A heuristic algorithm-based unmanned aerial vehicle hangar scheduling method

Abstract

The application discloses a kind of based on heuristic algorithm's unmanned plane hangar scheduling method, it is related to unmanned plane technical field, including steps: data acquisition;Filtering schedulable hangar, and based on this to construct alternative task set;Delete the task data with route data;To alternative task set initialization grouping;In the same group data, the sum of distance dist of each task data and other task data is calculated, and the average value Dist of dist;For an alternative task set, respectively select a task data of two groups of data;The sum of Dist of selected two groups of data before and after task data exchange, i.e. Dist1 and Dist2;Only when Dist1>Dist2, exchange is executed;When reaching preset target, switch the scheduling of alternative task set;Repeat the above steps, complete the task allocation of all schedulable hangar. Finally unmanned plane scheduling efficiency, task execution efficiency can be effectively improved, cost consumption is reduced.

Description

Technical Field

[0001] This invention relates to the field of unmanned aerial vehicle (UAV) technology, and in particular to a UAV hangar scheduling method based on heuristic algorithms. Background Technology

[0002] With my country's vigorous development of the low-altitude economy, unmanned aerial vehicle (UAV) technology, with its core advantages of low cost, high efficiency, and strong adaptability, has been widely applied across various industries. UAVs' capabilities, including real-time data acquisition, remote control, and autonomous navigation, enable them to complete complex tasks in diverse environments. As the number of UAV missions increases, many high-tech companies providing UAV services have built hangars at key urban nodes, allowing UAVs to automatically execute missions according to pre-deployed plans. However, how to efficiently and intelligently allocate and plan missions for each hangar's UAVs has become a key issue in improving UAV mission execution efficiency and reducing execution costs. Intelligent scheduling methods offer an effective solution to this problem, while also enabling companies to reduce costs and increase efficiency, and reducing the workload of scheduling personnel.

[0003] In existing technologies, the scheduling problem for drone missions in hangars mainly involves allocating tasks to drones from multiple hangars according to time periods, while simultaneously satisfying various constraints and optimizing specific objectives. Its main challenges include:

[0004] (1) Task cost: The cost of drone missions is proportional to the total flight distance. The tasks in each time slot of the schedule need to be close in distance, which requires high professional skills from the relevant personnel.

[0005] (2) High dynamism: UAV missions are usually in a dynamic environment, and mission requirements and UAV status may change in real time. The scheduling plan needs to be able to adjust quickly.

[0006] (3) Timeliness: When there are a large number of drone missions, traditional methods based on human experience can no longer provide a quick response, and the program needs to quickly provide a strategy. Summary of the Invention

[0007] To address the problems existing in the prior art, this invention provides a drone hangar scheduling method based on heuristic algorithms. By fully considering cost and multiple constraints, and through comprehensive analysis of airspace, drone missions, hangar information, and mission information, combined with heuristic algorithms, this method can automatically and intelligently schedule all hangars, effectively improving drone scheduling efficiency, increasing drone mission execution efficiency, and reducing the cost of drone mission execution.

[0008] The technical solution of this invention is implemented as follows:

[0009] A heuristic algorithm-based method for drone hangar scheduling includes the following steps:

[0010] T1. Collect data, including airspace data, hangar data, and mission data; the airspace data includes the legal airspace range; the hangar data includes hangar coordinates and the mission's executable radius; the mission data includes mission coordinates; wherein, some or all of the mission data includes flight path data.

[0011] T2. Select hangars whose hangar coordinates are located within the airspace range as available hangars; the area within the task execution radius centered on the hangar coordinates of any available hangar is the coverage area; several task data whose task coordinates are located within the coverage area constitute a candidate task set; one available hangar corresponds to one candidate task set.

[0012] T3. For a set of candidate tasks, delete the task data that contains the route data; tasks that already have route data are considered to have been scheduled; the remaining task data does not include route data.

[0013] T4. Initialize grouping for a set of candidate tasks, dividing the task data into several groups; for the same group of data, calculate the distance between any task data and other task data, and denot the sum of the distances as dist; denot the average value of dist for the same group of data as Dist.

[0014] T5. For a set of candidate tasks, select two sets of data based on Dist; for the two selected sets of data, select one set of task data from each set of data based on Dist.

[0015] Calculate the sum of the Dist values ​​of the two selected sets of data, denoted as Dist1; for the two selected sets of data, swap their positions according to the two task data, and calculate the sum of the Dist values ​​of the two sets of data, denoted as Dist2; only if Dist1 > Dist2, perform the task data swap; otherwise, do not perform the swap.

[0016] T6. Repeat T4 and T5 until the preset target is reached, and complete the task scheduling of one of the scheduled hangars;

[0017] T7. Repeat T3-T6 to complete the task assignment for all the scheduled hangars.

[0018] The legal airspace mainly includes flyable airspace and approved controlled airspace.

[0019] A flight path is the specific route an aircraft takes in the air, usually consisting of a series of navigation points (such as VOR, NDB, and GPS points).

[0020] By continuously optimizing the Dist value (i.e., the sum of distances) of each set of data, the task coordinates of the same set of task data can be made more aggregated and closer, enabling the drone to perform more tasks in a shorter time, greatly reducing the time cost of task execution and the energy consumption cost of the drone.

[0021] As a further optimization of the above scheme, the preset goal is: when executing step T6, the number of consecutive times that no swap is performed reaches a preset number.

[0022] As a further optimization of the above scheme, in step T5, for a set of candidate tasks, a first probability θ1 is assigned to each group of data according to Dist, that is:

[0023] Where i represents the i-th set of data;

[0024] Two sets of data are selected from one of the candidate task sets based on the first probability.

[0025] As a further optimization of the above scheme, in step T5, for a set of data, a second probability θ2 is assigned to each task data according to dist, that is:

[0026] Where j represents the j-th task data;

[0027] Select a task data from a set of data based on the second probability.

[0028] As a further optimization of the above scheme, the initial grouping is to divide the area equally according to the horizontal or vertical coordinate of the coverage area, or to divide the area into grids based on the coordinates, to obtain the equally divided area; finally, a preset number of equally divided areas are obtained; the task data located in the equally divided area constitutes the set of data.

[0029] As a further optimization of the above scheme, the initial grouping is to average the task data according to the horizontal or vertical coordinates of the task coordinates, or to divide the task data into grids according to the task coordinates; and finally obtain a number of groups of data corresponding to a preset number.

[0030] As a further optimization of the above scheme, a hangar is set with multiple time periods; a set of data corresponds to a time period; within a time period, drone tasks are executed according to the task data corresponding to a set of data.

[0031] As a further optimization of the above scheme, a hangar is also set with a task execution count threshold; the task execution count threshold corresponds to the maximum number of drone tasks that the hangar can execute within a time period.

[0032] In the initialization grouping, the task data is evenly divided into groups according to the task execution count threshold.

[0033] As a further optimization of the above scheme, in step T2, in one of the candidate task sets, for task data with flight path data, the task data is classified according to the flight path data, and the task data located on the same flight path executes the UAV task in the same time period.

[0034] As a further optimization of the above scheme, in step T1, the legality of the collected data is judged to obtain legal data and illegal data; the legal data is preprocessed and the illegal data is warned; the data preprocessing includes deleting invalid data and redundant data; the illegal data includes data whose value exceeds the preset range and data whose data type does not meet the requirements.

[0035] To alleviate memory pressure, delete some irrelevant or useless terms from the data. Alternatively, if a single data entry contains multiple name tags, only one unique name tag needs to be stored.

[0036] Compared with the prior art, the present invention achieves the following beneficial effects:

[0037] (1) This invention provides a method for scheduling drone hangars based on heuristic algorithms. By using heuristic algorithms to automatically schedule each hangar intelligently, a scheduling plan can be quickly and automatically generated while meeting airspace conditions and reducing task execution costs, which effectively improves the scheduling efficiency of drone tasks in the hangar.

[0038] (2) By continuously optimizing the Dist value of each set of data, that is, the sum of distances, the task coordinates of the same set of task data can be more aggregated and closer, enabling the UAV to perform more tasks in a shorter time, greatly reducing the time cost of task execution and the energy consumption cost of the UAV, and effectively improving the UAV's task execution efficiency.

[0039] (3) The present invention can avoid the errors caused by traditional scheduling strategies, and does not require the personnel to have extensive prior knowledge of the scheduling rules and strategies for UAV missions, thus greatly reducing the labor and experience costs of scheduling. Attached Figure Description

[0040] Figure 1This is a flowchart illustrating a heuristic algorithm-based drone hangar scheduling method provided in an embodiment of the present invention.

[0041] Figure 2 This is a schematic diagram illustrating the effect of a scheduled hangar coordinate system and the task coordinates of various task data within its coverage area, provided by an embodiment of the present invention.

[0042] Figure 3 yes Figure 2 A schematic diagram showing the effect obtained after initial grouping;

[0043] Figure 4 This is a data table of the first group of data provided in the embodiments of the present invention;

[0044] Figure 5 This is a data table of the second set of data provided in the embodiments of the present invention;

[0045] Figure 6 This is a data table for the 7th group of data provided in the embodiments of the present invention;

[0046] Figure 7 yes Figure 3 The diagram shows the effect obtained after scheduling. Detailed Implementation

[0047] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions in the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0048] like Figures 1 to 7 As shown, this embodiment provides a drone hangar scheduling method based on a heuristic algorithm, including the following steps:

[0049] T1. Collect data, including airspace data, hangar data, and mission data; airspace data includes the legal airspace range; hangar data includes hangar coordinates and the mission's executable radius; mission data includes mission coordinates; some mission data includes flight path data.

[0050] In this embodiment, the collected data is judged for legality to obtain legal and illegal data; legal data undergoes data preprocessing, while illegal data is flagged; data preprocessing includes deleting invalid and redundant data; illegal data includes data with values ​​exceeding a preset range and data whose data type does not meet requirements. Some irrelevant or useless terms in the data are deleted to alleviate memory pressure. Alternatively, for example, if a data entry contains multiple name tags, only one unique name tag needs to be stored.

[0051] T2. Select hangars whose coordinates are located within the airspace as available hangars for scheduling. The area within the executable radius of any available hangar is the coverage area. Several task data points whose coordinates are within the coverage area constitute a candidate task set. One available hangar corresponds to one candidate task set. In this embodiment, a hangar is set with multiple time periods. A hangar is also set with a task execution count threshold. The task execution count threshold corresponds to the maximum number of drone tasks that the hangar can execute within a time period. In this embodiment, a hangar can execute 10 tasks within a time period.

[0052] In this embodiment, in step T2, within a set of candidate tasks, task data with flight path data is classified according to the flight path data, and task data located on the same flight path execute UAV tasks within the same time period.

[0053] T3. For a set of candidate tasks, delete task data with route data; tasks with route data are considered to have been scheduled; the remaining task data do not include route data; in this embodiment, the resulting set of candidate tasks includes 69 task data.

[0054] T4. Initialize grouping for a candidate task set. In this embodiment, initial grouping involves dividing the task data into groups based on the ordinate of the task coordinates, resulting in a predetermined number of groups. The maximum number of task data in each group is a threshold for the number of task executions. Each group of data corresponds to a time period; within a time period, drone tasks are executed based on the task data corresponding to each group. In this example, the 69 tasks in the candidate task set are divided into 7 groups of 10 each, based on dimensions, using different colors and shapes (e.g., ...). Figure 3 As shown, from top to bottom, the data includes "light-colored triangles", "light-colored squares", "light-colored circles", "dark-colored triangles", "dark-colored squares", "dark-colored circles", and "black triangles" for identification; the last 9 task data items constitute a set of data.

[0055] For the same set of data, calculate the distance between any task data and other task data, and denot the sum of the distances as dist; the average dist of the same set of data is denoted as Dist; in this example, the dist values ​​of the 10 tasks in the first set are 19, 16, 17, 22, 21, 16, 15, 18, 22, and 29, so the Dist value is 19.8.

[0056] T5. For a set of candidate tasks, select two sets of data based on Dist; specifically, assign a first probability θ1 to each set of data according to Dist, that is:

[0057] Where i represents the i-th data group, and n is the number of data groups in the current candidate task set;

[0058] In this embodiment, the Dist values ​​of the 7 sets of data are [19.8, 24.4, 18.8, 21.3, 20.2, 17.6, 16.4], which, when converted to θ1, are respectively...

[0059] [0.143, 0.176, 0.136, 0.154, 0.146, 0.127, 0.118].

[0060] Based on the first probability, two sets of data are selected from a set of candidate tasks. Let's assume that set 1 and set 2 are selected.

[0061] For the two selected sets of data, using dist as the baseline, select one task data point from each set; specifically, assign a second probability θ2 to each task data point according to dist, that is:

[0062] Where j represents the j-th task data, and m is the number of task data in the current group; taking the first group as an example, dist is [19,16,17,22,21,16,15,18,22,29], which, when converted to θ2, are respectively

[0063] [0.10,0.08,0.09,0.11,0.11,0.08,0.08,0.09,0.11,0.15].

[0064] Based on a second probability, select one task from a set of data. Suppose we select task 10 from group 1 and task 1 from group 2.

[0065] Calculate the sum of Dist for the two selected sets of data, denoted as Dist1; for the two selected sets of data, swap their positions according to the selected task data, and calculate the sum of Dist for the two sets of data, denoted as Dist2; only if Dist1 > Dist2, perform the task data swap; otherwise, do not perform the swap.

[0066] In specific implementation, the changed part of each group of data is only the distance of the swapped task relative to other tasks. Therefore, when comparing Dist1 and Dist2, only the change value of the distance needs to be compared.

[0067] Before the task data is swapped, the sum of the distances dist of Task 10 in the first group relative to other tasks is 29, and the sum of the distances dist of Task 1 in the second group relative to other tasks is 24.

[0068] Assume that after two tasks are swapped, the distances of Task 1 in the second group relative to Tasks 1 - 9 in the first group become [2, 2, 3, 4, 1, 1, 2, 3, 4], then the dist of "Task 10" in the first group is 22.

[0069] Similarly, the distances of Task 10 in the first group relative to Tasks 2 - 10 in the second group become [2, 3, 4, 5, 1, 1, 3, 6, 7], then the dist of "Task 1" in the second group is 32.

[0070] Therefore, after the task swap, the comparison of Dist1 and Dist2 is transformed into the comparison of (29 + 24 = 53) and (22 + 32 = 54). Thus, it is obtained that Dist1 < Dist2, and this swap is not executed.

[0071] T6. Repeat T4 and T5 until the preset goal is reached, and complete the task scheduling and allocation of a schedulable hangar; in this embodiment, the preset goal is: for an alternative task set, the number of consecutive times without executing a swap reaches the preset number of times.

[0072] T7. Repeat T3 - T6 to complete the task allocation of all schedulable hangars.

[0073] The legal airspace range mainly includes flyable airspace and approved controlled airspace.

[0074] A route is the specific path of an aircraft flying in the air, usually connected by a series of navigation points (such as VOR, NDB, GPS points).

[0075] By continuously optimizing the Dist value of each group of data through dist and Dist, that is, the sum of distances, it is possible to make the task coordinates of the same group of task data relatively more aggregated and closer, enabling the UAV to execute as many tasks as possible in a shorter time, greatly reducing the time cost of task execution and the energy consumption cost of the UAV.

[0076] Based on the disclosure and teachings of the foregoing specification, those skilled in the art can make changes and modifications to the above embodiments. Therefore, the present invention is not limited to the specific embodiments disclosed and described above, and some modifications and changes to the present invention should also fall within the protection scope of the claims of the present invention. Furthermore, although some specific terms are used in this specification, these terms are only for convenience of explanation and do not constitute any limitation on the present invention.

Claims

1. A method for scheduling drone hangars based on heuristic algorithms, characterized in that, Includes the following steps: T1. Collect data, including airspace data, hangar data, and mission data; the airspace data includes the legal airspace range; the hangar data includes hangar coordinates and the mission's executable radius; the mission data includes mission coordinates; wherein, some or all of the mission data includes flight path data. T2. Select hangars whose hangar coordinates are located within the airspace range as available hangars; the area within the task execution radius centered on the hangar coordinates of any available hangar is the coverage area; several task data whose task coordinates are located within the coverage area constitute a candidate task set; one available hangar corresponds to one candidate task set. T3. For a given set of candidate tasks, delete the task data containing the flight route data; T4. Initialize grouping for a set of candidate tasks, dividing the task data into several groups; for the same group of data, calculate the distance between any task data and other task data, and denot the sum of the distances as dist; denot the average value of dist for the same group of data as Dist. T5. For a set of candidate tasks, select two sets of data based on Dist; for the two selected sets of data, select one set of task data from each set of data based on Dist. For a given set of candidate tasks, a first probability is assigned to each data set according to Dist. ,Right now: ; Where i represents the i-th set of data; two sets of data are selected from one of the candidate task sets according to the first probability; For a set of data, assign a second probability to each task data point according to dist. ,Right now: ; Where j represents the j-th task data; a task data is selected from a set of data according to the second probability; Calculate the sum of the Dist values ​​of the two selected sets of data, denoted as Dist1; for the two selected sets of data, swap their positions according to the two task data, and calculate the sum of the Dist values ​​of the two sets of data, denoted as Dist2; only if Dist1 > Dist2, perform the task data swap; otherwise, do not perform the swap. T6. Repeat T4 and T5 until the preset target is reached, and complete the task scheduling of one of the scheduled hangars; T7. Repeat T3-T6 to complete the task allocation for all scheduled hangars; each hangar is set with multiple time periods; a set of data corresponds to a time period; within a time period, execute drone tasks according to the task data corresponding to a set of data.

2. The method for scheduling drone hangars based on heuristic algorithms according to claim 1, characterized in that, The preset target is: when executing step T6, the number of consecutive times without performing a swap reaches a preset number.

3. The method for scheduling drone hangars based on heuristic algorithms according to claim 1, characterized in that, The initial grouping is achieved by dividing the coverage area into equal regions according to the horizontal or vertical coordinates, or by dividing the area into grids based on the coordinates, to obtain the equal regions; finally, a preset number of equal regions are obtained; the task data located within the equal regions constitute the set of data.

4. The method for scheduling drone hangars based on heuristic algorithms according to claim 1, characterized in that, The initial grouping is performed by dividing the task data into average groups based on the horizontal or vertical coordinates of the task coordinates, or by dividing the task data into grids based on the task coordinates; ultimately, a number of groups of data corresponding to a preset quantity are obtained.

5. The method for scheduling drone hangars based on heuristic algorithms according to claim 1, characterized in that, A hangar is also equipped with a task execution count threshold; the task execution count threshold corresponds to the maximum number of drone tasks that the hangar can execute within a given time period; In the initialization grouping, the task data is evenly divided into groups according to the task execution count threshold.

6. The method for scheduling drone hangars based on heuristic algorithms according to claim 1, characterized in that, In step T2, within one of the candidate task sets, task data with flight path data are classified according to the flight path data, and task data located on the same flight path execute UAV tasks within the same time period.

7. The method for scheduling drone hangars based on heuristic algorithms according to claim 1, characterized in that, In step T1, the collected data is judged for legality to obtain legal data and illegal data; the legal data is preprocessed and the illegal data is given a warning; the data preprocessing includes deleting invalid data and redundant data; the illegal data includes data whose value exceeds a preset range and data whose data type does not meet the requirements.

Images