Edge air defense node task allocation method and system based on genetic algorithm and contract net method

Abstract

The application discloses an edge air defense node task allocation method and system based on a genetic algorithm and a contract net method, and particularly relates to the following steps: establishing a target threat degree estimation and task allocation model; using an improved hybrid single-parent genetic algorithm to calculate a multi-platform cooperative task allocation problem through integer coding+dynamic double population, tournament selection+reverse order crossover+adaptive mutation genetic operator design, combined with an elite pool update and a mutation strategy triggered by concentration degree of a simulated annealing criterion; and using an improved contract net method to realize dynamic air defense task re-allocation by extending a contract protocol process, introducing a multi-Agent cooperative architecture, designing a consistency auction algorithm and a dynamic bid correction rule, and combining a load-sensitive contract exchange mechanism in view of problems encountered in executing tasks by air defense platforms in emergency situations. The application can rapidly and effectively perform multi-platform cooperative air defense task allocation, dynamically adapt to environmental changes, and improve multi-platform cooperative air defense task combat effectiveness and combat efficiency.

Description

Technical Field

[0001] This invention relates to the field of intelligent optimization and distributed collaborative decision-making technology, and in particular to a method and system for task allocation of edge air defense nodes based on genetic algorithms and contract network method. Background Technology

[0002] The distributed air defense mission system integrates various data sources, including simulation results, daily training, assessments, and exercises, and employs operations research methods to quantitatively describe its own capabilities and mission requirements. Under network-centric information sharing, the system can quickly detect targets and formulate efficient allocation strategies to achieve optimal operational defense. Its main components include algorithm models and software systems. The algorithm model covers key aspects such as self-state assessment, mission allocation model construction, objective function design, and scheme selection, ensuring the system can accurately track and intercept key targets.

[0003] Invention patent CN 118296479 A discloses a multi-target decision-making algorithm for intercepting ballistic missiles based on a covariance adaptive model. This algorithm calculates and ranks the threat levels of ballistic missile targets based on a given attack trajectory, predicted impact point, and threat assessment index set. Using constrained decision variable allocation and a covariance adaptive sampling strategy, it determines parameters such as the interceptor missile's launch azimuth, maximum negative angle of attack, and launch site for different targets, thus improving interception efficiency and accuracy in multi-target missile interception. However, this algorithm lacks cross-platform collaborative air defense capabilities, fails to fully utilize edge air defense nodes for multi-platform collaborative air defense, and cannot maximize the system's operational effectiveness. Summary of the Invention

[0004] The purpose of this invention is to provide a method and system for assigning tasks to edge air defense nodes based on genetic algorithms and contract network methods, so as to quickly, effectively and dynamically adapt to environmental changes to perform distributed air defense and anti-missile task assignment, improve weapon unit flexibility, and enhance combat effectiveness and efficiency.

[0005] The technical solution to achieve the purpose of this invention is: a method for assigning tasks to edge air defense nodes based on genetic algorithms and contract network method, comprising the following steps:

[0006] Step 1: Establish a target threat estimation and task allocation model;

[0007] Step 2: An improved hybrid single-parent genetic algorithm is used to calculate the multi-platform collaborative task allocation problem. The improved hybrid single-parent genetic algorithm is designed with genetic operators of integer encoding + dynamic dual population, tournament selection + reverse crossover + adaptive mutation, combined with elite pool update based on simulated annealing criteria and concentration-triggered mutation strategy.

[0008] Step 3: To address the problem of unforeseen circumstances encountered during the execution of missions by air defense platforms, an improved contract network method is adopted to solve the mission redistribution problem. The improved contract network method extends the contract protocol process, introduces a multi-agent collaborative architecture, designs a consistent auction algorithm and dynamic bidding correction rules, and combines a load-sensitive contract exchange mechanism to achieve dynamic air defense mission redistribution.

[0009] A task allocation system for edge air defense nodes based on genetic algorithms and contractual net methods is disclosed. This system implements the aforementioned task allocation method for edge air defense nodes based on genetic algorithms and contractual net methods. The system comprises a first module to a third module, and the functions of each module are as follows:

[0010] The first module is used to establish a target threat level estimation and task allocation model;

[0011] The second module employs an improved hybrid single-parent genetic algorithm to compute the multi-platform collaborative task allocation problem. The improved hybrid single-parent genetic algorithm is designed with genetic operators of integer encoding + dynamic dual population, tournament selection + reverse crossover + adaptive mutation, combined with elite pool update based on simulated annealing criteria and a concentration-triggered mutation strategy.

[0012] The third module addresses the problem of unforeseen circumstances encountered by air defense platforms during mission execution by employing an improved contract network method to solve the mission redistribution problem. This improved contract network method extends the contract protocol process, introduces a multi-agent collaborative architecture, designs a consistent auction algorithm and dynamic bidding correction rules, and combines a load-sensitive contract exchange mechanism to achieve dynamic air defense mission redistribution.

[0013] A mobile terminal includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the edge air defense node task allocation method based on genetic algorithm and contract network method.

[0014] Compared with the prior art, the significant advantages of this invention are: (1) It can quickly and effectively carry out multi-platform collaborative air defense mission allocation, dynamically adapt to environmental changes, and the weapon units are more flexible and elastic; (2) It adopts an auction algorithm to realize mission pre-planning, introduces mission transfer stations and mission priority to assist in the processing of mission allocation schemes on the basis of traditional contract network, and adopts exchange contracts to carry out real-time collaborative allocation on the basis of the original allocation scheme, thereby improving combat effectiveness and combat efficiency. Attached Figure Description

[0015] Figure 1 This is a flowchart of the edge air defense node task allocation method based on genetic algorithm and contract network method of the present invention.

[0016] Figure 2 This is a flowchart illustrating the improved hybrid single-parent genetic algorithm of this invention.

[0017] Figure 3 This is a flowchart illustrating the improved contract net algorithm of this invention. Detailed Implementation

[0018] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0019] Combination Figure 1 This invention discloses a method for task allocation of edge air defense nodes based on genetic algorithms and contract network method, comprising the following steps:

[0020] Step 1: Establish a target threat estimation and task allocation model;

[0021] Step 2: An improved hybrid single-parent genetic algorithm is used to calculate the multi-platform collaborative task allocation problem. The hybrid single-parent genetic algorithm uses a genetic operator design of integer encoding + dynamic dual population (ordinary population and elite pool), tournament selection + reverse crossover + adaptive mutation, combined with the elite pool update of simulated annealing criterion and the mutation strategy triggered by concentration, which significantly improves the solution efficiency and global convergence of the task allocation problem. It is especially suitable for collaborative optimization scenarios of air defense nodes with multiple constraints and high discreteness.

[0022] Step 3: To address the issue of unforeseen circumstances encountered during mission execution by air defense platforms, an improved contract network method is adopted to solve the mission redistribution problem. By extending the contract protocol process, introducing a multi-agent collaborative architecture (air defense / mission / management agent), designing a consistent auction algorithm and dynamic bidding correction rules, and combining a load-sensitive contract exchange mechanism, the real-time performance, load balancing, and global collaborative efficiency of the contract network method in dynamic air defense mission redistribution are significantly improved.

[0023] As a specific example, the task of the edge air defense node is as follows: A certain military defense location faces N incoming missiles, and there are M friendly air defense weapon units around it that need to intercept them. The allocation of targets needs to consider the following constraints:

[0024] All incoming missiles must be assigned weapons to engage them;

[0025] Each missile can only be intercepted by one weapon platform;

[0026] The number of missions a defense platform can perform must not exceed its capacity;

[0027] An air defense platform can only intercept one missile at a time.

[0028] When the number of platforms is less than the number of missiles, missiles with higher threat levels will be intercepted first.

[0029] As a specific example, the establishment of the target threat estimation and task allocation model described in step 1 is as follows:

[0030] Step 1.1: Define the attribute set of the air defense agent and missile information as follows:

[0031]

[0032] In the formula, This represents the set of attributes for the i-th air defense weapon unit. Let represent the set of attributes of the i-th target missile. Represents the coordinates (x, y) of the i-th air defense weapon unit. i y i , z i ), This represents the firing rate of the i-th air defense weapon unit. This indicates the integrity of the i-th air defense weapon unit. This represents the firing rate of the i-th air defense weapon unit. Represents the coordinates (x, y) of the j-th target missile. j y j , z j );

[0033] Let $\mathbf$ represent the value, speed, heading angle, and coverage radius of the missile targeting the $j$ target.

[0034] Step 1.2: Establish the objective function model for agent-coordinated task allocation as follows:

[0035] Max[f1(X)-f2(X)](3)

[0036] In the formula, f1(X) represents the reward gained by the agent in completing the task; f2(X) represents the cost incurred by the agent in completing the task, specifically defined as follows:

[0037]

[0038] Make

[0039]

[0040] Equation (5) represents the uniqueness constraint, meaning that a missile can be assigned at most once; the decision variable matrix X = {x ij |i=1,2…n;j=1,2…k}, where x ij A value of 1 indicates that target missile j is assigned to air defense unit i, and a value of 0 indicates that it is not assigned; Reward(WA) i (T j )) represents the reward function for the i-th air defense platform destroying the j-th target missile, where Cost(WA)i (T j )) represents the i-th air defense platform WA i Missile T destroys the j-th target j The cost estimation function;

[0041] Step 1.3: Attack revenue refers to the mission value that the air defense platform (WA) can obtain when performing a certain task. The attack revenue function is designed as follows:

[0042]

[0043] In the formula, WA i It refers to the i-th air defense platform, T j Let $\frac{j}{\frac ... i (T j )) represents the payoff function for the i-th air defense platform destroying the j-th target missile, where α is the weight coefficient of the payoff function, and α∈[0,1] represents the proportion of the payoff function to the target. The intrinsic value of a missile is typically determined by its type and destructive capabilities; P ij means WA i The probability of successfully destroying missile j;

[0044] To simplify the model, the damage probability P ij This can be derived from the polar coordinate equations relating the current states of the air defense platform and the missiles:

[0045]

[0046] In the formula, ρ(i,j) represents the current air defense platform WA. i The relative distance between the missile and the incoming missile. This represents the derivative of relative distance with respect to time; when WA fires and destroys the target, ρ = 0; q is the line-of-sight angle. These are the launch speed of the air defense weapon unit and the speed of the target missile, respectively; θ i θ j WA i The angle between the velocity vector of the j-th target missile and the horizontal baseline in the same vertical plane;

[0047] According to the quasi-parallel proximity rule, when The larger the value, the higher the probability that the agent will intercept the target;

[0048] Step 1.4: Design the cost estimation function as follows:

[0049] Cost(WA i (T j ))=β×ρ(i,j)×x ij(8)

[0050] In the formula, Cost(WA) i (T j )) represents the i-th air defense platform WA i Missile T destroys the j-th target j The cost estimation function, x ij A value of 1 indicates that task j is assigned to air defense unit i, and a value of 0 indicates that it is not assigned; ρ(i,j) represents the current air defense platform WA. i The relative distance between the missile j and the incoming missile j; β represents the weighting coefficient, β∈[0,1];

[0051] Step 1.5: Design the target threat level estimation model, as follows:

[0052] Range threat factor μ L for:

[0053]

[0054] In the formula, L represents the estimated range of the incoming missile;

[0055] Flight speed threat factor μ v for:

[0056] μ v =1-e -γv (10)

[0057] In the formula, γ = 0.0015, and v represents the missile's flight speed;

[0058] The distance between the incoming missile and our key defensive positions is used as a factor influencing the target threat assessment; the missile-target distance threat factor μ. r for:

[0059]

[0060] In the formula, r is the distance between the missile and the target. When r approaches the safety radius R of the defensive stronghold from ∞, the choice of the constant k determines the rate of decrease of the function. When k is larger, the rate of decrease of the function is faster. The closer the missile is to the stronghold, the more obvious the increase in threat level.

[0061] Range threat factor μ L Flight speed threat factor μ v Threat factor μ of target distance r Perform a weighted summation to obtain the value for the target missile T. j The threat level estimation function is shown below:

[0062] Threat j =ω L μ L +ωv μ v +ω r μ r ω L +ω v +ω r =1 (12)

[0063] In the formula, Threat j ω represents the threat level of the j-th target missile. L ω v ω r It is the range threat factor μ L Flight speed threat factor μ v Threat factor μ of target distance r The weighting coefficient is adjusted by ω. L ω v ω r The proportion of this will help air defense agents determine the priority of interception tasks based on the actual environment.

[0064] As a specific example, step 2 describes using an improved hybrid single-parent genetic algorithm to calculate the multi-platform collaborative task allocation problem, such as... Figure 2 As shown, the details are as follows:

[0065] Step 2.1: Using an integer encoding scheme, the integer decision vector is mapped to chromosomes, and the decision variables are mapped to gene loci. Each chromosome corresponds to one solution of the model.

[0066] Step 2.2, Population Initialization:

[0067] Normal population: randomly generated before evolution begins;

[0068] Elite pool: The best individuals or their variants in each generation of the ordinary population;

[0069] Population size: It grows dynamically in the early stages and reaches a fixed size in the later stages, usually between tens and hundreds;

[0070] Step 2.3: Calculate the fitness function: The fitness function consists of the objective function expression for multi-agent cooperative goal allocation, and the reward and cost functions, as shown in the following formula:

[0071]

[0072] Where T j U represents the set of genes for the j-th chromosome segment; i (T j ) indicates that weapon platform i is performing mission T j .

[0073] Step 2.3: Design genetic operators, including selection strategy operators, reverse crossover operators, and transposition mutation operators, and perform genetic operations as follows:

[0074] Step 2.3.1: Select strategy operator: Sort the population in descending order of fitness, select the best individual to replace the worst individual in the population, and select the next generation population based on the competition among multiple participants.

[0075] Specific operations:

[0076] (1) Determine the size of the tournament: Choose an appropriate tournament size, that is, the number of individuals participating in the competition each time;

[0077] (2) Calculate the fitness f of each individual in the population. M is the population size;

[0078] (3) Perform multiple tournament selections: Repeat the following steps until the new population is full:

[0079] a. Randomly select a group of individuals as participants in the tournament, the number of individuals being equal to the size of the tournament;

[0080] b. Assess fitness among tournament participants and select the individual with the highest fitness as the winner of the tournament;

[0081] c. Add the tournament winners to the new population;

[0082] (4) Sort all individuals and select the individual with the highest fitness to replicate, replacing the individual with the lowest fitness in the population;

[0083] Step 2.3.2, Reverse Crossover Operator: Select a parent chromosome, then randomly select two different random numbers less than the target missile number, and arrange the genes between the gene positions represented by the two random numbers in reverse order;

[0084] Formula for calculating reverse crossover:

[0085]

[0086] Where σ is e σx The differential coefficient, also known as the attenuation parameter, ranges from 0 to 1, and reflects P. c Probability trend; P c0 The initial crossover probability is given; Count is the number of consecutive occurrences of the current best fitness value; generation is the current generation; iter_Max is the maximum number of iterations.

[0087] Step 2.3.3, Transposition Mutation Operator: To avoid individuals getting trapped in local optima, a mutation operator is introduced. An adaptive transposition mutation operator is adopted to enhance the population's ability to escape local optima.

[0088] Let the mutation probability of the transposition mutation operator be P. m The calculation formula is:

[0089]

[0090] Where τ is e -τx The differential coefficient of P ranges from 0 to 5. m0 `count` is the initial mutation probability; `count` is the number of consecutive occurrences of the current best fitness value; `generation` is the current generation; `iter_Max` is the maximum number of iterations.

[0091] The mutation operation is performed by randomly selecting two adjacent gene loci and exchanging their gene values.

[0092] Step 2.4: Check if the termination condition is met. If yes, output the allocation result; otherwise, update the population and return to step 2.2 to perform the next generation of inheritance.

[0093] As a specific example, the design of the elite pool described in step 2.2 is as follows:

[0094] To enhance the algorithm's local optimization capability, the elite pool consists of the ordinary population and its variants from each generation. When the capacity (Maxsize) of the elite pool is not reached, the number of individuals in the elite pool dynamically increases. When the number of individuals reaches the capacity limit, the elite pool continuously checks the fitness of the individuals within it. The elite pool employs two strategies:

[0095] (1) Elite pool update: continuously update the pool based on the best individuals of each generation from the ordinary population according to the Metropolis criterion in the simulated annealing algorithm;

[0096] (2) Elite pool mutation: When the concentration of individuals in the population reaches a certain threshold, that is, when the diversity decreases to a certain extent, elite pool mutation is triggered.

[0097] As a specific example, the elite pool update strategy is as follows:

[0098] When the elite pool reaches its capacity limit, the Metropolis criterion from the simulated annealing algorithm is introduced for updating. By combining the probabilistic jump characteristic, the global optimal solution of the objective function is randomly searched in the solution space, specifically as follows:

[0099] During evolution, the normal population outputs the best individual of each generation with a fitness of E(n). The elite pool copies this individual and forces a transposition mutation. The fitness of the new individual after mutation is E(n+1). The update operation is completed according to probability P.

[0100] The formula for calculating probability P is:

[0101]

[0102] In the formula, T is the current temperature;

[0103] If E(n+1)>E(n), it indicates that the fitness has improved. The worst individual in the pool is replaced with a new individual, and the feedback is given to the general population. The general population completes the second update according to its own selection strategy.

[0104] As a specific example, the elite pool mutation strategy is as follows:

[0105] When the elite pool reaches its capacity limit, the average fitness f of the population in the elite pool is measured. avg With the individual with the highest fitness f max The degree of proximity between them;

[0106] The triggering condition satisfies the following inequality:

[0107]

[0108] In the formula, γ is the density factor, [γ lb ,γ ub [] represents the upper and lower limits of the cluster, indicating the degree of concentration of individuals; generation is the current generation, and iter_Max is the maximum number of iterations.

[0109] As a specific example, step 3 addresses the problem of unforeseen circumstances encountered by air defense platforms during mission execution, employing an improved contract net method to solve the task redistribution problem, such as... Figure 3 As shown, the details are as follows:

[0110] Step 3.1: Introduce a market contract mechanism into the online task allocation problem between air defense platforms and interceptor missiles. The contract network protocol is expanded to "bidding-tendering-winning-contracting-status update," and its input parameters are the platform and missile information transmitted by task pre-allocation, as well as the task matching relationship, defined in the form of triplets. <WA ch Missile ch ,X>, where WA ch Missile is a platform for pre-allocating and delivering tasks. ch X represents missile information, and X represents the matching relationship of the mission.

[0111] Step 3.2: Define three agent types: air defense agent, task agent, and management agent. All agents operate and cooperate based on their own rules to complete task allocation, using a triple W. A T A C A Let W represent the set of air defense agents. A for In the formula, Indicates air defense weapon unit WA i The Agent, where i is the air defense weapon unit number, is used to manage the WA. i Resource attributes and bidding calculations; each air defense agent exists on its corresponding weapon unit; based on the state update mechanism in the extended contract network, W i A WA will be applied in the following situations. i The information is passed to the management agent:

[0112] (1)WA i Lost or damaged;

[0113] (2)WA i The task set has changed;

[0114] The set T of task agents A for In the formula, Indicates interception of Missile j The missile's mission, where j is the missile's serial number, is responsible for auctioning off the mission. It generates a bidding contract based on the missile's attribute set and passes it to the management agent. Once the mission is successfully executed... The resources possessed are immediately destroyed and recycled to avoid waste.

[0115] The set C of management agents A Used to manage and receive information including air defense agents and mission agents, the contract trading area acts as a management agent, matching resources between bidding information from mission agents and tender information from air defense agents.

[0116] Step 3.3: After generating the initial task set for each air defense weapon unit using the improved hybrid parent genetic algorithm, the air defense agent and the task agent enter the monitoring state to detect whether there are any new missiles or damage to air defense weapon units. If so, proceed to step 3.4.

[0117] Step 3.4: Feedback the newly emerging missile's own attributes and the air defense missions of WAs that are damaged and unable to continue their missions to the management agent as pending bidding missions and include them in the contract trading area;

[0118] Step 3.5: The contract transaction area publishes bidding information according to the priority of the tasks;

[0119] Step 3.6: The air defense agents deployed on each air defense unit calculate their own mission benefits, assess the cost of executing the mission, publish bidding information, and conduct mission auctions in the contract trading area;

[0120] Step 3.7: The list of successful bidders is announced in the trading area, and the successful bidders complete the update of their own task sequence; if there are any unsuccessful tasks, proceed to step 3.5, otherwise proceed to step 3.8;

[0121] Step 3.8: Adjust local contracts between high-load air defense agents to improve the overall coordination benefits of multiple weapon units and complete the status update;

[0122] Step 3.9: The auction contract adopts the consensus auction algorithm. When the number of tasks T to be tendered in the contract transaction area is greater than the number of air defense agents that can be bid on, the task number is divided into T batches for auction. The quantity of each batch is equal to the number of buyers, so that each buyer can successfully bid for an auction item. After the auction ends, the task number T is updated in the next round.

[0123] Step 3.10: When T is less than the number of available air defense agents, the winner is determined based on the bid value of each agent. When WA i The number of tasks undertaken has reached the average load. At that time, the buyer revised the original bid value F for the next auction item j;

[0124] The calculation and bid value correction formulas are as follows:

[0125]

[0126] In the formula, N represents the total number of air defense weapon units, and load i for No. WA i The load, k is the coefficient for correcting the bid value F, F ij for WA i The revised bid value for auction item j;

[0127] Step 3.11: After each auction contract, the task with the highest workload, WA... i And the WA with the second highest workload of its type of tasks j To share and exchange ideas, if WA j Connect a task in its own task sequence with WAi If an exchange increases the overall objective function value of both parties, the exchange contract mechanism is triggered, and the exchange contract that increases the efficiency the most is selected and signed.

[0128] This invention also provides an edge air defense node task allocation system based on genetic algorithm and contract network method. This system is used to implement the aforementioned edge air defense node task allocation method based on genetic algorithm and contract network method. The system includes a first module to a third module, and the functions of each module are as follows:

[0129] The first module is used to establish a target threat level estimation and task allocation model;

[0130] The second module employs an improved hybrid single-parent genetic algorithm to compute the multi-platform collaborative task allocation problem. The improved hybrid single-parent genetic algorithm is designed with genetic operators of integer encoding + dynamic dual population, tournament selection + reverse crossover + adaptive mutation, combined with elite pool update based on simulated annealing criteria and a concentration-triggered mutation strategy.

[0131] The third module addresses the problem of unforeseen circumstances encountered by air defense platforms during mission execution by employing an improved contract network method to solve the mission redistribution problem. This improved contract network method extends the contract protocol process, introduces a multi-agent collaborative architecture, designs a consistent auction algorithm and dynamic bidding correction rules, and combines a load-sensitive contract exchange mechanism to achieve dynamic air defense mission redistribution.

[0132] The present invention also provides a mobile terminal, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the edge air defense node task allocation method based on genetic algorithm and contract network method.

[0133] The above are merely preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for task allocation of edge air defense nodes based on genetic algorithm and contract network method, characterized in that, Includes the following steps: Step 1: Establish a target threat estimation and task allocation model; Step 2: An improved hybrid single-parent genetic algorithm is used to calculate the multi-platform collaborative task allocation problem. The improved hybrid single-parent genetic algorithm is designed with genetic operators of integer encoding + dynamic dual population, tournament selection + reverse crossover + adaptive mutation, combined with elite pool update based on simulated annealing criteria and concentration-triggered mutation strategy. Step 3: To address the problem of unexpected situations encountered by air defense platforms during mission execution, an improved contract network method is adopted to solve the mission redistribution problem. The improved contract network method extends the contract protocol process, introduces a multi-agent collaborative architecture, designs a consistent auction algorithm and dynamic bidding correction rules, and combines a load-sensitive contract exchange mechanism to achieve dynamic air defense mission redistribution. In step 2, an improved hybrid single-parent genetic algorithm is used to calculate the multi-platform collaborative task allocation problem, as follows: Step 2.1: Using an integer encoding scheme, the integer decision vector is mapped to chromosomes, and the decision variables are mapped to gene loci. Each chromosome corresponds to one solution of the model. Step 2.2, Population Initialization: Normal population: randomly generated before evolution begins; Elite pool: The best individuals or their variants in each generation of the ordinary population; Population size: It grows dynamically in the early stages and reaches a fixed size in the later stages; Step 2.3: Calculate the fitness function: The fitness function consists of the objective function expression for multi-agent cooperative goal allocation, and the reward and cost functions, as shown in the following equation: （13） in The set of genes representing the j-th chromosome segment; Indicates weapon platform Execute the task ; Step 2.4: Design genetic operators, including selection strategy operators, reverse crossover operators, and transposition mutation operators, and perform genetic operations as follows: Step 2.4.1: Selecting the strategy operator: Sort the population in descending order of fitness, select the best individual to replace the worst-fit individual, and simultaneously select the next generation population based on competition among multiple participants, as follows: (1) Determine the size of the tournament: Choose the size of the tournament, that is, the number of individuals participating in the competition each time; (2) Calculate the fitness of each individual in the population. ; (3) Perform multiple tournament selections: Repeat steps a to c until the new population is full. a. Randomly select a group of individuals as participants in the tournament, with the number of individuals equal to the size of the tournament; b. Assess fitness among tournament participants and select the individual with the highest fitness as the winner of the tournament; c. Add the tournament winners to the new population; (4) Sort all individuals and select the individual with the highest fitness to replicate, replacing the individual with the lowest fitness in the population; Step 2.4.2, Reverse Crossover Operator: Select a parent chromosome, then randomly select two different random numbers less than the target missile number, and reverse the order of the genes represented by the two random numbers; Formula for calculating reverse crossover: （14） in, for The differential coefficient, also known as the attenuation parameter, has a range of values.

1. Reaction Probability change trend; The initial crossover probability is given; Count is the number of consecutive occurrences of the current best fitness value; generation is the current generation; iter_Max is the maximum number of iterations. Step 2.4.3, Transposition Mutation Operator: To avoid individuals getting trapped in local optima, a mutation operator is introduced. An adaptive transposition mutation operator is adopted to enhance the population's ability to escape local optima. The mutation probability of the transposition mutation operator is set as follows: The calculation formula is: （15） in, for The differential coefficients have a range of values ​​of . ; The initial mutation probability; The mutation operation is performed by randomly selecting two adjacent gene loci and exchanging their gene values. Step 2.5: Check if the termination condition is met. If yes, output the allocation result; otherwise, update the population and return to step 2.2 to perform the next generation of inheritance. Step 3 addresses the issue of unforeseen circumstances encountered by the air defense platform during mission execution. An improved contract net method is used to solve the task redistribution problem, as detailed below: Step 3.1: Introduce a market contract mechanism into the online task allocation problem between air defense platforms and interceptor missiles. The contract network protocol is extended to: bidding - tendering - awarding - signing - status update. The input parameters are the platform and missile information transmitted by task pre-allocation, as well as the task matching relationship, defined in the form of triples. ,in A platform for pre-allocating and transmitting tasks. For missile information, For task matching relationships; Step 3.2: Define three agent types: air defense agent, task agent, and management agent. All agents operate and cooperate based on their own rules to complete task allocation, using triples. Let represent the set of air defense agents. for In the formula, Indicates air defense weapon unit Agent, This is the serial number for air defense weapon units, used for management. Resource attributes and bidding calculations; each air defense agent exists on its corresponding weapon unit; based on the state update mechanism in the extended contract network. In the following situations, The information is passed to the management agent: (1) Lost or damaged; (2) The task set has changed; A collection of task agents for = In the formula, Indicates interception The missile's mission involves auctioning off the missile based on its attribute set, generating a bidding contract, and transmitting it to the management agent. Once the mission is successfully executed... The resources they possessed were immediately destroyed and recycled. For missile serial numbers; Management of the collection of Agents Used to manage and receive information including air defense agents and mission agents, the contract trading area acts as a management agent, matching resources between bidding information from mission agents and tender information from air defense agents. Step 3.3: After generating the initial mission set for each air defense weapon unit, the air defense agent and mission agent enter the monitoring state to detect whether there are any new missiles or damage to air defense weapon units. If so, proceed to step 3.

4. Step 3.4: Feedback the newly emerging missile's own attributes and the air defense missions of WAs that are damaged and unable to continue their missions to the management agent as pending bidding missions and include them in the contract trading area; Step 3.5: The contract transaction area publishes bidding information according to the priority of the tasks; Step 3.6: The air defense agents deployed on each air defense unit calculate their own mission benefits, assess the cost of executing the mission, publish bidding information, and conduct mission auctions in the contract trading area; Step 3.7: The list of successful bidders is announced in the trading area, and the successful bidders complete the update of their own task sequence; if there are any unsuccessful tasks, proceed to step 3.5, otherwise proceed to step 3.8; Step 3.8: Adjust local contracts between high-load air defense agents to improve the overall coordination benefits of multiple weapon units and complete the status update; Step 3.9: The auction contract adopts the consensus auction algorithm. When the number of pending bidding tasks stored in the contract transaction area... If the number of missions exceeds the current number of available air defense agents, then the number of missions will be divided. Auctions are conducted in batches, with each batch containing the same number of buyers as the number of buyers, ensuring that each buyer can successfully bid on an item. The task count is updated for the next round after each auction ends. ; Step 3.10, when If the number of available air defense agents is less than the current number of bidders, the winner will be determined based on the bid value of each agent. The number of tasks undertaken has reached the average load. At that time, the buyer was interested in the next item up for auction. The original bid value Make corrections; The calculation and bid value correction formulas are as follows: （18） （19） In the formula The total number of air defense weapon units. For the first The load, To correct the bid value coefficient, for Auction items The revised bid value; Step 3.11: After each auction contract, the task with the highest workload... And the second highest workload of similar tasks To share and exchange ideas, if Combine a task from its own task sequence with If an exchange increases the overall objective function value of both parties, the exchange contract mechanism is triggered, and the exchange contract that increases the efficiency the most is selected and signed.

2. The edge air defense node task allocation method based on genetic algorithm and contract network method according to claim 1, characterized in that, The specific tasks of the edge air defense node are as follows: A key military defense location faces N incoming missiles, surrounded by M friendly air defense weapon units that need to intercept them. Target allocation must consider the following constraints: All incoming missiles must be assigned weapons to engage them; Each missile can only be intercepted by one weapon platform; The number of missions a defense platform can perform cannot exceed its own capacity; An air defense platform can only intercept one missile at a time. When the number of platforms is less than the number of missiles, missiles with higher threat levels will be intercepted first.

3. The edge air defense node task allocation method based on genetic algorithm and contract network method according to claim 1, characterized in that, In step 1, a target threat estimation and task allocation model is established, as follows: Step 1.1: Define the attribute set of the air defense agent and missile information as follows: （1） （2） In the formula, Agent represents an intelligent agent. Indicates the first The set of attributes of an air defense weapon unit. Indicates the first A set of attributes for a target missile. , , Indicates the first The coordinates of an air defense weapon unit along the x, y, and z axes. Indicates the first Firing rate of each air defense weapon unit Indicates the first Completeness of each air defense weapon unit Indicates the first The components of the target missile's coordinates on the x, y, and z axes; They represent the first The value, speed, heading angle, and coverage radius of each target missile; Step 1.2: Establish the objective function model for agent-coordinated task allocation as follows: （3） In the formula, The rewards obtained by the intelligent agent for completing the task; The cost incurred by an intelligent agent in completing a task is defined as follows: （4） Make （5） Equation (5) represents the uniqueness constraint, meaning that a missile can be assigned at most once; the decision variable matrix A value of 1 indicates the target missile. Assigned to air defense unit number i; a value of 0 indicates no assignment. Indicates the first The first air defense platform destroyed the first The payoff function of a target missile. Indicates the first Air defense platform Destroy the missile targeting The cost estimation function; Step 1.3: Attack revenue refers to the mission value that the air defense platform (WA) can obtain when performing a certain task. The attack revenue function is designed as follows: （6） In the formula, It refers to the first One air defense platform, Indicates the first One target missile, Indicates the first The first air defense platform destroyed the first The payoff function of a target missile. These are the weighting coefficients of the payoff function. The proportion of the reward function to the objective; The intrinsic value of a missile is usually determined by its type and destructive capabilities. express The probability of successfully destroying missile j; To simplify the model, the probability of damage... The following is derived from the polar coordinate equations simultaneously established by the current states of the air defense platform and missiles: （7） In the formula, Indicates the current air defense platform With incoming missiles The relative distance between them This represents the derivative of the relative distance with respect to time, when the air defense platform WA fires and destroys the target. =0; The viewing angle; These are the launch speed of the air defense weapon unit and the speed of the target missile, respectively. , They are respectively The angle between the velocity vector of the j-th target missile and the horizontal baseline in the same vertical plane; According to the quasi-parallel proximity rule, when The larger the value, the higher the probability that the agent will intercept the target; Step 1.4: Design the cost estimation function as follows: （8） In the formula, Indicates the first Air defense platform Destroy the missile targeting The cost estimation function, A value of 1 indicates a task. Assigned to Air defense unit number 0 indicates no allocation; Indicates the current air defense platform With incoming missiles The relative distance between them; Indicates the weighting coefficient. ; Step 1.5: Design the target threat level estimation model, as follows: Range threat factor for: （9） In the formula, L represents the estimated range of the incoming missile; Flight speed threat factor for: （10） In the formula, =0.0015, Indicates the missile's flight speed; The distance between the incoming missile and our key defensive positions is used as a factor influencing the target threat assessment; missile-target distance threat factor. for: （11） In the formula, r is the missile-target distance. When r approaches the safety radius R of the defensive key area from ∞, the choice of constant k determines the rate of function descent. The larger k is, the faster the function descent rate, the closer the missile is to the key area, and the more obvious the increase in threat level. Range threat factor Flight speed threat factor Threat factor of target distance Perform a weighted summation to obtain the value for the target missile. The threat level estimation function is shown below: （12） In the formula, This indicates the threat level of the j-th target missile. , , It is a range threat factor Flight speed threat factor Threat factor of target distance The weighting coefficients are adjusted by... , , The proportion of this will help air defense agents determine the priority of interception tasks based on the actual environment.

4. The edge air defense node task allocation method based on genetic algorithm and contract network method according to claim 3, characterized in that, The design of the elite pool in step 2.2 is as follows: To enhance the local optimization capability of the algorithm, the elite pool consists of the ordinary population and its variants in each generation. When the capacity Maxsize of the elite pool has not reached its upper limit, the number of individuals in the elite pool is dynamically increased; when the number of individuals reaches the capacity upper limit, the elite pool begins to continuously detect the fitness of individuals in the pool. The elite pool has two strategies: (1) Elite pool update: continuously update the pool based on the best individuals of each generation from the ordinary population according to the Metropolis criterion in the simulated annealing algorithm; (2) Elite pool mutation: When the concentration of individuals in the population reaches a threshold, i.e., the diversity decreases to a set level, the elite pool mutation is triggered.

5. The edge air defense node task allocation method based on genetic algorithm and contract network method according to claim 4, characterized in that, The specific strategy for updating the elite pool is as follows: When the elite pool reaches its capacity limit, the Metropolis criterion from the simulated annealing algorithm is introduced for updating. By combining the probabilistic jump characteristic, the global optimal solution of the objective function is randomly searched in the solution space, specifically as follows: During evolution, the normal population outputs the best individual in each generation, whose fitness is: The elite pool copies the individual and forces a positional mutation. The fitness of the new individual after mutation is... The update operation is performed based on probability P; The formula for calculating probability P is: （16） In the formula, T is the current temperature; like If the fitness has improved, the worst individual in the pool is replaced with a new individual, and this is fed back to the general population. The general population then completes the second update according to its own selection strategy.

6. The edge air defense node task allocation method based on genetic algorithm and contract network method according to claim 4, characterized in that, The specific mutation strategy for the elite pool is as follows: When the elite pool reaches its capacity limit, the average fitness of the population in the elite pool is measured. With the most fitness individual The degree of proximity between them; The triggering condition satisfies the following inequality: （17） In the formula As a dense factor, for The upper and lower limits represent the concentration of individuals; generation is the current generation, and iter_Max is the maximum number of iterations.

7. A task allocation system for edge air defense nodes based on genetic algorithms and contract network method, characterized in that, This system is used to implement the edge air defense node task allocation method based on genetic algorithm and contract network method as described in any one of claims 1 to 6. The system includes a first module to a third module, and the functions of each module are as follows: The first module is used to establish a target threat level estimation and task allocation model; The second module employs an improved hybrid single-parent genetic algorithm to compute the multi-platform collaborative task allocation problem. The improved hybrid single-parent genetic algorithm is designed with genetic operators of integer encoding + dynamic dual population, tournament selection + reverse crossover + adaptive mutation, combined with elite pool update based on simulated annealing criteria and a concentration-triggered mutation strategy. The third module addresses the problem of unforeseen circumstances encountered by air defense platforms during mission execution by employing an improved contract net method to solve the task redistribution problem. The improved contract network method extends the contract agreement process, introduces a multi-agent collaborative architecture, designs a consistent auction algorithm and dynamic bid correction rules, and combines a load-sensitive contract exchange mechanism to achieve dynamic redistribution of air defense tasks.

8. A mobile terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the edge air defense node task allocation method based on genetic algorithm and contract network method as described in any one of claims 1 to 6.

Images