Multi-task non-ground network resource allocation method and device based on game theory

Abstract

The invention provides a multi-task non-ground network resource allocation method and device based on a game theory, and relates to the technical field of wireless communication. The method comprises the following steps: establishing a multi-task unloading and communication transmission network model which comprises a plurality of LEO satellites, a plurality of unmanned aerial vehicles and a plurality of ground users; establishing a network utility optimization problem based on time delay and energy consumption; obtaining a non-ground network resource allocation result according to an evolutionary minority game method and a Stackelberg game model; wherein the non-ground network resource allocation result comprises unloading association, unloading proportion and resource allocation, so as to realize optimization of communication delay and network energy consumption. According to the technical scheme provided by the invention, the multi-task transmission requirement of a ground user can be met in a non-ground network environment, the network load is balanced while the transmission delay in the communication process is effectively reduced, and green and sustainable development of non-ground network communication is realized.

Description

Technical Field

[0001] This invention relates to the field of wireless communication technology, and in particular to a method and apparatus for allocating resources in a multi-task non-terrestrial network based on game theory. Background Technology

[0002] Non-terrestrial networks, encompassing satellites and drones deployed at varying altitudes, enable three-dimensional coverage and broadband communication services globally, representing a key technology for achieving 6G all-time, all-terrain coverage. By deploying edge servers within satellites and drones, non-terrestrial networks can effectively shorten task processing time and improve service quality. However, current non-terrestrial networks still face challenges such as dynamic network heterogeneity, long communication response times, and difficulties in ensuring differentiated services. Furthermore, limitations in satellite computing and communication resources, as well as the energy consumption and computing power of drones, collectively constitute key bottlenecks restricting network performance improvement. Computation offloading technology allows users to transfer tasks to edge servers, compensating for the shortcomings of non-terrestrial networks in terms of communication resources, computing resources, and energy consumption, thus meeting users' communication needs for improved efficiency, service optimization, and real-time response.

[0003] Non-terrestrial network nodes face a conflict between limited resources and multi-tasking demands when processing user tasks. A partial offloading strategy dynamically allocates computing and communication resources based on task requirements and network status to balance the workload between users and computing devices. Simultaneously, game theory provides an effective analytical framework to help nodes maximize their individual interests and improve the efficiency of the entire network, offering a flexible solution to resource allocation problems in non-terrestrial networks. Therefore, combining partial offloading strategies with game theory methods is a good approach to solving the multi-task offloading and resource allocation problem.

[0004] In non-terrestrial networks, the resource allocation problem considering multi-tasking requirements, dynamic topology changes, and equipment energy consumption has not been systematically studied. Therefore, there is an urgent need to introduce a low-latency, low-energy resource allocation strategy to balance network load while meeting latency-sensitive communication needs, thereby achieving green and sustainable development of non-terrestrial network communication. Summary of the Invention

[0005] To address the technical challenges of resource allocation in non-terrestrial networks, this invention provides a game theory-based method and apparatus for multi-task non-terrestrial network resource allocation. The technical solution is as follows:

[0006] On the one hand, a game theory-based method for multi-task non-terrestrial network resource allocation is provided. This method is implemented by a multi-task non-terrestrial network resource allocation device and includes:

[0007] S1. Establish a multi-task offloading and communication transmission network model; the multi-task offloading and communication transmission network model includes: multiple LEO satellites, multiple UAVs and multiple ground users.

[0008] S2. Based on the multi-task offloading and communication transmission network model, establish a network utility optimization problem based on latency and energy consumption.

[0009] S3. Based on the evolutionary minority game method and the Stackelberg game model, the non-terrestrial network resource allocation results are obtained; among them, the non-terrestrial network resource allocation results include: offloading association, offloading ratio and resource allocation.

[0010] Optionally, the multi-task offloading and communication transmission network model in S1 includes:

[0011] Initialize multiple LEO satellites, multiple UAVs, and multiple ground users to establish a multi-task offloading and communication transmission network model.

[0012] In this process, each of the multiple ground users generates a task, and a partial offloading strategy is adopted to divide each ground user's task into a local computing task and a computing device computing task. The ground user completes the local computing task, while one of the multiple LEO satellites and multiple UAVs acts as a computing device to complete the computing device computing task.

[0013] The total time cost of completing a task for any ground user is expressed by the following formula (1):

[0014] (1)

[0015] The total energy consumption for completing a task for any ground user is expressed by the following formula (2):

[0016] (2)

[0017] In the formula, Indicates the total time cost. This represents the computation latency for a ground user to complete a local computing task. This indicates the transmission delay at which the computing device receives the computing task from the computing device. This represents the computational latency of a computing device in completing a computational task. Indicates total energy consumption. This represents the computing energy consumption of a ground user to complete a local computing task. This indicates the power consumption of the computing device when receiving a computing task. This indicates the energy consumption of a computing device to complete its computing tasks.

[0018] Optionally, the establishment of network utility optimization problem based on latency and energy consumption in S2 includes:

[0019] A network utility minimization problem based on latency and energy consumption is established. Based on this problem, an objective function for the total network utility value is established. The network utility minimization problem based on latency and energy consumption is decomposed into an offloading correlation subproblem, an offloading proportion subproblem, and a resource allocation subproblem.

[0020] Optionally, the objective function for the total network utility value in S21 is expressed by the following formula (3):

[0021] (3)

[0022] In the formula, Indicates whether the task should be uninstalled. This indicates the proportion of data that was uninstalled. Indicates the proportion of bandwidth resources. Indicates the proportion of computing resources. Represents any task. Represents a set of tasks. The weighting coefficients representing latency. Indicates the total time cost. The weighting coefficient representing energy consumption. Indicates total energy consumption. This indicates a weighted value constraint. This means the task can only be offloaded to a single computing device. Indicates computing device, Represents the LEO satellite set. Indicates a collection of drones. Indicates task Whether to transmit to computing device middle, This indicates the service time constraint of the computing device. Indicates the remaining service time of the computing device. This indicates bandwidth resource constraints. Indicates assignment to task The proportion of wireless bandwidth, Indicates computational resource constraints. This indicates that the computing device assigns tasks. The proportion of computing resources This indicates an unloading ratio constraint. This indicates the proportion of task data computed locally. Indicates local computation. This represents the set of ground users.

[0023] Optionally, in S3, the non-terrestrial network resource allocation results are obtained based on the evolutionary minority game method and the Stackelberg game model, including:

[0024] S31. Using the evolutionary minority game method, solve the decision variables of the unloading correlation subproblem.

[0025] S32. Establish a Stackelberg game model and solve the decision variables of the unloading ratio subproblem and the resource allocation subproblem using the Stackelberg game model.

[0026] S33. Obtain the total network utility value based on the decision variables of the unloading correlation subproblem, the unloading proportion subproblem, and the resource allocation subproblem.

[0027] S34. Determine whether the total utility value of the network is within a preset value range within a preset time.

[0028] If so, output the optimal solution for unloading association, unloading ratio and resource allocation to obtain the non-terrestrial network resource allocation result.

[0029] If not, determine whether the preset number of iterations has been reached. If it has, output the optimal solution for unloading association, unloading ratio and resource allocation to obtain the non-terrestrial network resource allocation result. If it has not been reached, proceed to step S31.

[0030] Optionally, S31 employs an evolutionary minority game approach to solve the decision variables of the unloading-related subproblem, including:

[0031] An evolutionary minority game approach is adopted to solve the decision variables of the unloading-related subproblem by fixing the unloading ratio, bandwidth resources, and computing resources.

[0032] Optionally, S32 establishes a Stackelberg game model, and solves for the decision variables of the unloading ratio subproblem and the resource allocation subproblem using the Stackelberg game model, including:

[0033] Based on the strategic interactions between ground users and computing devices, a Stackelberg game model is established. The objective of the Stackelberg game model is to minimize the utility value of the leader and the utility value of the followers; where ground users are the leaders and computing devices are the followers.

[0034] Construct the utility function of ground users, solve the utility function of ground users, and obtain the decision variables of the unloading ratio subproblem; wherein, the utility function of ground users is expressed by the following formula (4):

[0035] (4)

[0036] Construct the utility function of the computing device, solve the utility function of the computing device, and obtain the decision variables of the resource allocation subproblem; wherein, the utility function of the computing device is expressed by the following formula (5):

[0037] (5)

[0038] In the formula, Represents the user's utility function. The weighting coefficients representing latency. This represents the computation latency for a ground user to complete a local computing task. The weighting coefficient representing energy consumption. This represents the computing energy consumption of a ground user to complete a local computing task. Represents the utility function of a computing device. This indicates the transmission delay at which the computing device receives the computing task from the computing device. This represents the computational latency of a computing device in completing a computational task. This indicates the power consumption of the computing device when receiving a computing task. This indicates the energy consumption of a computing device to complete its computing tasks.

[0039] On the other hand, a game theory-based multi-task non-terrestrial network resource allocation device is provided. This device is applied to a game theory-based multi-task non-terrestrial network resource allocation method. The device includes:

[0040] A module is established to create a multi-task offloading and communication transmission network model; the multi-task offloading and communication transmission network model includes: multiple LEO satellites, multiple UAVs, and multiple ground users.

[0041] The module is used to build a network utility optimization problem based on latency and energy consumption, based on a multi-task offloading and communication transmission network model.

[0042] The output module is used to obtain the non-terrestrial network resource allocation results based on the evolutionary minority game method and the Stackelberg game model. The non-terrestrial network resource allocation results include: offloading association, offloading ratio and resource allocation.

[0043] Optionally, modules can be created for further use in:

[0044] Initialize multiple LEO satellites, multiple UAVs, and multiple ground users to establish a multi-task offloading and communication transmission network model.

[0045] In this process, each of the multiple ground users generates a task, and a partial offloading strategy is adopted to divide each ground user's task into a local computing task and a computing device computing task. The ground user completes the local computing task, while one of the multiple LEO satellites and multiple UAVs acts as a computing device to complete the computing device computing task.

[0046] The total time cost of completing a task for any ground user is expressed by the following formula (1):

[0047] (1)

[0048] The total energy consumption for completing a task for any ground user is expressed by the following formula (2):

[0049] (2)

[0050] In the formula, Indicates the total time cost. This represents the computation latency for a ground user to complete a local computing task. This indicates the transmission delay at which the computing device receives the computing task from the computing device. This represents the computational latency of a computing device in completing a computational task. Indicates total energy consumption. This represents the computing energy consumption of a ground user to complete a local computing task. This indicates the power consumption of the computing device when receiving a computing task. This indicates the energy consumption of a computing device to complete its computing tasks.

[0051] Optionally, building modules are further used for:

[0052] A network utility minimization problem based on latency and energy consumption is established. Based on this problem, an objective function for the total network utility value is established. The network utility minimization problem based on latency and energy consumption is decomposed into an offloading correlation subproblem, an offloading proportion subproblem, and a resource allocation subproblem.

[0053] Optionally, the objective function for the total utility value of the network is expressed by the following formula (3):

[0054] (3)

[0055] In the formula, Indicates whether the task should be uninstalled. This indicates the proportion of data that was uninstalled. Indicates the proportion of bandwidth resources. Indicates the proportion of computing resources. Represents any task. Represents a set of tasks. The weighting coefficients representing latency. Indicates the total time cost. The weighting coefficient representing energy consumption. Indicates total energy consumption. This indicates a weighted value constraint. This means the task can only be offloaded to a single computing device. Indicates computing device, Represents the LEO satellite set. Indicates a collection of drones. Indicates task Whether to transmit to computing device middle, This indicates the service time constraint of the computing device. Indicates the remaining service time of the computing device. This indicates bandwidth resource constraints. Indicates assignment to task The proportion of wireless bandwidth, Indicates computational resource constraints. This indicates that the computing device assigns tasks. The proportion of computing resources This indicates an unloading ratio constraint. This indicates the proportion of task data computed locally. Indicates local computation. This represents the set of ground users.

[0056] Optionally, the output module is further used for:

[0057] S31. Using the evolutionary minority game method, solve the decision variables of the unloading correlation subproblem.

[0058] S32. Establish a Stackelberg game model and solve the decision variables of the unloading ratio subproblem and the resource allocation subproblem using the Stackelberg game model.

[0059] S33. Obtain the total network utility value based on the decision variables of the unloading correlation subproblem, the unloading proportion subproblem, and the resource allocation subproblem.

[0060] S34. Determine whether the total utility value of the network is within a preset value range within a preset time.

[0061] If so, output the optimal solution for unloading association, unloading ratio and resource allocation to obtain the non-terrestrial network resource allocation result.

[0062] If not, determine whether the preset number of iterations has been reached. If it has, output the optimal solution for unloading association, unloading ratio and resource allocation to obtain the non-terrestrial network resource allocation result. If it has not been reached, proceed to step S31.

[0063] Optionally, the output module is further used for:

[0064] An evolutionary minority game approach is adopted to solve the decision variables of the unloading-related subproblem by fixing the unloading ratio, bandwidth resources, and computing resources.

[0065] Optionally, the output module is further used for:

[0066] Based on the strategic interactions between ground users and computing devices, a Stackelberg game model is established. The objective of the Stackelberg game model is to minimize the utility value of the leader and the utility value of the followers; where ground users are the leaders and computing devices are the followers.

[0067] Construct the utility function of ground users, solve the utility function of ground users, and obtain the decision variables of the unloading ratio subproblem; wherein, the utility function of ground users is expressed by the following formula (4):

[0068] (4)

[0069] Construct the utility function of the computing device, solve the utility function of the computing device, and obtain the decision variables of the resource allocation subproblem; wherein, the utility function of the computing device is expressed by the following formula (5):

[0070] (5)

[0071] In the formula, Represents the user's utility function. The weighting coefficients representing latency. This represents the computation latency for a ground user to complete a local computing task. The weighting coefficient representing energy consumption. This represents the computing energy consumption of a ground user to complete a local computing task. Represents the utility function of a computing device. This indicates the transmission delay at which the computing device receives the computing task from the computing device. This represents the computational latency of a computing device in completing a computational task. This indicates the power consumption of the computing device when receiving a computing task. This indicates the energy consumption of a computing device to complete its computing tasks.

[0072] On the other hand, a multi-task non-terrestrial network resource allocation device is provided, comprising: a processor; and a memory storing computer-readable instructions, wherein when the computer-readable instructions are executed by the processor, any one of the above-described game theory-based multi-task non-terrestrial network resource allocation methods is implemented.

[0073] On the other hand, a computer-readable storage medium is provided, wherein at least one instruction is stored in the storage medium, the at least one instruction being loaded and executed by a processor to implement any of the above-described game theory-based multi-task non-terrestrial network resource allocation methods.

[0074] The beneficial effects of the technical solutions provided by the embodiments of the present invention include at least the following:

[0075] This invention proposes a multi-task offloading and communication transmission network model. Combining the characteristics of multi-task requirements, dynamic topology changes, and equipment energy consumption, it flexibly offloads user tasks to dynamically changing LEO satellites or UAVs. This not only meets users' communication needs for low latency and low energy consumption, but also further alleviates the problem of multi-task service assurance faced by non-terrestrial networks.

[0076] The present invention relates to a game theory-based multi-task non-terrestrial network resource allocation method and system. With the goal of minimizing network latency and energy consumption, the method proposes a multi-task non-terrestrial network resource allocation approach based on game theory to obtain the optimal resource allocation strategy. This approach balances network load while meeting latency-sensitive communication requirements, thereby achieving green and sustainable development of non-terrestrial network communication.

[0077] This invention employs an evolutionary minority game approach to solve the offloading association problem, preventing users from making the same offloading decisions, reducing network congestion, and achieving a balance in network load. Simultaneously, it combines the Stackelberg game model to solve the offloading ratio and resource allocation problem, achieving a Nash equilibrium to realize the rational allocation of resources and achieve dual optimization of individual and network interests. Attached Figure Description

[0078] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0079] Figure 1 This is a flowchart of a multi-task non-terrestrial network resource allocation method based on game theory provided in an embodiment of the present invention;

[0080] Figure 2 This is a diagram of a multi-task offloading and communication transmission network provided in an embodiment of the present invention;

[0081] Figure 3 This is a block diagram of a multi-task non-terrestrial network resource allocation device based on game theory provided in an embodiment of the present invention;

[0082] Figure 4 This is a schematic diagram of the structure of a multi-task non-terrestrial network resource allocation device provided in an embodiment of the present invention. Detailed Implementation

[0083] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0084] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0085] In the embodiments of this invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning. Similarly, the terms "of," "corresponding (relevant)," and "corresponding" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning.

[0086] In this embodiment of the invention, sometimes a subscript such as W1 may be written in a non-subscript form such as W1. When the difference is not emphasized, the meaning they express is the same.

[0087] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0088] This invention provides a game theory-based method for allocating multi-task non-terrestrial network resources. This method can be implemented by a multi-task non-terrestrial network resource allocation device, which can be a terminal or a server. Figure 1 The flowchart shown is for a multi-task non-terrestrial network resource allocation method based on game theory. The processing flow of this method may include the following steps:

[0089] S1. Establish a multi-task offloading and communication transmission network model; the multi-task offloading and communication transmission network model includes: multiple LEO satellites, multiple UAVs and multiple ground users.

[0090] Specifically, such as Figure 2 As shown, the parameters of multiple LEO satellites, multiple UAVs and multiple ground users are initialized, and a multi-task offloading and communication transmission network model is established.

[0091] LEO satellites have fixed orbital paths; drones move towards the user's location at a certain speed when performing tasks; ground users generate a large number of tasks, which need to be relayed by LEO satellites and drones to offload the tasks to edge computing servers for computation; each LEO satellite and drone is equipped with a mobile edge computing server, which allocates communication bandwidth and computing resources to the tasks and can provide services to multiple ground users.

[0092] To fully utilize network computing resources, a partial offloading strategy is adopted. User tasks can be divided, with one part being computed on the local server. The computation latency of the user task computed locally is [missing information]. The calculated energy consumption is Another part is transmitted to LEO satellites or drones for execution, using LEO satellites and drones as computing devices; the transmission latency during the process of the computing device receiving the user task is... Transmission energy consumption is The computational latency for processing this task is Energy consumption is .

[0093] Complete the task Total time cost of uninstallation It is expressed by the following formula (1):

[0094] (1)

[0095] Complete the task Total energy consumption of unloading It is expressed by the following formula (2):

[0096] (2)

[0097] In the formula, Indicates the total time cost. This represents the computation latency for a ground user to complete a local computing task. This indicates the transmission delay at which the computing device receives the computing task from the computing device. This represents the computational latency of a computing device in completing a computational task. Indicates total energy consumption. This represents the computing energy consumption of a ground user to complete a local computing task. This indicates the power consumption of the computing device when receiving a computing task. This indicates the energy consumption of a computing device to complete its computing tasks.

[0098] S2. Based on the multi-task offloading and communication transmission network model, establish a network utility optimization problem based on latency and energy consumption.

[0099] Optionally, the establishment of a network utility optimization problem based on latency and energy consumption in step S2 above may include:

[0100] A network utility minimization problem based on latency and energy consumption is established. Based on this problem, an objective function for the total network utility value is established. The network utility minimization problem based on latency and energy consumption is decomposed into an offloading correlation subproblem, an offloading proportion subproblem, and a resource allocation subproblem.

[0101] The objective function for the total utility value of the network is expressed by the following formula (3):

[0102] (3)

[0103] In the formula, Indicates whether the task should be uninstalled. This indicates the proportion of data that was uninstalled. Indicates the proportion of bandwidth resources. Indicates the proportion of computing resources. Represents any task. Represents a set of tasks. and These are the weighting coefficients for latency and energy consumption, respectively, with different weighting coefficients for different communication tasks. Indicates the total time cost. Indicates total energy consumption. This indicates a weighted value constraint. This means the task can only be offloaded to a single computing device. Indicates computing device, Represents the LEO satellite set. Indicates a collection of drones. Indicates task Whether to transmit to computing device middle, This indicates the service time constraint of the computing device. Indicates the remaining service time of the computing device. This indicates bandwidth resource constraints. Indicates assignment to task The proportion of wireless bandwidth, Indicates computational resource constraints. This indicates that the computing device assigns tasks. The proportion of computing resources This indicates an unloading ratio constraint. This indicates the proportion of task data computed locally. Indicates local computation. This represents the set of ground users.

[0104] In one feasible implementation, with the goal of minimizing task execution latency and network energy consumption, the optimal offloading association, offloading ratio, and resource allocation strategy are solved to achieve a reasonable allocation of communication and computing resources and improve task execution efficiency.

[0105] S3. Based on the evolutionary minority game method and the Stackelberg game model, the non-terrestrial network resource allocation results are obtained; among them, the non-terrestrial network resource allocation results include: offloading association, offloading ratio and resource allocation.

[0106] Optionally, the process of obtaining the non-terrestrial network resource allocation result based on the evolutionary minority game method and the Stackelberg game model in step S3 above may include the following steps S31-S34:

[0107] S31. Using the evolutionary minority game method, the decision variables of the unloading-related subproblem are analyzed. Solve the problem.

[0108] Optionally, an evolutionary minority game approach can be adopted to solve the decision variables of the unloading-related subproblem by fixing the unloading ratio, bandwidth resources, and computing resources.

[0109] Specifically, an available set of policies is selected from the policy pool, and their initial probabilities are randomly set to initialize the unloading policy.

[0110] The cumulative probability of each strategy in the strategy set is calculated and stored, and the selected device index is determined by roulette wheel method.

[0111] Store the current connection state and update the current minority and majority policies.

[0112] Calculate the total network utility value of the current connection state and update the cumulative probability of the policy.

[0113] The process continues until the number of iterations reaches a pre-set threshold, at which point the network evolves to a stable state, yielding the optimal offloading association decision.

[0114] S32. Establish a Stackelberg game model and use it to analyze the decision variables of the unloading proportion subproblem. Decision variables of the resource allocation subproblem , Solve the problem.

[0115] Optionally, step S32 above may include the following steps S321-S323:

[0116] S321. Based on the strategic interaction between ground users and computing devices, establish a Stackelberg game model. The objective of the Stackelberg game model is to minimize the utility value of the leader and the utility value of the followers; where ground users are the leaders and computing devices are the followers.

[0117] In one feasible implementation, a Stackelberg game model is established based on the evolutionary minority game algorithm.

[0118] Specifically, the strategic interaction between users and computing devices is modeled as a Stackelberg game model, with the goal that leaders and followers want to minimize their own utility values, thereby ensuring that the total utility value of the network is minimized.

[0119] Ground users, acting as leaders, generate and divide tasks, and determine the decision variables for the offloading ratio. .

[0120] LEO satellites and drones, acting as followers, adjust their resource allocation strategies based on the received missions, thus determining the resource allocation decision variables. , .

[0121] S322. The user's utility function is defined as the weighted sum of execution delay and energy consumption during the execution of its own task, expressed by the following formula (4):

[0122] (4)

[0123] S323. The utility function of a computing device is defined as the weighted sum of execution delay and energy consumption during the transmission and processing of the receiving task, expressed by the following formula (5):

[0124] (5)

[0125] In the formula, Represents the user's utility function. The weighting coefficients representing latency. This represents the computation latency for a ground user to complete a local computing task. The weighting coefficient representing energy consumption. This represents the computing energy consumption of a ground user to complete a local computing task. Represents the utility function of a computing device. This indicates the transmission delay at which the computing device receives the computing task from the computing device. This represents the computational latency of a computing device in completing a computational task. This indicates the power consumption of the computing device when receiving a computing task. This indicates the energy consumption of a computing device to complete its computing tasks.

[0126] The issues of unloading ratio and resource allocation thus transform into a game between users and computing devices.

[0127] Furthermore, based on the Stackelberg game model, the decision variable for the unloading ratio is... Resource allocation decision variables , Solve the problem.

[0128] Specifically, the optimal unloading strategy for users is determined by: finding the Nash equilibrium solution of the Stackelberg game and discussing the optimal unloading strategy from the perspective of the unloading ratio; and solving the user utility function with respect to the decision variable of the unloading ratio. Based on the first-order optimality condition, the first and second derivatives can be used to calculate the optimal unloading ratio. .

[0129] Solving for the optimal resource allocation strategy for computing devices: Based on the Nash equilibrium value of the user's optimal offloading strategy, solve for the optimal resource allocation strategy for computing devices; solve for the utility function of computing devices with respect to the resource allocation decision variables. and Based on the first-order optimality condition, the first and second derivatives of the first-order derivatives can be used to calculate the value of the optimal resource allocation decision. and .

[0130] Through the above process, we can find a strategy combination. This prevents both leaders and followers from gaining higher utility by unilaterally changing their strategies, thus failing to obtain the Nash equilibrium solution required for the game process.

[0131] S33. Obtain the total network utility value based on the decision variables of the unloading correlation subproblem, the unloading proportion subproblem, and the resource allocation subproblem.

[0132] S34. Determine whether the total utility value of the network is within a preset value range within a preset time.

[0133] If so, output the optimal solution for unloading association, unloading ratio and resource allocation to obtain the non-terrestrial network resource allocation result.

[0134] If not, determine whether the preset number of iterations has been reached. If it has, output the optimal solution for unloading association, unloading ratio and resource allocation to obtain the non-terrestrial network resource allocation result. If it has not been reached, proceed to step S31.

[0135] In one feasible implementation, when the total utility value of the network is maintained within a certain range or the number of iterations reaches a preset fixed value, the optimal solution of unloading association, unloading ratio and resource allocation is obtained, and an optimized scheme for non-terrestrial network resource allocation is derived.

[0136] This invention proposes a multi-task offloading and communication transmission network model. Combining the characteristics of multi-task requirements, dynamic topology changes, and equipment energy consumption, it flexibly offloads user tasks to dynamically changing LEO satellites or UAVs. This not only meets users' communication needs for low latency and low energy consumption, but also further alleviates the problem of multi-task service assurance faced by non-terrestrial networks.

[0137] The present invention relates to a game theory-based multi-task non-terrestrial network resource allocation method and system. With the goal of minimizing network latency and energy consumption, the method proposes a multi-task non-terrestrial network resource allocation approach based on game theory to obtain the optimal resource allocation strategy. This approach balances network load while meeting latency-sensitive communication requirements, thereby achieving green and sustainable development of non-terrestrial network communication.

[0138] This invention employs an evolutionary minority game approach to solve the offloading association problem, preventing users from making the same offloading decisions, reducing network congestion, and achieving a balance in network load. Simultaneously, it combines the Stackelberg game model to solve the offloading ratio and resource allocation problem, achieving a Nash equilibrium to realize the rational allocation of resources and achieve dual optimization of individual and network interests.

[0139] Figure 3 This is a block diagram illustrating a game theory-based multi-task non-terrestrial network resource allocation apparatus according to an exemplary embodiment. The apparatus is used for a game theory-based multi-task non-terrestrial network resource allocation method. (Refer to...) Figure 3 The device includes a setup module 310, a construction module 320, and an output module 330. Wherein:

[0140] Module 310 is used to establish a multi-task offloading and communication transmission network model; the multi-task offloading and communication transmission network model includes: multiple LEO satellites, multiple UAVs and multiple ground users.

[0141] Module 320 is used to build a network utility optimization problem based on latency and energy consumption, based on a multi-task offloading and communication transmission network model.

[0142] Output module 330 is used to obtain the non-terrestrial network resource allocation results based on the evolutionary minority game method and the Stackelberg game model; wherein, the non-terrestrial network resource allocation results include: offloading association, offloading ratio and resource allocation.

[0143] This invention proposes a multi-task offloading and communication transmission network model. Combining the characteristics of multi-task requirements, dynamic topology changes, and equipment energy consumption, it flexibly offloads user tasks to dynamically changing LEO satellites or UAVs. This not only meets users' communication needs for low latency and low energy consumption, but also further alleviates the problem of multi-task service assurance faced by non-terrestrial networks.

[0144] The present invention relates to a game theory-based multi-task non-terrestrial network resource allocation method and system. With the goal of minimizing network latency and energy consumption, the method proposes a multi-task non-terrestrial network resource allocation approach based on game theory to obtain the optimal resource allocation strategy. This approach balances network load while meeting latency-sensitive communication requirements, thereby achieving green and sustainable development of non-terrestrial network communication.

[0145] This invention employs an evolutionary minority game approach to solve the offloading association problem, preventing users from making the same offloading decisions, reducing network congestion, and achieving a balance in network load. Simultaneously, it combines the Stackelberg game model to solve the offloading ratio and resource allocation problem, achieving a Nash equilibrium to realize the rational allocation of resources and achieve dual optimization of individual and network interests.

[0146] Figure 4 This is a schematic diagram of the structure of a multi-task non-terrestrial network resource allocation device provided in an embodiment of the present invention, as shown below. Figure 3 As shown, the multi-task non-terrestrial network resource allocation device may include the above-mentioned Figure 3 The illustrated multi-task non-terrestrial network resource allocation device is based on game theory. Optionally, the multi-task non-terrestrial network resource allocation device 410 may include a first processor 2001.

[0147] Optionally, the multitasking non-terrestrial network resource allocation device 410 may also include a memory 2002 and a transceiver 2003.

[0148] The first processor 2001, memory 2002, and transceiver 2003 can be connected via a communication bus.

[0149] The following is combined with Figure 4 A detailed description of each component of the multi-tasking non-terrestrial network resource allocation device 410 is provided below:

[0150] The first processor 2001 is the control center of the multi-task non-terrestrial network resource allocation device 410. It can be a single processor or a collective term for multiple processing elements. For example, the first processor 2001 can be one or more central processing units (CPUs), application-specific integrated circuits (ASICs), or one or more integrated circuits configured to implement embodiments of the present invention, such as one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs).

[0151] Optionally, the first processor 2001 can perform various functions of the multitasking non-terrestrial network resource allocation device 410 by running or executing software programs stored in the memory 2002 and calling data stored in the memory 2002.

[0152] In a specific implementation, as one example, the first processor 2001 may include one or more CPUs, for example... Figure 4 CPU0 and CPU1 are shown in the diagram.

[0153] In a specific implementation, as one example, the multi-task non-terrestrial network resource allocation device 410 may also include multiple processors, for example... Figure 4 The first processor 2001 and the second processor 2004 are shown in the diagram. Each of these processors can be a single-core processor or a multi-core processor. Here, a processor can refer to one or more devices, circuits, and / or processing cores used to process data (such as computer program instructions).

[0154] The memory 2002 is used to store the software program that executes the present invention, and is controlled by the first processor 2001 to execute it. The specific implementation method can be referred to the above method embodiment, and will not be repeated here.

[0155] Optionally, the memory 2002 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory 2002 may be integrated with the first processor 2001 or may exist independently, and may be connected via the interface circuit of the multitasking non-terrestrial network resource allocation device 410. Figure 4 (Not shown in the image) is coupled to the first processor 2001, and this embodiment of the invention does not specifically limit this.

[0156] The transceiver 2003 is used to communicate with network devices or with terminal devices.

[0157] Alternatively, transceiver 2003 may include a receiver and a transmitter. Figure 4 (Not shown separately). The receiver is used to implement the receiving function, and the transmitter is used to implement the transmitting function.

[0158] Optionally, the transceiver 2003 can be integrated with the first processor 2001, or it can exist independently and be connected to the interface circuit of the multi-tasking non-terrestrial network resource allocation device 410. Figure 4 (Not shown in the image) is coupled to the first processor 2001, and this embodiment of the invention does not specifically limit this.

[0159] It should be noted that, Figure 4 The structure of the multi-tasking non-terrestrial network resource allocation device 410 shown does not constitute a limitation on the router. Actual knowledge structure identification devices may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0160] Furthermore, the technical effects of the multi-task non-terrestrial network resource allocation device 410 can be referred to the technical effects of the game theory-based multi-task non-terrestrial network resource allocation method described in the above method embodiments, and will not be repeated here.

[0161] It should be understood that the first processor 2001 in the embodiments of the present invention may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0162] It should also be understood that the memory in the embodiments of the present invention can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0163] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0164] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0165] In this invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0166] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0167] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0168] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices, apparatuses, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0169] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0170] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0171] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0172] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0173] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A multi-task non-terrestrial network resource allocation method based on game theory, characterized in that: The method comprises: S1. Establishing a multi-task offloading and communication transmission network model; wherein the multi-task offloading and communication transmission network model includes: multiple LEO satellites, multiple drones and multiple ground users; S2. Based on the multi-task offloading and communication transmission network model, establish a network utility optimization problem based on latency and energy consumption; S3. Obtain a non-terrestrial network resource allocation result according to an evolutionary minority game method and a Stackelberg game model; wherein the non-terrestrial network resource allocation result includes: offloading association, offloading ratio and resource allocation.

2. The multi-task non-terrestrial network resource allocation method based on game theory according to claim 1 is characterized in that: The establishment of multi-task offloading and communication transmission network model in S1 includes: Initialize multiple LEO satellites, multiple drones, and multiple ground users, and establish a multi-task offloading and communication transmission network model; Each of the multiple ground users generates a task, and a partial offloading strategy is adopted to divide the task of each ground user into a local computing task and a computing device computing task, the ground user completes the local computing task, and one of the multiple LEO satellites and the multiple drones is used as a computing device to complete the computing device computing task; The total time cost to complete any ground user's task is expressed by the following formula (1): （1） The total energy consumption to complete the task of any ground user is expressed by the following formula (2): （2） In the formula, represents the total time cost, represents the computational delay for the ground user to complete the local computational task, represents the transmission delay of the computing device receiving the computing task of the computing device, represents the computing delay of the computing device to complete the computing task of the computing device, represents the total energy consumption, represents the computing energy consumption of the ground user to complete the local computing task, represents the transmission energy consumption of the computing device receiving the computing task of the computing device, Represents the energy consumption of a computing device to complete a computing task of the computing device.

3. The multi-task non-terrestrial network resource allocation method based on game theory according to claim 1 is characterized in that: The network utility optimization problem based on latency and energy consumption established in S2 includes: A network utility minimization problem based on delay and energy consumption is established, an objective function of the total network utility value is established according to the network utility minimization problem based on delay and energy consumption, and the network utility minimization problem based on delay and energy consumption is decomposed into an offloading association subproblem, an offloading ratio subproblem and a resource allocation subproblem.

4. The multi-task non-terrestrial network resource allocation method based on game theory according to claim 3 is characterized in that: The objective function of the total network utility value in S21 is expressed by the following formula (3): （3） In the formula, Indicates whether the task is uninstalled. Indicates the proportion of data that is uninstalled. Indicates the bandwidth resource ratio. Indicates the proportion of computing resources, Represents any task, Represents a set of tasks, represents the weight coefficient of delay, represents the total time cost, represents the weight coefficient of energy consumption, represents the total energy consumption, Represents the weighted value constraint, Indicates that the task can only be offloaded to a single computing device. represents a computing device, represents the LEO satellite set, represents a collection of drones, Indicates the task Whether to transfer to computing device middle, represents the computing device service time constraint, Indicates the remaining service time of the computing device. represents bandwidth resource constraints, Indicates the assignment to a task The proportion of wireless bandwidth represents the computational resource constraints, Indicates that computing devices are assigned to tasks The proportion of computing resources, represents the unloading ratio constraint, Indicates the proportion of task data calculated locally, Represents local computation, Represents the set of ground users.

5. The multi-task non-terrestrial network resource allocation method based on game theory according to claim 1, characterized in that: In S3, the non-ground network resource allocation result is obtained according to the evolutionary minority game method and the Stackelberg game model, including: S31. Using the evolutionary minority game method, the decision variables of the unloading association sub-problem are solved; S32, establishing a Stackelberg game model, and solving the decision variables of the unloading ratio sub-problem and the decision variables of the resource allocation sub-problem through the Stackelberg game model; S33, obtaining a total network utility value according to the decision variables of the offloading association subproblem, the decision variables of the offloading ratio subproblem, and the decision variables of the resource allocation subproblem; S34, determining whether the total network utility value is within a preset value range within a preset time; If so, the optimal solution of offloading association, offloading ratio and resource allocation is output to obtain the resource allocation result of the non-terrestrial network; If not, determine whether the preset number of iterations is reached. If reached, output the optimal solution of offloading association, offloading ratio and resource allocation to obtain the non-terrestrial network resource allocation result. If not reached, go to step S31.

6. The multi-task non-terrestrial network resource allocation method based on game theory according to claim 5 is characterized in that: The evolutionary minority game method is adopted in S31 to solve the decision variables of the unloading association sub-problem, including: The evolutionary minority game method is adopted to solve the decision variables of the offloading association sub-problem by fixing the offloading ratio, bandwidth resources and computing resources.

7. The multi-task non-terrestrial network resource allocation method based on game theory according to claim 5 is characterized in that: The step of establishing a Stackelberg game model in S32, and solving the decision variables of the unloading ratio sub-problem and the decision variables of the resource allocation sub-problem by using the Stackelberg game model, includes: According to the strategic interaction between the ground user and the computing device, a Stackelberg game model is established, wherein the goal of the Stackelberg game model is to minimize the utility value of the leader and the utility value of the follower; wherein the ground user is the leader and the computing device is the follower; Construct a utility function of the ground user, solve the utility function of the ground user, and obtain the decision variables of the unloading ratio subproblem; wherein the utility function of the ground user is expressed by the following formula (4): （4） Construct a utility function of the computing device, solve the utility function of the computing device, and obtain the decision variables of the resource allocation sub-problem; wherein the utility function of the computing device is expressed by the following formula (5): （5） In the formula, represents the user's utility function, represents the weight coefficient of delay, represents the computational delay for the ground user to complete the local computational task, represents the weight coefficient of energy consumption, represents the computing energy consumption of the ground user to complete the local computing task, represents the utility function of the computing device, represents the transmission delay of the computing device receiving the computing task of the computing device, represents the computing delay of the computing device to complete the computing task of the computing device, represents the transmission energy consumption of the computing device receiving the computing task of the computing device, Represents the energy consumption of a computing device to complete a computing task of the computing device.

8. A multi-task non-terrestrial network resource allocation device based on game theory, wherein the multi-task non-terrestrial network resource allocation device based on game theory is used to implement the multi-task non-terrestrial network resource allocation method based on game theory as claimed in any one of claims 1 to 7, characterized in that: The device comprises: Establishing a module for establishing a multi-task offloading and communication transmission network model; wherein the multi-task offloading and communication transmission network model includes: multiple LEO satellites, multiple drones and multiple ground users; A construction module, used to establish a network utility optimization problem based on latency and energy consumption based on the multi-task offloading and communication transmission network model; The output module is used to obtain the non-ground network resource allocation result according to the evolutionary minority game method and the Stackelberg game model; wherein the non-ground network resource allocation result includes: offloading association, offloading ratio and resource allocation.

9. A multi-task non-terrestrial network resource allocation device, characterized in that: The multi-task non-terrestrial network resource allocation device comprises: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program codes, which can be called by a processor to execute the method according to any one of claims 1 to 7.

Images