Edge computing network access point selection method, device and storage medium

Abstract

The present invention discloses a method, device, and storage medium for selecting an edge computing network access point. The method comprises: obtaining information about devices to be accessed based on an intelligent agent; grouping the devices to be accessed based on the information about the devices to be accessed; determining the access selection probability of each group of devices accessing each edge computing network access point based on a Poisson game model; and connecting the devices of the corresponding group to the edge computing network access point corresponding to the maximum value of the access selection probability. By implementing the present invention, an intelligent agent deployed in the edge computing network space is used to achieve collaborative decision-making between heterogeneous devices. Without knowing the total number of devices, the optimal access point selection strategy is solved based on the Poisson game model. While maximizing device benefits, the average waiting delay of devices accessing the network is effectively reduced, network congestion problems are improved, and ultimately load balancing of the edge computing network is achieved.

Description

Technical Field

[0001] The present invention relates to the field of communication technologies, and in particular to a method, device, and storage medium for selecting an access point in an edge computing network. Background Art

[0002] Edge computing networks are considered an effective solution for future large-scale, latency-sensitive network services. Their agile and efficient data processing capabilities and flexible deployment methods will provide strong support for the efficient operation of emerging networks such as 6G, the Internet of Vehicles, and the Industrial Internet. Currently, edge computing networks are developing towards large-scale, highly dynamic, distributed, and heterogeneous devices that can access them at any time. Therefore, computing tasks for a large number of devices require the assistance of edge servers.

[0003] However, as the scale of edge computing networks continues to grow, the types of devices accessing the network become more diverse, and the number of devices cannot be determined. In addition, there is currently a lack of an effective collaborative scheduling mechanism for heterogeneous devices, which can easily cause load imbalance in edge computing networks due to excessive local loads and idleness elsewhere. Summary of the Invention

[0004] In view of this, an embodiment of the present invention provides a method, device and storage medium for selecting an edge computing network access point to solve the technical problem in the prior art of excessive local load on the edge computing network and unbalanced load due to idleness elsewhere due to the increase in devices accessing the edge computing network.

[0005] The technical solutions proposed by the present invention are as follows:

[0006] A first aspect of an embodiment of the present invention provides an edge computing network access point selection method, comprising: obtaining information of devices to be accessed based on an intelligent agent; grouping the devices to be accessed according to the information of the devices to be accessed; determining the access selection probability of each group of devices accessing each edge computing network access point based on a Poisson game model; and connecting the devices of the corresponding group to the edge computing network access point corresponding to the maximum value of the access selection probability.

[0007] Optionally, the access selection probability of each group of devices accessing each edge computing network access point is determined based on a Poisson game model, including: determining the benefit of each group of devices accessing each edge computing network access point based on the access queuing waiting probability, access unit price, transmission energy consumption and corresponding weights of each group of devices accessing each edge computing network access point at the current moment; updating the expected access probability of each group of devices accessing each edge computing network access point at the next moment based on the proportion of the benefit of each group of devices accessing each edge computing network access point to the total benefit of accessing all edge computing network access points; calculating the actual access probability of each group of devices accessing each edge computing network access point at the next moment based on the actual access probability of each group of devices accessing each edge computing network access point at the current moment and the expected access probability at the next moment; and determining the access selection probability of each group of devices accessing each edge computing network access point based on whether the actual access probability at the next moment meets the equilibrium condition.

[0008] Optionally, the access queuing waiting probability is determined in the following manner: determining the access request arrival rate based on the number of devices in each group of devices, the access probability of each group of devices accessing each edge computing network access point at the current moment, and the access period; determining the access queuing waiting probability based on whether the ratio of the access request arrival rate to the service rate is less than 1.

[0009] Optionally, the access queue waiting probability is calculated using the following formula:

[0010]

[0011] Where, ρ m It represents the ratio of access request arrival rate to service rate, C m is the total number of servers in access point m.

[0012] Optionally, the access selection probability of each group of devices accessing each edge computing network access point is determined based on whether the actual access probability at the next moment meets the equilibrium condition, including: judging whether the sum of the actual access probabilities of each group of devices accessing all edge computing network access points at the next moment is equal to 1; when it is not equal to 1, continuing to calculate the actual access probability at the next moment according to the actual access probability at the next moment until it is equal to 1; when it is equal to 1, using the actual access probability equal to 1 as the access selection probability of each group of devices accessing each edge computing network access point.

[0013] Optionally, the information of the device to be accessed includes: the device location or the service type transmitted by the device; grouping the devices to be accessed according to the information of the device to be accessed includes: grouping the information of the device to be accessed by area according to the device location; or grouping the devices to be accessed according to the service type transmitted by the device.

[0014] Optionally, obtaining information of the device to be accessed based on the intelligent agent includes: determining whether the probability of successful access to the edge computing network is less than a preset value; when it is less than the preset value, using the intelligent agent to obtain information of the device to be accessed.

[0015] A second aspect of an embodiment of the present invention provides an edge computing network access point selection device, including: an information acquisition module for acquiring information of devices to be accessed based on an intelligent agent; a grouping module for grouping devices to be accessed according to the information of the devices to be accessed; a probability calculation module for determining the access selection probability of each group of devices accessing each edge computing network access point based on a Poisson game model; and an access module for connecting the devices of the corresponding group to the edge computing network access point corresponding to the maximum value of the access selection probability.

[0016] A third aspect of an embodiment of the present invention provides a computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable the computer to execute the edge computing network access point selection method as described in the first aspect of the embodiment of the present invention and any one of the first aspects.

[0017] A fourth aspect of an embodiment of the present invention provides an electronic device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to execute the edge computing network access point selection method as described in the first aspect of the embodiment of the present invention and any one of the first aspects.

[0018] The technical solution provided by the present invention has the following effects:

[0019] The edge computing network access point selection method, device and storage medium provided by the embodiments of the present invention realize collaborative decision-making among heterogeneous devices through an intelligent agent deployed in the edge computing network space. Without knowing the total number of devices, the optimal access point selection strategy is solved based on the Poisson game model. While maximizing the device benefits, it effectively reduces the average waiting delay of the device accessing the network, improves the network congestion problem, and ultimately achieves load balancing of the edge computing network. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1is a flow chart of a method for selecting an edge computing network access point according to an embodiment of the present invention;

[0022] Figure 2 2. This is a schematic diagram of an application scenario of the edge computing network access point selection method according to an embodiment of the present invention;

[0023] Figure 3 is a flow chart of a method for selecting an edge computing network access point according to another embodiment of the present invention;

[0024] Figure 4 is a flow chart of a method for selecting an edge computing network access point according to another embodiment of the present invention;

[0025] Figure 5 is a structural block diagram of an edge computing network access point selection device according to an embodiment of the present invention;

[0026] Figure 6 is a schematic diagram of the structure of a computer-readable storage medium provided according to an embodiment of the present invention;

[0027] Figure 7 is a schematic structural diagram of an electronic device provided according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0029] The terms "first," "second," "third," "fourth," and the like in the specification and claims of the present invention and in the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" and "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0030] As mentioned in the background, the number of connected devices in today's edge computing networks is increasing. To manage these devices, two main approaches are currently used: centralized management and distributed autonomous decision-making. Centralized management requires a control center to collect access requests from all devices and then centrally schedule them based on network load. Distributed autonomous decision-making, on the other hand, randomly selects available access points. If the selected node has an idle channel, it is immediately accessible; otherwise, it enters an access queue and waits for access.

[0031] However, the main drawback of centralized management is that it requires collecting information from all connected devices and can only handle situations where the number of connected devices is known. Distributed autonomous decision-making, on the other hand, is that devices cannot perceive the load of the edge computing network, which can easily lead to imbalances due to excessive load in some areas and low load elsewhere. Furthermore, because various devices come from different manufacturers and use different protocols and standards, distributed autonomous decision-making cannot achieve collaborative decision-making among heterogeneous devices.

[0032] In view of this, in order to achieve collaborative decision-making among heterogeneous devices, balance the load of the edge computing network, and reduce the average waiting delay for devices to access the network, an embodiment of the present invention provides an edge computing network access point selection method.

[0033] According to an embodiment of the present invention, a method for selecting an edge computing network access point is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0034] In this embodiment, a method for selecting an edge computing network access point is provided, which can be used in electronic devices such as computers, mobile phones, tablet computers, etc. Figure 1 is a flow chart of a method for selecting an edge computing network access point according to an embodiment of the present invention. Figure 2 A schematic diagram of an application scenario of the selection method according to an embodiment of the present invention is shown in FIG. Figure 1 As shown, the method includes the following steps:

[0035] Step S101: Obtain information about devices to be connected based on the intelligent agent. Specifically, to better demonstrate the effectiveness of the access point selection method of the present invention, the method of an embodiment of the present invention can be used when the probability of successful access to the edge computing network is less than a preset value. That is, before obtaining information about devices to be connected, a determination is made as to whether the probability of successful access to the edge computing network is less than a preset value; if the probability is less than the preset value, the information is obtained. This can prevent congestion at some access points. Furthermore, the information about devices to be connected can be directly obtained without considering the probability of successful access to the edge computing network.

[0036] The acquired device information includes device status information or service type. The device status information specifically refers to the coordinates of the device's geographic location at the time of access. Service types specifically include small-scale distributed data transmission services or large-scale continuous high-definition video services. When acquiring device information, an intelligent agent is used to collect the device information. This intelligent agent is a basic service defined on the edge cloud and is the only entry point for devices to access the network. As an access agent, mobile agent, and transmission agent for devices to access the network, the intelligent agent will fully utilize network resources while meeting the personalized needs of devices through resource collaboration.

[0037] In addition, since the intelligent agent is a microservice deployed in the edge computing network space, it is responsible for collecting user status information and business needs. The intelligent agents have unified information interaction specifications, so collaborative decision-making between heterogeneous devices can be achieved.

[0038] Step S102: Group the devices based on their information. To manage the devices, they are first grouped. For example, they can be divided into K groups, with the devices in each group numbered k = 1, ..., K. The groups can be based on device location or the type of service they transmit.

[0039] When grouping devices based on location, GPS positioning is used to obtain the specific coordinates of the devices. The area where the devices are located is then divided into multiple zones, with the devices in each zone forming a group. Furthermore, when grouping devices based on the type of services they transmit, the amount of data transmitted by the services is used to create multiple stages. The stage to which the devices belong is determined based on the amount of data transmitted by the services they transmit, and devices in the same stage are grouped together.

[0040] Since each device to be connected has an intelligent agent in the network space, after the devices to be connected are grouped, a corresponding intelligent agent is randomly generated for each group of devices as the representative of all devices in the group. That is, the representatives of each group will subsequently realize collaborative decision-making among the devices in each group.

[0041] Step S103: Determine the access selection probability of each device group for each edge computing network access point based on a Poisson game model. Specifically, the Poisson game model can solve the problem of finding an equilibrium solution when the number of game participants is uncertain. Therefore, by solving the equilibrium solution of the Poisson game model as the access selection probability of each device group for each edge computing network access point, the optimal access selection probability is obtained. This allows for achieving edge computing network load balancing even when the total number of devices is uncertain.

[0042] Step S104: Connect the devices of the corresponding group to the edge computing network access point corresponding to the maximum access selection probability. The access selection probability is the probability of each group's devices accessing each edge computing network access point. Each group representative then selects the access point with the maximum probability from the access probabilities of each edge computing network access point and selects the access point corresponding to this maximum probability as the access point for the devices of the group. After each group representative determines the access point, they distribute the access selection results to the devices of the corresponding group, so that the devices in each group can access the access point.

[0043] The edge computing network access point selection method provided by the embodiment of the present invention realizes collaborative decision-making among heterogeneous devices through an intelligent agent deployed in the edge computing network space. Without knowing the total number of devices, the optimal access point selection strategy is solved based on the Poisson game model. While maximizing the device benefits, it effectively reduces the average waiting delay for devices to access the network, improves network congestion problems, and ultimately achieves load balancing of the edge computing network.

[0044] In one embodiment, if Figure 3 As shown, the access selection probability of each group of devices accessing each edge computing network access point is determined based on the Poisson game model, including the following steps:

[0045] Step S201: Based on the access queuing waiting probability, access unit price, transmission energy consumption and corresponding weights of each group of devices accessing each edge computing network access point at the current moment, a sum operation is performed to determine the benefits of each group of devices accessing each edge computing network access point.

[0046] The access queue waiting probability is determined as follows: the access request arrival rate is determined based on the number of devices in each group of devices and the ratio of the expected access probability of each group of devices accessing each edge computing network access point at the current moment to the access period; and the access queue waiting probability is determined based on whether the ratio of the access request arrival rate to the service rate is less than 1.

[0047] Specifically, if the current moment is the initial moment, the expected access probability at that moment is randomly generated, and the expected access probability at subsequent moments is determined using step S202. m It is expressed by the following formula:

[0048]

[0049] Where, is the number of devices in group k, σ k,m is the expected access probability of the kth group of devices selecting access point m for access, and Δt is the period for collecting access requests.

[0050] The access queue waiting probability is calculated using the following formula:

[0051]

[0052] Where, ρ m represents the access request arrival rate and service rate μ m The ratio of C m is the total number of servers in access point m. Service rate μ m Refers to the number of devices that can be served per unit time. For example, if access services can be provided to 20 devices within Δt, then the service rate is

[0053] The benefits of each group of devices accessing each edge computing network access point are expressed using the following formula:

[0054] U k,m =α k θ m +β k P m +γ k E k,m Formula (3)

[0055] Where, P m The unit price of providing access service to access point m, E k,m is the transmission energy consumption of the kth group of devices to the access point m, α k ,β k ,γ k are the weights of access queue waiting probability, service unit price, and transmission energy consumption, respectively, and α k +β k +γ k = 1. The benefit is the utility. When each group of devices selects an access point, the benefit or utility is used as the objective function to maximize the objective function, that is, maximize the benefit.

[0056] Step S202: Update the next-moment expected access probability of each group of devices accessing each edge computing network access point based on the ratio of the revenue of each group of devices accessing each edge computing network access point to the total revenue of accessing all edge computing network access points. Specifically, the next-moment expected access probability is expressed using the following formula:

[0057]

[0058] Where, = represents the current revenue at time t. Since the above calculation of the access request arrival rate uses the expected access probability at the current time, the calculated revenue is the revenue at the current time.

[0059] Step S203: Calculate the actual access probability of each group of devices accessing each edge computing network access point at the next moment based on the actual access probability of each group of devices accessing each edge computing network access point at the current moment and the expected access probability at the next moment. Specifically, if the current moment is the initial moment, the actual access probability at this moment is randomly generated, and the actual access probability at the next moment is Calculated by the following formula:

[0060]

[0061] Where, δ (t) Indicates the iteration step size at the current moment; Indicates the actual access probability at the current moment.

[0062] Step S204: Determine the access selection probability of each group of devices accessing each edge computing network access point based on whether the actual access probability at the next moment meets the equilibrium condition. Specifically, the equilibrium condition can be expressed as M represents the total number of access points. When the equilibrium condition is met, the actual access probability that meets the equilibrium condition is used as the access selection probability for each group of devices to access each edge computing network access point. If the equilibrium condition is not met, the actual access probability at the next moment is calculated based on the actual access probability at the next moment until it is equal to 1.

[0063] In one embodiment, the edge computing network access point selection method is implemented using the following process: an intelligent agent collects device status information or the service type transmitted by the device; the intelligent agent groups the device status information or the service type transmitted by the device, and the sequence number of each group is k=1,...,K, where K is the total number of groups, and randomly generates an intelligent agent as the representative of all members of the group, that is, the representative of each group; then, the representatives of each group collaboratively decide on the optimal access strategy and announce the access selection results to their own group members.

[0064] Among them, such as Figure 4 As shown, the collaborative decision-making optimal access strategy process is implemented in the following way: each group representative initializes the expected access probability The actual access probability Get the expected access probability and actual access probability at time t=1, and then calculate the access request arrival rate of each access point of the edge computing network based on the expected access probability at that time Then calculate the access queue waiting probability of each access point according to formula (2): And calculate the benefits of each access point according to formula (3) Then calculate the expected access probability at the next moment according to formula (4): Based on Calculate the actual access probability at the next moment Determine the actual access probability Whether the equilibrium conditions are met When satisfied, according to the actual access probability Select the edge computing network access point with the largest probability value for access; if it is not satisfied, t=t+1, and continue to calculate based on the expected access probability and actual access probability at time t+1 Whether the equilibrium condition is met, the iterative process is continued, and finally the actual access probability that meets the equilibrium condition is obtained.

[0065] The embodiment of the present invention also provides an edge computing network access point selection device, such as Figure 5 As shown, the device includes:

[0066] The information acquisition module is used to obtain the information of the device to be connected based on the intelligent agent; the specific content can be found in the corresponding part of the above method embodiment, which will not be repeated here.

[0067] The grouping module is used to group the devices to be connected according to their information. For details, please refer to the corresponding part of the above method embodiment, which will not be repeated here.

[0068] The probability calculation module is used to determine the access selection probability of each group of devices accessing each edge computing network access point based on the Poisson game model; the specific content can be found in the corresponding part of the above method embodiment, which will not be repeated here.

[0069] The access module is configured to connect the devices in the corresponding group to the edge computing network access point corresponding to the maximum value of the access selection probability. For details, please refer to the corresponding part of the above method embodiment and will not be repeated here.

[0070] The edge computing network access point selection device provided by the embodiment of the present invention realizes collaborative decision-making among heterogeneous devices through an intelligent agent deployed in the edge computing network space. Without knowing the total number of devices, the optimal access point selection strategy is solved based on the Poisson game model. While maximizing the device benefits, it effectively reduces the average waiting delay for devices to access the network, improves network congestion problems, and ultimately achieves load balancing of the edge computing network.

[0071] For a detailed description of the functions of the edge computing network access point selection device provided in an embodiment of the present invention, please refer to the description of the edge computing network access point selection method in the above embodiment.

[0072] The embodiment of the present invention also provides a storage medium, such as Figure 6As shown, a computer program 601 is stored thereon, and when the instructions are executed by the processor, the steps of the edge computing network access point selection method in the above embodiment are implemented. The storage medium also stores audio and video stream data, feature frame data, interaction request signaling, encrypted data, and preset data size, etc. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory (Flash Memory), a hard disk drive (HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above types of memory.

[0073] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD), or a solid-state drive (SSD). The storage medium can also include a combination of the above-mentioned types of memory.

[0074] The embodiment of the present invention further provides an electronic device, such as Figure 7 As shown, the electronic device may include a processor 51 and a memory 52, wherein the processor 51 and the memory 52 may be connected via a bus or other means. Figure 7 The bus connection is taken as an example.

[0075] The processor 51 may be a central processing unit (CPU). The processor 51 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or a combination of the above chips.

[0076] Memory 52, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer executable programs, and modules, such as the corresponding program instructions / modules in the embodiments of the present invention. Processor 51 executes the non-transitory software programs, instructions, and modules stored in memory 52 to perform various processor functions and data processing, thereby implementing the edge computing network access point selection method in the above-mentioned method embodiment.

[0077] The memory 52 may include a program storage area and a data storage area, wherein the program storage area may store applications required for operating the device and at least one function; the data storage area may store data created by the processor 51, etc. In addition, the memory 52 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 52 may optionally include a memory remotely located relative to the processor 51, and these remote memories may be connected to the processor 51 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0078] The one or more modules are stored in the memory 52 and when executed by the processor 51, perform the following steps: Figure 1 -4 shows an edge computing network access point selection method in the embodiment.

[0079] For details of the above electronic equipment, please refer to Figures 1 to 4 The corresponding descriptions and effects in the embodiments shown can be understood and will not be repeated here.

[0080] Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention. Such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for selecting an edge computing network access point, characterized in that: include: Obtain information about devices to be connected based on intelligent agents; Grouping the devices to be connected according to their information; Determine the access selection probability of each group of devices accessing each edge computing network access point based on the Poisson game model; The edge computing network access point corresponding to the maximum value of the access selection probability connects the devices of the corresponding group; The access selection probability of each group of devices accessing each edge computing network access point is determined based on the Poisson game model, including: Based on the current access queue waiting probability, access unit price, transmission energy consumption and corresponding weights of each group of devices accessing each edge computing network access point, the benefits of each group of devices accessing each edge computing network access point are determined; Based on the ratio of the revenue of each group of devices accessing each edge computing network access point to the total revenue of accessing all edge computing network access points, the expected access probability of each group of devices accessing each edge computing network access point at the next moment is updated; Calculate the actual access probability of each group of devices accessing each edge computing network access point at the next moment based on the actual access probability of each group of devices accessing each edge computing network access point at the current moment and the expected access probability at the next moment; The access selection probability of each group of devices accessing each edge computing network access point is determined based on whether the actual access probability at the next moment meets the equilibrium condition.

2. The edge computing network access point selection method according to claim 1, characterized in that: The access queue waiting probability is determined in the following manner: Determine the access request arrival rate based on the number of devices in each group and the ratio of the access probability of each group of devices accessing each edge computing network access point at the current moment to the access period; The access queue waiting probability is determined based on whether the ratio of the access request arrival rate to the service rate is less than 1.

3. The edge computing network access point selection method according to claim 2, characterized in that: The access queue waiting probability is calculated using the following formula: Where, ρ m It represents the ratio of access request arrival rate to service rate, C m is the total number of servers in access point m.

4. The edge computing network access point selection method according to claim 1, characterized in that: The access selection probability of each group of devices accessing each edge computing network access point is determined based on whether the actual access probability at the next moment meets the equilibrium condition, including: Determine whether the sum of the actual access probabilities of each group of devices accessing all edge computing network access points at the next moment is equal to 1; If it is not equal to 1, the actual access probability at the next moment is calculated according to the actual access probability at the next moment until it is equal to 1; When it is equal to 1, the actual access probability equal to 1 is used as the access selection probability of each group of devices accessing each edge computing network access point.

5. The edge computing network access point selection method according to claim 1, characterized in that: The information of the device to be connected includes: the location of the device or the type of service transmitted by the device; The devices to be connected are grouped according to their information, including: Group the device information to be connected by region according to the device location; or The devices to be connected are grouped according to the service types transmitted by the devices.

6. The edge computing network access point selection method according to claim 1, characterized in that: Obtain information about devices to be connected based on intelligent agents, including: Determine whether the probability of successful access to the edge computing network is less than a preset value; When it is less than the preset value, an intelligent agent is used to obtain the information of the device to be connected.

7. An edge computing network access point selection device, characterized in that: include: An information acquisition module is used to obtain information about devices to be connected based on an intelligent agent; A grouping module, used to group the devices to be connected according to their information; A probability calculation module, used to determine the access selection probability of each group of devices accessing each edge computing network access point based on a Poisson game model; An access module, configured to connect the devices of the corresponding group to the edge computing network access point corresponding to the maximum value of the access selection probability; The access selection probability of each group of devices accessing each edge computing network access point is determined based on the Poisson game model, including: Based on the current access queue waiting probability, access unit price, transmission energy consumption and corresponding weights of each group of devices accessing each edge computing network access point, the benefits of each group of devices accessing each edge computing network access point are determined; Based on the ratio of the revenue of each group of devices accessing each edge computing network access point to the total revenue of accessing all edge computing network access points, the expected access probability of each group of devices accessing each edge computing network access point at the next moment is updated; Calculate the actual access probability of each group of devices accessing each edge computing network access point at the next moment based on the actual access probability of each group of devices accessing each edge computing network access point at the current moment and the expected access probability at the next moment; The access selection probability of each group of devices accessing each edge computing network access point is determined based on whether the actual access probability at the next moment meets the equilibrium condition.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the edge computing network access point selection method according to any one of claims 1 to 6.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the edge computing network access point selection method according to any one of claims 1 to 6 by executing the computer instructions.

Images