Unmanned aerial vehicle cluster formation configuration and spectrum resource joint optimization method, system, device, medium and product

Abstract

The application discloses a method, system, device, medium and product for unmanned aerial vehicle cluster formation configuration and spectrum resource joint optimization, and relates to the field of unmanned aerial vehicle planning control. The method comprises the following steps: under the condition of given spectrum resources and limited number of unmanned aerial vehicles, dispatching multiple unmanned aerial vehicle formations to perform multiple tasks, utilizing the coupling relationship among the number of unmanned aerial vehicle formations, target sensing sequence and spectrum resource allocation to construct an optimization problem model; utilizing an improved genetic algorithm to solve the optimization problem model, and outputting an optimal unmanned aerial vehicle cluster formation configuration and spectrum resource joint optimization scheme; wherein the improved genetic algorithm is an embedded simulated annealing algorithm in the genetic algorithm, and the crossover operator of the genetic algorithm is adjusted, and the elite strategy and dynamically adjustable mutation rate are introduced in the mutation operation. The application can realize the joint planning of task planning of unmanned aerial vehicles, number allocation of unmanned aerial vehicle formations and bandwidth selection, and has higher global optimization capability.

Description

Technical Field

[0001] This application relates to the field of unmanned aerial vehicle (UAV) planning and control, and in particular to a method, system, device, medium, and product for joint optimization of UAV swarm formation configuration and spectrum resources. Background Technology

[0002] Unmanned aerial vehicles (UAVs) are widely used in battlefield reconnaissance, joint attacks, and emergency rescue operations due to their low cost, high flexibility, and strong stealth capabilities. UAV swarms offer more advantages than single UAVs in mission execution, enabling them to perform more diverse tasks and conduct more efficient large-scale searches. Multi-UAV collaborative missions involve two or more UAVs working together in complex environments. Compared to single UAVs, multi-UAV collaborative missions offer greater flexibility in handling tasks and are better suited for complex missions. Despite the significant advantages of multi-mission systems, balancing mission requirements with resource planning remains a challenge. Focusing solely on mission requirements may lead to wasted UAV and spectrum resources; conversely, excessive focus on resource allocation can result in insufficient mission completion and reduced returns. Therefore, UAV mission requirements and resource allocation are interdependent, jointly determining the optimal UAV collaborative mission planning scheme.

[0003] Existing research often focuses solely on meeting task requirements while neglecting resource considerations. Extensive research has been conducted by scholars both domestically and internationally on meeting task requirements. For example: 1) By establishing an overall efficiency model of task allocation under factors such as task performance, execution time, and task load, a quantum genetic algorithm based on distribution estimation was proposed, enabling initial task allocation for UAVs in multi-base scenarios and dynamic allocation under sudden threats. 2) For the multi-UAV task allocation problem in multi-target tracking scenarios, a distributed allocation method based on the auction-pigeon flock optimization (auction-PIO) algorithm was proposed. The proposed algorithm exhibits good task allocation performance, and outdoor experiments verified its practicality. 3) Facing the dynamic task allocation problem of UAV swarms in complex scenarios, the behavioral characteristics of wolf packs in natural environments were modeled and used to solve the problem. A path planning algorithm and coverage search algorithm suitable for UAV swarms in complex scenarios were also proposed, achieving high task completion rates, balancing UAV load, and providing a suitable solution for complex scenarios. 4) For the coverage path planning problem of heterogeneous UAVs, a heuristic method based on the Ant Colony Algorithm (ACS) is proposed to seek an approximate optimal solution and minimize the time consumption of tasks in the cooperative search system. 5) For the multi-UAV cooperative search and attack task planning problem, an Intelligent Self-Organizing Algorithm (ISOA) is proposed. The proposed algorithm has stable and efficient convergence performance, external responsiveness, and internal scalability. 6) To address the problem of limited UAV flight time and payload capacity during task planning, an accurate Pareto optimal solution is derived using the E-constraint method. To find an approximate Pareto solution, an approximate two-phase (ATP) method is developed, which features high accuracy and reduces computation time by two orders of magnitude.

[0004] Reasonable spectrum resource optimization can effectively reduce the energy consumption of UAVs, and existing research has done a lot of work on spectrum resource optimization. 1) For the UAV-assisted user communication problem, the problem is modeled as a mixed integer non-convex optimization problem. Based on the different characteristics of discrete and continuous optimization variables, it is decomposed into integer optimization subproblems and non-convex optimization subproblems. Then, an iterative algorithm combining genetic algorithm and convex optimization is developed to alternately optimize these two separate subproblems. This algorithm jointly optimizes user association and UAV location to maximize the total downlink user rate, and the results show that the algorithm has good robustness. 2) For UAV wireless communication, the carrying capacity of a single UAV is limited. Multiple UAVs are dispatched to collect data from multiple ground nodes. Through joint optimization of trajectory and node communication time, the energy consumption of UAVs is minimized. 3) For the scenario of UAV swarms as auxiliary deployment of wireless networks, an average potential field game is constructed, and the model is solved using the original dual hybrid gradient (PDHG) method. High channel capacity is achieved while minimizing energy consumption.

[0005] The aforementioned existing technologies often focus only on mission requirements or spectrum resource planning, with little research on combining the two. In particular, as the scale of missions increases, mission complexity rises, and more drones are used, the spectrum becomes increasingly congested, and unreasonable resource allocation will reduce the quality of mission completion. Summary of the Invention

[0006] The purpose of this application is to provide a method, system, device, medium, and product for the joint optimization of UAV swarm formation configuration and spectrum resources, so as to solve the problem of not being able to take into account both UAV formation and spectrum resources.

[0007] To achieve the above objectives, this application provides the following solution:

[0008] Firstly, this application provides a method for joint optimization of UAV swarm formation configuration and spectrum resources, including:

[0009] Given a limited spectrum resource and a limited number of drones, multiple drone formations are dispatched to perform multiple tasks. An optimization problem model is constructed by utilizing the coupling relationship between the number of drone formations, the target perception order, and the spectrum resource allocation. The target perception order is the order in which each drone formation performs its tasks. One target is handled by one drone formation.

[0010] An improved genetic algorithm is used to solve the optimization problem model, outputting an optimal UAV swarm formation configuration and spectrum resource joint optimization scheme. The improved genetic algorithm embeds a simulated annealing algorithm, adjusts the crossover operator, and introduces an elitist strategy and a dynamically adjustable mutation rate in the mutation operation. Adjusting the crossover operator ensures the correctness of offspring while inheriting characteristics from different parents. The elitist strategy preserves the best individuals directly into the next generation without crossover or mutation. The dynamically adjustable mutation rate is used to dynamically adjust the mutation rate based on the operation of the improved genetic algorithm, exploring the solution space and adjusting the solution. The simulated annealing algorithm accepts poor solutions at high temperatures and gradually converges to the optimal solution at low temperatures. The optimal solution is the optimal UAV swarm formation configuration and spectrum resource joint optimization scheme. Poor solutions are those of lower quality than the current solution.

[0011] Secondly, this application provides a system for joint optimization of UAV swarm formation configuration and spectrum resources, including:

[0012] An optimization problem model building module is used to dispatch multiple drone formations to perform multiple tasks under the given spectrum resources and limited number of drones. It constructs an optimization problem model by utilizing the coupling relationship between the number of drone formations, the target perception order, and the spectrum resource allocation; wherein, the target perception order is the order in which each drone formation performs its tasks; one target is executed by one drone formation.

[0013] An optimal UAV swarm formation configuration and spectrum resource joint optimization scheme output module is used to solve the optimization problem model using an improved genetic algorithm and output the optimal UAV swarm formation configuration and spectrum resource joint optimization scheme. The improved genetic algorithm embeds a simulated annealing algorithm, adjusts the crossover operator, and introduces an elitist strategy and a dynamically adjustable mutation rate in the mutation operation. Adjusting the crossover operator ensures the correctness of offspring while inheriting characteristics from different parents. The elitist strategy preserves the best individuals directly into the next generation without crossover or mutation operations. The dynamically adjustable mutation rate is used to dynamically adjust the mutation rate based on the operation of the improved genetic algorithm, and is used to explore the solution space and adjust the solution. The simulated annealing algorithm accepts poor solutions at high temperatures and gradually converges to the optimal solution at low temperatures. The optimal solution is the optimal UAV swarm formation configuration and spectrum resource joint optimization scheme.

[0014] Thirdly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the unmanned aerial vehicle swarm formation configuration and spectrum resource joint optimization method described in any one of the above.

[0015] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the unmanned aerial vehicle swarm formation configuration and spectrum resource joint optimization method described above.

[0016] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the unmanned aerial vehicle (UAV) swarm formation configuration and spectrum resource joint optimization method described above.

[0017] To make reasonable use of UAV resources and maximize mission completion benefits, and considering the limited flight range of UAVs, this application proposes a joint optimization of the "reconnaissance-communication" mission planning and spectrum resources of multiple UAVs in rescue operations under a multi-mission scenario with limited resources. By utilizing the coupling relationship between the number of UAVs in the formation, the target perception order, and the spectrum resource allocation, an optimization problem model is constructed. An improved genetic algorithm is designed to solve this optimization problem model to obtain the optimal UAV swarm formation configuration and spectrum resource joint optimization scheme. The improved genetic algorithm embeds a simulated annealing algorithm, adjusts the crossover operator, and introduces an elitist strategy and a dynamically adjustable mutation rate in the mutation operation. The elitist strategy preserves the best individuals directly for the next generation without crossover or mutation. The dynamically adjustable mutation rate is adjusted based on the improved genetic algorithm's performance, exploring the solution space and adjusting solutions. The simulated annealing algorithm accepts poor solutions at high temperatures and gradually converges to the optimal solution at low temperatures. This optimal solution is a joint optimization scheme for optimal UAV swarm configuration and spectrum resources. This improved algorithm combines the wide-range exploration capability of the genetic algorithm with the fine-grained search advantage of the simulated annealing algorithm, achieving joint planning of UAV task planning, UAV swarm size allocation, and bandwidth selection. It possesses higher global optimization capabilities. Compared with other heuristic algorithms, the improved genetic algorithm plans more rational task selection and UAV swarm size, can handle more complex scenarios, and achieves greater network benefits. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart of a method for joint optimization of UAV swarm formation configuration and spectrum resources in one embodiment of this application;

[0020] Figure 2 A schematic diagram illustrating a scenario in which an unmanned aerial vehicle (UAV) performs an integrated "reconnaissance-communication" mission, as provided in an embodiment of this application.

[0021] Figure 3 for Figure 1 A detailed flowchart of step 102;

[0022] Figure 4 A schematic diagram of a three-chromosome scheme for three drone formations to execute 10 targets, provided in an embodiment of this application;

[0023] Figure 5 This is a schematic diagram of cross-operation provided in one embodiment of this application;

[0024] Figure 6 A schematic diagram illustrating the drone platooning range limitation provided in one embodiment of this application;

[0025] Figure 7 A detailed flowchart illustrating step 102 provided in an embodiment of this application;

[0026] Figure 8 A drone quantity planning diagram for a drone mission planning of 10 drones with a mission number of 8, allocated to drone formations at 3 airports, is provided for one embodiment of this application.

[0027] Figure 9 A drone quantity planning diagram for a drone mission planning of 10 drones assigned to a drone formation at 3 airports, provided in one embodiment of this application;

[0028] Figure 10 A frequency selection diagram for drone mission planning, in one embodiment of this application, shows the allocation of 10 drones with a mission count of 8 to a drone formation at 3 airports.

[0029] Figure 11 A frequency selection diagram for drone mission planning, in one embodiment of this application, shows the allocation of 10 drones to a drone formation at 3 airports with a mission count of 10.

[0030] Figure 12 The following diagram shows the results of different algorithms for assigning 8 tasks (a total of 10 drones) to a drone formation at 3 takeoff points, as provided in one embodiment of this application.

[0031] Figure 13 The following diagram shows the results of different algorithms for assigning 10 drones to a drone formation at 3 takeoff points in one embodiment of this application.

[0032] Figure 14 A diagram illustrating the revenue results for different numbers of drones under two different weights, as provided in an embodiment of this application;

[0033] Figure 15 A comparison chart of algorithm stability under the same resources provided in one embodiment of this application, with the addition of a takeoff point. Detailed Implementation

[0034] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0035] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0036] like Figure 1 As shown in the figure, this application provides a method for joint optimization of UAV swarm formation configuration and spectrum resources, including:

[0037] Step 101: Given the spectrum resources and the limited number of UAVs, dispatch multiple UAV formations to perform multiple tasks. Utilize the coupling relationship between the number of UAV formations, the target perception order, and the spectrum resource allocation to construct an optimization problem model; wherein, the target perception order is the order in which each UAV formation performs its tasks; one target is executed by one UAV formation.

[0038] Step 102: Solve the optimization problem model using an improved genetic algorithm, outputting the optimal UAV swarm formation configuration and spectrum resource joint optimization scheme; wherein, the improved genetic algorithm is a genetic algorithm that embeds a simulated annealing algorithm, and adjusts the crossover operator of the genetic algorithm, and introduces an elite strategy and a dynamically adjustable mutation rate in the mutation operation; adjusting the crossover operator of the genetic algorithm can inherit the characteristics of different parents while ensuring the correctness of the offspring, avoiding the omission and duplication of targets; the elite strategy is used to retain the best individuals directly into the next generation without crossover and mutation operations; the dynamically adjustable mutation rate is used to dynamically adjust the mutation rate according to the running status of the improved genetic algorithm, and the mutation rate is used to explore the solution space and adjust the solution; the simulated annealing algorithm is used to accept poor solutions in the high-temperature stage, and gradually converge from poor solutions to the optimal solution in the low-temperature stage; the optimal solution is the optimal UAV swarm formation configuration and spectrum resource joint optimization scheme.

[0039] In one exemplary embodiment, such as Figure 2 The diagram illustrates a scenario where drones perform an integrated "reconnaissance-communication" mission. Specifically, the scenario involves multiple heterogeneous drones carrying reconnaissance and communication payloads. The diagram considers a drone swarm performing "reconnaissance and communication" missions. Multiple airports serve as takeoff points, and multiple "reconnaissance-communication" missions need to be executed. Drones within the same airport form a drone swarm, traversing and executing their assigned tasks. After completing a fixed-time reconnaissance mission, they hover above the mission point and transmit the reconnaissance information to the airport's decision-making center for processing. Due to the relatively small battery capacity of drones, they cannot support prolonged operation. When there are many missions, a single drone swarm may not be able to complete all "reconnaissance-communication" tasks. Multiple nearby airports and drone swarms are set up. Assume that M drones need to be deployed to N different airports, with each airport sending drones to form a drone swarm, and that airport serving as the takeoff point, heading to K mission targets distributed on the ground to perform swarm reconnaissance-communication missions. The sets of drones, airports, and targets are M0 = {1,...,M}, N0 = {1,...,N}, and K0 = {1,...,K}, respectively.

[0040] Assume the total system bandwidth B is divided into N sub-channels, managed by the base station. Drones within the alliance sequentially use these channels to transmit information to local authorities. Different alliances use different channels, while within the same alliance, drones use the same channel via time-division multiplexing. Due to significant differences in weather and terrain in disaster-stricken areas, the difficulty of drone reconnaissance missions varies depending on the specific task. Relevant departments have already coordinated with the local meteorological bureau to assess the weather and terrain conditions, and can assign a probability P of success for a drone performing mission i. i Let the tuple (Val(i), λ) be... i T A (i))) are attributes of task i, where (Val(i), λ i T A (i) represents the value of task i, the amount of data transmitted by task i, and the fixed completion time, respectively.

[0041] Drone Cluster A i The probability of completing task i is:

[0042]

[0043] Assuming the value of a task increases with the probability of its completion, the value of task i can be expressed as:

[0044] V(i)=P(A i ,i)*Val(i)

[0045] The horizontal coordinates of ground-sensing targets are represented by q. k =R 2*1 The distance between the target k and the decision center can be represented as:

[0046] d k,n =||q k -q n ||

[0047] Where, q n Let q represent the horizontal coordinate of the nth airport decision-making center. k This represents the horizontal coordinate of the k-th task point, and ||*|| represents the Euclidean distance.

[0048] Assuming a small drone is used for a 'reconnaissance-communication' mission, it can hover in the air to obtain stable communication transmission quality. The drone's energy consumption is divided into motion energy consumption and communication energy consumption. Generally, communication energy consumption is several orders of magnitude lower than motion energy consumption and can be ignored. We mainly consider the drone's motion energy consumption. When the drone moves at a constant speed v, its power consumption can be expressed as:

[0049]

[0050] p0 and p i These represent the blade profile power and inductive power in hovering mode, respectively; U tip v0 and v0 represent the rotor tip speed and average rotor speed in hovering state, respectively; d0 and s represent the fuselage drag ratio and rotor solidity, respectively; ρ and A represent the air density and rotor disk area, respectively.

[0051] When the distance between targets is far, the acceleration and deceleration time of the UAV is very short compared to the time spent maneuvering between targets, so the acceleration and deceleration process of the UAV can be ignored. The UAV flies at a constant speed when maneuvering between targets and hovers when performing perception tasks.

[0052] The energy consumption of a drone varies at different flight speeds. As can be verified by the equation, the drone's flight power consumption first decreases and then increases with increasing speed, indicating a maximum range speed V. mr .

[0053] To save energy expenditure, assume that the drone uses a speed V when flying between targets. mr Therefore, the minimum flight energy required for the UAV to fly to the next target k' after completing the perception task of target k is:

[0054]

[0055] d represents the time it takes for the drone to fly from target k to k'; k.k' The distance between target k and k' is represented by the formula.

[0056] Because drones have limited battery power, hovering time is calculated based on the drone's data transmission time. Thanks to the drone's altitude gain, the air-to-ground channel power gain is primarily determined by the line-of-sight link, and can be expressed using a free-space path loss model:

[0057]

[0058] Where β0 represents the channel power gain at a reference distance of 1m. k,c This represents the distance from the starting point to the drone formation.

[0059] drone formation N i The allocated bandwidth is W i The fixed amount of information to be transmitted for task k is C. k The hovering time of the drone over target k is:

[0060]

[0061] σ 2 P represents the ambient noise power.m This indicates the transmit power of the drone m.

[0062] The hovering energy consumption of the drone at target k is:

[0063]

[0064] In the formula, P(0) represents the flight energy consumption of the UAV when its speed is 0, i.e., the flight power energy consumption when hovering. i It is the fixed completion time of task i.

[0065] A single target requires only one drone swarm to perform the mission. The relationship between target k and drone swarm n is as follows:

[0066]

[0067] The total distance S of any drone formation n n for:

[0068]

[0069] Total distance

[0070] in, This represents the distance from the airport of drone formation i to the first selected mission point. This represents the distance from the last task point to the airport π in team n. n (0) distance; K n The total number of tasks assigned to drone formation n; This represents the k-th mission point π selected by the drone formation n. n (k) to the (k+1)th task point π n The distance of (k+1); |A n | represents the number of drones in the drone formation n; N is the total number of drones in the formation.

[0071] The optimization objective of this invention is to dispatch drone swarms to perform information "reconnaissance and communication" tasks under given spectrum resources and a limited number of drones, and to deploy drones of different starting points, allocate bandwidth, rationally allocate tasks, and plan task paths. Multi-drone collaborative reconnaissance and communication tasks are essentially a constrained multiple traveling salesmen problem (MTSP), where different drone swarms start from different points, and each task requires only one drone swarm to execute.

[0072] A single drone swarm cannot complete large-scale reconnaissance and communication tasks; multiple drone swarms must work together. In real-world scenarios, most solutions only consider task completion rate, task completion time, drone requirements, or resource consumption, choosing one aspect for consideration. However, in reality, a reasonable balance between benefits and energy consumption should be struck. Weighting coefficients should be used to combine these considerations. A reasonable drone swarm execution order and spectrum allocation can improve task efficiency, reduce drone spectrum waste, and thus reduce drone energy consumption. Therefore, the optimization objective can essentially be transformed into optimizing the number of drones, the execution order of each drone swarm, and spectrum resource allocation, given a given number of drones, to maximize the total utility function of the multi-task problem. The mathematical model of the optimization problem is expressed as:

[0073]

[0074] C4: S≤S max

[0075] C5:|A n |>0

[0076]

[0077] Where U is the total utility function; k n p is the task number assigned to formation n; N is the number of formations; k The probability that a drone completes mission k; |A n | represents the number of drones in formation n; V(k) represents the value of the mission; γ is the weighting coefficient for hovering loss; P(v) is the power loss function for drones at speed v, where P(0) represents the power loss of the drone during hovering when the speed is 0; T(k) represents the fixed reconnaissance time of mission k; λ k W represents the amount of information data that task k needs to transmit. n P is the bandwidth of the formation n; m This refers to the drone's transmission power. Let β0 be the channel power gain at a distance of 1m for a UAV formation n performing mission k, and σ be the distance from the mission point to the airport of formation n. 2 V represents the environmental noise power spectral density; λ is the weighting coefficient for path loss; V mr The flight speed at which the drone can cruise for the longest distance; X is the time taken for the drone formation n to traverse the mission points; k,n For each drone formation n, execute task k; n is the drone formation number; K is the total number of tasks; M is the number of drones available for allocation; S max X represents the maximum range of the drone; n M is the formation number for executing the mission; M is the total number of allocable drones; Wsum C1 represents the total bandwidth of the drone formation; C2 indicates that each task corresponds to one formation; C3 indicates that all tasks are executed by drone formations; C4 indicates that the sum of the drones in each formation is the number to be assigned; C5 indicates that the formation mileage must be less than a limit; C6 indicates that each formation must be assigned a drone; C7 indicates that the sum of the bandwidths of each formation is the existing bandwidth; and C8 indicates that the bandwidth of each formation is greater than 0. This is a mixed-integer nonlinear programming (MINLP) problem, where the variables to be optimized are coupled and difficult to solve using existing optimization methods, making the solution to the optimal solution challenging. In an exemplary embodiment, genetic algorithms typically have a huge search space for optimization problems with discrete variables. Through random generation and evolution, they can effectively search a large-scale candidate solution space to find potential optimal solutions. The simulated annealing algorithm is introduced, and its role in the genetic algorithm is to further optimize individuals to help them escape local optima. Figure 3 As shown, step 102 can be replaced by the following steps 201-205:

[0078] Step 201: Initialize the drone formation's mission execution plan using a single chromosome to generate the first generation of individuals; wherein, a single chromosome consists of four segments of length: the first segment of length K represents the perception order of each target, the second segment of length K represents the mission assigned to each airport, the third segment of length N represents the number of drones in each drone formation, and the fourth segment of length N represents the bandwidth allocated to each drone formation.

[0079] Furthermore, Figure 4 The three-chromosome scheme of three drone formations executing 10 targets is shown. Drone formation 1 senses four targets in the order of 1, 4, 5 and 2. Drone formation 1 has three drones and the bandwidth is divided into standard one. The other drone formations are in the same manner.

[0080] Step 202: Introduce an elite strategy, selecting the best individuals from the first generation of individuals to directly serve as the next generation of individuals, without undergoing crossover or mutation operations.

[0081] Step 203: After the remaining individuals in the first generation are subjected to crossover operation, mutation operation and UAV mileage limit in sequence, the next generation of individuals is generated, and combined with the optimal individual to generate a new generation of individuals; wherein, the UAV mileage limit is used to process the feasibility of the new schemes generated after crossover operation and mutation operation, and to determine the mileage of each UAV formation in performing the mission.

[0082] Furthermore, the various operations in the improved genetic algorithm are explained.

[0083] Crossover operation: Crossover creates new offspring by mixing the genetic information of parent individuals. This encourages the genetic algorithm to explore diversity in the solution space. Task target numbers are unique and directional; traditional crossover operations are prone to target duplication and omission. To prevent this problem, this application adjusts the crossover operator, ensuring the correctness of offspring while inheriting characteristics from different parents, thus avoiding target omission and duplication. Specific operations are as follows... Figure 5 As shown.

[0084] Mutation: Mutation is a stochastic operation that introduces new gene combinations by randomly altering the genes of individuals, thereby increasing population diversity. This application focuses on the allocation of drone swarms for collaborative mission execution, requiring consideration of the number of drones within a swarm, the order of mission execution, the number of missions performed by each drone, and the bandwidth allocation for each drone swarm.

[0085] Drone Swarm Mileage Limitation: To meet drone energy consumption requirements, the feasibility of new solutions generated by crossover mutations needs to be addressed, requiring the determination of the mileage of each drone swarm performing tasks. A penalty value is set; if the mileage of a drone swarm traversing tasks exceeds the set value, the penalty value is subtracted from the fitness function. Then, one task within that drone swarm is assigned to another drone swarm, and the mileage value is reassessed. For example... Figure 6 As shown.

[0086] Elite strategy and dynamically adjustable mutation rate: In this optimization problem, there are many variables to be optimized, and the permutations and combinations of these variables are enormous. To improve the performance of the genetic algorithm, an elite strategy and a dynamically adjustable mutation rate are introduced in the selection and mutation operations. The elite strategy refers to retaining a subset of the best-performing individuals (i.e., elites) directly into the next generation without crossover and mutation operations during the selection process. The mutation rate is a mechanism used in genetic algorithms to introduce new individuals; it determines the probability of gene mutation in each generation. The dynamically adjustable mutation rate strategy refers to dynamically adjusting the mutation rate based on the algorithm's performance. The purpose of a dynamically adjustable mutation rate is usually to balance exploration and exploitation. In the early stages of the algorithm, a higher mutation rate helps explore the solution space; while in the later stages, a lower mutation rate helps fine-tune the solution, avoiding the destruction of already found good solutions. These ensure that the algorithm can effectively converge to the optimal solution while maintaining its exploratory capabilities.

[0087] Simulated annealing algorithm: As the number of iterations increases, the differences between individuals in the population decrease, leading to a decline in the convergence of the genetic algorithm and a gradual entrapment in local optima. To avoid this, simulated annealing is embedded in the genetic algorithm to perform local optimization on individuals in each generation. Simulated annealing, by accepting worse solutions at higher temperatures and gradually converging to better solutions at lower temperatures, helps the genetic algorithm escape local optima and improves its global search capability.

[0088] Step 204: Use the new generation of individuals as the initial solution of the simulated annealing algorithm, and evaluate the fitness of the initial solution.

[0089] Step 205: Based on the fitness of the initial solution, iteratively train the new generation of individuals until the maximum number of iterations is reached, and output the optimal UAV swarm formation configuration and spectrum resource joint optimization scheme.

[0090] In another exemplary embodiment, step 102 can be replaced by the following steps 301-307:

[0091] Step 301: Initialize the population. Divide the variables of the required solution into four chromosomes to form the genetic algorithm population. These chromosomes represent the execution order of each objective, the task assigned to each drone formation, the number of drones in each drone formation, and the bandwidth selection for each drone formation.

[0092] Step 302: The elite selection operation retains a portion of the best-performing individuals (i.e. elites) and directly enters the next generation without going through crossover and mutation operations.

[0093] Step 303: Crossover operation, randomly switch the arrangement of the first chromosome, i.e. the order in which the drone executes, to generate more types of chromosomes.

[0094] Step 304: Mutation operation. Perform the mutation operation based on the mutation probability.

[0095] Step 305: Determine the mileage of the drone formation and calculate the flight distance of each drone formation. If it exceeds the mileage constraint, the task of the drone formation will be reassigned. In the next stage, the number of tasks will be reduced or the nearest task will be selected.

[0096] Step 306: Calculate the fitness value and input the generated new generation of individuals into the simulated annealing algorithm.

[0097] Step 307: The simulated annealing algorithm continues the local search until it reaches its maximum number of iterations. Output the results.

[0098] In another exemplary embodiment, such as Figure 7 As shown, step 205 can be replaced by steps 401-406:

[0099] Step 401: First judgment process: Based on the fitness of the initial solution, determine whether the temperature of this iteration has reached the termination temperature or the number of iterations. If yes, proceed to step 402; otherwise, proceed to step 403.

[0100] Step 402: Output the optimal drone swarm formation configuration and spectrum resource joint optimization scheme.

[0101] Step 403: Generate neighborhood solutions and evaluate the fitness of the neighborhood solutions.

[0102] Step 404: Determine whether the fitness of the neighborhood solution is better than the fitness of the initial solution. If yes, proceed to step 405; otherwise, proceed to step 406.

[0103] Step 405: Accept the neighborhood solution, update the temperature and iteration number for this iteration, and return to the first judgment process.

[0104] Step 406: With probability e -(fit(R’)-fit(R) / T) Accept the neighborhood solution; where fit(R') is the fitness of the neighborhood solution; fit(R) is the fitness of the initial solution; and T is the current temperature.

[0105] To verify the efficiency and effectiveness of the proposed improved genetic annealing hybrid algorithm, it was compared with heuristic algorithms such as genetic algorithms and simulated annealing algorithms. Simulations also demonstrated the algorithm's performance under different task parameters. To ensure more reasonable simulation parameter settings, the key parameter settings are shown in Table 1.

[0106] Table 1 Simulation Parameter Settings

[0107]

[0108]

[0109] Figure 8 and Figure 9 The diagrams show the drone quantity planning and frequency selection for assigning 10 drones to drone formations at 3 airports when the mission count is 8 and 10, respectively.

[0110] Figure 10 and Figure 11The results of task allocation, drone number division, and bandwidth selection are presented for 8 and 10 tasks respectively. The algorithm considers not only drone losses but also the rewards of task execution, thus rationally configuring the number of drones within each drone formation. Since flight energy consumption remains the primary factor affecting the objective function, drone formations tend to choose the nearest task. However, mileage constraints limit the number of tasks each drone formation can choose, highlighting the necessity of multiple takeoff points. Increased bandwidth accelerates information transmission and reduces hovering losses; therefore, drone formation 2, with the largest task load, receives the largest bandwidth allocation. Increasing the number of drones within a formation not only increases the probability of task completion (reward) but also increases energy consumption; the model balances these two factors. The final results show that drone formation 3, with its task allocation unchanged, receives fewer drones. This is because drone formation 1's task allocation changed, altering its resource availability. This demonstrates the cooperative nature of the algorithm in allocating drone numbers.

[0111] Figure 12 and Figure 13 The results of different algorithms for assigning 10 drones (8 and 10 drones in total) to a drone formation at 3 takeoff points are shown. It can be seen that the simulated annealing algorithm is significantly affected by initialization. Furthermore, the simulated annealing algorithm is prone to getting trapped in local optima, quickly converging to a small reward value after the same number of iterations. Compared with other algorithms, its optimization results are clearly worse. The proposed algorithm, combined with the simulated annealing algorithm, converges to a more refined value compared to the traditional genetic algorithm. The simulated annealing algorithm enhances the algorithm's optimization ability, enabling it to better escape local optima.

[0112] Figure 14 The graphs show the payoff results for different numbers of drones under two different weightings. Regardless of the weighting values, as the number of drones increases, the curve first increases to a maximum value and then decreases. The increase in utility reflects the advantages of cooperation, while the decrease in utility reflects that the cost of cooperation outweighs the benefits. Furthermore, the ξ value represents the importance of energy consumption; a higher ξ value indicates more energy consumed during flight. A lower ξ value indicates lower energy consumption during cooperation, thus corresponding to a larger number of drones at the peak. The genetic simulated annealing algorithm shows more stable results and converges to a better value compared to the simulated annealing algorithm.

[0113] Figure 15This paper presents a comparison of algorithm stability under the same resource conditions, with the addition of a takeoff point. The existing 30M bandwidth is divided into 3 and 4 tiers, with 10 drones performing 8 tasks, and an additional takeoff point (drone formation) is added. The convergence results of the genetic simulated annealing algorithm and the simulated annealing algorithm are compared. It is clear that adding a takeoff point increases the number of tasks available to both drone formations and the simulated annealing algorithm, resulting in smaller initial values ​​and slower convergence. However, the added starting point reduces path loss, leading to a larger final reward. Compared to the traditional simulated annealing algorithm, the genetic simulated annealing algorithm converges faster, exhibits better global exploration and local search capabilities, and can search for optimal solutions over a large area of ​​the solution space. The algorithm's advantages become more pronounced with increasing complexity. The resource dispersion does not affect the increase in final reward, and the algorithm effectively plans tasks and resources based on different starting points.

[0114] This application studies the problem of UAV formation mission planning and spectrum resource allocation. By optimizing mission selection and sequence, UAV quantity planning, and bandwidth selection, the project maximizes the mission benefit function and achieves a reasonable balance between benefits and costs. Utilizing the coupling relationship between the variables to be optimized and benefits and energy consumption, the problem is transformed into mission network benefit optimization, and a hybrid genetic and simulated annealing algorithm is designed. First, the global search capability of the genetic algorithm is used to generate widely distributed candidate solutions. Then, the concentrated search characteristic of the simulated annealing algorithm is used for local re-search to obtain the final, better solution. The proposed algorithm can plan the target perception sequence, spectrum selection level, and UAV formation size for each UAV based on changes in mission load and the setting of UAV takeoff points. Simulation results demonstrate the effectiveness of the proposed algorithm, which maximizes the mission network benefit function, balances the relationship between benefits and energy consumption, and achieves better system performance. Future work will consider dynamically planning UAV formations and spectrum resources in response to mission changes to cope with complex and ever-changing battlefield environments.

[0115] Based on the same inventive concept, this application also provides a UAV swarm formation configuration and spectrum resource joint optimization system for implementing the aforementioned UAV swarm formation configuration and spectrum resource joint optimization method. The solution provided by this system is similar to the implementation scheme described in the above method. Therefore, the specific limitations of one or more UAV swarm formation configuration and spectrum resource joint optimization system embodiments provided below can be found in the limitations of the UAV swarm formation configuration and spectrum resource joint optimization method described above, and will not be repeated here.

[0116] In one exemplary embodiment, a joint optimization system for drone swarm formation configuration and spectrum resources is provided, comprising:

[0117] The optimization problem model construction module is used to dispatch multiple drone formations to perform multiple tasks under the condition of given spectrum resources and a limited number of drones. It constructs an optimization problem model by utilizing the coupling relationship between the number of drone formations, the target perception order, and the spectrum resource allocation; wherein, the target perception order is the order in which each drone formation performs its tasks; one target is executed by one drone formation.

[0118] An optimal UAV swarm formation configuration and spectrum resource joint optimization scheme output module is used to solve the optimization problem model using an improved genetic algorithm and output the optimal UAV swarm formation configuration and spectrum resource joint optimization scheme. The improved genetic algorithm embeds a simulated annealing algorithm, adjusts the crossover operator, and introduces an elitist strategy and a dynamically adjustable mutation rate in the mutation operation. Adjusting the crossover operator ensures the correctness of offspring while inheriting characteristics from different parents, avoiding the omission and duplication of targets. The elitist strategy preserves the best individuals directly into the next generation without crossover and mutation operations. The dynamically adjustable mutation rate is used to dynamically adjust the mutation rate based on the operation of the improved genetic algorithm, and is used to explore the solution space and adjust the solution. The simulated annealing algorithm accepts poor solutions at high temperatures and gradually converges to the optimal solution at low temperatures. The optimal solution is the optimal UAV swarm formation configuration and spectrum resource joint optimization scheme.

[0119] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal. The computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is connected to the system bus via the I / O interfaces. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database of the computer device stores UAV swarm formation configuration and spectrum resource joint optimization data. The I / O interfaces of the computer device are used for exchanging information between the processor and external devices. The communication interface of the computer device is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for UAV swarm formation configuration and spectrum resource joint optimization.

[0120] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the methods described above.

[0121] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the methods described above.

[0122] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the methods described above.

[0123] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0124] This application uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. In summary, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for joint optimization of UAV cluster formation and spectrum resource, characterized in that, The unmanned aerial vehicle cluster formation configuration and spectrum resource joint optimization method comprises: Under the condition of given spectrum resources and limited number of unmanned aerial vehicles, a plurality of unmanned aerial vehicle formations are dispatched to perform a plurality of tasks, and an optimization problem model is constructed by utilizing the coupling relationship of the number of unmanned aerial vehicle formations, target sensing sequence and spectrum resource allocation; wherein the target sensing sequence is the execution task sequence of each unmanned aerial vehicle formation; one target is executed by one unmanned aerial vehicle formation; and the optimization problem model is: wherein, is a total utility function; is a task sequence number assigned to the formation ; is a total number of unmanned aerial vehicle formations; is a completion probability of a task completed by an unmanned aerial vehicle; is a number of unmanned aerial vehicles of an unmanned aerial vehicle formation ; is a value quantity of a task; is a weight coefficient of hovering loss; is a power consumption of an unmanned aerial vehicle when hovering; is a fixed reconnaissance time of a task , is an information data quantity to be transmitted for a task ; is a bandwidth of an unmanned aerial vehicle formation ; is a transmission power of an unmanned aerial vehicle; is a distance from a task point to an airport of an unmanned aerial vehicle formation ; is a distance ; is a channel power gain, ; is an environmental noise power spectral density; is a weight coefficient of path loss; is a flight speed at which an unmanned aerial vehicle cruises the farthest distance; is a time for an unmanned aerial vehicle formation to traverse a task point; is a task executed by an unmanned aerial vehicle formation ; is a formation sequence number of an unmanned aerial vehicle; is a total number of tasks; is a number of assignable unmanned aerial vehicles; is a maximum range of an unmanned aerial vehicle; X n is a formation sequence number of a task; is a total number of assignable unmanned aerial vehicles; is a total bandwidth of an unmanned aerial vehicle formation; C1 indicates that one formation corresponds to each task; C2 indicates that all tasks are executed by unmanned aerial vehicle formations; C3 indicates that the sum of unmanned aerial vehicles of each formation is the number to be assigned; C4 indicates that the range of each formation is less than a limited value; C5 indicates that unmanned aerial vehicles are assigned to each formation; and C6 indicates that the sum of bandwidths of each formation is the existing bandwidth. An improved genetic algorithm is used to solve the optimization problem model, and an optimal unmanned aerial vehicle cluster formation configuration and spectrum resource joint optimization scheme is output; wherein the improved genetic algorithm is a simulated annealing algorithm embedded in a genetic algorithm, and the crossover operator of the genetic algorithm is adjusted, and an elite strategy and a dynamically adjustable mutation rate are introduced in the mutation operation; the elite strategy is used to retain the optimal individual to directly enter the next generation without going through the crossover operation and mutation operation; the dynamically adjustable mutation rate is used to dynamically adjust the mutation rate according to the running condition of the improved genetic algorithm, and the mutation rate is used to explore the solution space and adjust the solution; the simulated annealing algorithm is used to accept a poor solution at a high temperature stage and gradually converge to an optimal solution from a poor solution at a low temperature stage; the optimal solution is the optimal unmanned aerial vehicle cluster formation configuration and spectrum resource joint optimization scheme; and the poor solution is a solution with a worse quality than the current solution.

2. The method of claim 1, wherein, Any drone formation The total distance Is: The total distance of all drone formations is in, Indicates drone formation The distance from the airport to the first selected mission point This indicates that the last task point has been added to the team. airport The distance; To be assigned to drone formations Total number of tasks; Indicates drone formation The selected number Task points To the Task points The distance; Indicates drone formation The number of drones in the country; N This represents the total number of drones in the formation.

3. The method of claim 1, wherein, An improved genetic algorithm is used to solve the optimization problem model, and an optimal unmanned aerial vehicle cluster formation configuration and spectrum resource joint optimization scheme is output, specifically comprising: The method comprises the following steps: initializing a first generation of individuals by adopting a chromosome to initialize a UAV formation for performing a task; wherein the chromosome comprises four lengths, a first length of the four lengths is chromosomes represent the perception order of each target, a second length of the four lengths is chromosomes represent the task assigned to each airport, a third length of the four lengths is chromosomes represent the number of UAVs in each UAV formation, and a fourth length of the four lengths is chromosomes represent the bandwidth allocated to each UAV formation. An elite strategy is introduced to select the optimal individual from the first generation of individuals to directly serve as the next generation of individuals without going through the crossover operation and mutation operation; After the first generation of individuals undergoes the crossover operation, mutation operation and unmanned aerial vehicle mileage limitation in turn, the next generation of individuals is generated, and in combination with the optimal individual, a new generation of individuals is generated; wherein the unmanned aerial vehicle mileage limitation is used to perform feasibility processing on the new scheme generated after the crossover operation and mutation operation, and to judge the mileage of each unmanned aerial vehicle formation performing a task; The new generation of individuals is used as the initial solution of the simulated annealing algorithm, and the fitness of the initial solution is evaluated; Based on the fitness of the initial solution, the new generation of individuals is iteratively trained until the maximum number of iterations is reached, and an optimal unmanned aerial vehicle cluster formation configuration and spectrum resource joint optimization scheme is output.

4. The method of claim 3, wherein, Based on the fitness of the initial solution, the new generation of individuals is iteratively trained until the maximum number of iterations is reached, and an optimal unmanned aerial vehicle cluster formation configuration and spectrum resource joint optimization scheme is output, specifically comprising: Based on the fitness of the initial solution, it is judged whether the temperature of this iteration reaches the termination temperature or whether the maximum number of iterations is reached, and a first judgment result is obtained; If the first judgment result is yes, the optimal unmanned aerial vehicle cluster formation configuration and spectrum resource joint optimization scheme is output; If the first judgment result is no, a neighborhood solution is generated, and the fitness of the neighborhood solution is evaluated; It is judged whether the fitness of the neighborhood solution is better than the fitness of the initial solution, and a second judgment result is obtained; if the second determination result is no, accepting the new solution with a probability accepting the neighborhood solution, if a fitness of the new solution is better than a fitness of the current solution, then accepting the new solution; if the fitness of the new solution is not better than the fitness of the current solution, then accepting the new solution with a probability accepting the new solution; wherein, is a fitness of the neighborhood solution; is a fitness of the initial solution; T is the current temperature. 5.A system for joint optimization of UAV cluster formation and spectrum resource, characterized in that, The unmanned aerial vehicle cluster formation configuration and spectrum resource joint optimization system executes the unmanned aerial vehicle cluster formation configuration and spectrum resource joint optimization method of any one of claims 1-4, and the unmanned aerial vehicle cluster formation configuration and spectrum resource joint optimization system comprises: An optimization problem model construction module is configured to, under the condition of given spectrum resources and a limited number of unmanned aerial vehicles, dispatch multiple unmanned aerial vehicle formations to perform multiple tasks, and construct an optimization problem model by utilizing the coupling relationship of the number of unmanned aerial vehicle formations, target sensing order, and spectrum resource allocation; wherein the target sensing order is the execution task order of each unmanned aerial vehicle formation performing a task; and one target is performed by one unmanned aerial vehicle formation. An optimal unmanned aerial vehicle cluster formation configuration and spectrum resource joint optimization scheme output module is configured to solve the optimization problem model by utilizing an improved genetic algorithm, and output an optimal unmanned aerial vehicle cluster formation configuration and spectrum resource joint optimization scheme; wherein the improved genetic algorithm is an algorithm in which a simulated annealing algorithm is embedded in a genetic algorithm, and the crossover operator of the genetic algorithm is adjusted, and an elite strategy and a dynamically adjustable mutation rate are introduced in the mutation operation; the adjustment of the crossover operator of the genetic algorithm can inherit different parent characteristics while ensuring the correctness of the offspring; the elite strategy is used to retain the optimal individual to directly enter the next generation without going through the crossover operation and the mutation operation; the dynamically adjustable mutation rate is used to dynamically adjust the mutation rate according to the running condition of the improved genetic algorithm, and the mutation rate is used to explore the solution space and adjust the solution; the simulated annealing algorithm is used to accept a poor solution at a high temperature stage and gradually converge to an optimal solution from a poor solution at a low temperature stage; and the optimal solution is the optimal unmanned aerial vehicle cluster formation configuration and spectrum resource joint optimization scheme.

6. A computer device comprising: A memory and a processor to store a computer program stored on the memory and executable on the processor, characterized in that the processor executes the computer program to implement the unmanned aerial vehicle cluster formation configuration and spectrum resource joint optimization method of any one of claims 1-4.

7. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the unmanned aerial vehicle cluster formation configuration and spectrum resource joint optimization method of any one of claims 1-4.

8. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the unmanned aerial vehicle cluster formation configuration and spectrum resource joint optimization method of any one of claims 1-4. The computer program is executed by the processor to implement the unmanned aerial vehicle cluster formation configuration and spectrum resource joint optimization method of any one of claims 1-4.

Images