Determination Method, Device, Electronic Device, Storage Medium and Product for Accessing a Network

Abstract

An embodiment of the present application provides a method, device, electronic device, storage medium, and product for determining an access network. The method includes: sending an access request for an edge computing task, obtaining network information of a terrestrial cellular network, a drone network, and a satellite network according to the access request for the edge computing task, determining the information transmission rate and required transmit power needed by the user terminal to be accessed according to the network information of each network, obtaining the current location information of the user terminal to be accessed, determining the target network to which the access request for the edge computing task is to be accessed according to the information transmission rate, required transmit power, and current location information needed by the user terminal to be accessed, and accessing the target network, where the target network is any one of the terrestrial cellular network, the drone network, and the satellite network. The present application enables the user terminal to be accessed to not only access the terrestrial cellular network, but also access the drone network or the satellite network, so as to access the optimal network and improve the resource allocation efficiency.

Description

Technical Field

[0001] This application relates to the field of communication technologies, and in particular, to a method, apparatus, electronic device, storage medium, and product for determining an access network. Background Art

[0002] With the rapid development of wireless communication technologies, users' demand for efficient and stable network access is increasing continuously. The network accessed by a user terminal will directly affect the user experience and the utilization efficiency of network resources.

[0003] In related technologies, traditional network resource allocation methods usually allocate access points for user terminals to be accessed based on the network resource information of terrestrial cellular networks, where the access points can be terrestrial base stations.

[0004] However, the above method has low resource allocation efficiency and poor applicability. Summary of the Invention

[0005] Embodiments of this application provide a method, apparatus, electronic device, storage medium, and product for determining an access network, so as to achieve the technical effect of improving resource allocation efficiency.

[0006] In a first aspect, embodiments of this application provide a method for determining an access network, including:

[0007] Sending an edge computing task access request;

[0008] Obtaining network information of each of a terrestrial cellular network, a drone network, and a satellite network according to the edge computing task access request;

[0009] Determining the information transmission rate and required transmit power required by the user terminal to be accessed according to the network information of each network;

[0010] Obtaining the current location information of the user terminal to be accessed;

[0011] Determining a target network to which the edge computing task access request is to be accessed according to the information transmission rate required by the user terminal to be accessed, the required transmit power, and the current location information, where the target network is any one of the terrestrial cellular network, the drone network, and the satellite network;

[0012] Accessing the target network.

[0013] In a possible implementation manner, the determining the information transmission rate and required transmit power required by the user terminal to be accessed according to the network information of each network includes:

[0014] Determining an optimized network-side load function according to the network information of each network;

[0015] Determine an optimized user - side load function according to the network information of each network;

[0016] Merge the optimized network - side load function and the optimized user - side load function to obtain a target load function;

[0017] Determine the information transmission rate and the required transmit power of the user terminal to be connected according to the target load function.

[0018] In a possible implementation manner, the network information of each network includes: the current network resource usage data of each network, and the information transmission rate and transmit power of the user terminals currently connected to each network;

[0019] The determining of the optimized network - side load function according to the network information of each network includes:

[0020] Obtain an initial network - side load function according to the current network resource usage data of each network, and the information transmission rate and transmit power of the user terminals currently connected to each network;

[0021] Obtain the total network resources of the preset channels of each network and the preset required information transmission rate of the user terminal to be connected;

[0022] Determine the optimized network - side load function with the total network resources of the preset channels of each network and the preset required information transmission rate of the user terminal to be connected as constraint conditions and the initial network - side load function as the optimization target.

[0023] In a possible implementation manner, the network information of each network includes: the transmission delay, the maximum packet length, and the information transmission rate of the user terminals currently connected to each network;

[0024] The determining of the optimized user - side load function according to the network information of each network includes:

[0025] Obtain an initial user - side load function according to the transmission delay, the maximum packet length, and the information transmission rate of the user terminals currently connected to each network;

[0026] Obtain the total network resources of the preset channels of each network and the required channel network resources of the preset edge computing tasks;

[0027] Determine the optimized user - side load function with the total network resources of the preset channels of each network and the required channel network resources of the preset edge computing tasks as constraint conditions and the initial user - side load function as the optimization target.

[0028] In a possible implementation manner, determining the information transmission rate and the required transmission power of the to-be-connected user terminal according to the target load function includes:

[0029] Obtain the preset transmission power of the to-be-connected user terminal, the preset transmission powers of each network, and the preset average calculation delay of each network;

[0030] Input the preset transmission power of the to-be-connected user terminal, the preset transmission powers of each network, the preset average calculation delay of each network, and the target load function into a preset optimization algorithm to determine the information transmission rate required by the to-be-connected user terminal;

[0031] Input the information transmission rate required by the to-be-connected user terminal, the preset average calculation delay of each network, and the target load function into a preset optimization algorithm to determine the transmission power required by the to-be-connected user terminal.

[0032] In a possible implementation manner, determining the target network to which the edge computing task access request is to be connected according to the information transmission rate required by the to-be-connected user terminal, the required transmission power, and the current location information includes:

[0033] Input the information transmission rate required by the to-be-connected user terminal, the required transmission power, and the current location information into a pre-trained deep reinforcement learning model to obtain the target network to which the edge computing task access request is to be connected.

[0034] In a possible implementation manner, the training steps of the pre-trained deep reinforcement learning model include:

[0035] Obtain training data, where the training data includes the historical networks to which the to-be-connected user terminal sends multiple historical edge computing task accesses, the corresponding historical information transmission rates, historical transmission powers, and historical location information for accessing each historical network, and the accessed historical networks are labels;

[0036] Use the training data to train an initial deep reinforcement learning model until a preset convergence condition is met to obtain a trained deep reinforcement learning model.

[0037] In a second aspect, an access network determination device provided by an embodiment of the present application includes:

[0038] A sending module, configured to send an edge computing task access request;

[0039] An obtaining module, configured to obtain network information of each of a terrestrial cellular network, a drone network, and a satellite network according to the edge computing task access request;

[0040] A determination module, configured to determine the information transmission rate and the required transmission power required by the user terminal to be accessed according to the network information of each of the networks.

[0041] The obtaining module is further configured to obtain the current location information of the user terminal to be accessed.

[0042] The determination module is further configured to determine a target network to which the edge computing task access request is to be accessed according to the information transmission rate required by the user terminal to be accessed, the required transmission power, and the current location information, where the target network is any one of the terrestrial cellular network, the drone network, and the satellite network.

[0043] An access module, configured to access the target network.

[0044] In a third aspect, an embodiment of the present application provides an electronic device, including: a memory and a processor;

[0045] The memory stores computer-executable instructions;

[0046] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the first aspect and / or various possible implementation manners of the first aspect as above.

[0047] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored, and when the computer-executable instructions are executed by a processor, they are used to implement the first aspect and / or various possible implementation manners of the first aspect as above.

[0048] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the first aspect and / or various possible implementation manners of the first aspect as above.

[0049] A method, apparatus, electronic device, storage medium, and product for determining an access network provided by an embodiment of the present application. The method includes: sending an edge computing task access request, and obtaining network information of each of a terrestrial cellular network, a drone network, and a satellite network according to the edge computing task access request. Furthermore, according to the network information of each network, determine the information transmission rate and the required transmission power required by the user terminal to be accessed, and obtain the current location information of the user terminal to be accessed. According to the information transmission rate required by the user terminal to be accessed, the required transmission power, and the current location information, determine a target network to which the edge computing task access request is to be accessed, and access the target network, where the target network is any one of the terrestrial cellular network, the drone network, and the satellite network. Description of the Drawings

[0050] The accompanying drawings here are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with this application, and are used together with the specification to explain the principles of this application.

[0051] Figure 1 A schematic diagram of an application scenario provided for this application;

[0052] Figure 2 A schematic flowchart of a method for determining an access network provided by an embodiment of this application;

[0053] Figure 3 A schematic flowchart of a method for determining the information transmission rate and required transmit power of a user terminal to be accessed provided by an embodiment of this application;

[0054] Figure 4 A schematic flowchart of a method for instantiating and determining the information transmission rate and required transmit power of a user terminal to be accessed provided by an embodiment of this application;

[0055] Figure 5 A schematic flowchart of a method for training a network-side deep reinforcement learning model provided by an embodiment of this application;

[0056] Figure 6 A schematic diagram of a method for training a deep reinforcement learning model provided by an embodiment of this application;

[0057] Figure 7 A schematic structural diagram of a device for determining an access network provided by an embodiment of this application;

[0058] Figure 8 A schematic structural diagram of an electronic device provided by an embodiment of this application.

[0059] Through the above accompanying drawings, specific embodiments of this application have been shown, and there will be more detailed descriptions later. These drawings and textual descriptions are not intended to limit the scope of the concept of this application in any way, but to illustrate the concept of this application to those skilled in the art by referring to specific embodiments. Detailed Description of the Embodiments

[0060] Exemplary embodiments will be described in detail here, and the examples are shown in the accompanying drawings. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. On the contrary, they are merely examples of devices and methods consistent with some aspects of this application as detailed in the appended claims.

[0061] In the description of the embodiments of the present application, terms indicating directions or positional relationships such as "inner" and "outer" are based on the directions or positional relationships shown in the drawings. This is only for convenience of description and does not indicate or imply that the device or component must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present application.

[0062] In the description of the embodiments of the present application, unless otherwise clearly specified and limited, the terms "connected" and "coupled" shall be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two components. For those skilled in the art, the specific meanings of the above terms in the embodiments of the present application can be understood according to specific situations.

[0063] In the field of communication, resource allocation is crucial because communication resources (such as spectrum, bandwidth, power, etc.) are usually limited. By performing resource allocation, the use of resources can be optimized to improve network performance and user experience.

[0064] In the related art, when a user terminal sends an edge computing task access request, the traditional resource allocation method usually allocates an access point for the user terminal according to the network resource information of the terrestrial cellular network accessible to the user terminal and a pre-trained resource allocation model. The access point can be a terrestrial base station or the like.

[0065] However, only the terrestrial cellular network is considered in the above method, and other heterogeneous networks are not considered, resulting in low resource allocation efficiency and poor applicability to the space-ground integrated scenario.

[0066] The space-ground integrated scenario refers to a communication and computing environment that combines a terrestrial network and a space network. Among them, the space network may include a drone network and a satellite network. In the space-ground integrated scenario, since the location of the user terminal is variable and not limited to the ground, the resource allocation method applicable to the cellular network in the above related art is difficult to effectively adapt.

[0067] Therefore, in view of the above technical problems in the related art, the inventor found in the research process that when a user terminal sends an edge computing task access request, in addition to being able to access the terrestrial cellular network, if it can also access a drone network or a satellite network, the resources of the drone network or the satellite network can be fully utilized, thereby greatly improving the resource allocation efficiency. Specifically, after the user terminal sends an edge computing task access request, it can obtain the network information corresponding to each of the three networks, namely the terrestrial cellular network, the drone network, and the satellite network, and determine the information transmission rate and the required transmit power required by the user terminal to be accessed according to the network information of each network. The user terminal can also obtain the current location information of the user terminal to be accessed, and then determine the target network to which the above edge computing task access request is to be accessed according to the information transmission rate required by the user terminal to be accessed, the required transmit power, and the current location information, and finally access the target network, where the target network is any one of the terrestrial cellular network, the drone network, and the satellite network. Based on this, the present application proposes a method, apparatus, electronic device, storage medium, and product for determining an access network.

[0068] To facilitate the understanding of the present application, the following uses Figure 1 as an example to illustrate an application scenario diagram of the method for determining an access network in the present application, as Figure 1 shown Figure 1 is an application scenario schematic diagram provided by the present application. The specific application scenario of the present application may include multiple user terminals 01, a terrestrial cellular network 02, a drone network 03, and a satellite network 04. Each user terminal 01 can be wirelessly communicatively connected to the terrestrial cellular network 02, the drone network 03, and the satellite network 04 respectively. Among them, the user terminal 01 can also be referred to as a mobile station (Mobile Station, MS).

[0069] For any user terminal 01, after the user terminal 01 sends an edge computing task access request, it will obtain the network information of the three networks, namely the terrestrial cellular network 02, the drone network 03, and the satellite network 03, and can determine the information transmission rate and the required transmit power required by the user terminal 01 according to the network information corresponding to the three networks. The user terminal 01 can obtain its current location information, and the current location information can be a remote suburb, a near suburb, or a central urban area, etc. Then, the user terminal 01 determines one of the above networks to which the edge computing task access request is to be accessed according to the required information transmission rate, the required transmit power, and the current location information.

[0070] In this application, a core network controller 05 may also be included. The core network controller 05 may be communicatively connected to the terrestrial cellular network 02, the drone network 03, and the satellite network 04 either by wire or wirelessly. The core network controller 05 may obtain the communication data of the terrestrial cellular network 02, the drone network 03, and the satellite network 04.

[0071] It can be understood that in this application, the quantity, type, function, etc. of the user terminal 01, the terrestrial cellular network 02, the drone network 03, and the satellite network 04 are not limited, and they can be limited according to actual application scenarios, etc.

[0072] The technical solution of this application and how the technical solution of this application solves the above technical problems will be described in detail below with specific embodiments. These specific embodiments below can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of this application will be described below with reference to the accompanying drawings.

[0073] Please refer to Figure 2 , Figure 2 which is a schematic flowchart of a method for determining an access network provided by an embodiment of this application. The execution subject of this method may be a device for determining an access network, and the device for determining an access network may be implemented through a computer program; it may also be implemented through a medium storing relevant computer programs, such as a USB flash drive and / or an optical disc, etc., or, it may also be implemented through an entity device integrated or installed with relevant computer programs, such as a chip or an electronic device, etc. The electronic device may be a server, a server cluster, a computer, a smart terminal, etc. This method may include the following steps:

[0074] S201: Send an access request for an edge computing task.

[0075] In this embodiment, the execution subject is described by taking a smart terminal (abbreviated as user terminal) as an example. The user terminal may also be referred to as a mobile station, and the user terminal sends an access request for an edge computing task.

[0076] Among them, an edge computing task refers to providing various computing and data processing services by using edge computing technology. Edge computing is a distributed computing architecture that moves computing resources and data storage from a traditional centralized data center to the edge of the network, that is, closer to the data generation source or the user terminal.

[0077] Optionally, the edge computing task may be a real-time image and video processing task, a speech recognition and natural language processing task, an augmented reality application, a personalized content recommendation task, a game optimization task, etc.

[0078] S202. Obtain the network information of each of the terrestrial cellular network, the drone network, and the satellite network according to the edge computing task access request.

[0079] After the user terminal sends an edge computing task access request, the edge devices corresponding to the terrestrial cellular network, the drone network, and the satellite network will respond to this edge computing task access request and send their respective network information to the user terminal. Thus, the user terminal can obtain the network information of the terrestrial cellular network, the network information of the drone network, and the network information of the satellite network.

[0080] Among them, the terrestrial cellular network refers to a wireless communication network structure that provides mobile communication services by deploying a large number of base stations (also called cellular towers) on the ground.

[0081] The drone network is a system composed of multiple drones. The drones are interconnected and cooperate with each other through wireless communication technology to provide mobile communication services.

[0082] The satellite network is a system composed of multiple artificial satellites that provides mobile communication services by forming a widely covered communication network.

[0083] S203. Determine the information transmission rate and the required transmission power for the user terminal to be connected according to the network information of each network.

[0084] The user terminal can determine the required information transmission rate and the required transmission power according to the network information of the terrestrial cellular network, the network information of the drone network, and the network information of the satellite network.

[0085] Optionally, the network information of each network can be various parameters, including but not limited to: the current network resource usage data of each network, the information transmission rate and transmission power of the user terminals currently connected to each network, the transmission delay of the user terminals currently connected to each network, the maximum packet length, and the information transmission rate, etc.

[0086] S204. Obtain the current location information of the user terminal to be connected.

[0087] Optionally, the user terminal can obtain the current location information through a satellite navigation system, can obtain the current location information through cellular network positioning, can also obtain the current location information through the wireless network Wi-Fi, and can also obtain the current location information through sensors installed inside the user terminal, etc.

[0088] It can be understood that the above ways of obtaining the current location information are only for illustrative purposes and do not impose limitations on this application.

[0089] S205. Determine the target network to which the edge computing task access request is to be connected according to the information transmission rate required by the user terminal to be connected, the required transmission power, and the current location information.

[0090] Based on the information transmission rate required and the required transmission power determined by the user terminal according to step S203, and the current location information obtained in step S204, the user terminal determines the target network to which the edge computing task access request is to be connected based on a preset optimization algorithm or a pre-trained optimization model, etc.

[0091] Among them, the target network is any one of a terrestrial cellular network, a drone network, and a satellite network.

[0092] S206. Access the target network.

[0093] After the user terminal determines the target network, it accesses the target network.

[0094] In the above embodiments of the present application, by sending an edge computing task access request and according to the edge computing task access request, the network information of each of the terrestrial cellular network, the drone network, and the satellite network is obtained. Furthermore, according to the network information of each network, the information transmission rate required by the user terminal to be connected and the required transmission power are determined, and the current location information of the user terminal to be connected is obtained. According to the information transmission rate required by the user terminal to be connected, the required transmission power, and the current location information, the target network to which the edge computing task access request is to be connected is determined, and the target network is accessed. Among them, the target network is any one of a terrestrial cellular network, a drone network, and a satellite network. In the method of this embodiment, the user terminal to be connected can determine the information transmission rate required by the user terminal to be connected and the required transmission power according to the network information of each network, and then determine the target network according to the required information transmission rate, the required transmission power, and the current location information, so that the user terminal to be connected can not only access the terrestrial cellular network, but also access the drone network or the satellite network, thereby accessing the optimal network and improving the resource allocation efficiency.

[0095] Further, on the basis of the above embodiments, the process of determining the information transmission rate required by the user terminal to be connected and the required transmission power according to the network information of each network is described through the following embodiments.

[0096] Please refer to Figure 3 , Figure 3 which is a schematic flowchart of a method for determining the information transmission rate required by a user terminal to be connected and the required transmission power provided by an embodiment of the present application, and may include the following steps:

[0097] S301. Determine the optimized network-side load function according to the network information of each network.

[0098] Optionally, the network information of each network includes, but is not limited to: the current network resource usage data of each network, and the information transmission rate and transmission power of the user terminals currently connected to each network.

[0099] A possible implementation is:

[0100] Obtain an initial network-side load function according to the current network resource usage data of each network, and the information transmission rate and transmission power of the user terminals currently connected to each network.

[0101] The initial network-side load function can be as shown in formula (1), and the constraint conditions of some parameters in formula (1) are as shown in formulas (2) to (4):

[0102]

[0103]

[0104]

[0105]

[0106] Among them, represents the initial network-side load function; represents the network type matrix, and the network types are terrestrial cellular networks, drone networks, and satellite networks; represents the information transmission rate matrix of the user terminals currently connected to each network; represents the current network resource usage data of each network, that is, the current channel orthogonal resource usage data, which can change over time; represents the th channel slice; represents the th resource block in the total amount of resource blocks of the channel slice; represents the transmission power matrix of the user terminals currently connected to each network on the th resource block in the th channel slice, which can change over time; represents the first system sensitivity factor; represents the second system sensitivity factor; represents the third system sensitivity factor; represents the fourth system sensitivity factor, to can be adjusted by the user terminal according to local data pool learning; represents the total network resources of the channel; represents the A network, where the network is a terrestrial cellular network, a drone network, and a satellite network; Represents a minimum resource allocation unit in any one of the terrestrial cellular network, the drone network, and the satellite network; Represents the total number of resource allocation units.

[0107] Obtain the total network resources of the preset channels of each network and the transmission rate of the demand information preset by the user terminal to be connected, and use the total network resources of the preset channels of each network and the transmission rate of the demand information preset by the user terminal to be connected as constraint conditions, and use the initial network-side load function as the optimization target to determine the optimized network-side load function.

[0108] The optimized network-side load function can be as shown in formula That is, as shown in formula (5), the constraint conditions of some parameters in formula (5) are as shown in formulas (6)-(8):

[0109]

[0110]

[0111]

[0112]

[0113] S302. Determine the optimized user-side load function according to the network information of each network.

[0114] Optionally, the network information of each network includes but is not limited to: the transmission delay, the maximum packet length, and the information transmission rate of the user terminals currently connected to each network.

[0115] A possible implementation is:

[0116] Obtain the initial user-side load function according to the transmission delay, the maximum packet length, and the information transmission rate of the user terminals currently connected to each network.

[0117] The initial user-side load function can be as shown in formula (9), and the constraint conditions of some parameters in formula (9) are as shown in formulas (10)-(11):

[0118]

[0119]

[0120]

[0121] Wherein, Represents the initial user-side load function; Denote the transmission delay matrix of the currently connected user terminals in each of the terrestrial cellular network, the drone network, and the satellite network; Denote the current congestion index matrix of each network; Denote the computing power matrix of the edge devices corresponding to each network; Denote the maximum data packet length matrix of the currently connected user terminals in each network.

[0122] Obtain the total preset channel network resources of each network and the required channel network resources preset for the edge computing tasks. Taking the total preset channel network resources of each network and the required channel network resources preset for the edge computing tasks as the constraint conditions and the initial user-side load function as the optimization objective, determine the optimized user-side load function.

[0123] The optimized user-side load function can be as shown in Equation That is, as shown in Equation (12), the constraint conditions of some parameters in Equation (12) are as shown in Equations (13) to (16):

[0124]

[0125]

[0126]

[0127]

[0128]

[0129] S303. Combine the optimized network-side load function and the optimized user-side load function to obtain the target load function.

[0130] Combine the above-mentioned optimized network-side load function, i.e., Equation (5), and the optimized user-side load function, i.e., Equation (12), to obtain the target load function As shown in Equation That is, as shown in Equation (17), the constraint conditions of some parameters in Equation (17) are as shown in Equations (18) to (22):

[0131]

[0132]

[0133]

[0134]

[0135]

[0136]

[0137] S304. Determine the information transmission rate and the required transmission power of the user terminal to be accessed according to the target load function.

[0138] Furthermore, according to the determined target load function, determine the information transmission rate and the required transmission power of the user terminal to be accessed. The specific implementation manner will be described in detail in the following embodiments. Please refer to the following embodiments.

[0139] In the above embodiments of the present application, according to the network information of each network, determine the optimized network-side load function, and according to the network information of each network, determine the optimized user-side load function. Combine the optimized network-side load function and the optimized user-side load function to obtain the target load function, and according to the target load function, determine the information transmission rate and the required transmission power of the user terminal to be accessed. The method of this embodiment determines a more accurate target load function by using the optimized network-side load function and the optimized user-side load function, and thus the information transmission rate and the required transmission power of the user terminal to be accessed determined based on the accurate target load function are more accurate.

[0140] Further, on the basis of the above embodiments, the following embodiments illustrate the process of determining the information transmission rate and the required transmission power of the user terminal to be accessed according to the target load function.

[0141] Please refer to Figure 4 , Figure 4 which is a schematic flowchart of a method for instantiating and determining the information transmission rate and the required transmission power of the user terminal to be accessed provided by the embodiments of the present application. The method may include the following steps:

[0142] S401. Obtain the preset transmission power of the user terminal to be accessed, the preset transmission power of each network, and the preset average calculation delay of each network.

[0143] Since some parameters and constraints in the target load function are non-convex and very difficult to solve, in order to reduce the calculation delay, the solution problem can be converted into solving an information transmission rate sub-problem, solving the transmission power, and solving a target network sub-problem.

[0144] For solving the information transmission rate sub-problem, fix the transmission power of the user terminal to be accessed and the transmission power of each network, and given the average calculation delay of each network, that is, the transmission power of the user terminal to be accessed is preset, the transmission power of each network is preset, and the average calculation delay of each network is preset.

[0145] S402. Input the transmit power of the preset user terminal to be connected, the transmit powers of the preset networks, the average calculation delays of the preset networks, and the target load function into the preset optimization algorithm to determine the information transmission rate required by the user terminal to be connected.

[0146] To solve the information transmission rate sub-problem, a possible implementation is as follows:

[0147] Based on the preset optimization algorithm, input the transmit power of the preset user terminal to be connected, the transmit powers of the preset networks, the average calculation delays of the preset networks, and the target load function into the preset optimization algorithm, then the target load function is converted into the following formula That is, formula (23). The constraint conditions of some parameters in formula (23) are shown in formulas (24) - (26):

[0148]

[0149]

[0150]

[0151]

[0152] Among them, represents the information transmission rate required by the user terminal to be connected; represents the allocation situation of the number of certain orthogonal time-frequency resource blocks determined by the user terminal to be connected, and its value can be 0 or 1; represents in the th channel slice, the th resource block, the channel bandwidth of the determined resource block; represents the total channel resources of each network; is the channel capacity per unit spectrum represented by the Shannon formula, represents in the th channel slice, the th resource block, the estimated channel state matrix, which can change with time; represents the preset maximum information transmission rate; represents in the th resource block, the preset maximum channel bandwidth; represents the total number of channel slices; represents the total number of resource blocks of the channel slice; represents the preset average noise power of the channel slice; represents the total network resources of the channel of the i-th network; represents each network currently in the th channel slice, the The network resource usage data on a resource block can vary over time.

[0153] Thus, the information transmission rate required by the user terminal to be connected is obtained.

[0154] S403: Input the information transmission rate required by the user terminal to be connected, the average calculation delay of each preset network, and the target load function into a preset optimization algorithm to determine the transmission power required by the user terminal to be connected.

[0155] For solving the transmission power sub-problem, after determining the information transmission rate required by the user terminal to be connected, the average calculation delay of each network is given.

[0156] One possible implementation for solving the transmission power sub-problem is:

[0157] Based on the preset optimization algorithm, input the information transmission rate required by the user terminal to be connected, the average calculation delay of each preset network, and the target load function into this preset optimization algorithm, then the target load function is converted into the following formula That is, formula (27), and the constraint conditions of some parameters in formula (27) are shown in formula (28):

[0158]

[0159]

[0160] Among them, represents the transmission power required by the user terminal to be connected, represents the preset maximum transmission power.

[0161] Thus, the transmission power required by the user terminal to be connected is obtained.

[0162] In this embodiment, since the selection of the number of resource blocks and the transmission power has the characteristic of discreteness in practical engineering, and there is no problem of variable coupling in the transformed problem. In addition to using the above method to determine the information transmission rate and the required transmission power of the user terminal to be connected, the grid search method can also be used, that is, substituting the possible information transmission rate and the required transmission power of the user terminal to be connected into the target load function one by one until the information transmission rate and the transmission power that meet the requirements are found.

[0163] In the above embodiments of the present application, by obtaining the transmission power of the preset user terminal to be accessed, the transmission power of each preset network, and the average calculation delay of each preset network, and inputting the transmission power of the preset user terminal to be accessed, the transmission power of each preset network, the average calculation delay of each preset network, and the target load function into the preset optimization algorithm to determine the information transmission rate required by the user terminal to be accessed, and inputting the information transmission rate required by the user terminal to be accessed, the average calculation delay of each preset network, and the target load function into the preset optimization algorithm to determine the transmission power required by the user terminal to be accessed. The method of this embodiment determines the information transmission rate and the required transmission power of the user terminal to be accessed more accurately through the transmission power of the preset user terminal to be accessed, the transmission power of each preset network, and the average calculation delay of each preset network, reduces the delay required for calculation, and improves the calculation efficiency.

[0164] Furthermore, on the basis of the above embodiments, the process of determining the target network to which the edge computing task access request is to be accessed according to the information transmission rate required by the user terminal to be accessed, the required transmission power, and the current location information is described through the following embodiments.

[0165] After determining the information transmission rate and the required transmission power of the user terminal to be accessed through the above embodiments and substituting them into the target load function, the target load function is converted into the following formula That is, formula (29), and the constraint conditions of some parameters in formula (29) are shown in formulas (30) to (34):

[0166]

[0167]

[0168]

[0169]

[0170]

[0171]

[0172] Among them, represents the network resource allocation situation at the next moment, and the one that changes from 0 to 1 is the target network, and the target network can be any one of the terrestrial cellular network, the unmanned aerial vehicle network, and the satellite network.

[0173] For solving the above formula (33), a possible implementation is:

[0174] Transmit the information transmission rate, required transmit power, and current location information of the user terminal to be connected to a pre-trained deep reinforcement learning model to obtain the target network to which the edge computing task access request is to be connected.

[0175] Optionally, the pre-trained deep reinforcement learning model can be a Distributed-Deep Q Network (DP-DQN).

[0176] To facilitate understanding of the pre-trained deep reinforcement learning model in this embodiment, the following describes its training process. Please refer to Figure 5 , Figure 5 which is a schematic flowchart of a method for training a network-side deep reinforcement learning model provided by an embodiment of the present application. The method may include the following steps:

[0177] S501: Obtain training data.

[0178] In this embodiment, the execution subject is a user terminal, which can also be referred to as a mobile station.

[0179] Among them, the training data includes the historical networks to which the user terminal to be connected sends multiple historical edge computing task accesses, the historical information transmission rates, historical transmit powers, and historical location information corresponding to accessing each historical network, and the accessed historical networks are labels.

[0180] The accessed historical networks are terrestrial cellular networks, unmanned aerial vehicle networks, or satellite networks.

[0181] S502: Use the training data to train the initial deep reinforcement learning model until a preset convergence condition is met, and obtain a trained deep reinforcement learning model.

[0182] Use the training data to train the initial deep reinforcement learning model until the number of training times reaches a preset training times threshold or the loss function reaches a preset loss function threshold, and obtain a trained deep reinforcement learning model.

[0183] The training of the initial deep reinforcement learning model by the user terminal is the third training.

[0184] Please refer to Figure 6 , Figure 6 which is a schematic diagram of a method for training a deep reinforcement learning model provided by an embodiment of the present application. The following will combine Figure 5 and Figure 6 to illustrate the training process of the finally obtained trained deep reinforcement learning model.

[0185] Optionally, the initial deep reinforcement learning model can be comprehensively trained by network devices corresponding to the terrestrial cellular network, the drone network, and the satellite network respectively.

[0186] A possible implementation is as follows:

[0187] The edge device corresponding to the terrestrial cellular network trains the first deep reinforcement learning model based on its own network information to obtain the trained first sub-deep reinforcement learning model. Then, the edge device corresponding to the drone network trains the first sub-deep reinforcement learning model based on its own network information to obtain the trained second sub-deep reinforcement learning model. Then, the edge corresponding to the satellite network trains based on its own network information to obtain the trained third sub-deep reinforcement learning model.

[0188] Among them, the third sub-deep reinforcement learning model can be the initial deep reinforcement learning model in step S502.

[0189] It can be understood that in this application, the order of training the edge devices corresponding to the terrestrial cellular network, the drone network, and the satellite network is not limited. The training of the first deep reinforcement learning model by the edge devices of each network can be understood as the second model training.

[0190] Optionally, the first deep reinforcement learning model can be trained by the core network controller. The core network controller detects the status of each network and obtains the network information of each network. The core network controller takes the average network parameters of each network and the historical congestion index of each network preset as the input, and the accessed historical network as the label, and trains the second deep reinforcement learning model until the convergence condition is met to obtain the trained first deep reinforcement learning model. Among them, the second deep reinforcement learning model is an original model that has not undergone any training. The training of the original model by the core network controller can be understood as the first model training.

[0191] Optionally, in this application, the trained deep reinforcement learning model deployed on the user terminal can be not only the model after the third training, but also the model after the second training, or the model after the first training.

[0192] After the user terminal obtains the trained deep reinforcement learning model, it inputs the determined required information transmission rate, required transmission power, and current location information into the pre-trained deep reinforcement learning model to obtain the target network to which the edge computing task access request is to be accessed.

[0193] The trained deep reinforcement learning in this application has low network overhead and is applicable to the situation where the number of user terminals accessing in the space-ground integrated scenario surges.

[0194] In the above embodiments of the present application, by obtaining training data and using the training data to train an initial deep reinforcement learning model until a preset convergence condition is met, a trained deep reinforcement learning model is obtained, so that the target network accessed according to the accurate deep reinforcement learning model after training for the edge computing task access request of the user terminal to be accessed is more accurate, thereby accessing the optimal network and improving the resource allocation efficiency.

[0195] Figure 7 The following is a schematic structural diagram of a device for determining an access network provided by an embodiment of the present application. As Figure 7 shown, the device for determining an access network provided in this embodiment includes:

[0196] A sending module 701, configured to send an edge computing task access request.

[0197] An obtaining module 702, configured to obtain network information of each of a terrestrial cellular network, a drone network, and a satellite network according to the edge computing task access request.

[0198] A determining module 703, configured to determine the information transmission rate and the required transmission power required by the user terminal to be accessed according to the network information of each network.

[0199] The obtaining module 702 is further configured to obtain the current location information of the user terminal to be accessed.

[0200] The determining module 703 is further configured to determine the target network accessed by the edge computing task access request according to the information transmission rate, the required transmission power, and the current location information of the user terminal to be accessed, and the target network is any one of a terrestrial cellular network, a drone network, and a satellite network.

[0201] An access module 704, configured to access the target network.

[0202] In a possible implementation manner, the determining module 703 is specifically configured to:

[0203] Determine an optimized network-side load function according to the network information of each network.

[0204] Determine an optimized user-side load function according to the network information of each network.

[0205] Combine the network-side load function and the user-side load function to obtain a target load function.

[0206] Determine the information transmission rate and the required transmission power required by the user terminal to be accessed according to the target load function.

[0207] In a possible implementation, the network information of each network includes: the current network resource usage data of each network, as well as the information transmission rate and transmission power of the user terminals currently connected to each network. The determination module 703 is specifically configured to:

[0208] Obtain an initial network-side load function based on the current network resource usage data of each network, as well as the information transmission rate and transmission power of the user terminals currently connected to each network.

[0209] Obtain the total preset channel network resources of each network and the preset required information transmission rate of the user terminals to be connected.

[0210] Taking the total preset channel network resources of each network and the preset required information transmission rate of the user terminals to be connected as constraint conditions, and taking the initial network-side load function as the optimization objective, determine the optimized network-side load function.

[0211] In a possible implementation, the network information of each network includes: the transmission delay, maximum packet length, and information transmission rate of the user terminals currently connected to each network. The determination module 703 is specifically configured to:

[0212] Obtain an initial user-side load function based on the transmission delay, maximum packet length, and information transmission rate of the user terminals currently connected to each network.

[0213] Obtain the total preset channel network resources of each network and the preset required channel network resources of the edge computing tasks.

[0214] Taking the total preset channel network resources of each network and the preset required channel network resources of the edge computing tasks as constraint conditions, and taking the initial user-side load function as the optimization objective, determine the optimized user-side load function.

[0215] In a possible implementation, the determination module 703 is specifically configured to:

[0216] Obtain the transmission power of the user terminals to be connected preset, the transmission power of each network preset, and the average computing delay of each network preset.

[0217] Input the transmission power of the user terminals to be connected preset, the transmission power of each network preset, the average computing delay of each network preset, and the target load function into a preset optimization algorithm to determine the required information transmission rate of the user terminals to be connected.

[0218] Input the required information transmission rate of the user terminals to be connected, the average computing delay of each network preset, and the target load function into a preset optimization algorithm to determine the required transmission power of the user terminals to be connected.

[0219] In a possible implementation, the determining module 703 is specifically configured to:

[0220] Input the information transmission rate, required transmission power, and current location information of the user terminal to be connected into a pre-trained deep reinforcement learning model to obtain the target network to which the edge computing task access request is to be connected.

[0221] In a possible implementation, it further includes a training module, which is used to:

[0222] Obtain training data, where the training data includes the historical networks to which multiple historical edge computing tasks of the user terminal to be connected are sent, the historical information transmission rates, historical transmission powers, and historical location information corresponding to accessing each historical network, and the accessed historical networks are labels.

[0223] Use the training data to train the initial deep reinforcement learning model until a preset convergence condition is met to obtain a trained deep reinforcement learning model.

[0224] The device for determining the access network provided in this embodiment can execute the method provided in the above method embodiment, and its implementation principle and technical effects are similar, which will not be elaborated here in this embodiment.

[0225] Figure 8 It is a schematic structural diagram of an electronic device provided in an embodiment of the present application. As Figure 8 shown, the electronic device provided in this embodiment includes: at least one processor 801 and a memory 802. Optionally, the electronic device further includes a communication component 803. Among them, the processor 801, the memory 802, and the communication component 803 are connected through a bus 804.

[0226] In a specific implementation process, at least one processor 801 executes the computer execution instructions stored in the memory 802, so that at least one processor 801 executes the above method.

[0227] The specific implementation process of the processor 801 can be referred to in the above method embodiment, and its implementation principle and technical effects are similar, which will not be elaborated here in this embodiment.

[0228] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU for short), or other general-purpose processors, digital signal processors (DSP for short), application specific integrated circuits (ASIC for short), etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the method disclosed in combination with the invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules in the processor.

[0229] The memory may include a high-speed random access memory (RAM), and may also include non-volatile memory (NVM), such as at least one disk memory.

[0230] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of representation, the bus in the drawings of this application is not limited to only one bus or one type of bus.

[0231] This application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0232] This application also provides a computer-readable storage medium, in which computer-executable instructions are stored, and when the processor executes the computer-executable instructions, the above method is implemented.

[0233] The above-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, a magnetic disk or an optical disk. The readable storage medium can be any available medium accessible by a general-purpose or special-purpose computer.

[0234] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be an integral part of the processor. The processor and the readable storage medium can be located in an Application Specific Integrated Circuits (ASIC). Of course, the processor and the readable storage medium can also exist as discrete components in a device.

[0235] The division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Additionally, the couplings or direct couplings or communication connections shown or discussed among each other can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electrical, mechanical or other forms.

[0236] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0237] Furthermore, in each embodiment of the present invention, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0238] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in each embodiment of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks or optical discs that can store program codes.

[0239] Those of ordinary skill in the art will understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments; and the aforementioned storage medium includes: various media such as ROM, RAM, magnetic disks, or optical discs that can store program codes.

[0240] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses, or adaptations of the present invention, which follow the general principles of the present invention and include common general knowledge or conventional technical means in the technical field not disclosed in the present invention. It is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present invention is only limited by the appended claims.

Claims

1. A method for determining an access network, characterized in that: include: Send edge computing task access request; According to the edge computing task access request, obtain network information of the ground cellular network, the drone network, and the satellite network; Determine the information transmission rate and the required transmission power required by the user terminal to be connected according to the network information of each network; Acquire the current location information of the user terminal to be accessed; Determine a target network for the edge computing task access request according to the information transmission rate required by the user terminal to be accessed, the required transmission power, and the current location information, where the target network is any one of the ground cellular network, the drone network, and the satellite network; Accessing the target network; The determining, according to the network information of each network, the information transmission rate and the required transmission power required by the user terminal to be accessed includes: Determining an optimized network-side load function according to the network information of each network; Determining an optimized user-side load function according to the network information of each network; The optimized network-side load function is combined with the optimized user-side load function to obtain a target load function; According to the target load function, the information transmission rate and the required transmission power required by the user terminal to be connected are determined.

2. The method according to claim 1, characterized in that The network information of each network includes: current network resource usage data of each network, and information transmission rate and transmission power of user terminals currently connected to each network; The step of determining an optimized network side load function according to the network information of each network includes: Acquire an initial network side load function according to the current network resource usage data of each network, and the information transmission rate and transmission power of the user terminal currently connected to each network; Obtaining the total network resources of the channels preset by each network and the required information transmission rate preset by the user terminal to be connected; The optimized network side load function is determined by taking the total network resources of the channels preset by the networks and the required information transmission rate preset by the user terminal to be accessed as constraint conditions and taking the initial network side load function as the optimization target.

3. The method according to claim 1, characterized in that The network information of each network includes: the transmission delay, maximum data packet length and information transmission rate of the user terminal currently connected to each network; The step of determining an optimized user-side load function according to the network information of each network includes: Obtaining an initial user-side load function according to the transmission delay, maximum data packet length, and information transmission rate of the user terminals currently connected to each network; Obtain the total network resources of the channels preset for each network and the required channel network resources preset for the edge computing task; Taking the total channel network resources preset by each network and the required channel network resources preset by the edge computing task as constraints, taking the initial user-side load function as the optimization target, the optimized user-side load function is determined.

4. The method according to claim 2 or 3, characterized in that: The determining, according to the target load function, the information transmission rate and the required transmission power required by the user terminal to be connected includes: Obtaining a preset transmit power of the user terminal to be accessed, a preset transmit power of each network, and a preset average calculation delay of each network; Inputting the preset transmit power of the user terminal to be accessed, the preset transmit power of each network, the preset average calculation delay of each network and the target load function into a preset optimization algorithm to determine the information transmission rate required by the user terminal to be accessed; The information transmission rate required by the user terminal to be accessed, the average calculation delay of each preset network and the target load function are input into a preset optimization algorithm to determine the transmission power required by the user terminal to be accessed.

5. The method according to claim 1, characterized in that The determining, according to the information transmission rate required by the user terminal to be accessed, the required transmission power, and the current location information, a target network to be accessed by the edge computing task access request includes: The information transmission rate required by the user terminal to be accessed, the required transmission power and the current location information are input into a pre-trained deep reinforcement learning model to obtain the target network accessed by the edge computing task access request.

6. The method according to claim 5, characterized in that The training steps of the pre-trained deep reinforcement learning model include: Acquire training data, where the training data includes historical networks accessed by the user terminal to be accessed by sending multiple historical edge computing tasks, historical information transmission rates corresponding to accessing each historical network, historical transmission power, and historical location information, where the accessed historical network is a label; The training data is used to train the initial deep reinforcement learning model until a preset convergence condition is met to obtain a trained deep reinforcement learning model.

7. A device for determining access to a network, characterized in that: include: A sending module, used to send edge computing task access requests; An acquisition module, used to acquire network information of a ground cellular network, a drone network, and a satellite network according to the edge computing task access request; A determination module, used to determine the information transmission rate and the required transmission power required by the user terminal to be connected according to the network information of each network; The acquisition module is further used to acquire the current location information of the user terminal to be connected; The determination module is further used to determine the target network for access by the edge computing task access request according to the information transmission rate required by the user terminal to be accessed, the required transmission power, and the current location information, wherein the target network is any one of the ground cellular network, the drone network, and the satellite network; An access module, used for accessing the target network; The determination module is specifically used to determine the optimized network side load function according to the network information of each network; determine the optimized user side load function according to the network information of each network; merge the optimized network side load function with the optimized user side load function to obtain a target load function; and determine the information transmission rate and the required transmission power required by the user terminal to be accessed according to the target load function.

8. An electronic device, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 6 when executed by a processor.

10. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 6 when being executed by a processor.

Images