Security deployment and transmission scheme generation method and device for air-ground wireless system based on dynamic game and storage medium

Abstract

Embodiments of the present application relate to the field of unmanned aerial vehicles, and provide a security deployment and transmission scheme generation method and device for air-ground wireless systems based on dynamic game, and a storage medium. The method comprises: obtaining initial model parameters and an event occurrence sequence, taking the reverse order of the event occurrence sequence as a model construction sequence; determining a planner to maximize the weighted value of transmission cost and security rate as a planning target, and determining an eavesdropper to maximize the eavesdropping rate as an eavesdropping target; constructing a three-stage dynamic game model according to the initial model parameters, according to the model construction sequence, and according to the planning target and the eavesdropping target as the model construction target; solving the three-stage dynamic game model based on a two-stage optimization algorithm, and generating a security deployment and transmission scheme for the air-ground wireless system according to the target model parameters. The method can improve the security of unmanned aerial vehicle data transmission after deployment, improve the deployment efficiency, and improve the deployment effect.

Description

Technical Field

[0001] This application relates to the field of unmanned aerial vehicle (UAV) technology, and in particular to a method, apparatus, and storage medium for generating a secure deployment and transmission scheme for an air-to-ground wireless system based on dynamic game theory. Background Technology

[0002] In the field of drone technology, drones can provide flexible, intelligent, secure, and unlimited connectivity, which is of great significance for improving next-generation wireless communication systems.

[0003] However, in the wireless communication of drone networks, due to the inherent broadcast nature of the wireless medium, information can be easily intercepted by unauthorized receivers. Despite increasing research on drone networks, the security issues of drone networks have not yet been fully resolved.

[0004] In conclusion, traditional deployment methods suffer from low security when using drone networks for data transmission. Summary of the Invention

[0005] This application provides a method, apparatus, and storage medium for generating a secure deployment and transmission scheme for an air-to-ground wireless system based on dynamic game theory. This can improve the security of UAV data transmission after deployment, increase deployment efficiency, and enhance deployment effectiveness.

[0006] In a first aspect, embodiments of this application provide a method for generating a secure deployment and transmission scheme for an air-to-ground wireless system based on dynamic game theory, including:

[0007] Obtain the initial model parameters required for the representation process of the target task scenario;

[0008] Obtain the event occurrence order corresponding to the target task scenario, and use the reverse order of the event occurrence order as the model construction order;

[0009] The planner's planning objective is to maximize the expected value of the weighted average of transmission cost and confidentiality rate, and the eavesdropper's eavesdropping objective is to maximize the eavesdropping rate.

[0010] Following the model construction order, and taking the planning objective and the eavesdropping objective as the model construction objectives, a three-stage dynamic game model is constructed based on the initial model parameters.

[0011] The three-stage dynamic game model is solved using a two-stage optimization algorithm to obtain the target model parameters.

[0012] A secure deployment and transmission scheme for the air-to-ground wireless system is generated based on the target model parameters.

[0013] Secondly, embodiments of this application provide a device for generating a secure deployment and transmission scheme for an air-to-ground wireless system based on dynamic game theory, which has the function of implementing the secure deployment and transmission scheme generation method for an air-to-ground wireless system based on dynamic game theory provided in the first aspect above. The function can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above function, and the modules can be software and / or hardware.

[0014] In one possible design, the device includes:

[0015] The initial model parameter acquisition module is used to acquire the initial model parameters required for the representation process of the target task scenario;

[0016] The model building order determination module is used to obtain the event occurrence order corresponding to the target task scenario, and use the reverse order of the event occurrence order as the model building order;

[0017] The target determination module is used to determine the planner's planning target as maximizing the weighted value of transmission cost and confidentiality rate, and to determine the eavesdropper's eavesdropping target as maximizing the eavesdropping rate.

[0018] The model building module is used to construct a three-stage dynamic game model according to the model building order, with the planning objective and the eavesdropping objective as the model building objectives, and based on the initial model parameters.

[0019] The model solving module is used to solve the three-stage dynamic game model based on a two-stage optimization algorithm to obtain the target model parameters after solving;

[0020] The scheme generation module is used to generate a secure deployment and transmission scheme for the air-to-ground wireless system based on the target model parameters.

[0021] Another aspect of this application provides a secure deployment and transmission scheme generation device for an air-to-ground wireless system based on dynamic game theory, which includes at least one connected processor and a memory, wherein the memory is used to store program code, and the processor is used to call the program code in the memory to execute the methods described in the above aspects.

[0022] In another aspect, this application provides a computer storage medium including instructions that, when executed on a computer, cause the computer to perform the methods described in the above aspects.

[0023] In another aspect, this application provides a computer program product containing instructions that, when run on a computer, cause the computer to perform the methods described in the above aspects.

[0024] Compared to traditional drone deployment and transmission methods, the technical solution of this application optimizes the performance and confidentiality of the entire computing system by constructing and solving a three-stage dynamic game model, providing further guidance for the application of drones in the Internet of Things and edge computing; a targeted two-stage optimization algorithm is designed, which can converge to the optimal solution in a short time, thereby improving the security and deployment efficiency of drone data transmission after deployment and improving the deployment effect. Attached Figure Description

[0025] Figure 1 This is an application environment diagram from one embodiment;

[0026] Figure 2 This is a flowchart illustrating a method for generating a secure deployment and transmission scheme for an air-to-ground wireless system based on dynamic game theory in one embodiment.

[0027] Figure 3 This is a schematic diagram of an implementation scenario in one embodiment;

[0028] Figure 4 This is a schematic diagram of a task scenario in one embodiment;

[0029] Figure 5 This is a schematic diagram illustrating the optimal security deployment and transmission scheme for an air-to-ground wireless system in one embodiment.

[0030] Figure 6 This is a schematic diagram of the overall implementation process in one embodiment;

[0031] Figure 7 This is a flowchart illustrating a method for generating a secure deployment and transmission scheme for an air-to-ground wireless system based on dynamic game theory, as described in another embodiment.

[0032] Figure 8 This is a structural block diagram of a device for generating a secure deployment and transmission scheme for an air-to-ground wireless system based on dynamic game theory in one embodiment.

[0033] Figure 9 This is an internal structural diagram of a device for generating a secure deployment and transmission scheme for an air-to-ground wireless system based on dynamic game theory in one embodiment.

[0034] Figure 10 This is an internal structural diagram of a device for generating a secure deployment and transmission scheme for an air-to-ground wireless system based on dynamic game theory, as shown in another embodiment. Detailed Implementation

[0035] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or modules is not necessarily limited to those explicitly listed, but may include other steps or modules not explicitly listed or inherent to these processes, methods, products, or devices. The division of modules in the embodiments of this application is merely a logical division; in actual applications, there may be other division methods. For example, multiple modules may be combined into or integrated into another system, or some features may be ignored or not performed. Additionally, the shown or discussed mutual coupling or direct coupling or communication connection may be through some interface, and the indirect coupling or communication connection between modules may be electrical or other similar forms, none of which are limited in the embodiments of this application. Furthermore, the modules or sub-modules described as separate components may or may not be physically separated, may or may not be physical modules, or may be distributed among multiple circuit modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the embodiments of this application.

[0036] Figure 1 As shown in the application environment diagram of one embodiment, this application provides a method for generating a secure deployment and transmission scheme for an air-to-ground wireless system based on dynamic game theory, which can be applied to, for example... Figure 1 In the application scenario shown, terminal 102 communicates with server 104 via a network.

[0037] The terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. The server 104 can be implemented using a standalone server or a server cluster composed of multiple servers.

[0038] It should be specifically noted that the terminal 102 involved in the embodiments of this application can be a wired terminal or a wireless terminal, and can be a device that provides voice and / or data connectivity to a user, a handheld device with wireless connectivity, or other processing devices connected to a wireless modem. The wireless terminal can communicate with one or more core networks via a wireless access network. The wireless terminal can be a mobile terminal, such as a mobile phone or a computer with a mobile terminal. For example, it can be a portable, pocket-sized, handheld, computer-embedded, or vehicle-mounted mobile device that exchanges voice and / or data with the wireless access network. Examples include personal communication service telephones, cordless phones, session initiation protocol phones, wireless local loop stations, personal digital assistants, etc. The wireless terminal can also be referred to as a system, subscriber unit, subscriber station, mobile station, mobile, remote station, access point, remote terminal, access terminal, user terminal, terminal equipment, user agent, user device, or user equipment.

[0039] Figure 2 This is a flowchart illustrating a method for generating a secure deployment and transmission scheme for an air-to-ground wireless system based on dynamic game theory, as shown below. Figure 2 This application provides a method for generating a secure deployment and transmission scheme for an air-to-ground wireless system based on dynamic game theory, comprising:

[0040] S201, Obtain the initial model parameters required for the representation process of the target task scenario.

[0041] The target task scenario refers to the edge computing scenario involving drones and ground servers that are subject to eavesdropping.

[0042] The initial model parameters refer to the initial parameters required during the task scenario representation process, that is, the initial parameters required to build a planning model for solving the deployment and transmission scheme of UAVs.

[0043] For example, the initial model parameters may include a set of candidate deployment point numbers, the location of the candidate deployment points, the bandwidth of the UAV, the transmission power, the flight altitude, the power of white noise, the channel gain, the task area, the size of the computation task, and the unit transmission cost of the air-to-ground wireless transmission channel.

[0044] S202, obtain the event occurrence order corresponding to the target task scenario, and use the reverse order of the event occurrence order as the model construction order.

[0045] Step S202 specifically includes: determining the order of events as: first stage, second stage, third stage; reversing the order of events to determine the model construction order as: third stage, second stage, first stage.

[0046] The decision-making process involves three stages: the first stage involves planners determining the deployment location of the ground server; the second stage involves the eavesdropper deciding on its own location; and the third stage involves planners deciding on the deployment location and transmission ratio of the drones.

[0047] For example, the sequence of events could be: first stage, the planner determines the deployment location of the ground server; second stage, the eavesdropper decides its own location; third stage, the planner decides the deployment location and transmission ratio of the drone. In this case, the modeling process would begin in the third stage, proceed through the second stage, and end in the first stage.

[0048] In addition, more specifically, the third stage can also be: planners estimate the approximate range of eavesdroppers, planners deploy drones and determine the transmission ratio.

[0049] S203, determine that the planner's planning objective is to maximize the expected value of the weighted value of transmission cost and confidentiality rate, and determine that the eavesdropper's eavesdropping objective is to maximize the eavesdropping rate.

[0050] In the model planning process of this application, the planner refers to the builder and manager of the air-to-ground wireless system. Its core objective is to ensure the system transmits securely while controlling costs as much as possible. It is the defender in the game process of this application. The eavesdropper refers to the unauthorized jammer of the air-to-ground wireless system. Its core objective is to obtain as much data as possible from the system transmission. It is the attacker in the game process of this application.

[0051] Accordingly, the planning objective and the eavesdropping objective are the objectives set by the planner and the eavesdropper respectively during the model planning process, which facilitates the improvement of the planning model from the perspective of multiple objectives.

[0052] S204. Following the model construction order, with the planning objective and the eavesdropping objective as the model construction objectives, a three-stage dynamic game model is constructed based on the initial model parameters.

[0053] In this context, "according to the model construction order" refers to refining the objective function and constraints of each stage in the order of the third, second, and first stages, thereby completing the construction of the entire model.

[0054] The three-stage dynamic game model is the final model that is constructed. For example, it can be a nonlinear programming model.

[0055] S205, based on a two-stage optimization algorithm, solves a three-stage dynamic game model to obtain the target model parameters after the solution.

[0056] The two-stage optimization algorithm, also known as the two-stage solution algorithm, can include a first solution algorithm and a second solution algorithm. Generally, the solution accuracy of the first solution algorithm is lower than that of the second solution algorithm. More specifically, the first solution algorithm can be a coarse but fast solution algorithm, while the second solution algorithm can be a fine solution algorithm.

[0057] The target model parameters after the solution refer to the values ​​of each model parameter obtained after the solution, such as the specific deployment location of the drone server and the specific settings of the transmitted data.

[0058] S206, Generate a secure deployment and transmission scheme for the air-to-ground wireless system based on the target model parameters.

[0059] Once the values ​​of the model parameters obtained after solving the problem are determined, a secure deployment and transmission scheme for the air-to-ground wireless system can be generated. For example, in a secure deployment and transmission scheme, the specific deployment location of the UAV server is position (1,1), and the transmission power of the UAV is set to... wait.

[0060] Compared to traditional UAV deployment and transmission methods, this embodiment first obtains the initial model parameters required for representing the target task scenario and the event sequence corresponding to the target task scenario. The reverse order of these events is used as the model construction order. Then, the planning target and the eavesdropping target are determined. Following the model construction order, a three-stage dynamic game model is constructed using the planning target and the eavesdropping target as model construction targets. Finally, a two-stage optimization algorithm is used to solve the three-stage dynamic game model, generating a secure deployment and transmission scheme for the air-to-ground wireless system based on the target model parameters. This embodiment optimizes the performance and confidentiality of the entire computing system by constructing and solving a three-stage dynamic game model, providing further guidance for the application of UAVs in the Internet of Things and edge computing. The targeted two-stage optimization algorithm converges to the optimal solution in a short time, thereby improving the security and deployment efficiency of UAV data transmission after deployment and enhancing the deployment effect.

[0061] Figure 3 This is a schematic diagram of an implementation scenario in one embodiment. Figure 4 This is a schematic diagram of a task scenario in one embodiment. The following is in conjunction with... Figure 3 and Figure 4 The process of representing the target task scenario is described, specifically including the following steps:

[0062] S301. The alternative deployment point numbers of the ground server are combined to form a set of alternative deployment point numbers:

[0063] (1), in equation (1), This represents the set of numbers representing the candidate deployment points for m ground servers. In this embodiment, Alternative deployment points Figure 4 The circle in the diagram represents the candidate deployment point, and the number of the candidate deployment point is marked inside the circle.

[0064] S302, The location of the alternative deployment point numbered i is: In the embodiments of this application, Figure 4 The position of the middle circle indicates the location of the corresponding alternative deployment point.

[0065] S303, the bandwidth of the drone is In the embodiments of this application, .

[0066] S304, the transmission power of the drone is In the embodiments of this application, .

[0067] S305, the drone's flight altitude is H. In this embodiment of the application, .

[0068] S306, the power of white noise is In the embodiments of this application, .

[0069] S307, the channel gain at 1 meter is In the embodiments of this application, .

[0070] S308, Use This represents the entire task area. In this embodiment of the application, for Figure 3 A square region with a side length of 1400m.

[0071] S309, the size of the UAV's computational task is w. In this embodiment of the application, .

[0072] The unit transmission cost of the S310 air-to-ground wireless transmission channel is The unit transmission cost of other transmission channels is In the embodiments of this application, , .

[0073] In addition, in some embodiments, the reverse order of the events is used as the model building order. The modeling idea reflected in this model building order is to start from the last stage of the dynamic game and gradually deduce the optimal decision for each stage.

[0074] The essence of dynamic game theory is forward-looking decision-making. Each participant's current choice influences the actions of subsequent participants, and the reactions of subsequent participants, in turn, affect the expected payoff of the current participant. Therefore, forward-order analysis is prone to uncertainty because early decisions rely on predictions of uncertain future reactions. Thus, this application adopts the above-mentioned model construction sequence for modeling.

[0075] The advantage of using the above-described model building sequence in this application is that:

[0076] (1) Eliminate irrational behavior and empty threats: Orthogonal analysis may allow untrusted threats; for example, an eavesdropper may threaten to eavesdrop on a fixed location in advance, but in reality, such a threat is untrusted because a rational eavesdropper will change its own location depending on the location of the ground server and will not actually eavesdrop according to the prior threat.

[0077] Forward-order analysis cannot eliminate such untrusted threats, while reverse-order analysis automatically eliminates them because it only retains the optimal strategy in each subgame (from any stage of the subgame), thus obtaining a more realistic equilibrium.

[0078] (2) Systematicity and computability: Taking advantage of the phased nature of dynamic games, a two-stage solution algorithm was designed to decompose complex multi-stage games into simple subproblems, which is convenient for recursive algorithm solutions and numerical solutions for large-scale problems.

[0079] Optionally, in some embodiments of this application, a three-stage dynamic game model is constructed according to the model construction order, with the planning target and the eavesdropping target as the model construction targets, based on the initial model parameters. This includes: generating the objective function and constraints for the third stage based on the initial model parameters, the UAV deployment location decision variables, and the transmission ratio decision variables; generating the objective function and constraints for the second stage based on the eavesdropper location decision variables; generating the objective function and constraints for the first stage based on the ground server deployment decision variables; and determining the three-stage dynamic game model based on the objective functions and constraints for the first, second, and third stages.

[0080] For example, based on the target task scenario in the above embodiments, this embodiment proposes a three-stage dynamic game model in which the planner aims to maximize the expected value of the weighted value of transmission cost and confidentiality rate, and the eavesdropper aims to maximize the eavesdropping rate.

[0081] Optionally, in some embodiments of this application, a third-stage objective function is generated based on initial model parameters, UAV deployment location decision variables, and transmission ratio decision variables. This includes: determining the mission security rate and transmission cost of the UAV based on the initial model parameters, UAV deployment location decision variables, and transmission ratio decision variables; and, given the ground server deployment decision and the eavesdropper's location decision, setting the objective function in the third stage to maximize the expected value of the weighted value of transmission cost and security rate, thus obtaining the third-stage objective function.

[0082] The mission security rate of drones can be denoted as: Transmission costs can be recorded .

[0083] Among them, the decision variable for the deployment location of the drone can be denoted as: The transmission ratio decision variable can be denoted as: .

[0084] For example, the process of generating the objective function and constraints for the third stage specifically includes the following steps:

[0085] S401, the deployment location decision variables for the drone are: .

[0086] S402, the distance between the drone and the alternative deployment point numbered i is:

[0087] (2);

[0088] In equation (2), This represents the distance between the drone and the candidate deployment point numbered i.

[0089] S403, the two-dimensional position of the eavesdropper is .

[0090] S404, the distance between the drone and the eavesdropper is:

[0091] (3);

[0092] In equation (3), This indicates the distance between the drone and the eavesdropper.

[0093] S405, Channel gain of the UAV and the alternative deployment point numbered i: (4);

[0094] In equation (4), This represents the channel gain between the drone and the candidate deployment point numbered i.

[0095] S406, Data transmission rate between the drone and the alternative deployment point numbered i:

[0096] (5);

[0097] In equation (5), This represents the data transmission rate between the drone and the candidate deployment point numbered i.

[0098] S407, Channel Gain for Drones and Eavesdroppers:

[0099] (6); In equation (6), This indicates the channel gain for both the drone and the eavesdropper.

[0100] Data transmission rates between S408, drones, and eavesdroppers: (7);

[0101] In equation (7), This indicates the data transmission rate between the drone and the eavesdropper.

[0102] S409, the transmission ratio decision variable for drones is .

[0103] S4010, When the deployment point number of the ground server is i, the mission confidentiality rate of the UAV is:

[0104] (8); In equation (8), This indicates the mission confidentiality rate of the drone.

[0105] S411, transmission cost is: (9); In equation (9), This indicates the transmission cost.

[0106] S412. When the planner selects candidate deployment point i to deploy the server and the distance between the eavesdropper and the ground server is R, the location of the eavesdropper estimated by the planner is within the range... The random variable in the process. In this embodiment, when the planner selects the candidate deployment point numbered i to deploy the server, the location of the eavesdropper estimated by the planner follows a circle centered on the candidate deployment point numbered i. The interior of a circle with radius is a uniform distribution of values ​​within a range.

[0107] S413. Constraints on the range of values ​​for transmission ratio decision variables: (10);

[0108] S414. Constraints on the range of values ​​for drone deployment location decision variables: (11);

[0109] S415. Given the ground server deployment decision and the eavesdropper's location decision, the planner sets the objective function in the third phase to maximize the expected value of the weighted value of transmission cost and confidentiality rate:

[0110] (12);

[0111] In equation (12), This represents the objective function for the third stage, which is the expected value of the weighted average of transmission cost and confidentiality rate. Wherein, and These represent the weights of transmission cost and confidentiality rate, respectively. This represents the expectation operation. In the embodiments of this application, , .

[0112] The objective function for the third stage is: The constraints in the third stage include: the range of values ​​for the transmission ratio decision variables. Constraints on the range of values ​​for drone deployment location decision variables .

[0113] Optionally, in some embodiments of this application, generating a second-stage objective function based on the eavesdropper's location decision variables includes: characterizing a third-stage preset decision variable and a preset intermediate variable based on the second-stage eavesdropper's location decision variables; determining the eavesdropper's eavesdropping rate based on the characterized preset decision variables and preset intermediate variables; and, given a ground server deployment decision, setting the objective function in the second stage to maximize the eavesdropping rate, thus obtaining the second-stage objective function.

[0114] Among them, the preset decision variables include the optimal deployment location of the drone and the transmission ratio, and the preset intermediate variables include the data transmission rate between the drone and the eavesdropper.

[0115] Correspondingly, the decision variable for the eavesdropper's location is denoted as R, and the pre-defined decision variables for the third stage after characterization include: the optimal deployment decision of the drone in the third stage is denoted as... The transmission ratio decision in the third stage is denoted as The data transmission rate between the drone and the eavesdropper in the third phase is denoted as... .

[0116] The eavesdropping rate of the eavesdropper is recorded as follows: .

[0117] For example, the process of generating the objective function and constraints for the second stage includes the following steps:

[0118] S416. The maximum value of the objective function obtained in the third stage is related to the eavesdropper's location decision variable R in the second stage; therefore, it is denoted as... .

[0119] S417. The optimal deployment decision and transmission ratio decision for the drones in the third stage are related to the eavesdropper location decision variable R in the second stage. Therefore, they are denoted as... and .

[0120] The data transmission rate between the drone and the eavesdropper in the third stage is related to the eavesdropper's location decision variable R in the second stage; therefore, they are denoted as... .

[0121] In summary, the optimal values ​​of the decision variables in the third stage (including drone deployment decisions and transmission ratio decisions) and the maximum value of the objective function are all related to the decision variable R in the second stage. Therefore, these decision variables are all functions of R.

[0122] S418. The eavesdropper's eavesdropping rate is: (13); In formula (13), This indicates the eavesdropping rate of the eavesdropper. Among them, This represents the data transmission rate between the drone and the eavesdropper under the optimal drone deployment decision and transmission ratio decision obtained in the third stage.

[0123] S419. Constraints on the range of values ​​for the decision variable regarding the location of the eavesdropper: (14);

[0124] S420. Given the ground server deployment decision, the eavesdropper sets the objective function in the second phase to maximize the eavesdropping rate: (15); In equation (15), This represents the objective function for the second stage, namely the eavesdropping rate.

[0125] The objective function for the second stage is... The constraints for the second stage are: the range of values ​​for the eavesdropper's location decision variable. .

[0126] Optionally, in some embodiments of this application, generating a first-stage objective function based on the deployment decision variables of the ground server includes: characterizing the second-stage eavesdropper optimal location decision variables based on the first-stage ground server deployment decision variables; substituting the characterized eavesdropper optimal location decision variables into the expression for the maximum value of the objective function obtained in the third stage to obtain the substituted expression; and based on the substituted expression, setting the objective function in the first stage with the expected maximization of the weighted value of transmission cost and confidentiality rate under the second-stage eavesdropper optimal location decision to obtain the first-stage objective function.

[0127] In this context, the deployment decision variables for the ground servers in the first phase are denoted as follows: The optimal location decision variable for the eavesdropper in the second stage after characterization is denoted as... The expression after substitution is denoted as .

[0128] For example, the process of generating the objective function and constraints for the first stage includes the following steps:

[0129] S421, the deployment decision variables for the ground server are Among them, when When, it indicates that a ground server is deployed at the candidate deployment point numbered i. When the time is right, it means that the deployment will not be carried out at the alternative deployment point numbered i.

[0130] S422, Decision variables for the optimal location of the eavesdropper in the second phase and the deployment decision variables for the ground server in the first phase. It is relevant, therefore, it is recorded as .

[0131] S423. At this point, the maximum value of the objective function obtained in the third stage can be further denoted as... .

[0132] S424. Constraints on the range of values ​​for deployment decision variables of ground servers: (16);

[0133] S425, the constraint that ground servers can only be deployed in one location: (17);

[0134] S426. In the first phase, the planner sets the objective function to maximize the expected value of the weighted value of transmission cost and confidentiality rate under the optimal location decision of the eavesdropper in the second phase:

[0135] (18);

[0136] In equation (18), This represents the objective function of the first stage, which is the expected value of the weighted average of transmission cost and confidentiality rate under the optimal location decision of the eavesdropper in the second stage.

[0137] The objective function for the first stage is: The constraints in the first phase include the range of values ​​for the deployment decision variables of the ground server. The constraint that ground servers can only be deployed in one place. .

[0138] In addition, in some embodiments, a three-stage dynamic game model is determined based on the objective functions and constraints of the first, second, and third stages, specifically including:

[0139] S427. Summarize equations (2) to (18) in the above embodiments to obtain a three-stage dynamic game model.

[0140] Optionally, in some embodiments of this application, the three-stage dynamic game model is solved based on a two-stage optimization algorithm to obtain the target model parameters after the solution, including: obtaining the preliminary values ​​of the first-stage objective function under all ground server deployment decisions based on the first solution algorithm; arranging the preliminary values ​​from largest to smallest to obtain the arrangement result of the preliminary values; and using the second solution algorithm to solve the first preset number of ground server deployment decisions in the arrangement result to obtain the target model parameters after the solution.

[0141] The two-stage optimization algorithm includes a first solution algorithm and a second solution algorithm. The solution accuracy of the first solution algorithm is less than that of the second solution algorithm.

[0142] The preliminary value refers to the approximate value obtained from the initial calculation. The preset quantity is denoted as N, which can be adjusted according to the actual situation.

[0143] For example, this application also proposes a two-stage optimization algorithm, first coarse and then fine, for the above three-stage dynamic game model, to solve the optimal solution for secure deployment and transmission of air-to-ground wireless systems. First, a coarse but fast algorithm is used to obtain approximate values ​​of the objective function for the first stage under all ground server deployment decisions. After arranging these approximate values ​​from largest to smallest, a fine algorithm is then used to solve the first N ground server deployment decisions.

[0144] First, the implementation process of the first solution algorithm is as follows.

[0145] For each ground server deployment decision, a coarse algorithm is used to calculate the approximate value of the objective function for the first stage. The specific algorithm process is as follows:

[0146] S501, Determine the initial location of the eavesdropper. Let it be the current value. Let the maximum number of iterations be... , In the embodiments of this application, , ;

[0147] S502, given the current value R of the eavesdropper's position decision, replace its random distribution with the expected value of the eavesdropper's estimated position;

[0148] S503, given the current value R of the eavesdropper's location decision, for and Find the answer in two cases. By setting both partial derivatives to zero with respect to the drone deployment decision variables x and y, we can obtain... and The objective function value for the second stage is given below. The larger of the two objective function values ​​for the second stage is denoted as... The optimal deployment decision for the drone at this point is denoted as and ;

[0149] S504, generates random perturbations to the eavesdropper's location decision. The optimal deployment decision for the drone at this time is determined using the method in step S503. and ,as well as , and The objective function value of the second stage ;

[0150] S505, order .in, This is the learning rate for the gradient ascent algorithm. In the embodiments of this application, ;

[0151] S506, if Then let Then return to step S502; otherwise, let the approximate value of the objective function in the first stage be R. and The objective function value for the third stage;

[0152] It should be noted that in step S502, the distance between the eavesdropper and the ground server is R, and the update iteration method of R is as follows: first, an initial value is given. Then, R' is generated by randomly perturbing R, and then the formula is applied. Update R and iterate in this way.

[0153] The above iterative process only considers the distance R between the eavesdropper and the ground server; the planner does not know the eavesdropper's exact location. The planner obviously cannot know the eavesdropper's location before it determines its position. Even after the eavesdropper determines its location, the planner cannot know the exact location, only the approximate distribution of the eavesdroppers (which is relatively realistic). This approximate distribution is given in step S412. During the iteration of the coarse algorithm, whenever the specific location of the eavesdropper is needed, instead of randomly generating a location, the expected value of the distribution in step S412 is used.

[0154] The distribution pattern of the eavesdropper's two-dimensional position under each iteration of R is shown in step S412. Finally, knowing the distribution pattern, the expected value can be obtained directly by using the expected value operation.

[0155] The purpose of replacing the eavesdropper's two-dimensional position with the expected value is to reduce computational complexity. This is because the goal of the coarse algorithm is to quickly find multiple potentially optimal solutions, thus requiring a trade-off between sacrificing some accuracy (such as replacing random distribution with expected value) to reduce computational complexity. Calculations requiring high accuracy are left to the fine algorithm.

[0156] In step S503, C and μ are both linear functions of β, which means that although the range of β is [0,1], the possible optimal solution of β can only be obtained at two extreme points, that is, the optimal β can only be equal to 0 or 1; therefore, this application only needs to compare these two cases, thereby improving the solution efficiency.

[0157] Then, the approximate values ​​of the objective function for the first stage under all ground server deployment decisions are arranged from largest to smallest; first, they are arranged in descending order, and then the exact algorithm is used to solve them one by one.

[0158] In some practical situations, due to reasons such as limited computing resources or the pressure of real-time decision-making, it is not necessary to find the absolutely optimal solution; only a reasonably satisfactory solution is needed. In such cases, arranging the solutions in descending order and then using an exact algorithm can quickly yield a satisfactory solution. For example, if the largest solution, after being processed by the exact algorithm, is already a satisfactory solution, the algorithm can stop, and the exact algorithm is not needed for the remaining N-1 solutions, thus improving the resource utilization of the computation process.

[0159] Finally, the implementation process of the first solution algorithm is as follows.

[0160] A sophisticated algorithm is used to solve the deployment decisions for the first N ground servers. In the embodiments of this application, The specific process of the algorithm is as follows:

[0161] S601, randomly generate an initial solution for the eavesdropper's location decision as the current solution;

[0162] S602, given an initial temperature T0 that is sufficiently large for the given temperature parameter T. In this embodiment of the application, ;

[0163] S603, given the number of iterations K. In this embodiment of the application, ;

[0164] S604, given U. In this embodiment of the application, ;

[0165] S605, perform steps S606 to S613 for k=1, …, K;

[0166] S606, for the current solution The method utilizes Monte Carlo simulation to generate L possible scenarios for estimating the location of the eavesdropper. In the embodiments of this application, ;

[0167] S607, the average of the weighted values ​​of transmission cost and confidentiality rate under the above L possible scenarios. Replace the objective function of the third stage;

[0168] S608, for and Find the results for both cases. By setting both partial derivatives to zero with respect to the drone deployment decision variables x and y, we can obtain... and The objective function value for the second stage. The larger of the two objective function values ​​for the second stage is denoted as... The corresponding optimal deployment decision for drones is denoted as and ;

[0169] S609, Apply random perturbation to the current solution to generate a new solution. ;

[0170] S610, For the new solution, the same processing method as steps S606 to S608 is used to calculate the objective function value for the second stage under the new solution. ;

[0171] S611, Calculate the difference between the objective function of the solution before and after the random perturbation. ;

[0172] S612, if Then accept the solution after random perturbation as the new current solution; otherwise, use probability. The solution after random perturbation is taken as the new current solution;

[0173] S613, if U consecutive new solutions are not accepted, then output the current solution as the optimal solution, and let R, ... and Below The value of the first-stage objective function under the ground server deployment decision is taken as the value of the above N first-stage objective function values. Let the maximum value of the first-stage objective function be the maximum value of the first-stage objective function, and output the ground server deployment decision, eavesdropper location decision, UAV deployment and transmission decision corresponding to this maximum value as the optimal solution for the secure deployment and transmission of the air-to-ground wireless system, and then end;

[0174] S614, T decreases, Then proceed to step S605.

[0175] In the above calculation process, the second solution algorithm (refined algorithm) is a solution algorithm designed in this application by combining the simulated annealing algorithm and Monte Carlo simulation. The simulated annealing algorithm is responsible for finding the global optimum starting from the initial solution. During this search process, some steps require mathematical expectation operations (for example, since the location of the eavesdropper is randomly distributed, the calculation of G3 requires a mathematical expectation operation). At this time, the Monte Carlo simulation is responsible for generating multiple possible scenarios based on the random distribution and using the average value of these multiple possible scenarios to replace the expected value.

[0176] T is a control parameter in the simulated annealing algorithm, mainly used to adjust the probability of accepting suboptimal solutions, thereby balancing global exploration and local exploitation. T gradually decreases as the iteration process progresses. U is a control parameter in the simulated annealing algorithm, used to determine whether the algorithm has converged.

[0177] The entire process of using a refined algorithm to solve the deployment decision for the first N ground servers can be summarized as follows: give T a large initial value and set the value of U; in each iteration, a new solution is generated, and it is recorded whether the new solution has been accepted; as the number of iterations k increases, T decreases; when U consecutive new solutions have not been accepted, the current solution is output as the optimal solution, and the algorithm stops.

[0178] Figure 5 This is a schematic diagram illustrating the optimal deployment and transmission scheme for an air-to-ground wireless system in one embodiment. In this embodiment, the maximum value of the objective function for the first stage can be obtained as 2.37, and the following can be obtained: Figure 5The diagram illustrates the optimal deployment and transmission scheme for a secure air-to-ground wireless system. Solid circles represent the deployment points of the ground server, triangles represent the two-dimensional projection positions of the UAV, squares represent the positions of eavesdroppers, and the arrows pointing from the triangles to the circles indicate the transmission ratio.

[0179] Figure 6 This is a schematic diagram of the overall implementation process in one embodiment. The method for generating a secure deployment and transmission scheme for an air-to-ground wireless system based on dynamic game theory provided in this application is also known as a method for secure deployment and transmission of an air-to-ground wireless system based on dynamic game theory. Figure 6 As shown, the task scenario is first characterized, then a dynamic game model is established, and then a two-stage optimization method of coarse-to-fine optimization is used to solve the problem. Finally, the optimal solution for the secure deployment and transmission of the air-to-ground wireless system is obtained.

[0180] Figure 7 This is a flowchart illustrating a method for generating a secure deployment and transmission scheme for an air-to-ground wireless system based on dynamic game theory, as described in another embodiment. In this embodiment, the method specifically includes the following steps:

[0181] S701, Obtain the initial model parameters required for the representation process of the target task scenario; Obtain the event occurrence order corresponding to the target task scenario, and use the reverse order of the event occurrence order as the model construction order;

[0182] S702, determine that the planner aims to maximize the expected value of the weighted value of transmission cost and confidentiality rate as the planning objective, and determine that the eavesdropper aims to maximize the eavesdropping rate as the eavesdropping objective;

[0183] S703 determines the mission security rate and transmission cost of the UAV based on the initial model parameters, UAV deployment location decision variables, and transmission ratio decision variables. Given the ground server deployment decision and the eavesdropper's location decision, the planner sets the objective function in the third stage by maximizing the expected value of the weighted value of transmission cost and security rate, thus obtaining the objective function for the third stage.

[0184] S704, based on the eavesdropper location decision variables in the second stage, characterize the preset decision variables and preset intermediate variables in the third stage; determine the eavesdropper's eavesdropping rate based on the characterized preset decision variables and preset intermediate variables;

[0185] S705, given the ground server deployment decision, the eavesdropper sets the objective function to maximize the eavesdropping rate in the second phase, thus obtaining the objective function for the second phase;

[0186] S706, based on the deployment decision variables of the ground server in the first stage, characterize the optimal location decision variables of the eavesdropper in the second stage; substitute the obtained optimal location decision variables of the eavesdropper into the expression for the maximum value of the objective function obtained in the third stage to obtain the expression after substitution.

[0187] S707, based on the substituted expression, the planner sets the objective function in the first stage by maximizing the expected value of the weighted value of transmission cost and confidentiality rate under the optimal position decision of the eavesdropper in the second stage, and obtains the objective function of the first stage;

[0188] S708, based on the objective functions and constraints of the first, second and third stages, determine the three-stage dynamic game model;

[0189] S709, Based on the first solution algorithm, the preliminary values ​​of the objective function for the first stage under all ground server deployment decisions are obtained; the preliminary values ​​are arranged from largest to smallest to obtain the arrangement result of the preliminary values;

[0190] S710: The second solution algorithm is used to solve the deployment decisions of the first preset number of ground servers in the arrangement results to obtain the target model parameters after the solution; and a safe deployment and transmission scheme for the air-to-ground wireless system is generated based on the target model parameters.

[0191] It should be noted that the specific limitations of the above steps can be found in the above description of the specific limitations of a method for generating a secure deployment and transmission scheme for an air-to-ground wireless system based on dynamic game theory, and will not be repeated here.

[0192] Figures 1 to 7 Any technical feature in the embodiments corresponding to any of the above items is also applicable to the embodiments of this application. Figures 8 to 10 The corresponding implementation examples will not be repeated hereafter.

[0193] The above describes a method for generating a secure deployment and transmission scheme for an air-to-ground wireless system based on dynamic game theory in the embodiments of this application. The following describes the apparatus for performing the above method.

[0194] Figure 8 Here is a structural block diagram of a device for generating a secure deployment and transmission scheme for an air-to-ground wireless system based on dynamic game theory, as described below. Figure 8 A device for generating secure deployment and transmission schemes for an air-to-ground wireless system based on dynamic game theory is described. The device includes:

[0195] The initial model parameter acquisition module 801 is used to acquire the initial model parameters required for the representation process of the target task scenario;

[0196] The model building order determination module 802 is used to obtain the event occurrence order corresponding to the target task scenario and use the reverse order of the event occurrence order as the model building order.

[0197] The target determination module 803 is used to determine the planner's planning target as maximizing the weighted value of transmission cost and confidentiality rate, and to determine the eavesdropper's eavesdropping target as maximizing the eavesdropping rate;

[0198] The model building module 804 is used to build a three-stage dynamic game model according to the model building order, with the planning target and the eavesdropping target as the model building targets, and based on the initial model parameters.

[0199] The model solving module 805 is used to solve the three-stage dynamic game model based on the two-stage optimization algorithm to obtain the target model parameters after the solution.

[0200] The scheme generation module 806 is used to generate a secure deployment and transmission scheme for the air-to-ground wireless system based on the target model parameters.

[0201] In this embodiment of the application, based on, as follows Figure 8 The connections between the modules shown in the diagram demonstrate how the cooperation between these modules can improve the security of data transmission from the deployed drone, increase deployment efficiency, and enhance deployment effectiveness.

[0202] In another embodiment, a device for generating a secure deployment and transmission scheme for an air-to-ground wireless system based on dynamic game theory is provided. This device can be a computer device, such as a server, and its internal structure diagram can be as follows: Figure 9 As shown, the device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The device's database stores relevant data. The I / O interfaces are used for exchanging information between the processor and external devices. The device's communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements the various methods described in the above embodiments.

[0203] In another embodiment, a device for generating a secure deployment and transmission scheme for an air-to-ground wireless system based on dynamic game theory is provided. This device can be a computer device, such as a terminal, and its internal structure diagram can be as follows: Figure 10As shown, the device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements the various methods described in the above embodiments.

[0204] Those skilled in the art will understand that Figure 9 and Figure 10 The structure shown is merely a block diagram of a portion of the structure related to the solution of this application, and does not constitute a limitation on the secure deployment and transmission scheme generation device for the air-to-ground wireless system based on dynamic game theory applied thereto. Specifically, the device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements, in order to achieve the functions of computer equipment such as terminals or servers.

[0205] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0206] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and modules described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0207] In the embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, apparatuses, or modules, and may be electrical, mechanical, or other forms.

[0208] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0209] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium.

[0210] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product.

[0211] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., a solid-state disk (SSD)).

[0212] The technical solutions provided in the embodiments of this application have been described in detail above. Specific examples have been used in the embodiments of this application to illustrate the principles and implementation methods of the embodiments of this application. The description of the above embodiments is only for the purpose of helping to understand the methods and core ideas of the embodiments of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the embodiments of this application. Therefore, the content of this specification should not be construed as a limitation on the embodiments of this application.

Claims

1. A method for generating a secure deployment and transmission scheme for an air-to-ground wireless system based on dynamic game theory, characterized in that, The method includes: Obtain the initial model parameters required for the representation process of the target task scenario; The process involves obtaining the sequence of events corresponding to the target task scenario and using the reverse order of these events as the model building order. Specifically, this includes: determining the event sequence as: first stage, second stage, and third stage; reversing the event sequence to determine the model building order as: third stage, second stage, and first stage; wherein the decision-making content of the first stage is for the planner to determine the deployment location of the ground server, the decision-making content of the second stage is for the eavesdropper to determine its own location, and the decision-making content of the third stage is for the planner to determine the deployment location and transmission ratio of the drone. The planner's planning objective is to maximize the expected value of the weighted average of transmission cost and confidentiality rate, and the eavesdropper's eavesdropping objective is to maximize the eavesdropping rate. Following the model construction sequence, and using the planning objective and the eavesdropping objective as model construction targets, a three-stage dynamic game model is constructed based on the initial model parameters. Specifically, this includes: generating the objective function and constraints for the third stage based on the initial model parameters, UAV deployment location decision variables, and transmission ratio decision variables; generating the objective function and constraints for the second stage based on the eavesdropper location decision variables; generating the objective function and constraints for the first stage based on the ground server deployment decision variables; and determining the three-stage dynamic game model based on the objective functions and constraints of the first, second, and third stages. The three-stage dynamic game model is solved using a two-stage optimization algorithm to obtain the target model parameters. Specifically, this includes: obtaining preliminary values ​​of the first-stage objective function for all ground server deployment decisions using a first solution algorithm; arranging these preliminary values ​​from largest to smallest to obtain an arrangement result; and using a second solution algorithm to solve the first preset number of ground server deployment decisions in the arrangement result to obtain the target model parameters. The two-stage optimization algorithm includes the first solution algorithm and the second solution algorithm. The solution accuracy of the first solution algorithm is less than that of the second solution algorithm. A secure deployment and transmission scheme for the air-to-ground wireless system is generated based on the target model parameters.

2. The method according to claim 1, characterized in that, The step of generating the objective function for the third stage based on the initial model parameters, UAV deployment location decision variables, and transmission ratio decision variables includes: The mission security rate and transmission cost of the UAV are determined based on the initial model parameters, the UAV deployment location decision variables, and the transmission ratio decision variables. Given the decisions on ground server deployment and the location of the eavesdropper, the planner sets the objective function in the third phase by maximizing the expected value of the weighted value of transmission cost and confidentiality rate, thus obtaining the objective function for the third phase.

3. The method according to claim 1, characterized in that, The step of generating the objective function for the second stage based on the eavesdropper's location decision variable includes: Based on the eavesdropper location decision variables in the second stage, the preset decision variables and preset intermediate variables in the third stage are characterized; wherein, the preset decision variables include the optimal deployment location decision variable of the drone and the transmission ratio decision variable, and the preset intermediate variables include the data transmission rate decision variable between the drone and the eavesdropper; The eavesdropping rate of the eavesdropper is determined based on the preset decision variables and the preset intermediate variables obtained from the characterization. Given the ground server deployment decision, the eavesdropper sets the objective function to maximize the eavesdropping rate in the second phase, thus obtaining the objective function for the second phase.

4. The method according to claim 1, characterized in that, The step of generating the objective function for the first phase based on the deployment decision variables of the ground server includes: Based on the deployment decision variables of the ground server in the first stage, the optimal location decision variables of the eavesdropper in the second stage are characterized. Substitute the optimal location decision variables of the eavesdropper obtained from the characterization into the expression for the maximum value of the objective function obtained in the third stage to obtain the expression after substitution; Based on the substituted expression, the planner sets the objective function in the first stage by maximizing the expected value of the weighted value of transmission cost and confidentiality rate under the optimal location decision of the eavesdropper in the second stage, thus obtaining the objective function for the first stage.

5. A device for generating a secure deployment and transmission scheme for an air-to-ground wireless system based on dynamic game theory, characterized in that, The device includes: The initial model parameter acquisition module is used to acquire the initial model parameters required for the representation process of the target task scenario; The model building order determination module is used to obtain the event occurrence order corresponding to the target task scenario, and use the reverse order of the event occurrence order as the model building order; specifically, it is used to: determine the event occurrence order as: first stage, second stage, third stage; and reverse the event occurrence order to determine the model building order as: the third stage, the second stage, the first stage; wherein, the decision content of the first stage is for the planner to determine the deployment location of the ground server, the decision content of the second stage is for the eavesdropper to determine its own location, and the decision content of the third stage is for the planner to determine the deployment location and transmission ratio of the drone; The target determination module is used to determine the planner's planning target as maximizing the weighted value of transmission cost and confidentiality rate, and to determine the eavesdropper's eavesdropping target as maximizing the eavesdropping rate. The model building module is used to construct a three-stage dynamic game model according to the model building sequence, using the planning objective and the eavesdropping objective as model building objectives, and based on the initial model parameters. Specifically, it is used to: generate the objective function and constraints for the third stage based on the initial model parameters, UAV deployment location decision variables, and transmission ratio decision variables; generate the objective function and constraints for the second stage based on the eavesdropper location decision variables; generate the objective function and constraints for the first stage based on the ground server deployment decision variables; and determine the three-stage dynamic game model based on the objective functions and constraints for the first, second, and third stages. The model solving module is used to solve the three-stage dynamic game model based on a two-stage optimization algorithm to obtain the solved target model parameters. Specifically, it is used to: obtain preliminary values ​​of the first-stage objective function under all ground server deployment decisions based on a first solving algorithm; arrange the preliminary values ​​from largest to smallest to obtain the arrangement result of the preliminary values; and use a second solving algorithm to solve the first preset number of ground server deployment decisions in the arrangement result to obtain the solved target model parameters. The two-stage optimization algorithm includes the first solving algorithm and the second solving algorithm. The solution accuracy of the first solving algorithm is less than that of the second solving algorithm. The scheme generation module is used to generate a secure deployment and transmission scheme for the air-to-ground wireless system based on the target model parameters.

6. A device for generating a secure deployment and transmission scheme for an air-to-ground wireless system based on dynamic game theory, characterized in that, The device includes: At least one processor and memory; The memory is used to store program code, and the processor is used to call the program code stored in the memory to execute the method as described in any one of claims 1 to 4.

7. A computer storage medium, characterized in that, It includes instructions that, when executed on a computer, cause the computer to perform the method as described in any one of claims 1 to 4.

Images