Unmanned cluster networking equipment resource allocation method, device and storage medium

Abstract

The present invention relates to an unmanned cluster networking equipment resource allocation method, device and storage medium, the method comprising the following steps: based on a multi-to-multi confrontation mission scenario between an unmanned cluster networking and an enemy defense system, constructing an unmanned cluster mission benefit function, a cost loss function, a confrontation cost function and an enemy defense system damage function; comprehensively considering the performance differences and cost-effectiveness of a variety of weapon systems, constructing an unmanned cluster networking equipment resource allocation model by adjusting weight coefficients and introducing additional items for specific mission requirements; using a differential genetic algorithm to solve the unmanned cluster networking equipment resource allocation model to obtain an optimal weapon resource allocation strategy. Compared with the prior art, the present invention comprehensively considers a variety of complex factors, can quickly generate an optimal or near-optimal equipment resource allocation plan, and significantly improves the overall combat effectiveness and mission success rate of the unmanned cluster.

Description

Technical Field

[0001] The present invention belongs to the technical field of resource allocation, and in particular relates to a method, device and storage medium for allocating resources of unmanned cluster networking equipment based on a differential genetic algorithm. Background Art

[0002] Unmanned swarms, with their highly coordinated, flexible, and intelligent decision-making capabilities, are able to perform complex and varied tasks, such as regional surveillance, target tracking, and material delivery. However, in the process of networking unmanned swarms, the rational allocation of equipment resources is a crucial link, which is directly related to the overall combat effectiveness and mission success rate of the unmanned swarm. The equipment resource allocation problem is often highly complex and dynamic, and traditional resource allocation methods are difficult to meet actual needs. Therefore, an efficient and intelligent optimization algorithm is needed to guide the equipment resource allocation of unmanned swarms.

[0003] In the field of unmanned swarm equipment resource allocation, a series of important research results have been achieved at home and abroad. The paper "Multi-stage attack weapon target allocation method based on defense area analysis" (Zheng J, Fa L, Hang W. Journal of Systems Engineering and Electronics, 2020, 31(3): 539-550.) innovatively proposed a multi-stage weapon allocation strategy based on coverage status and number of layers for the target defense area, and confirmed its significant effect of weakening defense and improving efficiency through Monte Carlo simulation, opening up a new path for weapon allocation strategy. The paper "A hybrid multi-objective bi-level interactive fuzzy programming method for solving ECM-DWTA problem" (Zhao L, An Z, Wang B, et al. Complex & Intelligent Systems, 2022, 8(6): 4811-4829.) focuses on the dynamic allocation of weapon targets. From the dual perspectives of global and local optimization of operations, a hybrid multi-objective bi-level programming model that integrates the sum of electronic jamming effects and combat consumption is constructed, and a hybrid multi-objective bi-level interactive fuzzy programming algorithm is innovatively proposed. However, existing literature mostly focuses on electromagnetic energy or kinetic energy single weapon resources to counter radar, which has strategic limitations. In order to break through this limitation, it is urgent to design a new optimization algorithm that can not only process continuous variables but also effectively solve discrete decision allocation problems, so as to accurately formulate the optimal weapon resource allocation plan. Summary of the invention

[0004] The purpose of the present invention is to provide an efficient and intelligent unmanned cluster networking equipment resource allocation method based on differential genetic algorithm, which combines the advantages of differential evolution and genetic algorithm, can comprehensively consider a variety of complex factors, and quickly generate optimal or near-optimal equipment resource allocation plans, thereby significantly improving the overall combat effectiveness and mission success rate of unmanned clusters.

[0005] The purpose of the present invention can be achieved by the following technical solutions:

[0006] A method for allocating resources of unmanned cluster networking equipment based on differential genetic algorithm comprises the following steps:

[0007] Based on the many-to-many confrontation mission scenario between unmanned swarm networking and the enemy's defense system, the unmanned swarm mission benefit function, cost loss function, confrontation cost function and enemy defense system damage function are constructed;

[0008] Taking into account the performance differences and cost-effectiveness of various weapon systems, by adjusting the weight coefficients and introducing additional items for specific mission requirements, an objective function is established based on the unmanned swarm mission benefit function, cost loss function, confrontation cost function, and enemy defense system damage function, and a resource allocation model for unmanned swarm networking equipment is constructed;

[0009] A differential genetic algorithm is used to solve the unmanned cluster networking equipment resource allocation model to obtain the optimal weapon resource allocation strategy.

[0010] Furthermore, the weapon system includes jamming attack weapons, kinetic strike weapons and network attack weapons.

[0011] Furthermore, the objective function of the unmanned cluster networking equipment resource allocation model is expressed as:

[0012]

[0013] in, represents the weight coefficient, is the total number of jamming attack decisions made by the unmanned swarm in each iteration according to specific mission requirements, is the unmanned cluster task profit function, is the cost loss function, To be the adversarial cost function, is the enemy defense system damage function.

[0014] Furthermore, the total number of interference attack decisions Set to 0.

[0015] Furthermore, the constraint conditions of the unmanned cluster networking equipment resource allocation model include a first constraint, a second constraint, a third constraint, a fourth constraint and a fifth constraint.

[0016] The first constraint is expressed as:

[0017]

[0018] The second constraint is expressed as:

[0019]

[0020] The third constraint is expressed as:

[0021]

[0022] The fourth constraint is expressed as:

[0023]

[0024] The fifth constraint is expressed as:

[0025]

[0026] The first constraint indicates that an unmanned individual can only be equipped with one weapon from the jamming attack or kinetic strike, and the second constraint indicates that an unmanned individual can only have a maximum of one jamming attack at a time. enemy defense systems, and the third constraint states that an enemy defense system requires at most The fourth constraint states that an unmanned individual can only interfere with The fifth constraint indicates that the upper limit of the number of unmanned units equipped with kinetic strike equipment is ; Indicated in Moment Does an unmanned individual have any The decision of configuring electromagnetic interference or cyber attack weapons for an enemy defense system is 1 if adopted, otherwise 0; Indicated in Moment Does an unmanned individual have any The decision of equipping an enemy defense system with kinetic strike weapon resources is 1 if adopted, otherwise 0; represents the number of unmanned clusters, Indicates the number of enemy defense systems.

[0027] Furthermore, when using the differential genetic algorithm to solve the unmanned cluster networking equipment resource allocation model, based on the number of unmanned individuals in the unmanned cluster and the number of enemy defense systems, the decision variables for configuring different weapon systems for each unmanned individual are integrated to form a decision matrix as the population individual in the differential genetic algorithm. The size of the decision matrix is , represents the number of unmanned clusters, Represents the number of enemy defense systems, and each element of the decision matrix is ​​either 0 or 1.

[0028] Furthermore, when the differential genetic algorithm is used to solve the unmanned cluster networking equipment resource allocation model, the optimal decision obtained by iterative solution is discretized and converted into a 0-1 matrix.

[0029] Furthermore, the optimal decision is discretized using a Tanh activation function.

[0030] The present invention also provides an electronic device, comprising one or more processors, a memory and one or more programs stored in the memory, wherein the one or more programs include instructions for executing the unmanned cluster networking equipment resource allocation method as described above.

[0031] The present invention also provides a computer-readable storage medium, comprising one or more programs for execution by one or more processors of an electronic device, wherein the one or more programs include instructions for executing the unmanned cluster networking equipment resource allocation method as described above.

[0032] Compared with the prior art, the present invention has the following beneficial effects:

[0033] 1. The present invention comprehensively considers the performance differences and cost-effectiveness of various weapons, and by adjusting the weight coefficients and introducing additional items for specific mission requirements, the UAV cluster can maximize the combat effectiveness and minimize the cost in different combat phases and when facing different threats. It can flexibly adjust the resource allocation strategy according to the real-time data feedback during the mission execution process, so that the resource allocation process has dynamic adjustment capabilities, ensuring that the unmanned cluster always maintains the best combat state, which is of great significance to the future development of unmanned combat technology.

[0034] 2. The present invention adopts a differential genetic algorithm that combines the advantages of differential evolution and genetic algorithm. By improving the selection crossover mutation operation in the genetic algorithm and adopting the Tanh activation function discretization processing, the accuracy and efficiency of resource allocation of unmanned cluster equipment are effectively improved, ensuring that in a complex and changeable battlefield environment, accurate optimal resource allocation plans can be quickly obtained, thereby significantly enhancing the combat effectiveness of unmanned clusters and the success rate of mission execution. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a flow chart of the resource allocation method of unmanned cluster networking equipment based on differential genetic algorithm in the present invention;

[0036] Figure 2 It is a schematic diagram of a many-to-many confrontation task between an unmanned swarm network and an enemy defense system in the present invention;

[0037] Figure 3 It is a schematic diagram of the position coordinates of the unmanned cluster and the enemy defense system in the present invention;

[0038] Figure 4 It is a schematic diagram of the change of the fitness function value with the number of iterations and the optimal decision position in the present invention. DETAILED DESCRIPTION

[0039] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. This embodiment is implemented based on the technical solution of the present invention, and provides a detailed implementation method and specific operation process, but the protection scope of the present invention is not limited to the following embodiments.

[0040] refer to Figure 1 As shown, this embodiment provides a method for allocating resources of unmanned cluster networking equipment based on a differential genetic algorithm, comprising the following steps:

[0041] S1. Based on the multi-to-multi confrontation mission scenario between unmanned swarm networking and the enemy's defense system, the unmanned swarm mission benefit function, cost loss function, confrontation cost function and enemy defense system damage function are constructed;

[0042] S2. Comprehensively considering the performance differences and cost-effectiveness of three weapon systems, namely electromagnetic interference, kinetic strike and cyber attack, by adjusting the weight coefficient and introducing additional items for specific mission requirements, an objective function is established based on the unmanned swarm mission benefit function, cost loss function, confrontation cost function and enemy defense system damage function, and a resource allocation model for unmanned swarm networking equipment is constructed;

[0043] S3. A differential genetic algorithm combining differential evolution and genetic algorithm is used to optimize and solve the unmanned cluster networking equipment resource allocation model, aiming to search for a weapon resource allocation strategy that maximizes the combat effectiveness and minimizes the cost of the unmanned aerial vehicle cluster in different combat phases and when facing different threats.

[0044] In this embodiment, the multi-to-multi confrontation mission scenario between the unmanned cluster network and the enemy defense system is as follows: Figure 2 shown. Figure 2In the process, the unmanned swarm formation starts from the starting point and faces the close monitoring and tracking of the enemy's defense system on the way to the target point. It makes full use of three weapons: electromagnetic interference, kinetic strikes and network attacks to enhance the survivability and combat effectiveness of the unmanned swarm in a complex battlefield environment.

[0045] In this embodiment, in order to comprehensively consider the combat effectiveness of different weapon confrontations, the performance and cost functions corresponding to the three weapon confrontations of electromagnetic interference, kinetic strikes and network attacks are designed respectively. The unmanned swarm mission benefit function, cost loss function, confrontation cost function and enemy defense system damage function are constructed as follows:

[0046] Step 2-1: Construct the unmanned cluster task profit function as follows:

[0047] (1)

[0048] in, represents the number of unmanned individuals in the unmanned cluster, represents the number of enemy defense systems, Indicates The value of an individual Indicated in Moment Does an unmanned individual have any The decision of configuring electromagnetic interference or network attack equipment for an enemy defense system is 1 if adopted, otherwise 0. Indicated in Moment The enemy's defense system The detection probability of an unmanned individual is Indicated in Moment No individual The probability of interference or attack of an enemy defense system and satisfying By maximizing the function , to minimize the detection value of the enemy's defense system to our unmanned swarm.

[0049] Step 2-2: Construct the cost loss function as follows:

[0050] (2)

[0051] in, Indicates No individual The duration of each interference attack of the enemy defense system is determined by minimizing the function , achieving the lowest interference attack cost of our unmanned swarm equipped with electromagnetic interference or network attack equipment.

[0052] Step 2-3: Construct the adversarial cost function as follows:

[0053] (3)

[0054] in, Indicated in Moment Does an unmanned individual have any The decision of whether an enemy defense system is equipped with kinetic strike weapon resources is taken, and its value is 1 if adopted, otherwise it is 0. Indicates Does an unmanned individual have any The probability of a kinetic attack on an enemy defense system causing damage to itself is minimized by , achieving the lowest strike cost for our unmanned swarm equipped with kinetic strike equipment.

[0055] Step 2-4: Construct the enemy defense system damage function as follows:

[0056] (4)

[0057] in, Indicates The value of an enemy defense system, Indicates No individual The probability of a successful attack on an enemy defense system, Indicates No individual The probability of successful destruction of an enemy defense system is calculated by maximizing the function , to maximize the strike effect of our unmanned cluster equipped with kinetic strike equipment.

[0058] The above functions comprehensively consider the mission benefits, cost losses, confrontation costs and enemy damage, which can comprehensively evaluate the performance of unmanned swarms in confrontation tasks and ensure the scientificity and rationality of resource allocation plans.

[0059] In this embodiment, based on the multiple functions defined above, the objective function of the unmanned swarm networking equipment resource allocation model is constructed, as shown in formula (5). It comprehensively considers the performance differences and cost-effectiveness of the three weapon systems of electromagnetic interference, kinetic strike and network attack, and allows the weapon resource allocation preferences of the unmanned aerial vehicle swarm to be flexibly set in different combat phases and facing different threats by adjusting the weight coefficient and introducing additional items for specific mission requirements.

[0060] (5)

[0061] in, represents the weight coefficient, The total number of jamming attack decisions made by the unmanned swarm in each iteration according to the specific mission requirements. No special requirements General settings When the battlefield situation requires avoiding the use of kinetic strike strategies, The value of further increases the proportion of the unmanned cluster task benefit function, achieving the effect that the unmanned cluster is equipped with more electromagnetic interference or network attack equipment. In a specific implementation, D ≥ 0, which needs to be adjusted according to specific circumstances.

[0062] Any unmanned individual can only be equipped with one of the two equipments, interference attack or strike, because the two countermeasures are mutually exclusive, that is, when the interference attack decision is selected, the strike decision is invalid. When the strike decision is selected, the interference attack decision is invalid. In addition, the weapons and equipment of the unmanned swarm are also limited by environmental resources. In summary, the above objective function needs to be subject to some constraints in the actual task context, as shown in formula (6):

[0063] (6)

[0064] The above formula (6) contains the first constraint, the second constraint, the third constraint, the fourth constraint and the fifth constraint. The first constraint (i.e., the first formula) indicates that an unmanned individual can only be equipped with one weapon from interference attack or momentum strike. The second constraint (i.e., the second formula) indicates that an unmanned individual can have at most interference attack enemy defense systems, the third constraint (i.e. the third formula) indicates that an enemy defense system requires at most The fourth constraint (i.e., the fourth formula) indicates that an unmanned individual can interfere with at most The fifth constraint (the last equation) indicates that the upper limit of the number of unmanned units equipped with kinetic strike equipment is , this parameter needs to be adjusted in real time according to the battlefield situation.

[0065] In this embodiment, a differential genetic algorithm combining differential evolution and genetic algorithm ideas is used to solve the unmanned cluster networking equipment resource allocation model constructed above. The specific solution process includes:

[0066] Step 4-1: In order to solve the complex resource allocation problem, a differential genetic algorithm that integrates the ideas of differential evolution and genetic algorithm is proposed. This algorithm integrates the selection, crossover and mutation mechanisms of the genetic algorithm, and draws on the differential mutation strategy of differential evolution. It aims to search for weapon resource allocation strategies that maximize the combat effectiveness and minimize the cost of unmanned swarms in different combat phases and when facing different threats. First, the decision variables for equipping three types of weapons and equipment are integrated to form a decision matrix An example of is shown in formula (7), where the first three columns are the decision sub-matrices for configuring electromagnetic interference weapons, the fourth to sixth columns are the decision sub-matrices for configuring network attack weapons, and the last three columns are the decision sub-matrices for configuring kinetic strike weapons. Specifically, Line If the elements of the column are , then it means An unmanned individual equipped with an electromagnetic jammer attacked enemy defense system; if the element is , then it means The unmanned entity was not equipped with electromagnetic interference weapons to attack the Each row of the decision matrix corresponds to each unmanned individual, and each column of the matrix on the left and right of each dotted line corresponds to each enemy defense system.

[0067] (7)

[0068] The equipment resource allocation plan shown in the above example matrix is ​​that the first unmanned individual is equipped with electromagnetic interference weapons to interfere with the first enemy defense system, the second unmanned individual is equipped with network attack weapons to attack the first and second enemy defense systems, and the third unmanned individual is equipped with kinetic strike weapons to attack the second enemy defense system.

[0069] Step 4-2: Introduce the mutation and crossover mechanism of differential evolution into the genetic algorithm to enhance its search capability. Compared with the traditional genetic algorithm, it has faster convergence speed, relative insensitivity to parameter settings, easy implementation, advantages in continuous optimization problems and high-dimensional problems, strong robustness and good parallel processing capabilities. The following is a detailed description of the iterative update steps of the differential evolution algorithm.

[0070] Step 4-2-1: Population initialization: Randomly generate initial population ,in is the population size, It is The initial solution of an individual.

[0071] Step 4-2-2: Mutation operation: In the differential genetic algorithm, the mutation operation adopts the differential mutation method. This mutation method does not simply randomly change the gene value of an individual, but uses the difference information of other individuals in the population to generate a mutation vector. Specifically, for each individual , select the best solution in the current population and two random solutions and , and then generate a mutation vector according to formula (8). This mutation vector not only contains the information of the optimal solution, but also incorporates the difference information of other individuals in the population, which may guide the search process to move to a better solution space. Scaling factor It is used to control the degree of amplification of this difference information, and its size will affect the exploration range and search efficiency of the mutation vector.

[0072] (8)

[0073] in, is a scaling factor, usually a positive real number, used to control the magnification ratio of the difference vector. satisfy .

[0074] Step 4-2-3: Crossover operation: In differential genetic algorithms, crossover operation is usually used in combination with mutation operation to generate test vectors. This algorithm uses a standard binary crossover operation to convert the mutation vector and the target vector Mix some genes to generate test vectors , as shown in formula (9).

[0075] (9)

[0076] in, is the dimension index of the solution, express No. Quantity, is the crossover probability, controlling the probability of the mutation vector being accepted, is a random number between 0 and 1, is a randomly chosen index between 1 and D, where D is the dimension of the solution.

[0077] Step 4-2-4: Selection operation: In the differential genetic algorithm, the selection is performed by comparing fitness, i.e., “greedy selection”. Specifically, for each individual , generate a test vector , and compare the fitness of the two and If the fitness of the test vector is better, then the test vector is selected Enter the next generation population; otherwise, retain the original individual This selection method ensures that the currently known optimal solution is always retained in the population, while allowing new and potentially better solutions to be generated and enter the population through mutation and crossover operations. The specific method is shown in formula (10).

[0078] (10)

[0079] in, is the fitness function, which is the objective function in equation (5) and is used to evaluate the quality of the solution.

[0080] Step 4-2-5: Repeat steps 4-2-2 to 4-2-4 until the stop condition is met.

[0081] Step 4-3: Finally, due to the iterative decision obtained in step 4-2 The elements in may not be discrete values, so the Tanh activation function is used to discretize them, as shown in formula (11).

[0082] (11)

[0083] in, Representation Matrix No. Line Column elements. This activation function can continuously map all real numbers to intervals within, will After the element is activated, according to the rounding principle, if the new value is greater than or equal to , then the value is 1. If the new value is between -1 and 0.5, then the value is 0.

[0084] If the above method is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.

[0085] The above method is simulated and verified: Consider a multi-to-multi confrontation task scenario between an unmanned swarm network and an enemy defense system. The total number of individuals in the unmanned swarm is 6, and the number of enemy defense systems is 2. Their coordinate positions are as follows: Figure 3 As shown. One of the defense systems has a strong defense capability and is not easily disturbed by the outside world, while the other defense system has a normal value. The triangle is the location of the enemy's defense system, and the circle is the location of our unmanned individual. For convenience, it is assumed that the value of each unmanned individual is the same and is not limited by the number of kinetic weapons. By running the differential evolution algorithm, the optimal equipment allocation scheme is searched. The parameters of the unmanned cluster networking equipment resource allocation model used in the simulation are shown in Table 1. After 10,000 iterations, the optimal decision matrix is ​​obtained through discretization processing. , as shown in formula (12).

[0086] (12)

[0087] It can be seen from the optimal decision matrix that our unmanned cluster is mainly equipped with kinetic strike devices for the first enemy defense system with higher value, and mainly equipped with electromagnetic interference and network attack devices for the other enemy defense system.

[0088] Table 1 Parameter settings of the unmanned cluster networking equipment resource allocation model

[0089]

[0090] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0091] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0092] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0093] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0094] The preferred specific embodiments of the present invention are described in detail above. It should be understood that a person skilled in the art can make many modifications and changes based on the concept of the present invention without creative work. Therefore, any technical solution that can be obtained by a person skilled in the art through logical analysis, reasoning or limited experiments based on the concept of the present invention on the basis of the prior art should be within the scope of protection determined by the claims.

Claims

1. A method for allocating resources of unmanned cluster networking equipment based on differential genetic algorithm, characterized in that: The following steps are involved: Based on the many-to-many confrontation mission scenario between unmanned swarm networking and the enemy's defense system, the unmanned swarm mission benefit function, cost loss function, confrontation cost function and enemy defense system damage function are constructed; Taking into account the performance differences and cost-effectiveness of various weapon systems, by adjusting the weight coefficients and introducing additional items for specific mission requirements, an objective function is established based on the unmanned swarm mission benefit function, cost loss function, confrontation cost function, and enemy defense system damage function, and a resource allocation model for unmanned swarm networking equipment is constructed; A differential genetic algorithm is used to solve the unmanned cluster networking equipment resource allocation model to obtain the optimal weapon resource allocation strategy; The objective function of the unmanned cluster networking equipment resource allocation model is expressed as: ， in, represents the weight coefficient, D is the total number of jamming attack decisions made by the unmanned swarm in each iteration according to specific mission requirements, is the unmanned cluster task profit function, is the cost loss function, To be the adversarial cost function, is the enemy defense system damage function; The constraint conditions of the unmanned cluster networking equipment resource allocation model include a first constraint, a second constraint, a third constraint, a fourth constraint and a fifth constraint. The first constraint is expressed as: ， The second constraint is expressed as: ， The third constraint is expressed as: ， The fourth constraint is expressed as: ， The fifth constraint is expressed as: ， The first constraint indicates that an unmanned individual can only be equipped with one weapon from the jamming attack or kinetic strike, and the second constraint indicates that an unmanned individual can only have a maximum of one jamming attack at a time. enemy defense systems, and the third constraint states that an enemy defense system requires at most The fourth constraint states that an unmanned individual can only interfere with The fifth constraint indicates that the upper limit of the number of unmanned units equipped with kinetic strike equipment is ; Indicated in t Moment n Does an unmanned individual have any m The decision of configuring electromagnetic interference or cyber attack weapons for an enemy defense system is 1 if adopted, otherwise 0; Indicated in t Moment n Does an unmanned individual have any m The decision of equipping an enemy defense system with kinetic strike weapon resources is 1 if adopted, otherwise 0; N represents the number of unmanned clusters, M Indicates the number of enemy defense systems.

2. The method for allocating resources of unmanned cluster networking equipment based on differential genetic algorithm according to claim 1 is characterized in that: The weapon system includes jamming attack weapons, kinetic strike weapons and network attack weapons.

3. The method for allocating resources of unmanned cluster networking equipment based on differential genetic algorithm according to claim 1, characterized in that: The total number of interference attack decisions D Set to 0.

4. The unmanned cluster networking equipment resource allocation method based on differential genetic algorithm according to claim 2 is characterized in that: When using the differential genetic algorithm to solve the unmanned cluster networking equipment resource allocation model, based on the number of unmanned individuals in the unmanned cluster and the number of enemy defense systems, the decision variables for configuring different weapon systems for each unmanned individual are integrated to form a decision matrix as the population individual in the differential genetic algorithm. The size of the decision matrix is , N represents the number of unmanned clusters, M Represents the number of enemy defense systems, and each element of the decision matrix is ​​either 0 or 1.

5. The method for allocating resources of unmanned cluster networking equipment based on differential genetic algorithm according to claim 4 is characterized in that: When the differential genetic algorithm is used to solve the unmanned cluster networking equipment resource allocation model, the optimal decision obtained by iterative solution is discretized and converted into a 0-1 matrix.

6. The method for allocating resources of unmanned cluster networking equipment based on differential genetic algorithm according to claim 5 is characterized in that: The optimal decision is discretized using the Tanh activation function.

7. An electronic device, characterized in that: It comprises one or more processors, a memory and one or more programs stored in the memory, wherein the one or more programs comprise instructions for executing the resource allocation method for unmanned cluster networking equipment as claimed in any one of claims 1-6.

8. A computer-readable storage medium, characterized in that: It includes one or more programs for execution by one or more processors of an electronic device, and the one or more programs include instructions for executing the unmanned cluster networking equipment resource allocation method as described in any one of claims 1-6.

Images