Isomeric fusion algorithm network resource management and control method and device

Abstract

The application provides a heterogeneous fusion computing network resource management and control method and device, relates to the technical field of communication, and adopts a hierarchical game mode for the heterogeneous fusion computing network system with two communication systems of satellite communication and ground communication, adopts non-cooperative game between layers and cooperative game within layers, and the combination of the two game modes can effectively reasonably allocate network resources in the computing network system, and realizes efficient and accurate computing network resource management and control under diversified communication systems.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of communication, in particular to a heterogeneous fusion algorithm network resource management and control method and device. BACKGROUND

[0002] The computing power network is the evolution direction of future networks. When realizing the interconnection of distributed nodes, the network also needs to have the ability of collaborative scheduling of network resources and computing power resources. Therefore, a new network resource allocation method is needed to adapt to the current resource allocation scene of the computing power network, to make a comprehensive trade-off between network resources and computing power resources, and to obtain the optimal strategy, so as to realize the network resource management and control of the algorithm network. Figure 1 The structural diagram of the distributed computing power network scene is shown in Figure 1 As shown in the figure, the client node issues a service request through an application interface, the computing power routing node obtains network and computing power state information according to the resource interface of each computing service node to perform computing power resource scheduling and routing addressing, and after cross-node routing, the target computing service node is reached, and finally the specific computing service is completed according to the service interface of the target computing service node and then returned.

[0003] The current network resource allocation method includes static allocation and dynamic allocation. Among them, static allocation is a pre-allocation resource method, which allocates resources to tasks according to pre-set rules and strategies. For example, according to the priority and required resource amount of the task, the resources are allocated statically. Dynamic allocation is opposite to static allocation, which allocates resources according to the actual situation of the task when the network system is running, and can be adjusted according to the real-time demand of the task, thereby improving the utilization rate of network resources.

[0004] However, the existing network resource allocation method considers only a single communication system, and in the face of diversified communication systems in the system, how to perform efficient and accurate algorithm network resource management and control is the focus of current research. SUMMARY

[0005] The purpose of the present application is to provide a heterogeneous fusion algorithm network resource management and control method and device to realize efficient and accurate algorithm network resource management and control under diversified communication systems.

[0006] In a first aspect, the present application provides a heterogeneous fusion algorithm network resource management and control method applied to a computing power network system including a satellite link layer and a ground link layer. The satellite link layer corresponds to a satellite-based network using a satellite communication system, and the ground link layer corresponds to a ground-based network using a ground communication system. The heterogeneous fusion algorithm network resource management and control method includes:

[0007] Obtaining demand parameter data, current bandwidth resource data and current task data of the computing power network system; wherein the demand parameter data is parameter data of a market demand function corresponding to the computing power network system, and the market demand function is a function reflecting the relationship between bandwidth resource demand and bandwidth resource price;

[0008] According to the demand parameter data and the current bandwidth resource data, resource allocation is performed between the satellite link layer and the ground link layer through non-cooperative game to obtain total bandwidth resources of the satellite link layer and total bandwidth resources of the ground link layer.

[0009] According to the total bandwidth resources of the satellite link layer, the total bandwidth resources of the ground link layer and the current task data, resource allocation is performed in the layers through cooperative game to obtain node resource allocation results of the computing power network system.

[0010] Further, the demand parameter data of the computing power network system is obtained, including:

[0011] Obtaining historical market data of the computing power network system within a preset time range, wherein the historical market data includes historical bandwidth demand information, price information and cost information.

[0012] According to the historical market data, parameter estimation is performed on a preset market demand function through a rolling window algorithm to obtain the demand parameter data of the computing power network system.

[0013] Further, according to the demand parameter data and the current bandwidth resource data, resource allocation is performed between the satellite link layer and the ground link layer through non-cooperative game to obtain total bandwidth resources of the satellite link layer and total bandwidth resources of the ground link layer, including:

[0014] Under the constraint condition of the current bandwidth resource data, a first utility function model of the satellite link layer and the ground link layer under non-cooperative game is established;

[0015] According to the demand parameter data, an analytical solution of the first utility function model is obtained to obtain total bandwidth resources of the satellite link layer and total bandwidth resources of the ground link layer.

[0016] Further, the first utility function model includes:

[0017]

[0018]

[0019] wherein, a set of nodes of the satellite link layer M a corresponding utility value, a set of nodes of the ground link layer N a corresponding utility value, R M a set of nodes of the satellite link layer M a corresponding price, R N a set of nodes of the ground link layer N a corresponding price, C M a set of nodes of the satellite link layer M a corresponding cost, C N a set of nodes of the ground link layer N a corresponding cost, a an intercept value in the demand parameter data, b = k / ( B ), k a slope value in the demand parameter data, B the current bandwidth resource data, b M total bandwidth resource of the satellite link layer, b N total bandwidth resource of the ground link layer, c M cost per allocated unit bandwidth of the satellite link layer, c N cost per allocated unit bandwidth of the ground link layer.

[0020] Further, the solving an analytical solution of the first utility function model according to the demand parameter data to obtain the total bandwidth resource of the satellite link layer and the total bandwidth resource of the ground link layer comprises:

[0021] the demand parameter data, the cost per allocated unit bandwidth of the satellite link layer and the cost per allocated unit bandwidth of the ground link layer are brought into the following analytical solution of the first utility function model to obtain the total bandwidth resource of the satellite link layer and the total bandwidth resource of the ground link layer:

[0022]

[0023]

[0024] wherein, b M total bandwidth resource of the satellite link layer, b Na total bandwidth resource of the ground link layer, a an intercept value in the demand parameter data, b = k / (- B ), k a slope value in the demand parameter data, B the current bandwidth resource data, c M a cost required for each allocated unit bandwidth of the satellite link layer, c N a cost required for each allocated unit bandwidth of the ground link layer, B the current bandwidth resource data.

[0025] Further, the resource allocation of the satellite link layer and the ground link layer is performed in each layer by cooperative game according to the total bandwidth resource of the satellite link layer, the total bandwidth resource of the ground link layer and the current task data, to obtain the node resource allocation result of the computing power network system, comprising:

[0026] for each target link layer in the satellite link layer and the ground link layer, a second utility function model of the target link layer under cooperative game is established;

[0027] each node in the target link layer is taken as a single node alliance to form an initial alliance structure;

[0028] According to the initial alliance structure, the total bandwidth resource of the target link layer and the current task data, the switching and merging operation of the alliance is performed to maximize the total alliance revenue as the optimization target, to obtain a target alliance structure; wherein the alliance is formed by unloading tasks between other nodes, and the total alliance revenue is calculated based on the second utility function model;

[0029] The resource allocation result under the target alliance structure is determined as the node resource allocation result of the target link layer.

[0030] Further, the ground network corresponding to the ground link layer comprises a 5G network corresponding to a 5G link layer.

[0031] In a second aspect, the embodiments of the present application further provide a heterogeneous fusion computing network resource management and control device, applied to a computing power network system comprising a satellite link layer and a ground link layer, a space-based network corresponding to the satellite link layer adopts a satellite communication system, and a ground-based network corresponding to the ground link layer adopts a ground communication system; the heterogeneous fusion computing network resource management and control device comprises:

[0032] The data acquisition module is configured to acquire demand parameter data, current bandwidth resource data and current task data of the computing power network system, wherein the demand parameter data is parameter data of a market demand function corresponding to the computing power network system, and the market demand function is a function reflecting the relationship between the bandwidth resource demand and the bandwidth resource price.

[0033] The first allocation module is configured to perform resource allocation between the satellite link layer and the ground link layer through non-cooperative game according to the demand parameter data and the current bandwidth resource data, to obtain total bandwidth resources of the satellite link layer and total bandwidth resources of the ground link layer.

[0034] The second allocation module is configured to perform in-layer resource allocation of the satellite link layer and the ground link layer respectively through cooperative game according to the total bandwidth resources of the satellite link layer, the total bandwidth resources of the ground link layer and the current task data, to obtain a node resource allocation result of the computing power network system.

[0035] In a third aspect, an electronic device is provided, which includes a memory and a processor. The memory stores a computer program capable of running on the processor. When the processor executes the computer program, the method of the first aspect is implemented.

[0036] In a fourth aspect, a computer readable storage medium is provided, which stores a computer program. When the computer program is run by a processor, the method of the first aspect is executed.

[0037] The heterogeneous fusion algorithm network resource management and control method and device provided by the embodiment of the application are applied to a computing power network system including a satellite link layer and a ground link layer, the satellite link layer corresponds to a space-based network adopting a satellite communication system, and the ground link layer corresponds to a ground-based network adopting a ground communication system; the heterogeneous fusion algorithm network resource management and control method comprises the following steps: obtaining demand parameter data, current bandwidth resource data and current task data of the computing power network system; wherein the demand parameter data is parameter data of a market demand function corresponding to the computing power network system, and the market demand function is a function reflecting the relationship between the bandwidth resource demand and the bandwidth resource price; performing resource allocation between the satellite link layer and the ground link layer through non-cooperative game according to the demand parameter data and the current bandwidth resource data, to obtain total bandwidth resources of the satellite link layer and total bandwidth resources of the ground link layer; and performing resource allocation in the satellite link layer and the ground link layer respectively through cooperative game according to the total bandwidth resources of the satellite link layer, the total bandwidth resources of the ground link layer and the current task data, to obtain a node resource allocation result of the computing power network system. In this way, for the heterogeneous fusion computing power network system with the satellite communication and the ground communication two communication systems, a hierarchical game mode is adopted, non-cooperative game is adopted between layers, cooperative game is adopted in the layers, and the combination of the two game modes can effectively reasonably allocate the network resources in the computing power network system according to the demand, to realize efficient and accurate algorithm network resource management and control under the diversified communication system. BRIEF DESCRIPTION OF DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0039] Figure 1 is a structural diagram of a distributed computing power network scene;

[0040] Figure 2 is a content caching diagram of a 5G network;

[0041] Figure 3 is a whole architecture diagram of a computing power network system provided by the embodiment of the present application;

[0042] Figure 4 is a flowchart of a heterogeneous fusion algorithm network resource management and control method provided by the embodiment of the present application;

[0043] Figure 5 is a structural diagram of hierarchical game in a heterogeneous fusion algorithm network resource management and control method provided by the embodiment of the present application;

[0044] Figure 6An interlayer game model in a heterogeneous fusion algorithm network resource management and control method is provided for the embodiment of the application.

[0045] Figure 7 An intralayer game network topology graph in a heterogeneous fusion algorithm network resource management and control method is provided for the embodiment of the application.

[0046] Figure 8 A whole framework graph of a heterogeneous fusion algorithm network resource management and control method is provided for the embodiment of the application.

[0047] Figure 9 A structural schematic diagram of a heterogeneous fusion algorithm network resource management and control device is provided for the embodiment of the application.

[0048] Figure 10 A structural schematic diagram of an electronic device is provided for the embodiment of the application. DETAILED DESCRIPTION

[0049] The technical solutions of the application will be described clearly and completely in connection with the embodiments. Obviously, the described embodiments are part of the embodiments of the application, rather than all the embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the application.

[0050] The network resource allocation method in a simple scenario (i.e. the same communication system) includes static allocation and dynamic allocation. With the continuous development of algorithm network technology, when multiple network nodes exist in the network, different network nodes have individual differences, and it is difficult to use a single model to represent the whole system. In order to more accurately describe the actual algorithm network system and efficiently allocate network resources, the heterogeneity of the system in the communication system needs to be considered, and the method of game theory can achieve this goal. The resource allocation problem in the computing power network can be regarded as a game problem with global constraints. Different game methods are used to make each network node make its own decision according to the situation to complete the network resource allocation and control of the whole system.

[0051] By reasonably designing the incentive mechanism in game theory, each node can be encouraged to actively participate in resource sharing. The utility value-based incentive mechanism can give appropriate rewards according to the number, quality and sharing frequency of the resources provided by the nodes. In the network resource allocation problem, the utility refers to an important evaluation index of user satisfaction in the network service quality. A utility function u ( x i ) is defined, which represents the satisfaction of a user (i.e. a node in the network) to a certain network index x i . x iThat is, the network allocates the amount of resources to the network node, and the value meets the condition x a ≤ x i ≤ x b Similarly, the corresponding utility value has an upper limit. In mathematical terms, in order to ensure that the utility value can flexibly represent the user's satisfaction with the network index x i , the utility function needs to be twice differentiable within the limit interval. The change trend of the utility value and the allocated resources x i should be uniform. In order to ensure that the more resources allocated to the user, the higher the utility value reflecting the user's satisfaction, however, when the allocated resources reach a certain threshold and obtain a higher degree of satisfaction, the change of the utility value should tend to be flat, so that the marginal utility presents a decreasing trend, that is, the utility function must be a non-decreasing function, which can be expressed in mathematical formula as:

[0052] (1)

[0053] (2)

[0054] For elastic network resources such as bandwidth, the satisfaction of the bandwidth allocated to the user can be described by using a Sigmoid curve, which meets the characteristics of twice differentiable, non-decreasing, and also has a certain flexibility, and is suitable for describing elastic resources in the utility-based optimization model.

[0055] By using the utility function, and formulating a suitable incentive mechanism to obtain a reward value, the strategy selection of each node itself is optimized according to the reward value, and finally the network resource allocation management of the whole network is realized.

[0056] Based on this, the heterogeneous fusion algorithm network resource management and control method and device provided by the embodiment of the application can realize efficient and accurate algorithm network resource management and control under a diversified communication system by combining non-cooperative game and cooperative game two game modes.

[0057] In order to facilitate the understanding of the embodiment, the heterogeneous fusion algorithm network resource management and control method disclosed by the embodiment of the application is described in detail below.

[0058] The embodiment of the application provides a heterogeneous fusion algorithm network resource management and control method, which is applied to a computing power network system including a satellite link layer and a ground link layer. The satellite link layer corresponds to a space-based network using a satellite communication system, and the ground link layer corresponds to a ground-based network using a ground communication system. Optionally, the ground link layer corresponding to the ground-based network can include a 5G network corresponding to a 5G link layer. Hereinafter, the 5G network corresponding to the 5G link layer will be exemplarily introduced. The method can be executed by an electronic device with data processing capability, which can be a server device of an edge computing platform (i.e., a virtualization platform) added in the computing power network system.

[0059] It should be noted that the ground link layer corresponding to the ground-based network is not limited to the 5G network corresponding to the 5G link layer, and other networks such as a 6G network can also be used in other embodiments.

[0060] In order to meet the actual situation of the current computing power network with multiple communication systems, the resource management and control method based on the new game model proposed in this embodiment sets the specific application scenario as a multi-communication system computing power network scenario composed of satellite communication and 5G link communication. Two communication systems are used: satellite communication and 5G link communication. The satellite communication system is suitable for application in the computing power network environment with increasing network traffic and massive increase of Internet terminals due to its low latency, low cost, wide coverage, large bandwidth and other advantages. Figure 2 The content caching structure diagram of the 5G network is shown in FIG. 1. The 5G network is a new type of mobile communication network, and the communication nodes in the network have storage capability, which can meet the computing power cooperative scheduling requirements in the computing power network.

[0061] As shown in FIG. 1, the system is divided into two layers. The upper layer is the satellite link layer. Due to the limited resources of the satellite nodes, an edge computing platform (i.e., a virtualization platform) is added, so that the user terminal devices in the computing power network can directly perform traffic offloading with the satellite nodes. The user terminal devices can be any computing network user terminal accessing the system, such as ground-based users, air-based users, space-based users and sea-based users. Figure 3 The lower layer is the 5G link layer. The ground 5G network is composed of an access network (i.e., a 5G base station), a bearer network and a core network based on the virtualization platform.

[0062] Figure 3 The satellite link layer and the 5G link layer can interact between layers, and the adjacent nodes in each layer can interact within the layer. Figure 3It can be seen that each node participating in the game in the network does not need to transmit data to the center node, only needs to interact with the adjacent nodes, and therefore the communication cost is more saved. At the same time, there is no single point failure problem, which greatly improves the robustness of the system. Since the entire game optimization process does not depend on the center node, the scalability of the network is enhanced, and when applied to the computing power network scene, it has the characteristics of fast optimization convergence speed, less calculation resource occupation, etc.

[0063] Referring to Figure 4 A flowchart of a heterogeneous fusion algorithm network resource management and control method is shown, and the heterogeneous fusion algorithm network resource management and control method mainly includes the following steps S410 to S430:

[0064] Step S410, acquiring demand parameter data, current bandwidth resource data and current task data of the computing power network system; wherein the demand parameter data is the parameter data of the market demand function corresponding to the computing power network system.

[0065] The demand parameter data, current bandwidth resource data and current task data of the computing power network system can be acquired in real time to realize real-time dynamic resource allocation. Of course, the protection scope of the present application is not limited thereto, and in other embodiments, data acquisition and resource allocation can also be performed according to a preset frequency.

[0066] The above demand parameter data can be used for utility function calculation of the satellite link layer and the ground link layer in the interlayer non-cooperative game. The demand parameter data is the parameter data of the market demand function corresponding to the computing power network system, and the market demand function is a function reflecting the relationship between the bandwidth resource demand and the bandwidth resource price. A possible market demand function is a linear function, and the demand parameter data can include a slope value and an intercept value. The demand parameter data can be estimated based on historical data, or can be updated periodically or in real time.

[0067] In the computing power network, different computing power providers determine the total computing power supply that can be provided, and market parameters need to be defined when constructing the market demand function. The parameters of the market demand function are estimated and updated through historical market data and a rolling window algorithm. Based on this, the demand parameter data can be obtained as follows: obtaining historical market data of the computing power network system within a preset time range, the historical market data including historical bandwidth demand information, price information and cost information; according to the historical market data, the parameters of the preset market demand function are estimated through the rolling window algorithm to obtain the demand parameter data of the computing power network system.

[0068] The preset time range can be set according to actual needs, and the embodiment is not limited thereto. For example, the preset time range can be the last half year or the last year. In a possible implementation, in order to improve the accuracy of the demand parameter data, before the parameter estimation, the historical market data can be cleaned and features extracted to obtain target features corresponding to the historical bandwidth demand information, the price information and the cost information. When the parameter estimation is performed, the data in the rolling window is used, and data in the last 30 days can be selected as the rolling window. The window data is used for linear regression to obtain the demand parameter data.

[0069] The current bandwidth resource data can be the total bandwidth resource of the system. When the resource is allocated between layers, the sum of the total bandwidth resource of the satellite link layer and the total bandwidth resource of the ground link layer cannot exceed the current bandwidth resource data. The current task data can include a task identifier, a task type and a task priority. The task identifier is used to identify specific task information. The task type is divided into a computing task and a storage task. The task priority is used to determine the priority order when the task is allocated to a specific node and the resource is used. The current task data can be used for switching and merging of alliances when the cooperative game is performed in the layer. The alliance is formed by unloading the task to other nodes.

[0070] In step S420, according to the demand parameter data and the current bandwidth resource data, the resource is allocated between the satellite link layer and the ground link layer through the non-cooperative game to obtain the total bandwidth resource of the satellite link layer and the total bandwidth resource of the ground link layer.

[0071] The non-cooperative game is generally composed of participants, a strategy set, a cost function and an equilibrium point. In the embodiment, the participants are the node set of the satellite link layer and the node set of the ground link layer. The strategy set refers to a set of all possible bandwidth resource allocation results. The cost function is also called the utility function. The equilibrium point refers to a stable strategy combination, that is, a stable bandwidth resource allocation result. In the non-cooperative game, all participants are selfish and rational. The cost function often conflicts. Each party in the game adopts the best strategy to meet their own needs under the given game environment and rules. In the embodiment, under the constraint condition of the total bandwidth resource of the system, the two parties in the game seek the Nash equilibrium point by constructing the cost function to allocate the network resource between layers.

[0072] Since the total bandwidth resource is certain, the inter-layer game can regard the two-layer network as two subjects in competition, and the Cournot game is a classic oligopoly game, which is suitable for the inter-layer game scenario in the embodiment. In the two-layer network, each layer network is a game participant to decide its bandwidth resource allocation strategy. Based on this, in some possible embodiments, the step S420 can include: establishing a first utility function model of the satellite link layer and the ground link layer under non-cooperative game under the constraint condition of the current bandwidth resource data; and solving the first utility function model according to the demand parameter data to obtain the total bandwidth resource of the satellite link layer and the total bandwidth resource of the ground link layer.

[0073] In a possible implementation, the market demand function is linear and the price is , i M , N The first utility function model includes:

[0074]

[0075]

[0076] wherein, is a node set of the satellite link layer M corresponding utility value, is a node set of the ground link layer N corresponding utility value, R M is a node set of the satellite link layer M corresponding price, R N is a node set of the ground link layer N corresponding price, C M is a node set of the satellite link layer M corresponding cost, C N is a node set of the ground link layer N corresponding cost, a is an intercept value in the demand parameter data, b k , B , k is a slope value in the demand parameter data, B is the current bandwidth resource data, b M is the total bandwidth resource of the satellite link layer, b N is the total bandwidth resource of the ground link layer, c M ​​Cost required for each allocated unit bandwidth of the satellite link layer, c N Cost required for each allocated unit bandwidth of the ground link layer.

[0077] In a possible implementation, in order to prevent the system from not converging, an analytical solution is obtained for the inter-layer game, and the utility functions are respectively b M and b N Derivation is performed, and the derivative is set to zero to calculate the optimal solution. Then, the demand parameter data, the cost required for each allocated unit bandwidth of the satellite link layer, and the cost required for each allocated unit bandwidth of the ground link layer are brought into the following analytical solution of the first utility function model to obtain the total bandwidth resources of the satellite link layer and the total bandwidth resources of the ground link layer:

[0078]

[0079]

[0080] wherein, b M Total bandwidth resources of the satellite link layer, b N Total bandwidth resources of the ground link layer, a is an intercept value in the demand parameter data, b = k / (- B ), k is a slope value in the demand parameter data, B is current bandwidth resource data, c M Cost required for each allocated unit bandwidth of the satellite link layer, c N Cost required for each allocated unit bandwidth of the ground link layer.

[0081] Through the above solving steps, the network bandwidth resources allocated to each layer in the inter-layer game can be obtained, and the result is used as a conditional constraint for the subsequent intra-layer cooperative game optimization problem.

[0082] In step S430, according to the total bandwidth resources of the satellite link layer, the total bandwidth resources of the ground link layer, and the current task data, resource allocation is performed in the intra-layer of the satellite link layer and the ground link layer through cooperative game, and the node resource allocation result of the computing power network system is obtained.

[0083] The in-layer game mode of the satellite link layer and the ground link layer is the same. Taking the satellite link layer as an example, for the in-layer node game, the final optimization goal is to solve the optimal resource allocation strategy between the computing power network nodes, and the strategy selection of each communication node in the network is the best decision made for the strategies of other nodes in the layer, which is irrelevant to the lower participants (i.e., the ground link layer), and any satellite node in the layer needs to tend to an equilibrium point. Cooperative game refers to the game played by participants in the form of alliance and cooperation. Taking the satellite link layer as an example, the participants refer to the nodes of the satellite link layer, and the alliance is formed by unloading tasks between other nodes, that is, the nodes with task unloading relationship form an alliance. When studying the resource allocation problem between satellite communication link nodes using cooperative game, a node utility function model needs to be established first, and the optimization goal is set as the maximum income of the in-layer alliance.

[0084] In some possible embodiments, step S430 can include: for each target link layer in the satellite link layer and the ground link layer, establishing a second utility function model of the target link layer under cooperative game; wherein the target link layer is the satellite link layer or the ground link layer; regarding each node in the target link layer as a single-node alliance, forming an initial alliance structure; according to the initial alliance structure, the total bandwidth resource of the target link layer and the current task data, performing switching and merging operations of the alliance to obtain a target alliance structure, with the maximum total alliance income as the optimization goal; wherein the alliance is formed by unloading tasks between other nodes, and the total alliance income is calculated based on the second utility function model; and determining the resource allocation result under the target alliance structure as the node resource allocation result of the target link layer.

[0085] When performing the switching and merging operations of the alliance, the union set of each alliance set needs to satisfy that the union set of each alliance set is the node set in the layer, and the intersection of any two alliances is empty. The switching and merging operations of the alliance can be performed according to the set rules: a computing power node in the layer is randomly selected, a union is selected and joined in its communicable range, which is referred to as the first union, and a selectable union is randomly selected, which is referred to as the second union. The corresponding system total utility value of the computing power node in the two unions is calculated, respectively. If the system total utility value corresponding to the first union is greater than the system total utility value corresponding to the second union, it indicates that the union selected by the node to join is correct, otherwise the node is joined in the second union, and the current alliance structure is updated. The above process is repeatedly performed until the alliance structure satisfying the equilibrium state of the game is found.

[0086] In this embodiment, the maximization of alliance benefits is taken as the system optimization goal, and a stable alliance structure is obtained after game iteration convergence. Since cooperative game is used in the layer, collaboration and information sharing are needed among the computing power nodes, and particle swarm optimization (PSO) can be used for solving. Based on the above inter-layer game model, each particle represents an intra-layer computing power node and the bandwidth resource obtained thereby, and the optimal resource allocation strategy is found through iteration. Through continuous iteration, the bandwidth resource obtained by the intra-layer computing power node is adjusted each time to improve the overall efficiency of the system.

[0087] The heterogeneous fusion computing network resource management and control method provided by the embodiment of the application is used for a heterogeneous fusion computing network system with satellite communication and ground communication two communication systems, adopts a hierarchical game mode, uses non-cooperative game between layers and cooperative game within layers, and the combination of the two game modes can effectively reasonably allocate network resources in the computing network system, and realize efficient and accurate computing network resource management and control under diversified communication systems.

[0088] For ease of understanding, the above heterogeneous fusion computing network resource management and control method is described in detail below by taking the ground link layer corresponding ground network as the 5G link layer corresponding 5G network as an example.

[0089] The embodiment can solve the following problems:

[0090] 1. In the current computing network resource management and control method, the considered communication system is single, without considering the current development and changes. The communication system in the computing network will face diversification, and satellite-ground fusion is the future network development trend. The communication system involved in the network is no longer single, but diversified. In the face of diversified communication systems in the system, how to efficiently and accurately manage and control the computing network resources is the key point of the current research.

[0091] 2. The traditional computing network resource allocation method has many shortcomings. Among them, static allocation cannot dynamically adjust resources for allocation, which may result in low resource utilization. Dynamic allocation can improve resource utilization, but requires higher management overhead and more complex algorithms to support. In the computing network resource management and control method based on game theory, different game methods will have some impact on the results. For example, when a single non-cooperative game is used, since each participant in the non-cooperative game does not care whether the selected strategy will adversely affect the benefits of other game participants, the resulting result may not be the global optimal solution of the optimization problem.

[0092] The embodiment comprehensively considers two communication systems in the calculation network, combines satellite communication with 5G communication, and accurately characterizes the complex calculation power network system by constructing a new game model of multiple communication systems. Through the joint action of inter-layer game and intra-layer game, the inter-layer game regards the satellite link layer and the 5G link layer as a whole respectively, and carries out non-cooperative game between them to obtain the network resource allocation to each layer in the whole system. After the inter-layer game is completed, the intra-layer game is carried out, and the network nodes in each layer adopt cooperative game to find the equilibrium state that makes each node in the layer obtain the maximum benefit under the given constraint condition. The network resource allocated to each node in the system under this state is recorded as the optimal solution of the calculation power network system resource allocation optimization problem. By comprehensively considering the distribution of network resources and the network state in the system, online scheduling and distribution of calculation power network resources under multiple communication systems are realized.

[0093] The new layered game model proposed in the embodiment will be described in detail below. As shown in Figure 5 The satellite communication network node is selected as the upper game subject, and the ground 5G link communication network node is selected as the lower game subject. The resource allocation strategy selection of the nodes in the two different communication systems is considered, and the inter-layer game under the two different communication systems and the game between the nodes in each layer adopt different forms. The links under the two communication systems share the resources of the whole system. First, the upper network (i.e. the space-based network corresponding to the satellite link layer) and the lower network (i.e. the ground-based network corresponding to the ground link layer) carry out inter-layer non-cooperative game, and the allocated network bandwidth resources in each layer are obtained. Then, the communication nodes in each layer carry out cooperative game under the given constraint condition to find the equilibrium state that makes each node in the layer obtain the maximum benefit. Each node in the layer forms an initial alliance structure as a single node alliance, and each node finds the set of communicable nodes within its communication range. Since the network node devices in the system do not always produce bandwidth resource demand at each moment, other nodes in the system can independently choose to offload tasks to other idle nodes within their communication range, and relieve the pressure of a single node through such cooperation. In the intra-layer game process, the alliance is formed by offloading tasks between nodes. The switching and merging operations of the alliance are carried out according to the set rules, and finally converge to a stable state, so as to improve the resource allocation and control efficiency of the whole calculation power network system.

[0094] 1) Inter-layer non-cooperative game

[0095] As Figure 6The interlayer game model is shown, first, the interlayer non-cooperative game is analyzed, the non-cooperative game is generally composed of participants, strategy set, cost function, equilibrium point and the like. In the non-cooperative game, all participants are selfish and rational, and the cost function often conflicts, and each party in the game adopts the best strategy to meet their own needs under the given game environment and rules. In this embodiment, under the constraint condition of the given total bandwidth resource of the system, the game parties seek the Nash equilibrium point by constructing the cost function, and allocate the network resources between the layers.

[0096] Since the total bandwidth resource of the given system is certain, the interlayer game can regard the two-layer network as two competitive subjects, and the Cournot game is a classic oligopoly competition game, which is suitable for the interlayer game scene in this embodiment. In the two-layer network, each layer network is a game participant, and decides the bandwidth resource allocation strategy.

[0097] The participant is a decision subject, which is represented by , wherein M represents the node set in the space network, N represents the node set in the 5G network, and the node set M and N are allocated to the bandwidth resource b M and b N , which represents that the total bandwidth resource of the whole system is defined as . In order to obtain the utility function of the participant, it is assumed that the market demand function is linear and the price is , a and b are parameters related to actual network topology and other external factors (i.e. demand parameter data), and the mathematical expression of the utility function is shown in formula (3). c M and c N respectively represent the cost per unit bandwidth allocated in the satellite network and the 5G network.

[0098] (3)

[0099] In order to prevent the system from not converging, the interlayer game is solved analytically here, and the utility function is respectively derived with respect to b M and b N , and the derivative is zero to calculate the optimal solution. The analytical solution can be obtained as shown in formula (4) and formula (5).

[0100] (4)

[0101] (5)

[0102] Through the above solution steps, the network bandwidth resources allocated to each layer in the inter-layer game can be obtained. This result serves as the total bandwidth resources within the layer, which is used to constrain the subsequent intra-layer cooperative game optimization problem.

[0103] 2) Intra-layer cooperative game

[0104] The intra-layer game theory in satellite link layers is similar to that in 5G link layers. Taking the satellite link layer as an example, the ultimate optimization objective for the game between nodes within the layer is to find the optimal resource allocation strategy among the computing network nodes. Each communication node's strategy choice is the best decision made in relation to the strategies of other nodes within the layer, independent of lower-layer participants. Simultaneously, any satellite node within the layer needs to converge to an equilibrium point. When using cooperative game theory to study the resource allocation problem between satellite communication link nodes, it is first necessary to establish a node utility function model and set the optimization objective as maximizing the payoff of the intra-layer alliance.

[0105] like Figure 7 The diagram illustrates an intra-layer game network topology. Taking the intra-layer game in a 5G network as an example, in cooperative games within each layer, it's assumed that there are n users (i.e., computing nodes) competing for intra-layer network resources. These computing nodes can cooperate with each other. By setting constraint protocols, it's ensured that each user node can allocate system network resources rationally and efficiently after the cooperative game. When all nodes abide by the protocol, a cooperative game alliance is formed. Through the constraints of the protocol, different communication nodes within the layer adopt strategies according to rules, thereby maximizing system gains. A cooperative alliance game is defined as... ,in U This represents the set of participants in the game, that is, the set of all computing power nodes within the layer. V The utility of a coalition is defined in Real-valued mappings on, where This represents the set of all possible subsets of participants. U Any subset of a set can be viewed as a union, including the empty set and the universal set.

[0106] For the alliance The characteristic function represents and The maximum utility of a coalition in a game can be expressed by formula (6). V i It can be calculated using formula (7), representing the first in the system. i One computing node u i utility function a constant value related to a specific network topology, used to represent the utility value brought by a unit bandwidth; a penalty coefficient, which is generated when the actual network resource allocated to the node does not reach the bandwidth demand. b i a bandwidth amount actually allocated to the node, d i a bandwidth demand amount of the node.

[0107] (6)

[0108] (7)

[0109] In order to determine whether the nodes constitute an alliance, a judgment variable is defined , which is used to represent whether there is a task offloading relationship between the nodes, and the value is 1, indicating that there is a task offloading between the two nodes, and the value is 0, indicating that there is no task offloading.

[0110] At any time after the start of the intra-layer game, there will be an alliance structure divided into , which represents the division of the node set U into alliances, where represents the set of all possible alliance structures, n represents the number of nodes, and at the same time needs to satisfy the content described in the following formula (8). In the initial stage of the game, a single node alliance is adopted (i.e. each node is an alliance), and the initial alliance structure is obtained as .

[0111] (8)

[0112] After obtaining the initial single-node alliance structure, the switching and merging operations of the alliance are carried out according to the set rules: since the alliance state is not stable, a computing power node in the layer is randomly selected, and a union is selected and joined within its communicable range , and a selectable alliance is randomly selected, and the corresponding system total utility of the computing power node in the alliance and the alliance is calculated, if , it means that the alliance selected by the node to join is correct, otherwise the node is joined to the alliance , and the current alliance structure is updated, and the above process is repeatedly repeated until the alliance structure that satisfies the game reaching the equilibrium state is found.

[0113] The in-layer game model maximizes the alliance revenue as the system optimization target, and after game iteration convergence, a stable alliance structure is obtained. Therefore, the total revenue of the in-layer game alliance can be described as formula (9).

[0114] (9)

[0115] The optimization problem can be further expressed as formula (10):

[0116] (10)

[0117] Among them, b N The total bandwidth resource allocated to the 5G link layer after inter-layer game. There are three constraint conditions in the optimization problem, r 1 indicates that for the bandwidth resource allocation task, the processing time of the system t cannot exceed the set maximum time t max The processing time of the system refers to the time directly recorded after the system runs, and does not include the time required for inter-layer non-cooperative game. This constraint is to constrain the time of one game distribution to meet the requirements; r 2 indicates that the network bandwidth resource value allocated to each computing power node in the layer is non-negative; r 3 indicates that the total network bandwidth resource allocated to all computing power nodes does not exceed the total bandwidth resource allocated to the 5G link layer after inter-layer game.

[0118] Since cooperative game is used in the layer, cooperation and information sharing are needed between computing power nodes, and particle swarm optimization algorithm can be used for solution. Based on the above in-layer game model, each particle represents an in-layer computing power node and the bandwidth resource obtained by it, and the optimal resource allocation strategy is found through iteration. Through continuous iteration of the algorithm, the bandwidth resource obtained by the in-layer computing power node is adjusted each time to improve the overall efficiency of the system.

[0119] The embodiment of the present application has the following technical effects:

[0120] Compared with the existing computing power network resource management and control technology, the new game model in the embodiment of the present application is more suitable for the actual computing network environment, and comprehensively considers the current star-ground integrated network trend. Satellite communication and ground 5G link communication are introduced into the computing power network system, a hierarchical game model is constructed, non-cooperative game is used between layers, and cooperative federal game is used in the layer. The combination of the two game modes can effectively and reasonably allocate network resources in the computing network system according to demand.

[0121] For example, Figure 8As shown, the computing network user terminal offloads the task to the satellite link layer and the 5G link layer, after receiving the task information, the two-layer network first performs non-cooperative game between layers to allocate the total network resources of each layer. Then, the two-layer network simultaneously performs intra-layer cooperative federated game, according to the above process, and uses PSO algorithm to perform secondary computing power network resource allocation between intra-layer computing power nodes. By comprehensively considering the distribution of network resources and the network state in the system, the online scheduling and allocation of computing power network resources under multiple communication systems are finally realized.

[0122] Corresponding to the above-mentioned heterogeneous fusion computing network resource management method, the embodiment of the application also provides a heterogeneous fusion computing network resource management device. The device is applied to a computing power network system including a satellite link layer and a ground link layer. The satellite link layer corresponds to a satellite-based network using a satellite communication system, and the ground link layer corresponds to a ground-based network using a ground communication system. Referring to Figure 9 As shown in the structure diagram of the heterogeneous fusion computing network resource management device, the heterogeneous fusion computing network resource management device includes:

[0123] The data acquisition module 901 is configured to acquire demand parameter data, current bandwidth resource data and current task data of the computing power network system. The demand parameter data is parameter data of a market demand function corresponding to the computing power network system, and the market demand function is a function reflecting the relationship between bandwidth resource demand and bandwidth resource price.

[0124] The first allocation module 902 is configured to allocate resources between the satellite link layer and the ground link layer by non-cooperative game according to the demand parameter data and the current bandwidth resource data, and obtain the total bandwidth resource of the satellite link layer and the total bandwidth resource of the ground link layer.

[0125] The second allocation module 903 is configured to allocate resources in the satellite link layer and the ground link layer respectively by cooperative game according to the total bandwidth resource of the satellite link layer, the total bandwidth resource of the ground link layer and the current task data, and obtain the node resource allocation result of the computing power network system.

[0126] The heterogeneous fusion computing network resource management device provided by the embodiment of the application is applied to a heterogeneous fusion computing power network system with satellite communication and ground communication two communication systems, and adopts a hierarchical game mode, non-cooperative game between layers and cooperative game in the layer. The combination of the two game modes can effectively and reasonably allocate the network resources in the computing power network system according to demand, and realize efficient and accurate computing network resource management under diversified communication systems.

[0127] Further, the data acquisition module 901 is specifically configured to: acquire historical market data of the computing power network system within a preset time range, the historical market data including historical bandwidth demand information, price information and cost information; and perform parameter estimation on a preset market demand function through a rolling window algorithm according to the historical market data, to obtain demand parameter data of the computing power network system.

[0128] Further, the first distribution module 902 is specifically configured to: under a constraint condition of the current bandwidth resource data, establish a first utility function model of the satellite link layer and the ground link layer under non-cooperative game; and obtain total bandwidth resources of the satellite link layer and total bandwidth resources of the ground link layer by solving an analytical solution of the first utility function model according to the demand parameter data.

[0129] Further, the first utility function model includes:

[0130]

[0131]

[0132] wherein, is a node set of the satellite link layer M is a corresponding utility value, is a node set of the ground link layer N is a corresponding utility value, R M is a node set of the satellite link layer M is a corresponding price, R N is a node set of the ground link layer N is a corresponding price, C M is a node set of the satellite link layer M is a corresponding cost, C N is a node set of the ground link layer N is a corresponding cost, a is an intercept value in the demand parameter data, b = k / (- B ), k is a slope value in the demand parameter data, B is the current bandwidth resource data, b M is the total bandwidth resource of the satellite link layer, b N is the total bandwidth resource of the ground link layer, c Ma cost required for each allocated unit bandwidth of the satellite link layer, c N a cost required for each allocated unit bandwidth of the ground link layer.

[0133] Further, the first allocation module 902 is further configured to: bring the demand parameter data, the cost required for each allocated unit bandwidth of the satellite link layer, and the cost required for each allocated unit bandwidth of the ground link layer into the following analytical solution of the first utility function model, to obtain the total bandwidth resource of the satellite link layer and the total bandwidth resource of the ground link layer:

[0134]

[0135]

[0136] wherein, b M the total bandwidth resource of the satellite link layer, b N the total bandwidth resource of the ground link layer, a an intercept value in the demand parameter data, b = k / (- B ), k a slope value in the demand parameter data, B the current bandwidth resource data, c M the cost required for each allocated unit bandwidth of the satellite link layer, c N the cost required for each allocated unit bandwidth of the ground link layer, B the current bandwidth resource data.

[0137] Further, the second allocation module 903 is specifically configured to: for each target link layer in the satellite link layer and the ground link layer, establish a second utility function model of the target link layer under cooperative game; form an initial alliance structure by taking each node in the target link layer as a single-node alliance; and perform switching and merging operations of the alliance according to the initial alliance structure, the total bandwidth resource of the target link layer, and the current task data, to obtain a target alliance structure, wherein the alliance is formed by offloading tasks between other nodes, and the total alliance revenue is calculated based on the second utility function model; and determine a resource allocation result under the target alliance structure as a node resource allocation result of the target link layer.

[0138] Further, the ground link layer corresponds to a ground network including a 5G network corresponding to a 5G link layer.

[0139] The implementation principle and the technical effects of the heterogeneous fusion computing network resource management and control device provided by the embodiment are the same as those of the aforementioned heterogeneous fusion computing network resource management and control method embodiment. For brevity of description, the parts not mentioned in the heterogeneous fusion computing network resource management and control device embodiment can be referred to the corresponding content in the aforementioned heterogeneous fusion computing network resource management and control method embodiment.

[0140] As shown in Figure 10 The embodiment of the present application provides an electronic device 1000, which comprises a processor 1001, a memory 1002 and a bus. The memory 1002 stores a computer program capable of running on the processor 1001. When the electronic device 1000 runs, the processor 1001 and the memory 1002 communicate through the bus. The processor 1001 executes the computer program to implement the aforementioned heterogeneous fusion computing network resource management and control method.

[0141] Specifically, the aforementioned memory 1002 and processor 1001 can be general memory and processor, which are not specifically limited here.

[0142] The embodiment of the present application further provides a computer readable storage medium, which stores a computer program. When the computer program is run by a processor, the heterogeneous fusion computing network resource management and control method described in the foregoing method embodiment is executed. The computer readable storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a RAM, a magnetic disk or an optical disk and various storage program codes.

[0143] The term "and / or" in this paper is only a description of the association relationship between the associated objects, which means that there can be three kinds of relationships, for example, A and / or B, which can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. In addition, the term "at least one" in this paper means any one of the multiple or any combination of at least two of the multiple, for example, including at least one of A, B and C, which can represent including any one or more elements selected from the set consisting of A, B and C.

[0144] In all the examples shown and described herein, any specific value should be interpreted as merely exemplary and not as a limitation, therefore, other examples of the exemplary embodiments can have different values.

[0145] The flow diagrams and the block diagrams in the drawings are presented to illustrate the architecture, functionality, and operation of possible implementations of apparatuses, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flow diagrams or block diagrams can represent a module, a segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks can sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flow diagrams, and combinations thereof, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

[0146] In several embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented by other manners. The apparatus embodiments described above are merely illustrative, for example, the division of the units is merely a logical function division, and actual implementation can have another division manner, and for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some communication interfaces, devices or units, and can be electrical, mechanical or other forms.

[0147] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, i.e. can be located in one place or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0148] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically, or two or more units can be integrated into one unit.

[0149] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A heterogeneous fusion algorithm network resource management and control method, characterized in that, The application is applied to a computing power network system including a satellite link layer and a ground link layer, the satellite link layer corresponds to a space-based network adopting a satellite communication system, and the ground link layer corresponds to a ground-based network adopting a ground communication system; The heterogeneous fusion algorithm network resource management and control method comprises: obtaining demand parameter data, current bandwidth resource data and current task data of the computing power network system; wherein the demand parameter data is parameter data of a market demand function corresponding to the computing power network system, and the market demand function is a function reflecting the relationship between bandwidth resource demand and bandwidth resource price; According to the demand parameter data and the current bandwidth resource data, resource allocation is performed between the satellite link layer and the ground link layer through non-cooperative game to obtain total bandwidth resources of the satellite link layer and total bandwidth resources of the ground link layer; According to the total bandwidth resources of the satellite link layer, the total bandwidth resources of the ground link layer and the current task data, resource allocation is performed in the layers respectively through cooperative game to obtain node resource allocation results of the computing power network system.

2. The heterogeneous converged network resource management method of claim 1, wherein, The demand parameter data of the computing power network system is obtained, comprising: obtaining historical market data of the computing power network system within a preset time range, the historical market data comprising historical bandwidth demand information, price information and cost information; According to the historical market data, parameter estimation is performed on a preset market demand function through a rolling window algorithm to obtain the demand parameter data of the computing power network system.

3. The heterogeneous converged network resource management method of claim 1, wherein, According to the demand parameter data and the current bandwidth resource data, resource allocation is performed between the satellite link layer and the ground link layer through non-cooperative game to obtain total bandwidth resources of the satellite link layer and total bandwidth resources of the ground link layer, comprising: under the constraint condition of the given current bandwidth resource data, a first utility function model of the satellite link layer and the ground link layer under non-cooperative game is established; According to the demand parameter data, an analytical solution of the first utility function model is obtained to obtain the total bandwidth resources of the satellite link layer and the total bandwidth resources of the ground link layer.

4. The heterogeneous converged network resource management method of claim 3, wherein, The first utility function model comprises: wherein is a set of nodes of the satellite link layer M is a corresponding utility value, is a set of nodes of the ground link layer N is a corresponding utility value, R M is a set of nodes of the satellite link layer M is a corresponding price, R N is a set of nodes of the ground link layer N is a corresponding price, C M is a set of nodes of the satellite link layer M is a corresponding cost, C N is a set of nodes of the ground link layer N is a corresponding cost, a is an intercept value in the demand parameter data, b = k / (- B ), k is a slope value in the demand parameter data, B is the current bandwidth resource data, b M is the total bandwidth resource of the satellite link layer, b N is the total bandwidth resource of the ground link layer, c M is the cost per allocated unit bandwidth of the satellite link layer, c N is the cost per allocated unit bandwidth of the ground link layer.

5. The heterogeneous converged network resource management method of claim 3, wherein, According to the demand parameter data, an analytical solution of the first utility function model is obtained to obtain the total bandwidth resources of the satellite link layer and the total bandwidth resources of the ground link layer, comprising: The demand parameter data, the cost required by each allocated unit bandwidth of the satellite link layer and the cost required by each allocated unit bandwidth of the ground link layer are brought into the following analytical solution of the first utility function model to obtain the total bandwidth resources of the satellite link layer and the total bandwidth resources of the ground link layer: wherein, b M is a total bandwidth resource for the satellite link layer, b N is a total bandwidth resource for the ground link layer, a is an intercept value in the demand parameter data, b = k / ( B ), k is a slope value in the demand parameter data, B is the current bandwidth resource data, c M is a cost per allocated unit of bandwidth for the satellite link layer, c N is a cost per allocated unit of bandwidth for the ground link layer.

6. The heterogeneous converged network resource management method of claim 1, wherein, According to the total bandwidth resources of the satellite link layer, the total bandwidth resources of the ground link layer and the current task data, resource allocation is performed in the layers respectively through cooperative game to obtain node resource allocation results of the computing power network system, comprising: For each target link layer in the satellite link layer and the ground link layer, a second utility function model of the target link layer in cooperative game is established; Each node in the target link layer is taken as a single-node alliance to form an initial alliance structure; According to the initial alliance structure, total bandwidth resources of the target link layer, and the current task data, a switching and merging operation of the alliance is performed to maximize the total alliance revenue as an optimization target, to obtain a target alliance structure; wherein the alliance is formed by unloading tasks between other nodes, and the total alliance revenue is calculated based on the second utility function model; A resource allocation result under the target alliance structure is determined as a node resource allocation result of the target link layer.

7. The heterogeneous fusion network resource management method according to any one of claims 1-6, wherein, The ground link layer corresponds to a ground-based network including a 5G network corresponding to a 5G link layer.

8. A heterogeneous converged network resource management and control device, characterized in that, The application is applied to a computing power network system including a satellite link layer and a ground link layer, the satellite link layer corresponds to a space-based network adopting a satellite communication system, and the ground link layer corresponds to a ground-based network adopting a ground communication system; The heterogeneous fusion computing network resource management and control device includes: A data acquisition module is configured to acquire demand parameter data, current bandwidth resource data, and current task data of the computing power network system; wherein the demand parameter data is parameter data of a market demand function corresponding to the computing power network system, and the market demand function is a function reflecting the relationship between bandwidth resource demand and bandwidth resource price; A first allocation module is configured to perform resource allocation between the satellite link layer and the ground link layer through non-cooperative game according to the demand parameter data and the current bandwidth resource data, to obtain total bandwidth resources of the satellite link layer and total bandwidth resources of the ground link layer; A second allocation module is configured to perform resource allocation in the satellite link layer and the ground link layer through cooperative game according to the total bandwidth resources of the satellite link layer, the total bandwidth resources of the ground link layer, and the current task data, to obtain a node resource allocation result of the computing power network system.

9. An electronic device comprising a memory, a processor, the memory having stored therein a computer program executable on the processor, characterized in that, The processor executes the computer program to implement the heterogeneous fusion computing network resource management and control method of any one of claims 1-7.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is run by the processor to perform the heterogeneous fusion computing network resource management and control method of any one of claims 1-7.

Images