set by matching the regions of the control points with the data types and organizing the classification information;
Task allocation submodule: based on the regional time signal classification set, according to the load state of each node in the system and the task allocation rules, extract the control point information and node state, assign the tasks to the most suitable nodes in order to generate the control task list;
Coordinate extraction submodule: Based on the real-time data flow of measurement control points, the geographic coordinates of each measurement point are extracted by bilinear interpolation algorithm, specifically, the observed value of each measurement point is bilinearly interpolated, the input parameters include the geographic coordinates of the neighboring control points as well as the corresponding weights of each control point, and at the same time the weight calculation is performed, and the coordinate interpolation is performed by inputting the coordinates of the measurement points to extract results and organize information, sort each control point according to the specified coordinate system, and use rounding LU508576 algorithm to adjust the data to a fixed number of decimal places to generate a set of geographic coordinates of control points. Organize the information, sort the control points according to the specified coordinate system, and use the rounding algorithm to adjust the data to a fixed number of decimal places to generate a set of geographic coordinates of the control points;
Data division sub module: based on the geographical coordinate set of control points, K-Means clustering algorithm is used to cluster the coordinates and measurement attributes of each measurement point. First, set the number of cluster centers, enter the geographical coordinate set of control points as the initial data set, and set the initial center of each cluster as the coordinates of control points of each region. The execution steps include calculating the distance of each measurement point, Allocate each measurement point to the nearest cluster center, recalculate the position of the center of mass after completion, continue to iterate until the center of mass no longer changes, classify each measurement point with its time parameters and signal types, output the classification information of each area, and generate the regional time signal classification set;
Task allocation submodule: Based on the regional time signal classification set, the genetic algorithm is used for task allocation, firstly, the load state of each node in the system is encoded, the binary encoding method is used to represent the node load, the initial population size is set, the roulette selection mechanism is used to select the suitable individual from the node state as the mating object, the node state and task information are inputted, the crossover probability is set, and the load state of the node is updated using a single-point crossover operation to update the load state of nodes, using mutation operation to randomly change the state of some individuals, setting the mutation probability, calculating the fithess of each generation of new populations, selecting the individuals with higher fitness values as the next generation of populations, and optimizing the task allocation scheme through multi-generation iteration to generate the list of control tasks.
Referring to Fig. 2,the task scheduling module includes a priority analysis sub-module, a time condition judgment sub-module, and a node assignment sub-module, wherein:
Priority analysis submodule: based on the list of control tasks, using the earliest deadline priority scheduling algorithm, extracting the priority parameters of the tasks, identifying the importance and urgency of the tasks, and prioritizing them by comparing the control area and the task requirements, as well as building the execution sequence of the tasks step by step to generate the prioritized task sequencing results;
Time condition judgment submodule: based on the prioritized task sorting results, extract the execution time window of the task, analyze the time constraints of the task, compare the execution time of the task with the current system time and complete the time matching judgment by selecting the most suitable time node to generate the time matching judgment results; LU508576
Node allocation submodule: Based on the result of time matching judgment, extract the load state information of the node, analyze the current processing capacity of the node, and allocate the high-priority task to the node with lower load, and generate the task allocation scheme;
Priority analysis submodule: based on the control task list, the earliest deadline priority scheduling algorithm is used to extract the priority parameters of the task, specifically based on the deadline of each task, using the start time and deadline time of the task for the calculation, inputting the relevant time information of the task, setting up a base time window, comparing the deadline time of the task with the base time, and gradually establishing the priority queue of the task by traversing the task list, sorting the tasks according to their deadline time from early to late, and further identifying the urgency of each task during execution, using the time difference value of the task to further identify the urgency of each task, and gradually building the priority queue of the task. The priority queue of tasks is gradually established by sorting the tasks from early to late according to their deadlines, further identifying the urgency of each task during execution, defining the priority weights by using the time difference of the tasks, prioritizing the tasks according to the order, generating the execution sequence of the tasks, and generating the prioritized task sorting results;
Time condition judgment submodule: based on the prioritized task sorting results, the dynamic time window algorithm is used to extract the execution time window of the task, first of all, extract the start time and cut-off time of the task, and analyze the time constraints of each task, use the dynamic time window model to match the execution time of each task with the current system time, by analyzing the current system clock, use the way of sliding window to gradually judge the execution time of the task, and dynamically adjust the window size to ensure that the task is executed within its time constraints, by setting a time node within the allowable error range, time matching, by setting an allowable error range, time matching. Gradually judge the task execution time, and dynamically adjust the window size to ensure that the task is executed within its time constraints, by setting a time node within the allowable error range for time matching, set the time error parameter to the time difference within the allowable range, and generate the time matching judgment results;
Node allocation submodule: based on the time matching judgment results, the load balancing algorithm is used for node allocation, firstly, the load state of each node in the current system is extracted, specifically, the load balancing algorithm's weighted polling mechanism is used to allocate the nodes, the processing capacity of each node is extracted, and the weighting parameter is set for the current load state of each node, and the execution step is to monitor the load of each node, use the task execution time to compare with the idle time of the node, and carry out weighted processing according to the current load of the node. The execution time of the task is compared with the idle time LU508576 of the node, weighted according to the current load of the node, by comparing the priority of the task, set the correspondence between the high priority task and the low load node, and gradually establish the allocation scheme to generate the task allocation scheme.
Refer to Fig. 2, Earliest Deadline Priority Scheduling Algorithm, according to Eq:
P = a(D, —C op J+ i i Xi — yu,
E,
Of which:P,for the mandateiThe combined priority value of theD;for the mandateithe deadline, theC;for the mandateiof the projected completion date of the project, andR;for the mandateiresource requirements, andE;is the total amount of resources currently available, theU;for the mandateithe task utilization rate, thea. B, yis the weighting factor;
Implementation process: First, byD; — C;computing tasksiof time urgency, the smaller the time difference represents the more urgent the task, affects prioritization, introduces that theR;/E;parameter to measure the relationship between the task's resource requirements and available resources, calculating the ratio to understand the extent of the task's occupation of resources, for tasks with high resource requirements, the priority will be appropriately lowered to ensure the rational allocation of system resources, byU; Calculation of task utilization, which measures the occupancy and importance of the task in the system, with higher values representing more critical tasks, and weighting factorsa. By is obtained by optimizing the historical data of the system and the task completion rate. The step-by-step adjustment method is used to optimize. According to the implementation data of the historical task, the proportion of the three coefficients is adjusted to ensure the optimal calculation result.
Referring to Fig. 2, the node allocation module includes a computational capacity evaluation sub-module, a task complexity matching sub-module, and a load balancing allocation sub-module, wherein:
Computing capability evaluation sub module: based on the task allocation scheme, obtain the CPU and memory usage of each node, extract the real-time processing speed of the node, evaluate the node resource status by analyzing the node resource usage, record the resource parameters of each node into the form, and generate the node performance evaluation table;
Task complexity matching submodule: based on the node performance evaluation table, obtain the complexity information of each task, by comparing the task complexity and node processing capacity, select the node with sufficient resources for task allocation, assign the high complexity task to the high performance node, and generate the task complexity matching table;
Load balancing allocation submodule: based on the task complexity matching table, extract the remaining unallocated tasks, analyze the LU508576 low-complexity tasks and the node load state, select the nodes with lighter loads, and monitor the changes in node loads to generate the node task allocation table;
Computing capability evaluation sub module: based on the task allocation scheme, the resource monitoring algorithm is used to obtain the CPU and memory utilization of each node. Specifically, the system API interface is used to extract the CPU utilization and memory utilization of each node, set the extraction interval time parameter, extract the real-time processing speed of nodes, and perform node resource analysis by comparing the CPU utilization and memory utilization, Gradually evaluate the load condition of the node, and set the CPU utilization threshold to 80% based on threshold judgment. When the CPU or memory utilization of a node exceeds the threshold, record the overrun status, and record the resource status parameters of the node, including CPU utilization, memory utilization, and the number of current tasks, into a form to generate a node performance evaluation table;
Task complexity matching sub-module: based on the node performance evaluation table, the complexity analysis algorithm is used to obtain the complexity information of each task, specifically, the computational requirements of the task and the time requirements of the task complexity is quantitatively analyzed, the computational requirements of the task are extracted from the parameters of the task, including the number of floating-point operations and the memory requirements, the complexity indicators of the task are computed and the complexity indicators of the task are set through the comparison of the task complexity and the node's processing capacity. By comparing the task complexity and node processing capability, set the performance level of the node, select the node with sufficient resources for task allocation, use the scheduling strategy based on performance matching to compare the task complexity with the processing capability of the node when executing the task, gradually allocate the high complexity task to the high-performance node, record the allocation situation, and generate the task complexity matching table;
Load balancing allocation submodule: based on the task complexity matching table, the dynamic load balancing algorithm is used to extract the remaining unallocated tasks, specifically by traversing the list of low-complexity tasks, utilizing the current load state of the nodes, dynamically monitoring the load of each node, setting the monitoring interval for the load changes, and firstly, extracting the current load state of each node and the residual resources, and setting the load threshold for the tasks. The low-complexity tasks are assigned to the nodes with lighter loads, and the weighted polling mechanism is used to assign the unassigned tasks in real time, monitor the load changes of the nodes and adjust the tasks dynamically, and generate the node task assignment table.
Referring to Fig. 2, the parallel computing module includes a task parallel allocation sub-module, a resource usage analysis sub-module, and a task LU508576 conflict optimization sub-module, wherein:
Task parallel allocation submodule: based on the node task allocation table, extract high-priority tasks, allocate them to multiple computing nodes at the same time, detect the parallel execution status of nodes, ensure the parallel execution of high-priority tasks, and generate parallel task execution records;
Resource utilization analysis sub module: based on parallel task execution records, obtain the resource utilization rate of each node, analyze whether there is insufficient node resources by monitoring the real-time utilization of CPU and memory, extract and compare resource utilization and record data, and generate resource utilization analysis results;
Task conflict optimization submodule: based on the results of resource usage analysis, extract the nodes with task conflicts, analyze the reasons for the conflicts, determine whether it is necessary to re-adjust the order of task allocation, select the free resource nodes to optimize the execution process, and generate parallel processing task records;
Task parallel allocation sub module: based on the node task allocation table, use the multithreading parallel algorithm to extract high priority tasks.
First, divide the threads of each high priority task, set the number of threads as the upper limit of the number of nodes, process the tasks in parallel through the multithreading library, and start the tasks synchronously using the resources of each computing node, During execution, the task load is dynamically allocated according to the idle CPU and memory resources of each node, the task allocation weight is set, the parallel execution status of each node is detected, the task progress is synchronized by regularly checking the thread status, the intermediate status during the parallel task execution is gradually collected, the parallel status of each node is recorded, and the parallel task execution record is generated;
Resource utilization analysis sub module: based on the parallel task execution record, the resource monitoring algorithm is used to obtain the resource utilization rate of each node. First, the real-time CPU utilization rate and memory utilization of each node are extracted through the node resource monitoring interface, the monitoring interval is set to a fixed time unit, and the resource utilization rate in each time period is extracted, During execution, by comparing the trends of CPU utilization and memory utilization, we gradually analyze whether there is a shortage of resources, compare the resource utilization data in different time periods, record the node resource utilization in the data form, sort the resource utilization of nodes during the analysis process, mark the nodes whose resource utilization exceeds the preset threshold, and generate the resource utilization analysis results;
Task conflict optimization sub-module: based on the results of resource usage analysis, task conflict detection algorithm is used to extract nodes with task conflicts, firstly, analyze the relationship between task allocation and resource usage of each node, extract the reasons for conflicts, compare the LU508576 task execution time and resource usage of the conflicting nodes, determine whether the task allocation order needs to be readjusted, extract all the information of idle resource nodes during execution, select suitable nodes through the resource usage records of idle nodes, reassign the conflicting tasks to suitable nodes, re-adjust the tasks in parallel processing and record the execution process, and generate the task conflict optimization sub-module.
During the execution process, extract the information of all free resource nodes, select the suitable nodes through the resource utilization records of free nodes, reassign the conflicting tasks to the suitable nodes, re-adjust the tasks to be processed in parallel and record the execution process, and generate the records of parallel processing tasks.
Referring to FIG. 2, the resource dynamic adjustment module includes a resource monitoring submodule, a dynamic allocation submodule, and a load balancing submodule, wherein:
Resource monitoring sub module: based on the parallel processing task record, extract the CPU and memory utilization of each node, obtain the current resource consumption data of the node by monitoring the resource utilization of each node, analyze the change of resource consumption, record the resource consumption rate, and generate the node resource consumption status;
Dynamic allocation submodule: based on the node resource consumption state, extract the resource load of the node, analyze whether the processing thread of the task needs to be adjusted by comparing the resource occupancy rate with the consumption rate, reallocate the resources to the high load node or reduce the occupancy, and generate the result of the resource allocation adjustment;
Load balancing submodule: based on the resource allocation adjustment result, extract the information of high load nodes, analyze the resource occupation situation and task allocation status of nodes, and generate the dynamic resource adjustment result by transferring part of the tasks to the low load nodes and allocating the tasks to other nodes in a balanced way;
Resource monitoring sub module: based on parallel processing task records, the system resource monitoring algorithm is used to extract the CPU and memory occupancy of each node. First, the real-time CPU occupancy and memory occupancy of each node are obtained through the system resource monitoring API. Set the monitoring interval parameter as a fixed time unit to extract the current resource consumption data of the node, The specific steps are: according to the real-time monitoring information of the node, compare the
CPU utilization and memory utilization before and after the time period, analyze the change trend of resource consumption, use the moving average algorithm to smooth the resource consumption rate, record the processed resource consumption rate in the resource monitoring log, and gradually generate the node resource consumption status;
Dynamic allocation submodule: Based on the node resource consumption LU508576 state, the dynamic resource allocation algorithm is used to extract the resource load of the node, first classify the resource occupancy rate of each node, analyze the high load node and low load node using the comparison between the resource consumption rate and the resource occupancy rate, set the resource occupancy threshold, adjust the processing threads of the task by using the dynamic allocation rules, and first judge whether the resource consumption rate reaches the set threshold when the node exceeds the threshold, dynamically adjust the number of threads of the node or reduce the occupied resources, and record the load state of the adjusted node. rate reaches the set threshold, when the node exceeds the threshold reallocate resources to the high load node, dynamically adjust the number of threads in the node or reduce the occupied resources, record the adjusted node load status in the form, and generate the results of the resource allocation adjustment;
Load balancing submodule: based on the resource allocation adjustment results, the task migration load balancing algorithm is used to extract the information of high load nodes, firstly, analyze the resource occupancy and task allocation status of each node, extract the task load information, use the task transfer function of the load balancing algorithm to transfer part of the tasks on the high load nodes to the low load nodes based on the current resource occupancy of the nodes, set the load balancing parameters as the number of tasks and resource occupancy, dynamically adjust the distribution status of tasks on each node, use the polling mechanism to monitor the load change of the nodes, and generate the dynamic resource adjustment results.
Set the load balancing parameters as the number of tasks and resource occupancy rate, dynamically adjust the distribution of tasks on each node, use the polling mechanism to monitor the load changes of the nodes, and generate dynamic resource adjustment results.
Referring to FIG. 2, the fault detection and recovery module includes a task monitoring submodule, a fault detection submodule, and a task recovery submodule, wherein:
Task monitoring submodule: based on the dynamic resource adjustment results, extract the task execution status of nodes, monitor the task processing progress of each node, identify the nodes with processing exceptions by comparing the task progress with the resource occupancy, and record the task processing progress to generate a record of the task execution status of nodes;
Fault detection submodule: based on the node task execution state records, extract the state information of the node, analyze the task processing progress and node load, determine whether there is a fault, by checking the response time of the node and the task has not been completed state, extract the fault information, and generate fault detection results;
Task recovery submodule: based on the fault detection results, extract the faulty node information, transfer the task to the standby node, restore the latest LU508576 progress of the task by accessing the task snapshots of the node, reassign the uncompleted tasks to the available nodes, and generate the failover records and recovery scenarios;
Task monitoring sub module: based on the dynamic resource adjustment results, the process monitoring algorithm is used to extract the task execution status of the node. First, the system API call is used to obtain the task information currently being executed by each node. The monitoring interval parameter is set as a fixed cycle. During the execution process, the node that handles exceptions is identified by comparing the completed percentage of the task with the resource occupancy, The specific operation is to compare the progress update and resource consumption rate of tasks in each time cycle, extract the nodes whose progress update lags behind, record the task processing progress in the progress form, and gradually generate node task execution status records;
Fault detection submodule: based on the node task execution state records, using fault detection algorithms to extract the state information of the node, first analyze the task processing progress of each node and the node's load, use the preset response time threshold to determine the state of the node, extract the node's response time and the task is not completed state during the execution, and gradually determine the existence of faulty nodes by comparing the node's response time and task progress. Faulty nodes, using the state detection rules to mark the nodes whose response time exceeds the threshold, recording the detected fault information and generating fault detection results;
Task recovery submodule: based on the fault detection results, the task snapshot recovery algorithm is used to extract the fault node information, firstly, the uncompleted task is extracted from the task list of the fault node, and the latest progress of the task is recovered to the standby node through the task snapshot of the access node by the system call, and firstly, the recovery parameter is set based on the progress information in the task snapshot to ensure the consistent progress of the task from the fault node to the standby node. When executing the task, first set the recovery parameters according to the progress information in the task snapshot to ensure that the progress of the task from the faulty node to the standby node is consistent, reassign the uncompleted task to the standby node, set the resource parameter of task allocation as the comparison between the remaining resources of the node and the required resources of the task, adjust the allocation priority of the task through the comparison and gradually generate the failover record and the recovery program.
Referring to FIG. 2, the data transmission and optimization module includes a transmission state monitoring submodule, a priority analysis submodule, and a path optimization submodule, wherein:
Transmission status monitoring submodule: based on the failover recording and recovery scheme, extract the data transmission status of each task node, monitor the real-time data flow by obtaining the data transmission LU508576 rate and delay between each node, analyze the data bandwidth usage between nodes, and record the transmission delay and data loss rate, and generate the transmission status record;
Priority analysis submodule: based on the transmission status record, extract the priority of each task, judge the transmission order by comparing the importance parameter of the task with the data bandwidth occupancy of the current node, select the task with higher priority for bandwidth allocation, and adjust the transmission order of the low-priority task to generate the data transmission priority ranking;
Path optimization submodule: Based on the data transmission priority ranking, extract the bandwidth and latency information of the current transmission paths, adjust the data transmission paths by comparing the transmission loads of each path, optimize the task data transmission by selecting paths with high bandwidth utilization and low latency, and generate the transmission path scheme;
Transmission status monitoring sub module: based on the failover recording and recovery scheme, the network transmission monitoring algorithm is used to extract the data transmission status of each task node.
First, the real-time data transmission rate and delay between each node are obtained by calling the network interface API, and the monitoring interval time is set as a fixed cycle. During execution, the data packet transmission rate in the real-time data stream is analyzed, Extract the transmission delay information, record the arrival time and transmission time of each packet, calculate the data loss rate, analyze the number of data packets lost in the data transmission process using the packet loss detection mechanism, record the packet loss rate, transmission rate and delay to the transmission log, and generate the transmission status record;
Priority analysis submodule: Based on the transmission state records, the bandwidth allocation algorithm is used to extract the priority of each task, firstly, the priority parameter of each task is parsed, and the priority weight is set as the importance parameter of the task, then by comparing the data bandwidth occupancy of the current node with the priority parameter of the task, the order of data transmission is judged, and when executing, more bandwidth resources are allocated to the task of higher priority, and the bandwidth occupancy parameter of the task of higher priority is extracted. bandwidth occupancy parameter of the higher priority task, and readjust the bandwidth resources of the lower priority task, adjust the transmission order through the dynamic scheduling of the bandwidth occupancy, and gradually generate the data transmission priority ordering;
Path optimization submodule: Based on the data transmission priority ranking, the shortest path optimization algorithm is used to extract the bandwidth and delay information of the current transmission path, first of all, by traversing the currently available paths, extracting the bandwidth utilization and delay parameters of the paths, setting the path optimization weights as the LU508576 weighted ratio of the bandwidth utilization and delay values, and then comparing the transmission loads of the paths during the execution to select the paths with high bandwidth utilization and low delay, dynamically adjusting the data transmission paths, assigning the task data to the optimal paths, gradually recording the changes in the transmission paths, and generating the transmission path scheme. When executing, compare the transmission load of each path, select the path with high bandwidth utilization and low latency, allocate the task data to the optimal path by dynamically adjusting the data transmission path, gradually record the changes of the transmission path, and generate the transmission path scheme.
Above, is only a better embodiment of the present invention, is not a limitation of the present invention in other forms, any skilled person familiar with the profession may use the above disclosure of the technical content of the change or restyling for equivalent changes in the equivalent embodiment applied in other fields, but not out of the content of the technical program of the present invention, based on the technical substance of the present invention of the embodiment of the above simple modifications, equivalent changes and modifications, still belongs to the scope of protection of the technical program of the present invention. However, any simple modifications, equivalent changes and adaptations to the above embodiments based on the technical substance of the present invention without departing from the content of the technical program of the present invention still fall within the scope of protection of the technical program of the present invention.

Claims (10)

Claims
1. A real-time update management system for measurement control points based on a digital campus, characterized in that said system comprises: Task decomposition module: based on the real-time data flow of the measurement control points, extract the geographic coordinates of the control points and the measurement data, analyze the data attributes of the control points, divide the region, time and signal type, and assign them according to the node load, and correlate the related measurement data to generate the control task list; Task scheduling module: based on the list of control tasks, using the earliest deadline priority scheduling algorithm, by extracting the task priority and control region, analyzing the task complexity and node status, combining the regional parameters and time conditions to match the judgment, the high-priority task is assigned to the corresponding node, and based on the urgency of the task to adjust to generate the task allocation plan; Node allocation module: based on the task allocation scheme, by obtaining the computing power, load status and processing speed of each node, matching the task complexity with the node performance parameters, assigning tasks with high complexity to high-performance nodes, and balancing the rest of the tasks to the lighter-loaded nodes, generating a node task allocation table; Parallel computing module: based on the node task allocation table, select the task with high priority to be executed in parallel on multiple nodes, analyze the resource usage of the nodes to determine whether the task needs to be reallocated to prevent task conflicts, and optimize the distribution of tasks among nodes to generate parallel processing task records; Resource dynamic adjustment module: based on the parallel processing task record, by monitoring the consumption of CPU, memory and other resources of each node, analyze the progress of task processing, judge whether it is necessary to dynamically adjust resource allocation, reduce the resource pressure of high load nodes, adjust thread allocation, optimize resource use, and generate dynamic resource adjustment results; Failure detection and recovery module: based on the results of the dynamic resource adjustment, monitor the task execution status of each node, analyze the task progress and node status, determine whether a failure or resource abnormality occurs, such as detecting the problem, switch the task to the backup node, restore the task progress and keep the node stable, and generate fault switching records and recovery programs; Data Transmission and Optimization Module: Based on the mentioned failover recording and recovery scheme, it monitors the data transmission status between task nodes, analyzes the priority of the task and the transmission path bandwidth, determines the transmission priority order of the data flow, adjusts the data transmission path, reduces the transmission delay,
and generates the transmission path scheme. LU508576
2. areal-time update management system for measurement control points based on a digital campus according to claim 1, characterized in that said control task list includes a task type, an execution region, and a data collection time point, said task allocation scheme includes a node allocation of priority tasks, an execution time window, and a node load allocation, said node task allocation table includes a node resource utilization rate, a task processing time, a task priority allocation, said parallel processing task record includes task execution order, node parallel load, computational resource occupancy, said dynamic resource adjustment result includes adjusted memory allocation, number of processing threads, node resource optimization parameters, said failover record and recovery scheme includes list of faulty nodes, standby node task allocation, task recovery progress status, said transmission path scheme includes bandwidth optimization The said transmission path scheme includes bandwidth optimization, data prioritization order, and path delay parameter adjustment.
3. A real-time update management system for measuring control points based on a digital campus according to claim 1, characterized in that said task decomposition module comprises a coordinate extraction sub-module, a data division sub-module, and a task assignment sub-module, wherein: Coordinate extraction submodule: based on the real-time data flow of the measurement control point, extract the geographic coordinate data of the said measurement point, carry out the preliminary organization of the said coordinate data by identifying the position information of each measurement point, and arrange and calibrate the position information according to the coordinate system to generate the geographic coordinate set of the control point; Data division submodule: based on the set of geographic coordinates of the said control points, analyze the data attributes of each measurement point, combine the said position information with the measurement attributes such as time parameter, signal type and other measurement attributes, carry out the regional division, and generate the regional time signal classification set by matching the region of the said control points with the data type and organizing the classification information; Task allocation submodule: based on the regional time signal classification set, according to the load state of each node in the system and the task allocation rules, extract the control point information and node state, assign the task to the most suitable node in turn, and generate the control task list.
4. a real-time update management system for measurement control points based on a digital campus according to claim 1, characterized in that said task scheduling module comprises a priority analysis submodule, a time condition judgment submodule, and a node allocation submodule, wherein: Priority analysis submodule: based on the list of said control tasks,
adopting the earliest deadline priority scheduling algorithm, extracting the LU508576 priority parameters of said tasks, identifying the importance and urgency of said tasks, and, by comparing the said control area and task requirements, carrying out the priority ranking, and gradually establishing the execution sequence of said tasks, generating the results of prioritized task ranking; Time condition judgment submodule: based on the said prioritized task sorting results, extract the execution time window of the said task, analyze the time constraints of the said task, compare the execution time of the said task with the current system time and complete the time matching judgment by selecting the most suitable time node to generate the time matching judgment results: Node allocation submodule: based on the results of the time matching judgment, extract the load state information of the node, analyze the current processing capacity of the node, and assign the high priority task to the node with lower load, and generate the task allocation scheme.
5. Areal-time update management system for measurement control points based on a digital campus according to claim 1, characterized in that said earliest deadline priority scheduling algorithm, according to the formula: P = a(D, —C op J+ i i Xi — yu, E, Of which:P,for the mandateiThe combined priority value of theD;for the mandateithe deadline, theC;for the mandateiof the projected completion date of the project, andR;for the mandateiresource requirements, andE;is the total amount of resources currently available, theU;for the mandateithe task utilization rate, thea. B, yis the weighting factor.
6. A real-time update management system for measurement control points based on a digital campus according to claim 1, characterized in that said node allocation module comprises a computational capacity assessment submodule, a task complexity matching submodule, and a load balancing allocation submodule, wherein: Computing capability evaluation sub module: based on the task allocation scheme, obtain the CPU and memory usage of each node, extract the real-time processing speed of the node, evaluate the node resource status by analyzing the node resource usage, record the resource parameters of each node to the table, and generate the node performance evaluation table; Task complexity matching submodule: based on the node performance evaluation table, obtain the complexity information of each task, by comparing the task complexity and node processing capacity, select the node with sufficient resources for task allocation, assign the high complexity task to the high-performance node, and generate the task complexity matching table; Load balancing allocation submodule: based on the task complexity matching table, extract the remaining unallocated tasks, analyze the low-complexity tasks and the node load state, select the nodes with lighter LU508576 loads, and monitor the node load changes to generate the node task allocation table.
7. A real-time update management system for measurement control points based on a digital campus according to claim 1, characterized in that said parallel computing module comprises a task parallel allocation sub-module, a resource usage analysis sub-module, and a task conflict optimization sub-module, wherein; Task parallel allocation submodule: based on the node task allocation table, extract high-priority tasks, simultaneously allocated to multiple computing nodes, detect the node parallel execution state, ensure the parallel execution of high-priority tasks, generate parallel task execution records; Resource utilization analysis sub module: based on the parallel task execution record, obtain the resource utilization rate of each node, analyze whether there is insufficient node resources by monitoring the real-time utilization of CPU and memory, extract and compare the resource utilization, record data, and generate the resource utilization analysis results; Task conflict optimization submodule: based on the results of the resource usage analysis, extract the nodes with task conflicts, analyze the reasons for the conflicts, determine whether it is necessary to re-adjust the order of task allocation, select the idle resource nodes to optimize the execution process, and generate parallel processing task records.
8. A real-time update management system for measurement control points based on a digital campus according to claim 1, characterized in that said resource dynamic adjustment module comprises a resource monitoring submodule, a dynamic allocation submodule, and a load balancing submodule, wherein: Resource monitoring sub module: extract the CPU and memory utilization of each node based on the parallel processing task record, obtain the current resource consumption data of the node by monitoring the resource utilization of each node, analyze the change of resource consumption, record the resource consumption rate, and generate the resource consumption status of the node; Dynamic allocation submodule: based on the state of resource consumption of said node, extract the resource load of said node, analyze whether the processing thread of said task needs to be adjusted by comparing the occupancy rate of said resource with the rate of consumption, reallocate the resources to said high-load node or reduce the occupancy, and generate the result of the adjustment of the allocation of said resource; Load balancing submodule: based on the said resource allocation adjustment result, extract the said high load node information, analyze the resource occupancy and task allocation status of the said node, and generate the said dynamic resource adjustment result by transferring part of the task to the low load node and assigning the said task to other nodes in a balanced manner. LU508576
9. À real-time update management system for measurement control points based on a digital campus according to claim 1, characterized in that said fault detection and recovery module comprises a task monitoring submodule, a fault detection submodule, and a task recovery submodule, wherein: Task monitoring submodule: based on the results of said dynamic resource adjustment, extract the task execution status of said nodes, monitor the task processing progress of each node, identify the nodes with processing abnormalities by comparing the progress of said tasks with the resource utilization, and record the processing progress of said tasks to generate a record of the task execution status of said nodes; Fault detection submodule: based on the node task execution state record, extract the state information of said node, analyze the processing progress of said task and node load, determine whether there is a fault, by checking the response time of said node and the task is not completed state, extract the fault information, generate the fault detection results; Task recovery submodule: based on said fault detection results, extract said faulty node information, transfer the task to the standby node, restore the latest progress of said task by accessing the task snapshot of said node, and reassign the uncompleted task to the available node, and generate said failover record and recovery program.
10. A real-time update management system for measurement control points based on a digital campus according to claim 1, characterized in that said data transmission and optimization module comprises a transmission state monitoring submodule, a priority analysis submodule, and a path optimization submodule, wherein: Transmission status monitoring submodule: based on the mentioned failover recording and recovery scheme, extract the data transmission status of each task node, monitor the real-time data flow by obtaining the data transmission rate and delay between each node, analyze the data bandwidth usage between the nodes, and record the transmission delay and data loss rate, and generate the transmission status record; Priority analysis submodule: based on the said transmission status record, extract the priority of each task, determine the transmission order by comparing the importance parameter of the task with the data bandwidth occupancy of the current node, select the task with higher priority for bandwidth allocation, and adjust the transmission order of the low-priority task to generate the data transmission priority ordering; Path optimization submodule: based on the data transmission priority ranking, extract the bandwidth and latency information of the current transmission path, adjust the data transmission path by comparing the transmission load of each path, optimize the task data transmission by selecting the path with high bandwidth utilization and low latency, and generate the transmission path scheme.
LU508576A 2024-10-16 2024-10-16 A real-time update management system for measuring control points based on digital campus LU508576B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
LU508576A LU508576B1 (en) 2024-10-16 2024-10-16 A real-time update management system for measuring control points based on digital campus

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
LU508576A LU508576B1 (en) 2024-10-16 2024-10-16 A real-time update management system for measuring control points based on digital campus

Publications (1)

Publication Number Publication Date
LU508576B1 true LU508576B1 (en) 2025-04-23

Family

ID=95451673

Family Applications (1)

Application Number Title Priority Date Filing Date
LU508576A LU508576B1 (en) 2024-10-16 2024-10-16 A real-time update management system for measuring control points based on digital campus

Country Status (1)

Country Link
LU (1) LU508576B1 (en)

Similar Documents

Publication Publication Date Title
CN119356879B (en) Distributed real-time data stream processing system and method
CN120123099B (en) Resource scheduling method, system, equipment and medium in edge cloud computing platform
CN119645950B (en) A distributed file processing method and system
CN121056463A (en) A fully intelligent analog load distributed cooperative control method
CN119828649A (en) Sequential control testing system based on Internet of things
CN119862037A (en) Dynamic scheduling system and method for container calculation
CN112256418A (en) Big data task scheduling method
CN118939427B (en) A resource allocation management method and computer equipment for cloud servers
CN120804765A (en) Real-time data analysis system based on big data
CN120540850A (en) A heterogeneous computing resource allocation system and method for collaborative scheduling
CN119835280B (en) Data synchronization method and system of communication software
Gao Simulation design of load balancing optimization for cloud computing data stream storage based on big data algorithms
LU508576B1 (en) A real-time update management system for measuring control points based on digital campus
CN111857990B (en) A method and system for strengthening YARN long-type service scheduling
CN120336000A (en) A computing resource scheduling method and system in a cloud environment
CN118839886A (en) Scheduling management method and system based on big data intelligent platform
CN118138590A (en) Data center load balancing method
CN119651913B (en) An intelligent substation sequential control method and system
CN120743547B (en) Multitasking method and system in computing network fusion environment
CN120602398B (en) Communication unit data transmission optimization method and system for large-scale electric energy data
CN121008924B (en) A task control method based on real-time communication
CN120540804B (en) A method and platform for scheduling multi-heterogeneous computing power in public AI computing centers
CN119996634B (en) A cloud-based camera remote access system
CN120743535A (en) Cluster computing resource real-time scheduling system and method
CN121387566A (en) Efficient operation and maintenance software architecture setting method for multi-task parallel scheduling

Legal Events

Date Code Title Description
FG Patent granted

Effective date: 20250423