A multifunctional phased array task scheduling method based on tolerance aperture segmentation

Through the multi-functional phased array task scheduling method of tolerance aperture segmentation, combined with task observation list and comprehensive priority sorting, the problem of low resource utilization in the existing technology is solved, more efficient resource allocation and task execution is achieved, and the The overall resource utilization efficiency of the system.

CN118885283BActive Publication Date: 2024-12-03SOUTHWEST CHINA RES INST OF ELECTRONICS EQUIP
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202411389818.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-10-08
Publication Date
2024-12-03
Estimated Expiration
2044-10-08

AI Technical Summary

Technical Problem

The existing multi-function phased array task scheduling method based on aperture segmentation has low resource utilization, which is difficult to meet the needs of flexible allocation of resources. The multi-slot scheduling plan only considers a certain aspect of factors and fails to comprehensively consider improving resource utilization.

Method used

A multi-functional phased array task scheduling method is proposed to set up a tolerance parameter list, forming a task observation list, reasonably allocating scheduling resources, comprehensive priority sorting and resource release, and ensuring efficient utilization of resources.

Benefits of technology

It effectively improves resource utilization, reduces resource waste, ensures that tasks in the scheduling time slots can be successfully executed according to priority, and improves the overall resource utilization efficiency of the system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118885283B_ABST
    Figure CN118885283B_ABST
Patent Text Reader

Abstract

The present invention discloses a tolerance aperture segmentation multifunctional phased array task scheduling method, which includes: setting a tolerance parameter list and forming a task observation chain list according to the tolerance parameter list; taking the tasks of the current scheduling interval to form a task application chain list; obtaining all the tasks executable at the current moment in the scheduling process, if the percentage of aperture resources required for each task is less than a preset value, then allocating aperture resources, making the current moment in the scheduling process equal to the actual execution moment of the task, finding the earliest task to be completed after the current moment in the scheduling process, releasing the aperture resources occupied by it, and updating the current moment in the scheduling process to the completion moment of the task, if the task application chain list is empty and the task observation chain list is fully traversed, then taking the minimum value of the aperture resources occupied by the task, and taking the task observation chain list corresponding to the task as the final scheduling chain list, and ending the scheduling of the scheduling interval. The present invention improves the utilization rate of system resources.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of task scheduling, and in particular to a tolerance aperture segmentation multifunctional phased array task scheduling method. Background Art

[0002] The existing aperture-segmentation-based multifunctional phased array task scheduling method has limited resource utilization. The task priority is generally a fixed sequence, which is difficult to meet the needs of flexible resource allocation, resulting in a large section of resources being wasted in a scheduling time slot, resulting in low resource utilization; some schemes only consider using the actual task execution time instead of the expected task execution time to improve resource utilization, while some schemes consider the performance improvement of multi-slot scheduling schemes compared to single-slot scheduling schemes, but these schemes only consider one aspect of the factor, and do not take multiple factors into consideration to improve resource utilization. Summary of the invention

[0003] In order to solve the problem that the existing multifunctional phased array scheduling method based on traditional multi-task parallel (MTPEDF) is difficult to fully utilize aperture resources, the present invention proposes an improved tolerance aperture partitioning multifunctional phased array task scheduling method, which can be used for resource scheduling of multifunctional phased array, and can more reasonably allocate scheduling resources within one or more scheduling time slots to improve resource utilization.

[0004] The present invention discloses a tolerance aperture segmentation multifunctional phased array task scheduling method, which comprises:

[0005] Set the tolerance parameter list and form D task observation lists based on it. Each task observation list corresponds to a tolerance parameter. Take the tasks of this scheduling interval to form a task application list. ; Get all the tasks that can be executed at the current time in the scheduling process. If the percentage of aperture resources required by each task is less than the preset value, allocate aperture resources, make the current time in the scheduling process equal to the actual execution time of the task, find the earliest task to be completed after the current time in the scheduling process, release the aperture resources it occupies, and update the current time in the scheduling process to the completion time of the task. If the task application list If it is empty and all D task observation linked lists have been traversed, the minimum value of the aperture resources occupied by the task is taken, and the task observation linked list corresponding to the task is used as the final scheduling linked list to end the scheduling of this scheduling interval.

[0006] Furthermore, the acquisition of all tasks that can be executed at the current moment in the scheduling process includes:

[0007] Link the task application list The tasks whose latest executable time is less than the current time in this scheduling process are sent to the deletion list, and the task application list is taken out The earliest executable time is less than or equal to the current time in the scheduling process There are M tasks in total.

[0008] Furthermore, each task is represented as , represents the i-th task, and are the expected execution time and actual execution time of each task, For each task, a comprehensive priority is given. The percentage of aperture resources that each task needs to occupy; , is an adjustable parameter. All tasks are arranged from low to high according to the work mode priority and task deadline, and the sequence number of each task in the two arrangements is recorded as and .

[0009] Furthermore, the step of setting the current time in the scheduling process equal to the actual execution time of the task, finding the earliest completed task after the current time in the scheduling process, releasing the aperture resources occupied by the task, and updating the current time in the scheduling process as the completion time of the task includes:

[0010] calculate The comprehensive priority of tasks based on tolerance is set at each step. The tasks are sorted according to the comprehensive priority, and the observation list of each task is ,make ;

[0011] Take out the observation list Tasks in ;like ≤ , it is sent to the execution list, and its actual execution time , ; Otherwise, return it to the task application list middle; The remaining aperture resource of the radar at the current moment;

[0012] Until the observation list is traversed , find the task in the execution list with the earliest actual completion time that is greater than the current time, and set its completion time to , the aperture resource occupancy rate is ,at this time ,make , release the aperture resources occupied by the task, .

[0013] Furthermore, it also includes: when the task application list If it is not empty and the current time is greater than the end time of the scheduling process, the task application list will be The remaining unscheduled tasks have a deadline greater than or equal to The tasks whose deadline is less than the end time of scheduling are sent to the deletion list.

[0014] Furthermore, after the task whose deadline is less than the scheduling end time is sent to the deletion linked list, the process further includes:

[0015] Determine whether all D task observation linked lists have been traversed. If not, re-execute the step of obtaining all tasks that can be executed at the current moment in the scheduling process.

[0016] Furthermore, if the percentage of aperture resources that each task needs to occupy is greater than or equal to a preset value, it is returned to the task application linked list.

[0017] Furthermore, after the scheduling of the current scheduling interval is ended, the method further includes:

[0018] Take the next scheduling cycle task in turn; determine whether the radar's remaining aperture resources and remaining time resources meet the scheduling. If so, the task is executed in this scheduling time slot and this scheduling interval ends. Otherwise, determine whether all tasks of the next cycle have been traversed. If all tasks of the next cycle have been traversed, this scheduling interval ends. Otherwise, take the next scheduling cycle task in turn until this scheduling interval ends.

[0019] Due to the adoption of the above technical solution, the present invention has the following advantages:

[0020] 1. The introduction of tolerance factors can leave a certain degree of ambiguity for task priorities. By reasonably scheduling resources within a scheduling time slot, the waste of resources such as time and aperture can be effectively reduced, thereby improving the resource utilization of the entire system.

[0021] 2. By introducing the tolerance factor and jointly scheduling time slots, the utilization of time and aperture resources can be further improved, so that tasks that are discarded in certain time slots can be executed, thereby further improving the utilization of system resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the embodiments of the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0023] Figure 1 It is a schematic diagram of a single time slot task scheduling method; Figure 1 (a) is a schematic diagram of task definition of a single-time-slot task scheduling method, (b) is a schematic diagram of a traditional single-time-slot tolerance task scheduling method, and (c) is a schematic diagram of an improved single-time-slot tolerance task scheduling method;

[0024] Figure 2 The flowchart of the improved single time slot tolerance task scheduling method is as follows;

[0025] Figure 3 It is a schematic diagram of a multi-slot task scheduling method; Figure 3 (a) is a schematic diagram of task definition of a multi-slot task scheduling method, (b) is a schematic diagram of a traditional multi-slot tolerance task scheduling method, and (c) is a schematic diagram of an improved multi-slot tolerance task scheduling method;

[0026] Figure 4 A flowchart of an improved multi-slot tolerance task scheduling method;

[0027] Figure 5 It is a schematic diagram of the performance simulation curve of the improved single time slot tolerance task scheduling method;

[0028] Figure 6 Schematic diagram of the performance simulation curve of the improved multi-slot tolerance task scheduling method. DETAILED DESCRIPTION

[0029] The present invention is further described in conjunction with the accompanying drawings and embodiments, and the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field should fall within the scope of protection of the embodiments of the present invention.

[0030] Embodiment 1:

[0031] The single-slot task scheduling process is as follows: Figure 2 As shown, the task model is described by the following model , where represents the i-th task, and are the expected execution time and actual execution time of each task, For each task, a comprehensive priority is given. The percentage of aperture resources that each task needs to occupy. ,in is an adjustable parameter (and sets the tolerance parameter ), all tasks in the task set are arranged from low to high priority and from large to small deadline according to the working mode priority and the order of each task in the two arrangements is recorded. and .

[0032] In a scheduling time slot ( ) contains N tasks, forming a task application list The scheduling start time is , the end time is , is the current time in the scheduling process, It is the remaining aperture resource of the radar at the current moment.

[0033] ① Initialization ,at this time .

[0034] ②Set tolerance parameter list ,according to Form D task observation lists, each task observation list corresponds to a tolerance parameter, take the first task observation list .

[0035] ③ Take out the task application list The latest executable time is less than The task is sent to the deletion list.

[0036] ④ Take out the task application list The earliest executable time is less than or equal to The task is to , calculate this The comprehensive priority of each task is based on tolerance, and these tasks are sorted from high to low according to the comprehensive priority at each step. The sorting of each task observation list is ,make .

[0037] ⑤ Take out the task observation list Tasks in .like ≤ , it is sent to the execution list, and its actual execution time , ; Otherwise, return it to the task application list middle.

[0038] ⑥ ,like Then go to ⑤; otherwise go to ⑦.

[0039] ⑦ Find the task in the execution list with the earliest actual completion time that is greater than the current time, and set its completion time to , the aperture resource occupancy rate is ,at this time , Lingling Release the aperture resources it occupies, .

[0040] ⑧ Check the task application list Is it empty? If so, go to step ⑩; if not, go to step ⑨.

[0041] ⑨If , then the task application list The remaining unscheduled tasks have a deadline greater than or equal to The task is sent to the delay list and participates in the task scheduling of the next scheduling time slot. The deadline is small. The task is sent to the deletion list and go to ⑩; otherwise go to ③.

[0042] ⑩ , Then turn to ②; otherwise turn to ;

[0043] Pick minimum value, and As the final dispatch list

[0044] The scheduled time slot ends.

[0045] Embodiment 2:

[0046] The multi-slot task scheduling process is as follows Figure 4 As shown, the task model is described by the following model , where represents the i-th task, and are the expected execution time and actual execution time of each task, For each task, a comprehensive priority is given. The percentage of aperture resources that each task needs to occupy. ,in is an adjustable parameter (and sets the tolerance parameter , Available in Floating), all tasks in the task set are arranged from low to high priority and from large to small deadline according to the working mode priority and the order of each task in the two arrangements is recorded. and .

[0047] In a scheduling time slot ( ) contains N tasks, forming a task application list The scheduling start time is , the end time is , is the current time in the scheduling process, It is the remaining aperture resource of the radar at the current moment.

[0048] ① Initialization ,at this time .

[0049] ②Set tolerance parameter list ,according to Form D task observation lists, each task observation list corresponds to a tolerance parameter, take the first task observation list .

[0050] ③ Take out the task application list The latest executable time is less than The task is sent to the deletion list.

[0051] ④ Take out the task application list The earliest executable time is less than or equal to The task is to , calculate this The comprehensive priority of each task is based on tolerance, and these tasks are sorted from high to low according to the comprehensive priority at each step. The sorting of each task observation list is ,make .

[0052] ⑤ Take out the task observation list Tasks in .like ≤ , it is sent to the execution list, and its actual execution time , ; Otherwise, return it to the task application list middle.

[0053] ⑥ ,like Then go to ⑤; otherwise go to ⑦.

[0054] ⑦ Find the task in the execution list with the earliest actual completion time that is greater than the current time, and set its completion time to , the aperture resource occupancy rate is ,at this time ,make Release the aperture resources it occupies, .

[0055] ⑧ Check the task application list Is it empty? If so, go to step ⑩; if not, go to step ⑨.

[0056] ⑨If , then the task application list The remaining unscheduled tasks have a deadline greater than or equal to The task is sent to the delay list and participates in the task scheduling of the next scheduling time slot. The deadline is small. The task is sent to the deletion list and go to ⑩; otherwise go to ③.

[0057] ⑩ , Then turn to ②; otherwise turn to ;

[0058] Pick minimum value, and As the final scheduling list;

[0059] Take the next scheduling period task in turn;

[0060] judge , whether the remaining time resources meet the scheduling, if so, transfer If not, then turn ;

[0061] The task is executed in this scheduling time slot. ;

[0062] Determine whether all tasks in the next cycle have been traversed. If so, turn to If not, then turn ;

[0063] This scheduling interval ends.

[0064] For ease of understanding, the present invention provides a more specific embodiment:

[0065] like Figure 1 As shown in (a), there are 5 scheduling tasks in a scheduling time slot, namely task 1, task 2, task 3, task 4, and task 5. There are 5 scheduling tasks, namely task 1, task 2, task 3, task 4, and task 5. The working priority of task 1 to task 5 is sorted from low to high as {task 4, task 5, task 3, task 2, task 1}. ,like Figure 1 As shown in (b), the deadline priority is sorted from low to high. , ,according to and Conduct comprehensive prioritization, , , , , , that is, the comprehensive scheduling priority is from high to low , Task 5 is deleted because it exceeds the scheduling time slot. Introducing task tolerance factor ,make ,Right now ,when When, according to and Conduct comprehensive prioritization, , , , , , that is, the comprehensive scheduling priority is from high to low ,like Figure 1 As shown in (c), task 5 can be executed in this scheduling time slot, thereby improving system resource utilization and task execution success rate.

[0066] like Figure 3 As shown in (a), there are two scheduling time slots (scheduling time slot 1 and scheduling time slot 2), and 12 tasks are scheduled, among which tasks 1 to 5 are expected to be scheduled in scheduling time slot 1, and tasks 6 to 12 are expected to be scheduled in scheduling time slot 2. In scheduling time slot 1, there are 5 scheduling tasks in one scheduling time slot, namely task 1, task 2, task 3, task 4, and task 5. There are 5 scheduling tasks in total, namely task 1, task 2, task 3, task 4, and task 5. The working mode priority of tasks 1 to 5 is sorted from low to high as {task 4, task 5, task 3, task 2, task 1}. ,like Figure 3 As shown in (b), the deadline priority is sorted from low to high. , ,according to and Conduct comprehensive prioritization, , , , , , that is, the comprehensive scheduling priority is from high to low , Task 12 in scheduling time slot 2 is deleted due to no idle resources. Introducing task tolerance factor ,make ,Right now ,when When, according to and Conduct comprehensive prioritization, , , , , , that is, the comprehensive scheduling priority is from high to low , , , , ,like Figure 3 As shown in (c), task 6 of scheduling time slot 2 can be executed in scheduling time slot 1, and task 12 of scheduling time slot 2 can also be executed in scheduling time slot 2, thereby improving system resource utilization and task execution success rate.

[0067] Figure 5 It is a schematic diagram of the performance simulation curve of the improved single time slot tolerance task scheduling method; Figure 6 Schematic diagram of the performance simulation curve of the improved multi-slot tolerance task scheduling method.

[0068] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A tolerance aperture segmentation multifunctional phased array task scheduling method, characterized in that: include: Set the tolerance parameter list and form D task observation lists based on it. Each task observation list corresponds to a tolerance parameter. Take the tasks of this scheduling interval to form a task application list. ; Get all the tasks that can be executed at the current time in the scheduling process. If the percentage of aperture resources required by each task is less than the preset value, allocate aperture resources, make the current time in the scheduling process equal to the actual execution time of the task, find the earliest task to be completed after the current time in the scheduling process, release the aperture resources it occupies, and update the current time in the scheduling process to the completion time of the task. If the task application list If it is empty and all D task observation linked lists have been traversed, the minimum value of the aperture resources occupied by the task is taken, and the task observation linked list corresponding to the task is used as the final scheduling linked list to end the scheduling interval scheduling; The acquisition of all tasks that can be executed at the current moment in the scheduling process includes: Link the task application list The tasks whose latest executable time is less than the current time in this scheduling process are sent to the deletion list, and the task application list is taken out The earliest executable time is less than or equal to the current time in the scheduling process There are M tasks in total.

2. The method according to claim 1, characterized in that Each task is represented as , represents the i-th task, and are the expected execution time and actual execution time of each task, For each task, a comprehensive priority is given. The percentage of aperture resources that each task needs to occupy; , is an adjustable parameter. All tasks are arranged according to the work mode priority from low to high and the task deadline, and the sequence number of each task in the two arrangements is recorded as and .

3. The method according to claim 2, characterized in that The step of setting the current time in the scheduling process equal to the actual execution time of the task, finding the earliest completed task after the current time in the scheduling process, releasing the aperture resources occupied by the task, and updating the current time in the scheduling process as the completion time of the task includes: calculate The comprehensive priority of tasks based on tolerance is set at each step. The tasks are sorted according to the comprehensive priority, and the observation list of each task is ,make ; Take out the observation list Tasks in ;like ≤ , it is sent to the execution list, and its actual execution time , ; Otherwise, return it to the task application list middle; The remaining aperture resource of the radar at the current moment; Until the observation list is traversed , find the task in the execution list with the earliest actual completion time that is greater than the current time, and set its completion time to , the aperture resource occupancy rate is ,at this time ,make , release the aperture resources occupied by the task, .

4. The method according to claim 2, characterized in that: Also includes: When the task application list If it is not empty and the current time is greater than the end time of the scheduling process, the task application list will be The remaining unscheduled tasks have a deadline greater than or equal to the scheduled end time. The tasks whose deadline is less than the end time of the scheduling are sent to the deletion list.

5. The method according to claim 4, characterized in that After the task whose deadline is less than the scheduling end time is sent to the deletion linked list, the method further includes: Determine whether all D task observation linked lists have been traversed. If not, re-execute the step of obtaining all tasks that can be executed at the current moment in the scheduling process.

6. The method according to claim 1, characterized in that If the percentage of aperture resources required by each task is greater than or equal to the preset value, it will be returned to the task application list.

7. The method according to claim 1, characterized in that After the scheduling of the current scheduling interval is ended, the method further includes: Take the next scheduling cycle task in turn; determine whether the radar's remaining aperture resources and remaining time resources meet the scheduling. If so, the task is executed in this scheduling time slot and this scheduling interval ends. Otherwise, determine whether all tasks of the next cycle have been traversed. If all tasks of the next cycle have been traversed, this scheduling interval ends. Otherwise, take the next scheduling cycle task in turn until this scheduling interval ends.

Citation Information

Patent Citations

  • Container placement method and system in power edge cloud computing network

    CN115022188A

  • Vehicle side cloud cooperative task unloading method in edge computing resource limited environment

    CN117061553A

  • Task execution control device and method therefor

    JP2003131892A