An optimization method, system, device, and storage medium for an edge warfare system.

Abstract

This invention discloses an optimization method, system, device, and storage medium for a periphery warfare system. The method includes constructing a function-dependent network model based on the functional types of the periphery warfare system; constructing system constraints based on the system resources of the periphery warfare system; constructing an optimization objective function for the periphery warfare system based on the function-dependent network model and system constraints; and solving the optimization objective function using a multi-group differential evolution algorithm to obtain the optimization result. This invention can provide a reference for the architecture design and resource optimization of periphery warfare systems, thereby improving the joint combat capability of the system.

Description

Technical Field

[0001] This invention relates to an optimization method, system, device, and storage medium for an edge warfare system, belonging to the field of automation technology. Background Technology

[0002] With the rapid development of network information technology and military technology, the scale and style of warfare have undergone profound changes. Warfare in the information age is dynamic, more uncertain, and harder to predict, rendering the traditional centralized command and control warfare model inapplicable. To address this, Zhang Weiming, Yang Dongsheng, and others proposed the concept of edge warfare in their article "Edge Rise: Background, Concept, and Model Mechanism Analysis of Edge C2." Edge warfare is a decentralized warfare style that achieves self-organization, self-action, and self-adaptation through mutual communication and coordination between weapon systems. The informationized battlefield situation updates at an accelerated pace, making the speed of battlefield situational awareness a core competitive factor. Various sensors and intelligent command and control systems not only independently perform basic combat functions but also interconnect, communicate, and interoperate to achieve situational awareness, collaborative positioning, joint command and control, and collaborative strike capabilities, thereby forming a system-wide joint combat capability. However, existing technologies still have shortcomings in addressing the above description. Summary of the Invention

[0003] The purpose of this invention is to overcome the shortcomings of the prior art and provide an optimization method, system, device and storage medium for edge warfare systems. The invention models and analyzes edge warfare systems and uses multiple group differential evolution algorithms to optimize the models in order to obtain the best combat architecture.

[0004] To achieve the above objectives, the present invention is implemented using the following technical solution:

[0005] In a first aspect, the present invention provides an optimization method for a perimeter warfare system, comprising:

[0006] Construct a function-dependent network model based on the functional types of the edge combat system;

[0007] System resource construction and system constraints based on edge warfare system;

[0008] An optimization objective function for edge warfare systems is constructed based on a functionally dependent network model and system constraints.

[0009] The optimization objective function is solved using a multi-group differential evolution algorithm to obtain the optimization results.

[0010] Optionally, the functional types include decision-making functions, reconnaissance functions, and strike functions; the decision-making functions include headquarters command and control functions and battlefield command and control functions; the reconnaissance functions include long-range reconnaissance functions, medium-range reconnaissance functions, and short-range reconnaissance functions; the strike functions include long-range strike functions, medium-range strike functions, short-range strike functions, and electronic attack functions.

[0011] Optionally, the construction of a function-dependent network model based on the functional types of the edge combat system includes:

[0012] Each function in the various functional types of the edge combat system is treated as a network node. The network nodes are connected by unidirectional arrows to generate a directed acyclic network, which is then used as a functionally dependent network model.

[0013] Optionally, the dependencies between the network nodes connected by the unidirectional arrows satisfy:

[0014] O j =min(SOD_O j COD_O j )

[0015] SOD_O j =Average(SOD_O j1 SOD_O j2 ,…,SOD_O jn )

[0016] SOD_O ji =α ij O i +(1-α ij SE j

[0017] COD_O j =min(COD_O j1 COD_O j2 ,…,COD_O jn )

[0018] COD_O j =O i +β ij

[0019] i = 1, 2, 3, ..., n

[0020] In the formula, O i O j Let α represent the operating performance of network nodes i and j, 'Average' be the average value function, 'n' be the number of network nodes, and α be the average value function. ij β ij SE represents the dependency strength and dependency criticality of network nodes i and j, respectively. jFor the active performance of network node j;

[0021]

[0022] In the formula, F(s) k ) for system s k The active energy efficiency that can be provided to network node j For the k-th system s k The number, K is the system s k The number of types.

[0023] Optionally, the system constraints are:

[0024] Budget constraints are:

[0025]

[0026] In the formula, K represents the system s k Quantity, For the k-th system s k Quantity, Cost(s) k ) for deploying system s k Budget, B d This is the budget threshold;

[0027] Quantity limit:

[0028] 0≤c≤Q k

[0029] In the formula, Q k The number of each system The threshold;

[0030] The communication bandwidth limit is:

[0031]

[0032] In the formula, Comm(s) k ) for system s k Consumed communication bandwidth, B w This is the communication bandwidth threshold.

[0033] Dependency parameters are restricted to:

[0034] α min <<α<<α max

[0035] β min <<β<<β max

[0036] In the formula, α min α max For the theoretical minimum and maximum values ​​of the dependence strength α, βmin β max These are the theoretical minimum and maximum values ​​depending on the criticality β;

[0037] The limits of fringe charges are:

[0038] 0 << SE C <<L

[0039] In the formula, SE C Let L be the active effectiveness of the network nodes corresponding to each function of the decision-making function, and SE be the active effectiveness. C The threshold.

[0040] Optionally, the optimization objective function is:

[0041]

[0042] P = D(B) d +B w )

[0043] In the formula, O x Let P be the operating performance of the network nodes corresponding to each function of function type x, and D be the penalty term and the penalty coefficient.

[0044] Optionally, the step of solving the objective function based on multiple group difference evolution algorithms to obtain the optimization result includes:

[0045] Initialize multiple populations and calculate the fitness of individuals in each population based on the optimization objective function;

[0046] Individuals with high fitness in various groups are selected as high-quality individuals based on the preset generation gap rate.

[0047] High-quality individuals are crossover, recombination, and mutation operations to produce offspring individuals;

[0048] Replace individuals with low fitness in each population with offspring individuals to generate each offspring population, and calculate the fitness of individuals in each offspring population based on the optimization objective function;

[0049] Based on the migration operator, the individual with the highest fitness in each offspring population replaces the individual with the lowest fitness in the next offspring population, thus updating each offspring population;

[0050] The individual with the highest fitness in each updated offspring population is selected as the elite individual based on manual operators;

[0051] Select the individuals with the highest fitness from the elite individuals and add them to the elite population;

[0052] Repeat the above steps until the preset maximum number of iterations is reached;

[0053] The individual with the highest fitness is selected from the elite population as the output optimization result;

[0054] Population I is:

[0055] I = [I1, I2, ..., I m ]

[0056] I r =[α r ,β r ,n r ], r = 1, 2, ..., m

[0057] α r =[α r,1 ,α r,2 ,…α r,l ]

[0058] β r =[β r,1 ,β r,2 ,…β r,l ]

[0059]

[0060] In the formula, I r Let r be an individual in the population, and α be an individual. r,l β r,l Let α be the dependency strength and β be the dependency criticality corresponding to the one-way arrow l for individual r, and l be the number of one-way arrows. For individual r, the Kth type of system s k The number, K is the system s k The number of types.

[0061] Secondly, the present invention provides an optimization system for a perimeter warfare system, the system comprising:

[0062] The model building module is used to build function-dependent network models based on the function types of the edge combat system;

[0063] The constraint construction module is used to construct system constraints based on system resources in the edge warfare system.

[0064] The function building module is used to construct the optimization objective function of the edge combat system based on the function-dependent network model and system constraints;

[0065] The optimization solution module is used to solve the optimization objective function and obtain the optimization results based on multiple group difference evolution algorithms.

[0066] Thirdly, the present invention provides an optimization device for an edge combat system, including a processor and a storage medium;

[0067] The storage medium is used to store instructions;

[0068] The processor is configured to operate according to the instructions to perform the steps according to the method described above.

[0069] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method.

[0070] Compared with the prior art, the beneficial effects achieved by the present invention are as follows:

[0071] This invention provides an optimization method, system, device, and storage medium for an edge warfare system. It constructs a functionally dependent network model, system constraints, and optimization objective function based on the edge warfare system. It employs multiple group differential evolution algorithms for efficient solution and provides a reference for edge warfare system architecture design and resource optimization based on the solution results, thereby improving the joint combat capability of the system. Attached Figure Description

[0072] Figure 1 This is a flowchart of an optimization method for an edge warfare system provided in Embodiment 1 of the present invention;

[0073] Figure 2 This is a flowchart of solving the objective function and obtaining the optimization result provided in Embodiment 1 of the present invention;

[0074] Figure 3 This is a schematic diagram of the structure of a function-dependent network model provided in Embodiment 1 of the present invention;

[0075] Figure 4 This is a graph showing the optimization process of network node I1 provided in Embodiment 1 of the present invention.

[0076] Figure 5 This is a graph showing the optimization process of network node I2 provided in Embodiment 1 of the present invention;

[0077] Figure 6 This is a graph showing the optimization process of network node I3 provided in Embodiment 1 of the present invention;

[0078] Figure 7 This is a graph showing the optimization process of network node I4 provided in Embodiment 1 of the present invention. Detailed Implementation

[0079] The present invention will be further described below in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solutions of the present invention and are not intended to limit the scope of protection of the present invention.

[0080] Example 1:

[0081] like Figure 1 As shown, this invention provides an optimization method for an edge warfare system, comprising the following steps:

[0082] 1. Construct a function-dependent network model based on the functional types of the edge combat system;

[0083] In this embodiment, (1) the functional types include decision-making function, reconnaissance function and strike function; the decision-making function includes headquarters command and control function and battlefield command and control function; the reconnaissance function includes long-range reconnaissance function, medium-range reconnaissance function and short-range reconnaissance function; the strike function includes long-range strike function, medium-range strike function, short-range strike function and electronic attack function.

[0084] (2) Constructing a function-dependent network model based on the functional types of the edge combat system includes:

[0085] Each function in the various functional types of the edge combat system is treated as a network node. The network nodes are connected by unidirectional arrows to generate a directed acyclic network, which is then used as a functionally dependent network model.

[0086] (3) The dependency relationships between network nodes connected by a one-way arrow satisfy the following:

[0087] O j =min(SOD_O j COD_O j )

[0088] SOD_O j =Average(SOD_O j1 SOD_O j2 ,…,SOD_O jn )

[0089] SOD_O ji =α ij O i +(1-α ij SE j

[0090] COD_O j =min(COD_O j1 COD_O j2 ,…,COD_O jn )

[0091] COD_O j =O i +β ij

[0092] i = 1, 2, 3, ..., n

[0093] In the formula, O i Oj Let α represent the operating performance of network nodes i and j, 'Average' be the average value function, 'n' be the number of network nodes, and α be the average value function. ij β ij SE represents the dependency strength and dependency criticality of network nodes i and j, respectively. j For the active performance of network node j;

[0094]

[0095] In the formula, F(s) k ) for system s k The active energy efficiency that can be provided to network node j For the k-th system s k The number, K is the system s k The number of types.

[0096] 2. System resource construction and system constraints based on edge warfare system;

[0097] The system constraints are:

[0098] Budget constraints are:

[0099]

[0100] In the formula, K represents the system s k Quantity, For the k-th system s k Quantity, Cost(s) k ) for deploying system s k Budget, B d This is the budget threshold;

[0101] Quantity limit:

[0102] 0≤c≤Q k

[0103] In the formula, Q k The number of each system The threshold;

[0104] The communication bandwidth limit is:

[0105]

[0106] In the formula, Comm(s) k ) for system s k Consumed communication bandwidth, B w This is the communication bandwidth threshold.

[0107] Dependency parameters are restricted to:

[0108] α min<<α<<α max

[0109] β min <<β<<β max

[0110] In the formula, α min , α max For the theoretical minimum and maximum values ​​of the dependence strength α, β min β max These are the theoretical minimum and maximum values ​​depending on the criticality β;

[0111] The limits of fringe charges are:

[0112] 0 << SE C <<L

[0113] In the formula, SE C Let L be the active effectiveness of the network nodes corresponding to each function of the decision-making function, and SE be the active effectiveness. C The threshold.

[0114] 3. Construct an optimization objective function for the edge warfare system based on a functionally dependent network model and system constraints;

[0115] The objective function to be optimized is:

[0116]

[0117] P = D(B) d +B w )

[0118] In the formula, O x Let P be the operating performance of the network nodes corresponding to each function of function type x, and D be the penalty term and the penalty coefficient.

[0119] 4. Solve the objective function using multiple group difference evolution algorithms to obtain the optimization results;

[0120] like Figure 2 As shown, obtaining the optimization results includes the following steps:

[0121] 4.1. Initialize multiple populations and calculate the fitness of individuals in each population based on the optimization objective function (take the output value of the optimization objective function as the fitness);

[0122] 4.2. Select individuals with high fitness from various groups as high-quality individuals based on the preset generation gap rate;

[0123] 4.3. Perform crossover and mutation operations on high-quality individuals to generate offspring individuals;

[0124] 4.4 Replace individuals with low fitness in each population with offspring individuals to generate each offspring population, and calculate the fitness of individuals in each offspring population based on the optimization objective function;

[0125] 4.5. Based on the migration operator, replace the individual with the lowest fitness in the next generation population with the individual with the highest fitness in the next generation population, and update each generation population.

[0126] 4.6. Select the individual with the highest fitness in each updated offspring population as the elite individual based on manual operators;

[0127] 4.7 Select the individual with the highest fitness from the elite individuals and add it to the elite population;

[0128] 4.8 Repeat the above steps until the preset maximum number of iterations is reached;

[0129] 4.9 Select the individual with the highest fitness from the elite population as the output optimization result;

[0130] Population I is:

[0131] I = [I1, I2, ..., I m ]

[0132] I r =[α r ,β r ,n r ], r = 1, 2, ..., m

[0133] α r =[α r,1 ,α r,2 ,…α r,l ]

[0134] β r =[β r,1 ,β r,2 ,…β r,l ]

[0135]

[0136] In the formula, I r Let r be an individual in the population, and α be an individual. r,l β r,l Let α be the dependency strength and β be the dependency criticality corresponding to the one-way arrow l for individual r, and l be the number of one-way arrows. For individual r, the Kth type of system s k The number, K is the system s k The number of types.

[0137] like Figure 3As shown, this embodiment provides a function-dependent network model. The headquarters command and control function and the battlefield command and control function of the decision-making function are network nodes D1 and D2, respectively. The long-range reconnaissance function, the medium-range reconnaissance function and the short-range reconnaissance function of the reconnaissance function are network nodes S1, S2 and S3, respectively. The long-range strike function, the medium-range strike function, the short-range strike function and the electronic attack function of the strike function are nodes I1, I2, I3 and I4, respectively.

[0138] Construct an optimization objective function using the functional type of the strike operation as the optimization objective:

[0139]

[0140] P = D(B) d +B w )

[0141] In the formula, I = [I1, I2, I3, I4];

[0142] The objective function was solved iteratively 300 times using a multi-group difference evolution algorithm:

[0143] When the combat mission I = I1, for ease of analysis, the capability value of network node I1, system budget, and target value of the optimization objective function output are recorded for each iteration, and a graph is generated as follows: Figure 4 As shown:

[0144] The optimization results of the system are shown in Table 1. Table 1 is as follows:

[0145] S1 S2 S3 S4 S5 S6 S7 S8 S9 S10 S11 S12 S13 S14 S15 S16 1 0 1 0 3 1 0 0 0 2 2 0 1 0 1 0

[0146] The optimization of the function-dependent network model is shown in Table 2. Table 2 is as follows:

[0147] D1→D2 D1→I1 D1→I2 D1→I3 D1→I4 D2→I1 D2→I2 S1→D1 S1→D2 S1→S2 S1→S3 α 0.33 0.63 0.57 0.91 0.53 0.56 0.89 0.92 0.61 0.27 0.76 β 72 37 54 88 42 76 74 46 60 26 42 S1→I1 S1→I4 S2→D1 S2→D2 S2→S3 S2→I2 S2→I4 S3→D1 S3→I3 S3→I4 α 0.48 0.42 0.89 0.44 0.75 0.71 0.57 0.99 0.89 0.55 β 43 15 66 30 28 23 29 14 28 16

[0148] When the combat mission I = I2, the iterative process is as follows: Figure 5 As shown:

[0149] The optimization results of the system are shown in Table 3. Table 3 is as follows:

[0150] S1 S2 S3 S4 S5 S6 S7 S8 S9 S10 S11 S12 S13 S14 S15 S16 0 2 1 0 0 0 0 0 2 1 0 2 0 1 0 1

[0151] The optimization of the function-dependent network model is shown in Table 4. Table 4 is as follows:

[0152] D1→D2 D1→I1 D1→I2 D1→I3 D1→I4 D2→I1 D2→I2 S1→D1 S1→D2 S1→S2 S1→S3 α 0.35 0.85 0.83 0.95 0.5 0.54 0.97 0.97 0.48 0.66 0.72 β 32 53 84 83 41 86 50 76 52 13 30 S1→I1 S1→I4 S2→D1 S2→D2 S2→S3 S2→I2 S2→I4 S3→D1 S3→I3 S3→I4 α 0.72 0.85 0.99 0.8 0.48 0.75 0.74 0.96 0.73 0.53 β 12 15 70 13 44 34 26 75 14 43

[0153] When the combat mission I = I3, the iterative process is as follows: Figure 6 As shown:

[0154] The optimization results of the system are shown in Table 5. Table 5 is as follows:

[0155] S1 S2 S3 S4 S5 S6 S7 S8 S9 S10 S11 S12 S13 S14 S15 S16 0 0 2 0 0 0 0 0 2 1 1 1 0 3 0 1

[0156] The optimization of the function-dependent network model is shown in Table 6. Table 6 is as follows:

[0157] D1→D2 D1→I1 D1→I2 D1→I3 D1→I4 D2→I1 D2→I2 S1→D1 S1→D2 S1→S2 S1→S3 α 0.63 0.59 0.91 0.9 0.87 0.54 0.78 0.99 0.68 0.38 0.78 β 48 85 76 68 35 33 29 53 70 39 18 S1→I1 S1→I4 S2→D1 S2→D2 S2→S3 S2→I2 S2→I4 S3→D1 S3→I3 S3→I4 α 0.41 0.61 0.97 0.56 0.44 0.56 0.51 0.92 0.56 0.56 β 24 26 35 69 56 36 18 11 14 14

[0158] When the combat mission I = I4, the iterative process is as follows: Figure 7 As shown:

[0159] The optimization results of the system are shown in Table 7. Table 7 is as follows:

[0160] S1 S2 S3 S4 S5 S6 S7 S8 S9 S10 S11 S12 S13 S14 S15 S16 0 1 0 0 3 0 0 0 2 0 1 0 1 0 1 0

[0161] The optimization of the function-dependent network model is shown in Table 8. Table 8 is as follows:

[0162] D1→D2 D1→I1 D1→I2 D1→I3 D1→I4 D2→I1 D2→I2 S1→D1 S1→D2 S1→S2 S1→S3 α 0.67 0.96 0.93 0.53 0.5 0.74 0.5 0.98 0.79 0.62 0.79 β 36 67 44 54 50 78 27 37 18 29 53 S1→I1 S1→I4 S2→D1 S2→D2 S2→S3 S2→I2 S2→I4 S3→D1 S3→I3 S3→I4 α 0.65 0.74 1 0.96 0.79 0.4 0.87 0.93 0.59 0.64 β 37 37 15 57 42 33 42 52 29 33

[0163] The final optimized edge warfare system's capability values ​​and budget are shown in Table 9. Table 9 is as follows:

[0164] I1 I2 I3 I4 Ability Values 96.9471 96.8326 98.111 96.0975 Budget 1390 1530 1240 1993

[0165] Example 2:

[0166] This invention provides an optimization system for edge warfare, the system comprising:

[0167] The model building module is used to build function-dependent network models based on the function types of the edge combat system;

[0168] The constraint construction module is used to construct system constraints based on system resources in the edge warfare system.

[0169] The function building module is used to construct the optimization objective function of the edge combat system based on the function-dependent network model and system constraints;

[0170] The optimization solution module is used to solve the optimization objective function and obtain the optimization results based on multiple group difference evolution algorithms.

[0171] Example 3:

[0172] Based on Embodiment 1, the present invention provides an optimization device for an edge warfare system, including a processor and a storage medium;

[0173] Storage media are used to store instructions;

[0174] The processor is used to perform operations according to instructions to execute the steps according to the method described above.

[0175] Example 4:

[0176] Based on Embodiment 1, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method.

[0177] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0178] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0179] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0180] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0181] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the technical principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. An optimization method for a perimeter warfare system, characterized in that, include: Construct a function-dependent network model based on the functional types of the edge combat system; System resource construction and system constraints based on edge warfare system; An optimization objective function for edge warfare systems is constructed based on a functionally dependent network model and system constraints. The optimization objective function is solved using a multi-group differential evolution algorithm to obtain the optimization results; The functional type-based functional dependency network model constructed based on the edge combat system includes: Each function in each functional type of the edge combat system is taken as a network node, and a directed acyclic network is generated by connecting the network nodes through unidirectional arrows. The directed acyclic network is then used as a functionally dependent network model. The dependency relationships between the network nodes connected by the one-way arrows satisfy the following: ; ; ; ; ; ; In the formula, For network nodes Operating performance It is a function of average value. The number of network nodes, Network nodes Dependency strength and dependency criticality, For network nodes Active effectiveness; ; In the formula, For the system Can be a network node Provided active energy efficiency, For the first Type System Quantity, For the system The number of types; The system constraints are as follows: Budget constraints are: ; In the formula, For system deployment The budget, This is the budget threshold; Quantity limit: ; In the formula, The number of each system The threshold; The communication bandwidth limit is: ; In the formula, For the system Consumed communication bandwidth This is the communication bandwidth threshold. Dependency parameters are restricted to: ; ; In the formula, Dependency strength The theoretical minimum and maximum values, For the sake of criticality The theoretical minimum and maximum values; The limits of fringe charges are: ; In the formula, The proactive effectiveness of network nodes corresponding to each function of the decision-making process. For proactive efficiency The threshold.

2. The optimization method for a perimeter warfare system according to claim 1, characterized in that, The functional types include decision-making, reconnaissance, and strike functions; the decision-making functions include headquarters command and control functions and battlefield command and control functions; the reconnaissance functions include long-range reconnaissance, medium-range reconnaissance, and short-range reconnaissance functions; and the strike functions include long-range strike functions, medium-range strike functions, short-range strike functions, and electronic attack functions.

3. The optimization method for a perimeter warfare system according to claim 1, characterized in that, The optimization objective function is: ; ; In the formula, Functional type The operational performance of the network nodes corresponding to each function. As a penalty item, This is the penalty coefficient.

4. The optimization method for a perimeter warfare system according to claim 3, characterized in that, The process of solving the objective function and obtaining the optimization result based on a multi-group differential evolution algorithm includes: Initialize multiple populations and calculate the fitness of individuals in each population based on the optimization objective function; Individuals with high fitness in various groups are selected as high-quality individuals based on the preset generation gap rate. High-quality individuals are crossover, recombination, and mutation operations to produce offspring individuals; Replace individuals with low fitness in each population with offspring individuals to generate each offspring population, and calculate the fitness of individuals in each offspring population based on the optimization objective function; Based on the migration operator, the individual with the highest fitness in each offspring population replaces the individual with the lowest fitness in the next offspring population, thus updating each offspring population; The individual with the highest fitness in each updated offspring population is selected as the elite individual based on manual operators; Select the individuals with the highest fitness from the elite individuals and add them to the elite population; Repeat the above steps until the preset maximum number of iterations is reached; The individual with the highest fitness is selected from the elite population as the output optimization result; Among them, the population for: ; ; ; ; ; In the formula, For individuals in a population , For individuals One-way arrow Corresponding Dependency Strength and dependency criticality , This refers to the number of one-way arrows. For individuals The Type System Quantity, For the system The number of types.

5. An optimized system for edge warfare, characterized in that, The system includes: The model building module is used to build function-dependent network models based on the function types of the edge combat system; The constraint construction module is used to construct system constraints based on system resources in the edge warfare system. The function building module is used to construct the optimization objective function of the edge combat system based on the function-dependent network model and system constraints; The optimization solution module is used to solve the optimization objective function based on multiple group difference evolution algorithms to obtain the optimization results; The functional type-based functional dependency network model constructed based on the edge combat system includes: Each function in each functional type of the edge combat system is taken as a network node, and a directed acyclic network is generated by connecting the network nodes through unidirectional arrows. The directed acyclic network is then used as a functionally dependent network model. The dependency relationships between the network nodes connected by the one-way arrows satisfy the following: ; ; ; ; ; ; In the formula, For network nodes Operating performance It is a function of average value. The number of network nodes, Network nodes Dependency strength and dependency criticality, For network nodes Active effectiveness; ; In the formula, For the system Can be a network node Provided active energy efficiency, For the first Type System Quantity, For the system The number of types; The system constraints are as follows: Budget constraints are: ; In the formula, For system deployment The budget, This is the budget threshold; Quantity limit: ; In the formula, The number of each system The threshold; The communication bandwidth limit is: ; In the formula, For the system Consumed communication bandwidth This is the communication bandwidth threshold. Dependency parameters are restricted to: ; ; In the formula, Dependency strength The theoretical minimum and maximum values, For the sake of criticality The theoretical minimum and maximum values; The limits of fringe charges are: ; In the formula, The proactive effectiveness of network nodes corresponding to each function of the decision-making process. For proactive efficiency The threshold.

6. An optimized system device for edge warfare, characterized in that, Including processor and storage media; The storage medium is used to store instructions; The processor is configured to operate according to the instructions to perform the steps of the method according to any one of claims 1-4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the program implements the steps of the method according to any one of claims 1-4.

Images