Multi-scene composite scheduling method and system for heterogeneous unmanned aerial vehicles

Abstract

The invention provides a multi-scene composite scheduling method and system for heterogeneous unmanned aerial vehicles, and the method comprises the steps: collecting the flight demand data and flight resource data of a heterogeneous unmanned aerial vehicle cluster in real time, and constructing an unmanned aerial vehicle global resource pool; calculating a matching degree between each flight demand and each flight resource in the unmanned aerial vehicle global resource pool; and constructing a multi-target composite optimization model based on the matching degree, and solving the multi-target composite optimization model to obtain an optimal scheduling result of the unmanned aerial vehicle. According to the invention, for the demands of multi-task concurrence, dynamic environment change and resource collaborative allocation in logistics distribution, forest and equipment inspection, emergency disaster rescue, agricultural plant protection and wide-area monitoring scenes, the matching degree of a flight task and an idle unmanned aerial vehicle is calculated in a multi-dimensional manner, and the tasks are dynamically allocated; the method is suitable for efficient matching of heterogeneous computing resources and diversified tasks of a large-scale unmanned aerial vehicle cluster so as to realize collaborative improvement of global scheduling efficiency and system fault tolerance.

Description

Technical Field

[0001] This invention relates to the field of unmanned aerial vehicle (UAV) technology, and in particular to a multi-scenario composite scheduling method and system for heterogeneous UAVs. Background Technology

[0002] As the core of intelligent unmanned systems, drone scheduling technology has developed rapidly in recent years in fields such as logistics, agriculture, and rescue. With the increasing demand for multi-scenario tasks, the efficient collaboration of heterogeneous drone swarms has become a key challenge. Existing technologies mainly focus on static or dynamic scheduling within a single scenario, such as logistics route optimization and farmland spraying task allocation, but they generally suffer from problems such as resource isolation and insufficient cross-scenario collaboration, leading to hardware idleness and task response delays.

[0003] Currently, similar implementation schemes include: 1. Single-scenario dynamic scheduling methods: For example, the improved discrete particle swarm optimization algorithm (CN649545): used for multi-UAV collaborative strike missions, avoiding local optima through cross-mutation, but only for military strike scenarios, lacking cross-scenario task considerations. 2. Multi-task collaborative scheduling methods: For example, the State Grid Smart Technology patent (CN118552002B): airport multi-task scheduling system, dynamically adjusting flight plans to meet logistics, rescue, and other needs, but the optimization scope is limited to airport scheduling and does not consider general scenarios.

[0004] In summary, existing drone scheduling technologies have the following drawbacks: 1. Resource silos: Drones are fixedly assigned to a single scenario, lacking a coordination mechanism for cross-scenario reuse, resulting in high hardware idle rates; 2. Single optimization dimension: Traditional algorithms mainly focus on path length and task completion time, without integrating multi-objective constraints such as cross-scenario priority and resource reuse cost; 3. Insufficient dynamic response: Sudden cross-scenario tasks rely on manual intervention and lack the system's ability to dynamically adjust tasks autonomously. Summary of the Invention

[0005] The purpose of this invention is to provide a multi-scenario composite scheduling method and system for heterogeneous unmanned aerial vehicles (UAVs), aiming to solve the above-mentioned problems in the prior art.

[0006] This invention provides a multi-scenario composite scheduling method for heterogeneous unmanned aerial vehicles (UAVs), including: Real-time collection of flight demand and flight resource data from heterogeneous drone swarms to construct a global resource pool for drones; Calculate the matching degree between each flight requirement and each flight resource in the global resource pool of the UAV; A multi-objective composite optimization model is constructed based on the matching degree, and the optimal scheduling result of the UAV is obtained by solving the multi-objective composite optimization model.

[0007] This invention provides a multi-scenario composite scheduling system for heterogeneous unmanned aerial vehicles (UAVs), comprising: The data module is used to collect flight demand data and flight resource data of heterogeneous drone swarms in real time and build a global resource pool for drones; The matching degree calculation module is used to calculate the matching degree between each flight requirement and each flight resource in the global resource pool of the UAV; The scheduling module is used to construct a multi-objective composite optimization model based on the matching degree, and solve the multi-objective composite optimization model to obtain the optimal scheduling result of the UAV.

[0008] This invention also provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the steps of the above-described multi-scenario composite scheduling method for heterogeneous unmanned aerial vehicles.

[0009] This invention also provides a computer-readable storage medium storing an information transmission implementation program, which, when executed by a processor, implements the steps of the above-described multi-scenario composite scheduling method for heterogeneous unmanned aerial vehicles.

[0010] The embodiments of this invention can include the following beneficial effects: This invention proposes a composite scheduling method for heterogeneous unmanned aerial vehicle (UAV) systems. This method addresses the needs of multi-task concurrency, dynamic environmental changes, and resource collaborative allocation in scenarios such as logistics delivery, forest and equipment inspection, emergency disaster relief, agricultural plant protection, and wide-area monitoring. By calculating the matching degree between flight tasks and idle UAVs from multiple dimensions, it dynamically allocates tasks, solving the problems of task conflicts, response delays, and insufficient resource utilization in complex scenarios caused by traditional single scheduling strategies. This invention is applicable to the efficient matching of heterogeneous computing resources and diverse tasks in large-scale UAV swarms, achieving a synergistic improvement in global scheduling efficiency and system fault tolerance. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in one or more embodiments of this specification or in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a flowchart of a multi-scenario composite scheduling method for heterogeneous UAVs according to an embodiment of the present invention; Figure 2This is a schematic diagram of a multi-scenario composite scheduling system for heterogeneous unmanned aerial vehicles according to an embodiment of the present invention. Detailed Implementation

[0013] To enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the technical solutions in one or more embodiments of this specification 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 specification, and not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of this document.

[0014] Method Implementation Examples According to embodiments of the present invention, a multi-scenario composite scheduling method for heterogeneous unmanned aerial vehicles (UAVs) is provided. Figure 1 This is a flowchart of a multi-scenario composite scheduling method for heterogeneous UAVs according to an embodiment of the present invention, as follows: Figure 1 As shown, the multi-scenario composite scheduling method for heterogeneous UAVs according to an embodiment of the present invention specifically includes: Step S101: Collect flight demand data and flight resource data of heterogeneous drone clusters in real time to build a global resource pool for drones; The flight demand data includes last-mile delivery, routine transportation operations, and inspection requirements. The flight resource data includes drone airports and drones at logistics transfer stations, drone airports and drones at transportation sites, and drone airports and drones at inspection takeoff points. The global resource pool for drones is a dynamic resource pool with multiple scenarios, including logistics and distribution, forest and equipment inspection, emergency disaster relief, agricultural plant protection, and wide-area monitoring scenarios.

[0015] Step S102, calculate the matching degree between each flight requirement and each flight resource in the global resource pool of the UAV, specifically including: Formula 1 is used to calculate the matching degree between each flight requirement and each flight resource in the global resource pool of the UAV; Formula 1; in, This represents the matching degree between the i-th takeoff requirement and the j-th UAV resource. Indicates flight demand The k-th dimension feature, Indicates drone resources The k-th dimension feature, This represents the weight of the k-th dimension, where K represents the number of matching features.

[0016] Step S103: Construct a multi-objective composite optimization model based on the matching degree, and solve the multi-objective composite optimization model to obtain the optimal UAV scheduling result, specifically including: Based on the matching degree, and with the objective of maximizing the total matching degree, a multi-objective composite optimization model as shown in Formula 2 is constructed. Formula 2; in, Indicates flight demand Are drone resources matched? , U represents the total number of takeoff requests, P represents the total number of flight resources, NP represents the minimum number of drone resources that must be allocated to each flight request, and NU represents the maximum number of requests that each drone resource can handle.

[0017] The following describes in detail the above-mentioned technical solutions of the present invention with reference to the specific circumstances of the multi-scenario composite scheduling method for heterogeneous UAVs in the embodiments of the present invention.

[0018] This invention proposes a multi-scenario composite scheduling scheme for drones. Unlike existing schemes, this invention defines drone flight demands from multiple scenarios, such as last-mile delivery, routine transportation operations, and surrounding municipal inspections, as flight demands. It defines all available drone airports and drones, such as those at logistics transfer stations, transportation sites, and inspection takeoff points, as flight resources. The matching degree between flight demands and flight resources is calculated based on multiple dimensions, and combined with the load capacity of the flight resources, a batch scheduling scheme for flight resources is calculated. The scheduling scheme mainly consists of three parts: ① calculating the matching degree between flight demands and drone resources; ② establishing a scheduling model; ③ calculating the scheduling results and completing the scheduling.

[0019] The specific steps of this invention embodiment are as follows: 1. Collect flight demand and UAV resource data Real-time data collection of flight demand and UAV resource information is used for subsequent scheduling calculations.

[0020] 2. Calculate the matching degree between flight requirements and UAV resources. Based on real-time data of flight requirements and drone resources (such as: flight route of the flight requirement and location of the drone resource, distance of the flight requirement and remaining range of the drone resource, weight of the flight requirement and payload capacity of the drone resource, whether the flight requirement requires video information and whether the flight resource has a high-definition camera, etc.), the matching degree between each takeoff requirement and each drone resource is calculated. : (1); in, This represents the matching degree between the i-th takeoff requirement and the j-th UAV resource. It is a flight requirement The k-th dimension feature, It is a drone resource The k-th dimension feature, It represents the weight of the k-th dimension, where K is the number of matching features. The larger the value, the better the match between flight requirements and drone resources.

[0021] 3. Establish a scheduling model Establish a scheduling model with 0-1 variables. Indicates flight demand Are drone resources matched? .by As optimization variables, an optimization model is established with the objective of maximizing the total matching degree. The constraint is that NP drone resources must be allocated to each flight requirement (usually NP=1). The drone resources... The number of flights to be undertaken cannot exceed (This represents the upper limit of demand that the j-th drone resource needs to handle): (2); (3); (4); in, U is the total number of takeoff requests, P is the total number of flight resources, NP represents the minimum number of UAV resources that must be allocated for each flight request, and NU represents the maximum number of requests that each UAV resource can handle.

[0022] 4. Calculate the allocation results and complete the allocation. Solve the above optimization model and allocate flight requests to drone resources based on the optimal solution. This optimal solution is the best-matched drone resource for allocating flight requests to drones that have not yet reached the upper limit of the queued request number.

[0023] Preferably, in calculating the matching degree between flight demand and UAV resources, this embodiment of the invention, in addition to adopting a weighted feature-based calculation method, may also consider introducing machine learning algorithms. By learning from historical scheduling data, the weights of features in each dimension can be automatically determined, and even hidden feature associations can be mined to achieve more accurate matching degree calculation.

[0024] Preferably, in the embodiments of the present invention, when solving the optimization model after establishing the scheduling model, in addition to solving the 0-1 integer programming model, a heuristic algorithm can also be used, which may have better search efficiency and global optimization capability, and is especially suitable for scenarios with large-scale UAV swarms and complex task requirements.

[0025] Preferably, embodiments of the present invention can employ a centralized global resource pool management approach. Alternatively, a distributed resource pool management model can also be considered. In the distributed model, drone resource nodes in different scenarios communicate collaboratively through the network to jointly complete task scheduling and allocation. This model can reduce the pressure on the central node to a certain extent, improve the system's fault tolerance and scalability, and is particularly suitable for large-scale drone swarm systems with relatively stable network environments.

[0026] Preferably, in the task allocation of this embodiment of the invention, in addition to aiming for the maximum overall matching degree, different priority objectives can be set according to different application scenarios. For example, in emergency disaster relief scenarios, the urgency of the task can be taken as the primary objective to ensure a rapid response to urgent tasks; in agricultural plant protection scenarios, energy efficiency and operating costs can be taken as the main optimization objectives to achieve economical and efficient use of resources. By flexibly adjusting the objective function, personalized scheduling needs under different scenarios can be met.

[0027] The key points of the embodiments of the present invention are as follows: 1. Cross-scenario dynamic resource reuse mechanism A global drone resource pool is constructed to support real-time task migration and scheduling across different scenarios such as logistics, rescue, agriculture, and inspection. A dynamic matching degree evaluation algorithm automatically identifies cross-scenario task requirements. Flight requirements and drone resources from multiple scenarios are all aggregated into flight requirement features and drone resource features, and the global matching degree is dynamically calculated.

[0028] 2. Multi-objective composite optimization model The mathematical expression and solution method of the multi-objective composite optimization model integrates multi-dimensional constraints such as path planning, task allocation, energy efficiency, and cross-scenario priority to design a scheduling model; it solves the resource competition problem when multiple tasks are concurrent in multiple scenarios, and the optimization objectives include task priority, completion time, etc.

[0029] 3. Compatible with all heterogeneous drones Dynamic matching is performed between drone models (endurance, payload, functions) and mission requirements (urgency, geographical range). Scenario requirements are quantified as flight requirement characteristics, and drone resources are quantified as drone resource characteristics, adapting to heterogeneous drones.

[0030] The following are examples of applications of embodiments of the present invention: 1. Scenario Setting: The following tasks occur simultaneously in a certain area: Emergency medical transport: 3 emergency medicine deliveries (load ≤ 3kg, delivery time ≤ 15 minutes, highest priority).

[0031] Forest fire risk inspection: 2 suspected fire spots (requires thermal imaging sensor, flight time ≥150 minutes, flight altitude ≥200 meters).

[0032] Urban logistics: 10 fresh produce deliveries (load weight ≤ 5kg, delivery radius ≤ 10km, delivery time requirement ≤ 30 minutes).

[0033] 2. Global resource pool status: Rescue drone: 1 unit (payload 20kg, top speed 60km / h, flight time 200 minutes, equipped with emergency communication module).

[0034] Logistics drones: 5 units (payload 30kg, speed 40km / h, flight time 180 minutes, standard logistics cargo hold).

[0035] Inspection drones: 2 (8kg payload, 30km / h speed, 240 minutes flight time, thermal imaging + 4K camera).

[0036] 3. Priority sorting and matching degree calculation (1) Emergency medical mission (priority weight 0.5): Compatibility with rescue drones: Time-based matching: A round trip of 10 kilometers takes 10 minutes (60km / h) to 15 minutes, with a matching degree of 1.0; Load capacity matching: 20kg≥3kg, matching degree 1.0; Total matching degree = 0.5×1.0 + 0.3×1.0 (battery redundancy) + 0.2×1.0 (emergency module) = 1.0.

[0037] Compatibility with logistics drones: Time-based matching: 10 kilometers takes 15 minutes (40km / h) = 15 minutes, matching degree 0.9; Load capacity matching: 30kg≥3kg, matching degree 1.0; Total compatibility = 0.5 × 0.9 + 0.3 × 1.0 (180 minutes of battery life ≥ 15 minutes) + 0.2 × 0.5 (no emergency module) = 0.75.

[0038] (2) Forest fire risk inspection (priority weight 0.3): Compatibility with inspection drones: Thermal imaging sensor matching degree 1.0, battery life ≥ 150 minutes (matching degree 1.0), flight altitude ≥ 200 meters (matching degree 1.0). Total compatibility = 0.3 × 1.0 + 0.4 × 1.0 (functions) + 0.3 × 1.0 (battery life) = 1.0.

[0039] (3) Urban logistics (priority weight 0.2): Compatibility with logistics drones: Time-sensitivity matching: 10 kilometers requires 15 minutes to 30 minutes, matching degree 1.0; Load capacity matching: 30kg≥5kg, can carry 6 loads per flight, matching degree 1.0; Total matching degree = 0.2×1.0 + 0.3×1.0 (battery range) + 0.5×1.0 (logistics module) = 1.0.

[0040] 4. Establish scheduling model and resource allocation (1) Objective function: Maximize the total matching degree and prioritize the NP=1 allocation of high priority tasks.

[0041] (2) Allocation scheme: ① Emergency medical mission: One rescue drone handled the first case (matching score 1.0).

[0042] Two of the five logistics drones were deployed to handle the second and third orders, respectively (matching degree 0.75×2).

[0043] ② Forest fire risk inspection: Two inspection drones each handled one fire point (matching degree 1.0×2).

[0044] ③ Urban logistics tasks: Three logistics drones will handle 10 orders, with each drone carrying 3-4 orders (30kg ≥ 5 × 4 = 20kg). The route planning is as follows: Drone A: Delivers 3 orders (total payload 15kg), route duration 25 minutes.

[0045] Drone B: Delivered 3 orders (total payload 15kg), route duration 28 minutes.

[0046] Drone C: Delivered 4 orders (total payload 20kg), route duration 30 minutes.

[0047] 5. Scheduling Results and Effect Verification (1) Response timeliness: The average response time for emergency medical missions is 12 minutes, which is 50% faster than the traditional approach (which only uses rescue drones) (the original approach required waiting for external rescue drones, with a delay of ≥15 minutes).

[0048] Forest fire risk inspections can transmit thermal images back within 30 minutes, buying time for firefighting decisions.

[0049] (2) Resource utilization rate: Logistics drones support emergency medical care across various scenarios, achieving a 66.7% gap-filling rate for rescue resources and reducing hardware idleness by 40%.

[0050] Urban logistics utilizes batch delivery, with 3 drones completing 10 tasks, reducing energy consumption by 20% compared to traditional decentralized dispatching.

[0051] (3) Advantages of heterogeneous adaptation: Although logistics drones lack emergency modules, they meet the timeliness requirements of medical care through their speed and payload advantages, thus verifying the flexibility of the multi-objective optimization model.

[0052] In summary, the beneficial effects of the embodiments of the present invention include: 1. Cross-scenario dynamic reuse mechanism: Construct a global resource pool to support real-time scheduling of drones in scenarios such as logistics, rescue, agriculture, and inspection, thereby improving drone utilization and the timeliness of flight mission response. 2. Multi-objective composite optimization model: This model comprehensively considers objectives such as path distance, task urgency, and task value for composite optimization.

[0053] 3. Heterogeneous UAV Adaptation Algorithm: Supports dynamic matching rules for different UAV models (endurance, payload, functions) to improve resource utilization.

[0054] System Implementation Examples According to embodiments of the present invention, a multi-scenario composite scheduling system for heterogeneous unmanned aerial vehicles (UAVs) is provided. Figure 2 This is a schematic diagram of a multi-scenario composite scheduling system for heterogeneous UAVs according to an embodiment of the present invention, such as... Figure 2 As shown, the multi-scenario composite scheduling system for heterogeneous unmanned aerial vehicles according to an embodiment of the present invention specifically includes: Data module 20 is used to collect flight demand data and flight resource data of heterogeneous UAV clusters in real time and build a global resource pool for UAVs; The flight demand data includes last-mile delivery, routine transportation operations, and inspection requirements. The flight resource data includes drone airports and drones at logistics transfer stations, drone airports and drones at transportation sites, and drone airports and drones at inspection takeoff points. The global resource pool for drones is a dynamic resource pool with multiple scenarios, including logistics and distribution, forest and equipment inspection, emergency disaster relief, agricultural plant protection, and wide-area monitoring scenarios.

[0055] Matching degree calculation module 22 is used to calculate the matching degree between each flight requirement and each flight resource in the global resource pool of the UAV, specifically for: Formula 1 is used to calculate the matching degree between each flight requirement and each flight resource in the global resource pool of the UAV; Formula 1; in, This represents the matching degree between the i-th takeoff requirement and the j-th UAV resource. Indicates flight demand The k-th dimension feature, Indicates drone resources The k-th dimension feature, This represents the weight of the k-th dimension, where K represents the number of matching features.

[0056] The scheduling module 24 is used to construct a multi-objective composite optimization model based on the matching degree, and to solve the multi-objective composite optimization model to obtain the optimal scheduling result of the UAV. Specifically, it is used for: Based on the matching degree, and with the objective of maximizing the total matching degree, a multi-objective composite optimization model as shown in Formula 2 is constructed. Formula 2; in, Indicates flight demand Are drone resources matched? , U represents the total number of takeoff requests, P represents the total number of flight resources, NP represents the minimum number of drone resources that must be allocated to each flight request, and NU represents the maximum number of requests that each drone resource can handle.

[0057] The embodiments of the present invention are system embodiments corresponding to the above method embodiments. The specific operation of each module can be understood by referring to the description of the method embodiments, and will not be repeated here.

[0058] In summary, the embodiments of the present invention have the following beneficial effects: 1. Significantly improved cross-scenario resource utilization: In existing technologies, drones are fixedly assigned to a single scenario, resulting in high hardware idle rates. However, the embodiments of this invention construct a global resource pool to support real-time scheduling of drones across multiple scenarios such as logistics, rescue, agriculture, and inspection, effectively breaking down resource silos and significantly improving the resource utilization rate of drones.

[0059] 2. Multi-dimensional optimization better meets complex needs: Traditional algorithms mainly focus on path length and task completion time, with a single optimization dimension. However, the embodiments of this invention comprehensively consider multiple objectives such as path distance, task urgency, and task value for composite optimization, which can better solve the resource competition problem when multiple tasks are concurrent and improve the global scheduling efficiency.

[0060] 3. Significantly enhanced dynamic response capability: Existing technologies rely on manual intervention when facing sudden cross-scenario tasks, resulting in insufficient dynamic response. The embodiments of this invention use a dynamic matching degree evaluation algorithm to automatically identify cross-scenario task requirements and combine it with a scheduling model to enable the system to autonomously and dynamically adjust tasks, significantly improving the timeliness of flight mission response.

[0061] 4. Enhanced adaptability to heterogeneous drones: Existing technologies lack adaptability to different drone models. This invention dynamically matches drone models (endurance, payload, functions) with mission requirements (urgency, geographical range) and designs dynamic matching rules to improve resource utilization of heterogeneous drones.

[0062] Device Example 1 This invention provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, performs the steps described in the method embodiment.

[0063] Device Example 2 This invention provides a computer-readable storage medium storing an information transmission implementation program, which, when executed by a processor, performs the steps described in the method embodiment.

[0064] The computer-readable storage media described in this embodiment include, but are not limited to, ROM, RAM, disk, or optical disk.

[0065] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A multi-scenario composite scheduling method for heterogeneous unmanned aerial vehicles, characterized in that... include: Real-time collection of flight demand and flight resource data from heterogeneous drone swarms to construct a global resource pool for drones; Calculate the matching degree between each flight requirement and each flight resource in the global resource pool of the UAV; A multi-objective composite optimization model is constructed based on the matching degree, and the optimal scheduling result of the UAV is obtained by solving the multi-objective composite optimization model.

2. The method according to claim 1, characterized in that, The flight demand data includes last-mile delivery, routine transportation operations, and inspection requirements. The flight resource data includes drone airports and drones at logistics transfer stations, drone airports and drones at transportation sites, and drone airports and drones at inspection takeoff points. The global resource pool for drones is a dynamic resource pool with multiple scenarios, including logistics and distribution, forest and equipment inspection, emergency disaster relief, agricultural plant protection, and wide-area monitoring scenarios.

3. The method according to claim 1, characterized in that, Calculating the matching degree between each flight requirement and each flight resource in the global resource pool of the UAV specifically includes: Formula 1 is used to calculate the matching degree between each flight requirement and each flight resource in the global resource pool of the UAV; Formula 1: in, This represents the matching degree between the i-th takeoff requirement and the j-th UAV resource. Indicates flight demand The k-th dimension feature, Indicates drone resources The k-th dimension feature, This represents the weight of the k-th dimension, where K represents the number of matching features.

4. The method according to claim 3, characterized in that, Constructing a multi-objective composite optimization model based on the matching degree specifically includes: Based on the matching degree, and with the objective of maximizing the total matching degree, a multi-objective composite optimization model as shown in Formula 2 is constructed. Formula 2: in, Indicates flight demand Are drone resources matched? , U represents the total number of takeoff requests, P represents the total number of flight resources, NP represents the minimum number of drone resources that must be allocated to each flight request, and NU represents the maximum number of requests that each drone resource can handle.

5. A multi-scenario composite scheduling system for heterogeneous unmanned aerial vehicles, characterized in that... include: The data module is used to collect flight demand data and flight resource data of heterogeneous drone swarms in real time and build a global resource pool for drones; The matching degree calculation module is used to calculate the matching degree between each flight requirement and each flight resource in the global resource pool of the UAV; The scheduling module is used to construct a multi-objective composite optimization model based on the matching degree, and solve the multi-objective composite optimization model to obtain the optimal scheduling result of the UAV.

6. The system according to claim 5, characterized in that, The flight demand data includes last-mile delivery, routine transportation operations, and inspection requirements. The flight resource data includes drone airports and drones at logistics transfer stations, drone airports and drones at transportation sites, and drone airports and drones at inspection takeoff points. The global resource pool for drones is a dynamic resource pool with multiple scenarios, including logistics and distribution, forest and equipment inspection, emergency disaster relief, agricultural plant protection, and wide-area monitoring scenarios.

7. The system according to claim 5, characterized in that, The matching degree calculation module is specifically used for: Formula 1 is used to calculate the matching degree between each flight requirement and each flight resource in the global resource pool of the UAV; Formula 1: in, This represents the matching degree between the i-th takeoff requirement and the j-th UAV resource. Indicates flight demand The k-th dimension feature, Indicates drone resources The k-th dimension feature, This represents the weight of the k-th dimension, where K represents the number of matching features.

8. The system according to claim 7, characterized in that, The scheduling module is specifically used for: Based on the matching degree, and with the objective of maximizing the total matching degree, a multi-objective composite optimization model as shown in Formula 2 is constructed. Formula 2: in, Indicates flight demand Are drone resources matched? , U represents the total number of takeoff requests, P represents the total number of flight resources, NP represents the minimum number of drone resources that must be allocated to each flight request, and NU represents the maximum number of requests that each drone resource can handle.

9. An electronic device, characterized in that, include: The memory, the processor, and the computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the multi-scenario composite scheduling method for heterogeneous unmanned aerial vehicles as described in any one of claims 1-4.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores an implementation program for information transmission, which, when executed by a processor, implements the steps of the multi-scenario composite scheduling method for heterogeneous unmanned aerial vehicles as described in any one of claims 1-4.

Images