A method for providing user plane service of satellite core network

Abstract

The present application discloses a method for providing user-plane service of a satellite core network, a system and a training method, device, storage medium, equipment and computer program product of its policy model, belonging to the field of satellite communication, including: in response to a task request, adding the task request to the task queue of a local low-orbit satellite, and updating the local low-orbit satellite to a service state in the case of a standby state; in the case of a service state, executing the task request in the task queue; in the case that the continuous standby time of the standby state of the local low-orbit satellite exceeds a preset standby time threshold, updating the local low-orbit satellite to a closed state; in the case that the local low-orbit satellite is in a closed state and the number of task requests in the task queue is greater than or equal to a preset request number threshold, updating the local low-orbit satellite to a set state. The problem of insufficient continuity of user-plane service of the satellite core network caused by the fast moving speed of the satellite is solved.

Description

Technical Field

[0001] The present application belongs to the field of satellite communications, and specifically relates to a satellite core network user plane service provision method, system, and training method, device, storage medium, equipment, and computer program product of its strategy model. Background Art

[0002] With the development of mobile communication network technology, building satellite Internet through large-scale low-orbit satellite constellations can provide hotspots and coverage supplementary services for ground users, and even support edge computing services based on satellite Internet. The combination of low-orbit constellations and wireless communication technology is the key to achieving this goal.

[0003] In the existing technology, the 5G core network adopts a service-based architecture, realizes the separation of the control plane and the user plane, and supports network slicing and service customization. The user plane function (UPF) is an important network element in the 5G core network, responsible for processing and forwarding user data traffic under the control of the session management function.

[0004] However, although existing technologies have deployed UPF on satellites, the high-speed movement of low-orbit satellites causes frequent interruptions of UPF services. After users access a new UPF, they need to quickly migrate the status and establish a new traffic path to ensure service continuity. Existing solutions generally cannot guarantee the continuity of user services. Summary of the invention

[0005] The present application aims to provide a method and system for providing user-plane services of a satellite core network, a training method, an apparatus, a storage medium, a device and a computer program product for their strategy models, which at least solves the problem of insufficient continuity of user-plane services of the satellite core network caused by the fast movement speed of the satellite.

[0006] In a first aspect, an embodiment of the present application discloses a method for providing user plane services of a satellite-borne core network, which is applied to a local low-orbit satellite of a low-orbit satellite network, including:

[0007] In response to a task request of a traffic routing type or a state migration type, adding the task request to a task queue of the local low-orbit satellite, and updating the local low-orbit satellite to a service state when the local low-orbit satellite is in a standby state;

[0008] When the local low-orbit satellite is in service state, executing the task request in the task queue;

[0009] When the continuous standby time of the standby state of the local low-orbit satellite exceeds a preset standby time threshold, updating the local low-orbit satellite to a shutdown state;

[0010] When the local low-orbit satellite is in a closed state and the number of task requests in the task queue is greater than or equal to a preset request number threshold, the local low-orbit satellite is updated to a setting state; the setting state is used to state migrate the task requests in the task queue, and the local low-orbit satellite is updated to a service state to execute the remaining task requests in the task queue after the state migration.

[0011] In a second aspect, the embodiment of the present application further discloses a method for providing user plane services of a satellite core network, which is applied to a mission management device of a low-orbit satellite network, including:

[0012] In response to a task request of a traffic routing type or a state migration type, obtaining the operation status data of each low-orbit satellite in the low-orbit satellite network; each of the low-orbit satellites processes the task request of the low-orbit satellite by executing the onboard core network user plane service provision method as described in the first aspect;

[0013] Determine a target low-orbit satellite from among all the low-orbit satellites according to a total delay minimization optimization model of the low-orbit satellite network established by all the operating status data;

[0014] The mission request is sent to the target low-orbit satellite, so that the target low-orbit satellite executes the mission request.

[0015] In a third aspect, the embodiment of the present application further discloses a method for providing user plane services of a satellite core network, which is applied to a mission management device of a low-orbit satellite network, including:

[0016] In response to a task request of a traffic routing type or a state migration type, obtaining the operation status data of each low-orbit satellite in the low-orbit satellite network; each of the low-orbit satellites processes the task request of the low-orbit satellite by executing the onboard core network user plane service provision method as described in the first aspect;

[0017] Determine a target low-orbit satellite from among all the low-orbit satellites according to a total delay minimization optimization model of the low-orbit satellite network established by all the operating status data;

[0018] Sending the mission request to the target low-orbit satellite so that the target low-orbit satellite executes the mission request;

[0019] Determining a target low-orbit satellite from among all the low-orbit satellites according to a total delay minimization optimization model of the low-orbit satellite network established by all the operating status data comprises:

[0020] Inputting all of the operating status data into a strategy model to obtain a probability vector of the low-orbit satellite network; the probability vector is used to characterize the probability value of each low-orbit satellite in the low-orbit satellite network being a target low-orbit satellite;

[0021] The executable low-orbit satellite with the largest probability value corresponding to the low-orbit satellite network is selected as the target low-orbit satellite; the executable low-orbit satellite is a low-orbit satellite whose current state is in the service phase or the standby phase.

[0022] In a fourth aspect, an embodiment of the present application further discloses a method for training a policy model, which is used to train the policy model as described in the third aspect, and is characterized by comprising:

[0023] Initially setting the strategy model according to the switch control parameters of the low-orbit satellite in the low-orbit satellite network;

[0024] For the strategy model that has been initially set, a preset target training low-orbit satellite is input to obtain a cross entropy loss function of the strategy model under the target training low-orbit satellite;

[0025] The parameter gradient of the cross entropy loss function is updated through back propagation, and when the parameter gradient reaches a minimum value, the trained policy model is obtained.

[0026] In a fifth aspect, an embodiment of the present application further discloses a low-orbit satellite network system, comprising a plurality of low-orbit satellites and a mission management device;

[0027] The low-orbit satellite is used to respond to a task request of a traffic routing type or a state migration type, add the task request to the task queue of the local low-orbit satellite, and when the local low-orbit satellite is in a standby state, update the local low-orbit satellite to a service state, and when the local low-orbit satellite is in a service state, execute the task request in the task queue, and when the continuous standby time of the standby state of the local low-orbit satellite exceeds a preset standby time threshold, update the local low-orbit satellite to a closed state, and when the local low-orbit satellite is in a closed state and the number of task requests in the task queue is greater than or equal to a preset request number threshold, update the local low-orbit satellite to a setting state; the setting state is used to state migrate the task request in the task queue, and update the local low-orbit satellite to a service state to execute the remaining task requests in the task queue after the state migration;

[0028] The task management device is used to respond to a task request of a traffic routing type or a state migration type, obtain the operating status data of each low-orbit satellite in the low-orbit satellite network, and determine the target low-orbit satellite among all the low-orbit satellites based on a total delay minimization optimization model of the low-orbit satellite network established by all the operating status data, and send the task request to the target low-orbit satellite so that the target low-orbit satellite executes the task request.

[0029] In a sixth aspect, the embodiment of the present application further discloses a satellite-borne core network user plane service providing device, which is applied to a local low-orbit satellite, including:

[0030] A queue module, configured to respond to a task request of a traffic routing type or a state migration type, add the task request to a task queue of the local low-orbit satellite, and update the local low-orbit satellite to a service state when the local low-orbit satellite is in a standby state;

[0031] A service module, used for executing the task request in the task queue when the local low-orbit satellite is in service state;

[0032] A shutdown module, configured to update the local low-orbit satellite to a shutdown state when the continuous standby time of the standby state of the local low-orbit satellite exceeds a preset standby time threshold;

[0033] A setting module is used to update the local low-orbit satellite to a setting state when the local low-orbit satellite is in a closed state and the number of task requests in the task queue is greater than or equal to a preset request number threshold; the setting state is used to state migrate the task requests in the task queue and update the local low-orbit satellite to a service state to execute the remaining task requests in the task queue after the state migration.

[0034] In a seventh aspect, the embodiment of the present application further discloses a satellite core network user plane service providing device, which is applied to a mission management device of a low-orbit satellite:

[0035] A state acquisition module, configured to obtain the operation state data of each low-orbit satellite in the low-orbit satellite network in response to a task request of a traffic routing type or a state migration type; each of the low-orbit satellites processes the task request of the low-orbit satellite by executing the onboard core network user plane service provision method as described in the first aspect;

[0036] a target decision module, configured to determine a target low-orbit satellite from among all the low-orbit satellites according to a total delay minimization optimization model of the low-orbit satellite network established by all the operating status data;

[0037] A decision sending module is used to send the task request to the target low-orbit satellite so that the target low-orbit satellite executes the task request.

[0038] In an eighth aspect, an embodiment of the present application further discloses a training device for a policy model, which is used to train the policy model as described in the third aspect, and is characterized by comprising:

[0039] An initial setting module, used for initially setting the strategy model according to the switch control parameters of the low-orbit satellite in the low-orbit satellite network;

[0040] A function generation module, used for inputting a preset target training low-orbit satellite into the strategy model after the initial setting, so as to obtain a cross entropy loss function of the strategy model under the target training low-orbit satellite;

[0041] The network training module is used to update the parameter gradient of the cross entropy loss function through back propagation, and obtain the trained strategy model when the parameter gradient reaches a minimum value.

[0042] In a ninth aspect, an embodiment of the present application further discloses a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps described in the first aspect or the second aspect are implemented.

[0043] In a tenth aspect, an embodiment of the present application further discloses an electronic device, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps described in the first aspect or the second aspect are implemented.

[0044] In the eleventh aspect, an embodiment of the present application further discloses a computer program product, on which a computer program is stored, and when the computer program is executed by a processor, the steps described in the first aspect or the second aspect are implemented.

[0045] In summary, in the embodiment of the present application, when the low-orbit satellite receives a task request of a traffic routing type or a state migration type, it is added to the task queue. When the low-orbit satellite is in a standby state, the state is updated to a service state to ensure that the low-orbit satellite responds quickly after receiving the task request, thereby improving the real-time and efficiency of task processing; and when the standby state duration of the low-orbit satellite exceeds the preset standby time threshold, its state is updated to a closed state, saving satellite resources, especially computing and power resources, and improving the resource utilization of the system. When the low-orbit satellite is in a closed state and the number of task requests in the task queue is greater than or equal to the preset request number threshold, its state is updated to a set state, and the state migration of the task request is performed, so as to effectively manage and allocate computing resources by dynamically adjusting the satellite state, ensure the smoothness and efficiency of the task migration process, and reduce service interruptions caused by satellite switching. In this process, the target low-orbit satellite is determined by minimizing the total delay optimization model, and the task request is sent to the target low-orbit satellite to ensure that the task request is processed under the conditions of minimum delay and maximum resource utilization, thereby improving the performance of the entire system. Therefore, based on the method of the embodiment of the present application, not only the delay of service migration and traffic routing is significantly reduced, but also by dynamically managing the computing resources of the satellite, resource utilization is optimized, and the continuity and efficiency of the user-plane services of the onboard core network are ensured. The problems of frequent interruptions and excessive resource consumption of the user-plane services of the onboard core network of low-orbit satellites in the existing technology are solved, and the service quality and reliability of satellite Internet are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present application. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0047] Figure 1 is a timing diagram of a switch control strategy provided in an embodiment of the present application;

[0048] Figure 2 It is a flowchart of the steps of a method for providing a satellite core network user plane service provided by an embodiment of the present application;

[0049] Figure 3 It is a flowchart of the steps of another method for providing a satellite core network user plane service provided by an embodiment of the present application;

[0050] Figure 4 It is the operation process of a satellite network under the method of the embodiment of the present application;

[0051] Figure 5It is a flowchart of the steps of another method for providing a satellite core network user plane service provided by an embodiment of the present application;

[0052] Figure 6 It is the operation process of the policy model under the method of the embodiment of the present application;

[0053] Figure 7 is a block diagram of a low-orbit satellite network system provided by an embodiment of the present application;

[0054] Figure 8 It is a flowchart of the steps of a training method of a strategy model provided in an embodiment of the present application;

[0055] Fig. 9 This is the training process of the policy model under the method of the embodiment of the present application;

[0056] Fig.10 It is a loop process of program execution logic under the method of the embodiment of the present application.

[0057] Fig.11 It is a structural diagram of a satellite core network user plane service providing device provided in an embodiment of the present application;

[0058] Fig.12 It is a structural diagram of another onboard core network user plane service providing device provided in an embodiment of the present application;

[0059] Fig.13 This is a structural diagram of a training device for a strategy model provided in an embodiment of the present application.

[0060] Fig.14 is a block diagram of an electronic device provided in an embodiment of the present application;

[0061] Fig.15 It is a block diagram of another electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0062] The exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present application and to fully convey the scope of the present application to those skilled in the art.

[0063] Based on the actual situation that low-orbit satellites run faster and are therefore frequently interrupted, the present invention designs and implements a method for providing user-plane services of a satellite-borne core network, which is mainly achieved through the following methods: Figure 1The switch control strategy shown in the figure is implemented as follows: the time period before point A in the figure belongs to the service state, and there are tasks being executed in the task queue at this time. The stage from point A to point B belongs to the standby state, and the task queue is empty at this time. The stage from point B to C is the closing stage. Although the task is received and entered into the task queue at this time, the task is not executed until the length of the task queue reaches a certain limit, then it enters the setting state (the part after C until the next service state is turned on), which is the process of judging, screening, and circulating the tasks in the task queue.

[0064] Figure 2 This is a method for providing user plane services of a satellite core network provided by the present application. The method provided in this embodiment is applied to a local low-orbit satellite of a low-orbit satellite network, and specifically includes the following steps:

[0065] Step 101, in response to a task request of a traffic routing type or a state migration type, the task request is added to a task queue of a local low-orbit satellite, and when the local low-orbit satellite is in a standby state, the local low-orbit satellite is updated to a service state.

[0066] In some embodiments of the present application, the local low-orbit satellite will respond to a task request of a traffic routing type or a state migration type, add the task request to the task queue of the local low-orbit satellite, and update the local low-orbit satellite to a service state when the local low-orbit satellite is in a standby state. The purpose of this step is to ensure that when a task request is received, the local low-orbit satellite can respond in a timely manner and process the task request, thereby improving the real-time performance and efficiency of task processing.

[0067] For example, in a low-orbit satellite network, a user equipment (UE) sends a traffic routing type task request. After receiving the task request, the system will first check the current status of the local low-orbit satellite. If the low-orbit satellite is in standby state, the system will add the task request to the task queue of the low-orbit satellite and update the status of the low-orbit satellite to the service state to ensure that the task request can be processed in time. The purpose of this is to be able to respond quickly to user requests and improve the task processing efficiency and resource utilization of the entire system.

[0068] Step 102: When the local low-orbit satellite is in service, execute the task request in the task queue.

[0069] In some embodiments of the present application, when the local low-orbit satellite is in service, the task request in the task queue is executed. This means that once the low-orbit satellite enters the service state, it will process each task request in the queue in turn to ensure that each task is processed in a timely and efficient manner. This step is intended to improve the efficiency of task processing, reduce the latency of task requests, and optimize the resource utilization of the low-orbit satellite.

[0070] For example, consider a scenario where, after the LEO satellite successfully switches to the service state, it starts executing tasks in the task queue. Assume that the task queue contains two task requests, one is a traffic routing type request and the other is a state migration type request. First, the LEO satellite will execute the state migration request to migrate the context state of the user device from one onboard core network user plane function (UPF) to another UPF. Once completed, it will process the traffic routing request and transmit the user device's traffic to the ground network through the appropriate routing path to ensure service continuity. When executing each task request, the LEO satellite will make full use of its computing and bandwidth resources to improve the real-time and efficiency of task processing.

[0071] Step 103: When the continuous standby time of the local low-orbit satellite in the standby state exceeds a preset standby time threshold, the local low-orbit satellite is updated to a closed state.

[0072] In some embodiments of the present application, if the standby state of the local low-orbit satellite lasts for more than a preset standby time threshold, the low-orbit satellite is updated to a shutdown state. The purpose of this step is to save computing resources and power resources by updating its state from standby to shutdown when the low-orbit satellite has not received a new mission request for a long time, thereby improving the resource utilization of the satellite system.

[0073] For example, suppose a low-orbit satellite enters standby mode for a period of time, but does not receive any new mission requests during this period. The system will continue to monitor the duration of the standby state and compare it with the preset standby time threshold. If the standby time exceeds the preset threshold, the system will update the state of the low-orbit satellite to the off state. In the off state, the satellite will consume minimal computing resources and power resources, thereby extending its service life and improving resource utilization efficiency. In this way, the satellite can automatically enter energy-saving mode when there is no mission demand, ensuring the efficient operation of the entire satellite network.

[0074] Step 104: When the local low-orbit satellite is in a closed state and the number of task requests in the task queue is greater than or equal to a preset request number threshold, the local low-orbit satellite is updated to a set state.

[0075] Among them, setting the state is used for the task requests in the state migration task queue, and updating the local low-orbit satellite to the service state to execute the remaining task requests in the task queue after the state migration.

[0076] In some embodiments of the present application, when the local low-orbit satellite is in a closed state and the number of task requests in the task queue reaches or exceeds a preset request number threshold, the system updates the state of the local low-orbit satellite to a set state. In the set state, the low-orbit satellite can effectively process the task requests in the state migration task queue to ensure that the task requests can be responded to and processed quickly. The goal of the set state is to minimize the delay caused by the switching process during the state migration process, and after the state migration is completed, the low-orbit satellite is updated to a service state to continue processing the remaining task requests in the task queue.

[0077] For example, suppose a low-orbit satellite is in the off state, and five task requests have accumulated in its task queue, while the system preset threshold for the number of requests is four. Once the number of task requests reaches or exceeds this threshold, the system will automatically update the state of the low-orbit satellite from the off state to the set state. In the set state, the low-orbit satellite will execute the state migration task request in the task queue, and migrate the UE's state information from one onboard UPF to a new UPF to ensure service continuity. After the state migration is completed, the low-orbit satellite will switch to the service state again and continue to process the remaining task requests, thereby maintaining the efficiency and real-time performance of task processing.

[0078] Based on the LEO satellite execution process executed by the above switching strategy, consider a LEO satellite system with Represents a satellite collection, satellite CPU resource capacity express, represent The intersatellite link bandwidth at that time. A UE request is represented as a set , and Respectively represent UE requests The state size and data size. Used to indicate exist Is it connected? ,like ,but Accessed ,like , then it is not connected. At the same time, Deployed on satellite The UPF becomes the UE request The new UPF of the service Satellite The UPF is not new for UE requests Provide services to the target UPF.

[0079] In order to ensure the continuity of the onboard UPF service, it is necessary to select a new target UPF as soon as possible and perform state migration and traffic routing path establishment. The delays generated in this process mainly include state sending delay, state propagation delay, data sending delay, and data propagation delay.

[0080] So the following definition can be made:

[0081] Total sending delay of all UE state transitions: ,

[0082] in is the number of intersatellite link hops of the state migration path, express Time Satellite and The bandwidth of the intersatellite link between and Represents two adjacent satellites.

[0083] Total propagation delay of all UE state transitions: ,

[0084] in are two adjacent satellites in the state migration path and The distance between Represents the speed of light.

[0085] Total sending delay for all UE traffic routes: ,

[0086] in is the number of ISL hops in the traffic routing path.

[0087] Total propagation delay for all UE traffic routes: .

[0088] Since the operation of the satellite-borne UPF with light load or even no load will lead to unnecessary waste of satellite resources, the following considerations are adopted: Figure 1 The N-limitation strategy shown provides on-off control of the onboard UPF function.

[0089] In this case, the onboard UPF The CPU resources consumed during the service phase of providing services Indicates that when the satellite UPF When the service queue becomes empty, UPF switches to the standby phase, and the CPU resources consumed at this time are The duration of the standby phase is If any UE request reaches the onboard UPF during this time , it immediately returns to the service phase, otherwise it enters the shutdown phase, which consumes less CPU resources If N UE requests arrive during this phase, the onboard UPF From the shutdown phase to the setup phase, the CPU resources consumed in this phase are , the duration is .

[0090] If the UE request arrives during the shutdown phase or setup phase, the UE request cannot be immediately served by the onboard UPF, resulting in additional delay. Shortening the duration of the shutdown phase or setup phase can effectively shorten the delay, but it will lead to higher resource consumption. Therefore, it is necessary to effectively handle the delay-resource consumption trade-off in the onboard UPF switch control process. The additional delay caused by the switching control process is expressed as , the total delay caused by the introduction of the switch control mechanism for all onboard UPFs is ,

[0091] in Is to judge the onboard UPF Indicator variable for whether the event from the closing stage to the opening stage occurs: When the satellite UPF A transition from the Close / Setup phase to the Service phase occurs, and if , it means that the process did not occur.

[0092] By adjusting the parameters in the onboard UPF switch control model and N, can effectively reduce latency and resource consumption, thereby ensuring the continuity of onboard UPF services.

[0093] Then, by establishing the onboard UPF state migration and traffic routing delay model and the onboard UPF switch control model, the ultimate goal of onboard UPF service optimization is transformed into solving the optimization problem of minimizing the total delay, that is, the following optimization problem: .

[0094] Figure 3 The specific process of applying the onboard core network user plane service provision method provided by this application to the mission management equipment of the low-orbit satellite network is demonstrated:

[0095] Step 201, in response to a task request of a traffic routing type or a state migration type, obtain the operation status data of each low-orbit satellite in the low-orbit satellite network.

[0096] Each low-orbit satellite processes the mission request of the low-orbit satellite by executing the onboard core network user plane service provision method in the above embodiment.

[0097] In some embodiments of the present application, when a task request of a traffic routing type or a state migration type is received, the task management device needs to obtain the operating status data of each low-orbit satellite in the low-orbit satellite network. This data includes the current resource usage, link bandwidth, location and other information related to task execution of all satellites. The purpose of obtaining this data is to analyze the operating status of low-orbit satellites, ensure that task requests can be efficiently allocated and executed across the entire network, and improve the real-time and efficiency of task processing.

[0098] For example, when a state migration type task request is initiated, the task management device will immediately respond to the request and start collecting the operating status data of all low-orbit satellites in the low-orbit satellite network. Assuming there are three low-orbit satellites A, B, and C, the system will obtain their CPU usage, link bandwidth, satellite position and other data respectively. Through the analysis of these data, the system can determine which satellite's state is most suitable for executing the task request, and determine the best way to allocate tasks accordingly. This ensures that the task request is processed under the conditions of minimum latency and maximum resource utilization, improving the overall performance of the system.

[0099] Step 202: Determine a target low-orbit satellite from among all the low-orbit satellites according to a total delay minimization optimization model of the low-orbit satellite network established by all the operation status data.

[0100] In some embodiments of the present application, the target low-orbit satellite is determined from all low-orbit satellites using a total delay minimization optimization model based on the operating status data collected from all low-orbit satellites. The main purpose of this model is to select the optimal low-orbit satellite by calculating the total delay of various possible paths to ensure that the mission request can be processed under the conditions of the shortest delay and the highest resource utilization.

[0101] For example, assume that the system has obtained the operating status data of all low-orbit satellites, including CPU resource usage, link bandwidth, satellite position, etc. Using this data, the total delay minimization optimization model will analyze all possible paths and solutions and calculate the total delay of each path. After calculation, assuming that low-orbit satellite B exhibits the best total delay under the current task request, the system will determine it as the target low-orbit satellite. Subsequently, the system will send the task request to low-orbit satellite B to execute the task request, thereby ensuring efficient processing of the task and optimal utilization of resources. This method not only improves the real-time and accuracy of task processing, but also optimizes the overall performance of the low-orbit satellite network.

[0102] Step 203: Send the mission request to the target low-orbit satellite, so that the target low-orbit satellite executes the mission request.

[0103] In some embodiments of the present application, the mission management device sends the mission request to the previously determined target low-orbit satellite. The purpose of this step is to ensure that the optimal low-orbit satellite can receive the mission request and execute these tasks in the most efficient way, thereby improving the speed of mission processing and the performance of the overall system.

[0104] For example, assume that through the total delay minimization optimization model, the system has determined that low-orbit satellite B is the optimal target satellite for executing a specific mission request. The system will quickly send the mission request to low-orbit satellite B. After receiving the mission request, low-orbit satellite B immediately starts to execute the mission, such as processing the traffic routing request or state migration request of the user device, to ensure that the mission is completed with the lowest latency and the highest resource utilization. In this way, low-orbit satellite B can efficiently process mission requests and improve the service quality and performance of the entire low-orbit satellite network.

[0105] like Figure 4 As shown, in a further embodiment, multiple satellites (sat1 to sat9) can cover the same UE at the same time, and the UE can also access any satellite that covers it. Each UE request consists of data and status. The data is the signaling and service traffic actually processed by the core network, and the status is generated when the core network establishes a session related to the UE. The satellite in the middle of the satellite network topology is selected as the logic controller, which is responsible for calculating and executing strategies such as state migration and traffic routing.

[0106] At T1, the UE accesses the satellite network through sat4, and the data traffic is routed through the intersatellite link and forwarded to the ground network (Internet) by the satellite UPF1. Due to satellite movement, the UE and the Internet enter the coverage of other satellites at T2. At this time, the UE accesses the satellite network through sat8, so a new satellite UPF needs to be selected to route the data traffic. At this time, relevant calculations are performed in the logic controller to obtain the optimal satellite UPF switch control parameters, state migration strategy, and traffic routing strategy. Finally, it is calculated that the service is provided by the satellite UPF3. Since UPF3 was previously in the closed state, it needs to go through a startup process. The user state is migrated from the satellite UPF1 to the satellite UPF3, and the new traffic routing path is also established between sat8 and sat6. Subsequently, since the satellite UPF1 is in an idle state, it enters the shutdown phase to save resources.

[0107] In summary, in the embodiment of the present application, when the low-orbit satellite receives a task request of a traffic routing type or a state migration type, it is added to the task queue. When the low-orbit satellite is in a standby state, the state is updated to a service state to ensure that the low-orbit satellite responds quickly after receiving the task request, thereby improving the real-time and efficiency of task processing; and when the standby state duration of the low-orbit satellite exceeds the preset standby time threshold, its state is updated to a closed state, saving satellite resources, especially computing and power resources, and improving the resource utilization of the system. When the low-orbit satellite is in a closed state and the number of task requests in the task queue is greater than or equal to the preset request number threshold, its state is updated to a set state, and the state migration of the task request is performed, so as to effectively manage and allocate computing resources by dynamically adjusting the satellite state, ensure the smoothness and efficiency of the task migration process, and reduce service interruptions caused by satellite switching. In this process, the target low-orbit satellite is determined by minimizing the total delay optimization model, and the task request is sent to the target low-orbit satellite to ensure that the task request is processed under the conditions of minimum delay and maximum resource utilization, thereby improving the performance of the entire system. Therefore, based on the method of the embodiment of the present application, not only the delay of service migration and traffic routing is significantly reduced, but also by dynamically managing the computing resources of the satellite, resource utilization is optimized, and the continuity and efficiency of the user-plane services of the onboard core network are ensured. The problems of frequent interruptions and excessive resource consumption of the user-plane services of the onboard core network of low-orbit satellites in the existing technology are solved, and the service quality and reliability of satellite Internet are improved.

[0108] Figure 5 This is another method for providing user plane services of a satellite core network provided by this embodiment, wherein steps 301 to 304 are applied to a local low-orbit satellite of a low-orbit satellite network; steps 305 to 307 are applied to a task management device of the low-orbit satellite network:

[0109] Step 301, in response to a task request of a traffic routing type or a state migration type, adds the task request to the task queue of the local low-orbit satellite, and when the local low-orbit satellite is in a standby state, updates the local low-orbit satellite to a service state, and sends the operating status data of the local low-orbit satellite to the task management device of the low-orbit satellite network.

[0110] In some embodiments of the present application, the local low-orbit satellite will respond to a task request of a traffic routing type or a state migration type, add the task request to the task queue of the local low-orbit satellite, and when the local low-orbit satellite is in a standby state, update the local low-orbit satellite to a service state, and send the operating state data of the local low-orbit satellite to the task management device of the low-orbit satellite network. The purpose of this step is to ensure that the task request can be processed in a timely manner and to feed back the operating state of the satellite to the task management device in real time for global scheduling and optimization.

[0111] For example, after a task request of a state migration type is initiated, the system will first add it to the task queue of low-orbit satellite A, which is currently in standby state, after receiving the request. Subsequently, the system will update the state of low-orbit satellite A to the service state, indicating that it is processing the task. At the same time, the system will send the operating status data of low-orbit satellite A (such as CPU usage, link bandwidth, etc.) to the task management device of the low-orbit satellite network. After receiving these status data, the task management device can perform scheduling optimization based on them to ensure that the task request can be efficiently processed across the entire network. Doing so not only improves the task processing efficiency of a single satellite, but also optimizes the resource utilization of the entire low-orbit satellite network.

[0112] Step 302: When the local low-orbit satellite is in service, execute the task request in the task queue.

[0113] The method shown in this step has been explained in step 102 and will not be repeated here.

[0114] Step 303: When the continuous standby time of the local low-orbit satellite in the standby state exceeds a preset standby time threshold, the local low-orbit satellite is updated to a closed state.

[0115] The method shown in this step has been explained in step 103 and will not be repeated here.

[0116] Step 304: When the local low-orbit satellite is in a closed state and the number of task requests in the task queue is greater than or equal to a preset request number threshold, the local low-orbit satellite is updated to a set state.

[0117] Among them, setting the state is used for the task requests in the state migration task queue, and updating the local low-orbit satellite to the service state to execute the remaining task requests in the task queue after the state migration.

[0118] The method shown in this step has been described in step 104 and will not be repeated here.

[0119] Step 305, in response to a task request of a traffic routing type or a state migration type, obtaining the operation status data of each low-orbit satellite in the low-orbit satellite network.

[0120] The method shown in this step has been described in step 201 and will not be repeated here.

[0121] Step 306: Determine a target low-orbit satellite from among all the low-orbit satellites according to the total delay minimization optimization model of the low-orbit satellite network established by all the operation status data.

[0122] The method shown in this step has been explained in step 202 and will not be repeated here.

[0123] Optionally, step 306 includes the following sub-steps:

[0124] Sub-step 3061, input all the operating status data into the strategy model to obtain the probability vector of the low-orbit satellite network.

[0125] The probability vector is used to represent the probability value of each low-orbit satellite in the low-orbit satellite network being the target low-orbit satellite.

[0126] In some embodiments of the present application, the mission management device inputs all the operating status data into the strategy model to obtain the probability vector of the low-orbit satellite network. The probability vector is used to characterize the probability value of each low-orbit satellite in the low-orbit satellite network as a target low-orbit satellite. By inputting the operating status data, the strategy model can analyze and calculate the possibility of each low-orbit satellite as a target satellite, thereby providing a basis for subsequent decision-making.

[0127] For example, in a low-orbit satellite network, the mission management device receives the operating status data of all low-orbit satellites, including CPU resource utilization, link bandwidth, location, etc. The system then inputs this data into the policy model. The policy model analyzes and calculates based on this data to generate a probability vector. Assume that the probability vector is {0.2, 0.3, 0.5}, where the first value corresponds to satellite A, the second value corresponds to satellite B, and the third value corresponds to satellite C. Each value in the probability vector represents the probability that the corresponding satellite is the target low-orbit satellite. For example, the probability value of satellite C is the largest, which is 0.5. This result shows that satellite C is most likely to become the target low-orbit satellite for executing the mission request under the current circumstances. In this way, the system can allocate resources more intelligently and improve the efficiency and reliability of task processing.

[0128] Sub-step 3062, selecting the executable low-orbit satellite with the largest probability value corresponding to the low-orbit satellite network as the target low-orbit satellite.

[0129] Among them, the executable low-orbit satellite is a low-orbit satellite whose current status is in the service phase or the standby phase.

[0130] In some embodiments of the present application, the executable low-orbit satellite with the largest probability value in the low-orbit satellite network is further selected as the target low-orbit satellite. An executable low-orbit satellite refers to a low-orbit satellite whose current state is in the service phase or the standby phase. The purpose of this step is to select the optimal low-orbit satellite using the calculation results of the strategy model under the premise of ensuring efficient execution of the task request, thereby further optimizing the task processing process.

[0131] For example, suppose that in a certain low-orbit satellite network, the probability vector generated by the strategy model is {0.2, 0.3, 0.5}, and the corresponding low-orbit satellites are A, B, and C. The current system status shows that satellites A and B are in the standby stage, and satellite C is in the shutdown stage. Therefore, although the probability value of satellite C in the probability vector is the largest (0.5), because satellite C is in the shutdown stage, the system will not select satellite C as the target low-orbit satellite, but will select B (0.3) with a higher probability among the remaining two satellites as the target low-orbit satellite. In this way, satellite B can efficiently execute the task request and ensure that the task is completed under the conditions of minimum latency and maximum resource utilization. This selection method improves the task processing efficiency and overall performance of the system and ensures the stable operation of the low-orbit satellite network.

[0132] like Figure 6 As shown, in a specific embodiment of the present application, the target low-orbit satellite is predicted and selected through the strategy model:

[0133] First, the reinforcement learning system is described:

[0134] state It is a description of the satellite network environment where the onboard UPF is located. When , the satellite network status is expressed as ,in Indicates onboard UPF The eigenvector of , Indicates the deployment of spaceborne UPF The available CPU resources of the satellite, represents the total bandwidth of the intersatellite links connected to the satellites deployed by UPF, It represents the average distance from the satellite where the UPF is located to other satellite-borne UPFs. Indicates the on / off status of the onboard UPF.

[0135] Action refers to selecting the appropriate target onboard UPF for state migration and traffic routing, which is expressed as .

[0136] In the onboard UPF service optimization scenario, the reward is affected by factors such as delay, resource consumption, and onboard UPF switch. express.

[0137] The policy network interacts with the satellite network environment as a reinforcement learning agent. When the satellite movement triggers the selection of a new onboard UPF and performs state migration and traffic routing, the policy network extracts relevant states from the environment. Since satellite resources are limited, only a limited number of UE requests can be satisfied, and different state migration and traffic routing paths will produce different delays, especially when the target onboard UPF is turned off, which will cause additional delays. Therefore, as mentioned above, four attributes are extracted to represent the satellite network state and formalized as the feature vector of each onboard UPF Furthermore, the eigenvectors of all onboard UPFs are aggregated into a state matrix to reflect the satellite network in The state at this time can be recorded as:

[0138] ;

[0139] The policy model consists of four layers:

[0140] The input layer is responsible for extracting the feature matrix and normalizing it;

[0141] The computation layer is used to calculate each feature vector Perform convolution operation to obtain the available resource vector ;

[0142] The activation (softmax) layer represents the result of the convolution calculation as the probability of the onboard UPF being selected. The output layer outputs a set of target onboard UPFs with probabilities and filters out onboard UPFs that do not meet the requirements.

[0143] The state migration and traffic routing process of UE requests triggered by the motion of the low-orbit constellation, and the reinforcement learning agent extracts the state matrix from the satellite network , which is equivalent to sensing the state of the environment The policy network outputs a set of satellite UPFs and corresponding probabilities. The reinforcement learning agent selects a satellite UPF as the target satellite UPF for state migration and traffic routing according to the probability. This process is equivalent to the reinforcement learning agent applying actions to the environment. , then the satellite network will feedback an immediate reward to the agent based on resource consumption and delay , this instant reward After training the policy model, it is finally negatively correlated with the expected delay. The reinforcement learning agent will Adjust its target onboard UPF selection strategy, the goal is to maximize the reward, the environment is imposed action After that, enter a new state .

[0144] Step 307: Send the mission request to the target low-orbit satellite, so that the target low-orbit satellite executes the mission request.

[0145] The method shown in this step has been explained in step 203 and will not be repeated here.

[0146] Optionally, based on all received operating status data, the mission management device may further update various thresholds of the satellite according to the following steps:

[0147] Step 308: Determine the standby time threshold update value and / or request quantity threshold update value of the low-orbit satellite through a greedy algorithm according to all the received operation status data.

[0148] In some embodiments of the present application, the standby time threshold update value and / or the request quantity threshold update value of the low-orbit satellite are determined by a greedy algorithm based on all the received operating status data. The greedy algorithm is an algorithm for gradually building a global optimal solution, and finally reaches the overall optimal solution by selecting the current optimal local solution at each step. The purpose of this step is to optimize and update the standby time threshold and request quantity threshold of the low-orbit satellite using a greedy algorithm after the task management device receives the operating status data of all low-orbit satellites, thereby achieving efficient use of resources and optimization of task processing.

[0149] For example, in a low-orbit satellite network, the task management device receives the operating status data of multiple low-orbit satellites, including their current CPU usage, link bandwidth, and task queue length. The task management device uses a greedy algorithm to analyze this data to determine the optimal standby time threshold and request quantity threshold update value for each satellite. Assume that through analysis, the task management device determines that the standby time threshold update value of satellite A is 5 minutes, and the request quantity threshold update value is 3 tasks. Then, the task management device sends these updated values ​​to low-orbit satellite A so that it can apply the new threshold settings in subsequent task processing. This optimization process ensures that low-orbit satellites can manage resources more flexibly and improve the task processing efficiency and resource utilization of the overall network.

[0150] Step 309, sending the standby time threshold update value and / or the request quantity threshold update value to the low-orbit satellite, so that the low-orbit satellite updates the standby time threshold of the low-orbit satellite to the standby time threshold update value and / or updates the request quantity threshold of the low-orbit satellite to the request quantity threshold update value.

[0151] In some embodiments of the present application, the task management device sends the determined standby time threshold update value and / or request quantity threshold update value to the low-orbit satellite. The purpose of this step is to ensure that the low-orbit satellite can adjust its operating parameters after receiving the new threshold value to optimize resource utilization and task processing efficiency and reduce unnecessary resource consumption and delay.

[0152] For example, by analyzing the operating status data, the task management device calculates that the standby time threshold update value of low-orbit satellite A is 10 minutes, and the request quantity threshold update value is 5 tasks. The task management device sends these updated values ​​to low-orbit satellite A. After receiving these updated values, satellite A will update its standby time threshold to 10 minutes and the request quantity threshold to 5 tasks. This adjustment enables satellite A to manage its standby and task processing processes more effectively, ensuring optimal use of resources and efficient processing of tasks.

[0153] Accordingly, the local low-orbit satellite performs the update in the following manner after receiving the updated threshold:

[0154] Step 310, receiving a standby time threshold update value and / or a request quantity threshold update value sent from a task management device of a low-orbit satellite network to update the standby time threshold to the standby time threshold update value and / or update the request quantity threshold to the request quantity threshold update value.

[0155] In some embodiments of the present application, after receiving the standby time threshold update value and / or the request quantity threshold update value from the mission management device, the local low-orbit satellite will update its operating parameters. The purpose of this step is to ensure that the low-orbit satellite can optimize its standby and mission processing process according to the latest threshold setting, thereby improving resource utilization efficiency and real-time performance of mission processing.

[0156] For example, a low-orbit satellite A receives a standby time threshold update value of 8 minutes and a request number threshold update value of 4 tasks from a task management device. After receiving these updated values, satellite A updates its standby time threshold to 8 minutes and the request number threshold to 4 tasks. This means that when satellite A enters the standby state, if no new task requests arrive within 8 minutes, it will switch to the off state. Similarly, when the number of task requests reaches 4, satellite A will switch from the off state to the service state to ensure that the tasks can be processed in a timely manner. With these updates, low-orbit satellite A can manage its resources and tasks more flexibly, improving the overall efficiency and performance of the system.

[0157] In summary, in the embodiment of the present application, when the low-orbit satellite receives a task request of a traffic routing type or a state migration type, it is added to the task queue. When the low-orbit satellite is in a standby state, the state is updated to a service state to ensure that the low-orbit satellite responds quickly after receiving the task request, thereby improving the real-time and efficiency of task processing; and when the standby state duration of the low-orbit satellite exceeds the preset standby time threshold, its state is updated to a closed state, saving satellite resources, especially computing and power resources, and improving the resource utilization of the system. When the low-orbit satellite is in a closed state and the number of task requests in the task queue is greater than or equal to the preset request number threshold, its state is updated to a set state, and the state migration of the task request is performed, so as to effectively manage and allocate computing resources by dynamically adjusting the satellite state, ensure the smoothness and efficiency of the task migration process, and reduce service interruptions caused by satellite switching. In this process, the target low-orbit satellite is determined by minimizing the total delay optimization model, and the task request is sent to the target low-orbit satellite to ensure that the task request is processed under the conditions of minimum delay and maximum resource utilization, thereby improving the performance of the entire system. Therefore, based on the method of the embodiment of the present application, not only the delay of service migration and traffic routing is significantly reduced, but also by dynamically managing the computing resources of the satellite, resource utilization is optimized, and the continuity and efficiency of the user-plane services of the onboard core network are ensured. The problems of frequent interruptions and excessive resource consumption of the user-plane services of the onboard core network of low-orbit satellites in the existing technology are solved, and the service quality and reliability of satellite Internet are improved.

[0158] Figure 7 A low-orbit satellite network system 40 provided in this embodiment includes a plurality of low-orbit satellites 401 and a mission management device 402;

[0159] The low-orbit satellite 401 is used to respond to a task request of a traffic routing type or a state migration type, add the task request to the task queue of the local low-orbit satellite, and when the local low-orbit satellite is in a standby state, update the local low-orbit satellite to a service state, and when the local low-orbit satellite is in a service state, execute the task request in the task queue, and when the continuous standby time of the standby state of the local low-orbit satellite exceeds a preset standby time threshold, update the local low-orbit satellite to a closed state, and when the local low-orbit satellite is in a closed state and the number of task requests in the task queue is greater than or equal to a preset request number threshold, update the local low-orbit satellite to a set state; the set state is used for the task request in the state migration task queue, and the local low-orbit satellite is updated to a service state to execute the remaining task requests in the task queue after the state migration;

[0160] The task management device 402 is used to respond to a task request of a traffic routing type or a state migration type, obtain the operating status data of each low-orbit satellite in the low-orbit satellite network, and determine the target low-orbit satellite among all the low-orbit satellites based on a total delay minimization optimization model of the low-orbit satellite network established by all the operating status data, and send the task request to the target low-orbit satellite so that the target low-orbit satellite executes the task request.

[0161] In summary, in the embodiment of the present application, when the low-orbit satellite receives a task request of a traffic routing type or a state migration type, it is added to the task queue. When the low-orbit satellite is in a standby state, the state is updated to a service state to ensure that the low-orbit satellite responds quickly after receiving the task request, thereby improving the real-time and efficiency of task processing; and when the standby state duration of the low-orbit satellite exceeds the preset standby time threshold, its state is updated to a closed state, saving satellite resources, especially computing and power resources, and improving the resource utilization of the system. When the low-orbit satellite is in a closed state and the number of task requests in the task queue is greater than or equal to the preset request number threshold, its state is updated to a set state, and the state migration of the task request is performed, so as to effectively manage and allocate computing resources by dynamically adjusting the satellite state, ensure the smoothness and efficiency of the task migration process, and reduce service interruptions caused by satellite switching. In this process, the target low-orbit satellite is determined by minimizing the total delay optimization model, and the task request is sent to the target low-orbit satellite to ensure that the task request is processed under the conditions of minimum delay and maximum resource utilization, thereby improving the performance of the entire system. Therefore, based on the method of the embodiment of the present application, not only the delay of service migration and traffic routing is significantly reduced, but also by dynamically managing the computing resources of the satellite, resource utilization is optimized, and the continuity and efficiency of the user-plane services of the onboard core network are ensured. The problems of frequent interruptions and excessive resource consumption of the user-plane services of the onboard core network of low-orbit satellites in the existing technology are solved, and the service quality and reliability of satellite Internet are improved.

[0162] Furthermore, Figure 8 This is a training method for a policy model provided in this embodiment, which is used to train the policy model in the embodiments of sub-steps 3061 and 3062, and specifically includes the following steps:

[0163] In some embodiments of the present application,

[0164] Step 501, initially setting the strategy model according to the switch control parameters of the low-orbit satellite in the low-orbit satellite network.

[0165] In some embodiments of the present application, the strategy model is initially set according to the switch control parameters of the low-orbit satellite in the low-orbit satellite network. The purpose of the initial setting is to provide the strategy model with an initial operating environment and parameters so that the actual operation in the low-orbit satellite network can be effectively simulated and optimized in the subsequent training process. The switch control parameters include the satellite's standby time threshold and request quantity threshold, etc. These parameters will affect the state transition and task processing efficiency of the low-orbit satellite.

[0166] For example, in a low-orbit satellite network, the system administrator first obtains the current switch control parameters, including the standby time threshold of 5 minutes and the request quantity threshold of 3 tasks. Then, the administrator enters these parameters into the policy model for initial settings. The policy model will simulate the operating environment of the low-orbit satellite based on these parameters and prepare to start the subsequent training process. After the initial settings are completed, the policy model has the basic operating conditions and can accurately reflect the actual situation of the low-orbit satellite network, providing a basis for subsequent training and optimization. In this way, the policy model can more efficiently handle the state transitions and task requests of the low-orbit satellite in the subsequent training process, and optimize the overall performance.

[0167] Step 502: For the strategy model that has been initially set up, a preset target training low-orbit satellite is input to obtain a cross entropy loss function of the strategy model under the target training low-orbit satellite.

[0168] In some embodiments of the present application, a preset target training low-orbit satellite is input into the policy model after the initial setting to obtain the cross entropy loss function of the policy model under the target training low-orbit satellite. The cross entropy loss function is a commonly used loss function used to measure the difference between the actual value and the predicted value. By calculating the cross entropy loss function under the target training low-orbit satellite, the accuracy of the policy model can be evaluated and optimized.

[0169] For example, in a certain low-orbit satellite network, the system administrator selects satellite B as the preset target training low-orbit satellite. The administrator inputs the relevant data of satellite B into the policy model with the initial settings completed. The policy model is trained based on this data and calculates the cross entropy loss function, assuming the loss value is 0.25. This loss value reflects the prediction accuracy of the policy model under the current target training low-orbit satellite. Through this process, the system can evaluate the performance of the policy model and further optimize it based on the results of the loss function to improve the accuracy and reliability of the policy model. In this way, the policy model can more efficiently handle the mission requests of low-orbit satellites in subsequent practical applications and improve the overall system performance.

[0170] Step 503, update the parameter gradient of the cross entropy loss function through back propagation, and obtain the trained policy model when the parameter gradient reaches the minimum value.

[0171] like Fig. 9 As shown, in some embodiments of the present application, the parameter gradient of the cross entropy loss function is updated by back propagation to optimize the policy model. Back propagation is an algorithm for training neural networks. By minimizing the loss function, the parameters of the model are adjusted to make the prediction of the training data more accurate. When the parameter gradient reaches the minimum value, it indicates that the model has achieved the best performance and a trained policy model is obtained.

[0172] For example, in a low-orbit satellite network, after the initial setup and input of the target training low-orbit satellite data, the policy model calculates the initial cross-entropy loss function. The system starts back propagation and adjusts the model parameters layer by layer to reduce the value of the loss function. Assuming that the initial cross-entropy loss function value is 0.25, through multiple iterations and parameter adjustments, the loss value gradually decreases until it reaches a local minimum, such as 0.05. After the loss value reaches the minimum and stabilizes, the system confirms that the model parameters have been optimized and a trained policy model has been obtained. This model can efficiently process the mission requests of low-orbit satellites in practical applications and improve the overall system performance and accuracy.

[0173] Optionally, the cross entropy loss function is: ;

[0174] in, represents the cross entropy loss function value, It is a representative element of the user-side service of the onboard core network of low-orbit satellites. is the label vector of the target training low-orbit satellite, is the output value of the policy model.

[0175] The cross entropy loss function is used to measure the difference between the actual label vector of the target training LEO satellite and the predicted output value of the policy model. The advantage of the cross entropy loss function is that it can well capture the accuracy of the model prediction results in the classification problem. By calculating the logarithmic difference between the predicted probability of each class and the actual label, the model parameters are adjusted to make the prediction results more accurate.

[0176] like Fig.10 As shown, a program execution logic loop process of a low-orbit satellite network provided in an embodiment of the present application is as follows:

[0177] Step W1, dynamic update of thresholds: According to new task requests, the thresholds in the system are dynamically updated to adapt to current task requirements and network status.

[0178] Step W2, state matrix input: input the updated state matrix M into the system for subsequent strategy model calculation and decision-making.

[0179] Step W3, target low-orbit satellite selection: According to the strategy model, select the satellite that is most suitable for performing the current mission from the available low-orbit satellites.

[0180] Step W4, perform state migration and traffic routing: perform state migration and traffic routing of the selected satellite to ensure that the mission request can be effectively processed and transmitted.

[0181] In summary, in the embodiment of the present application, when the low-orbit satellite receives a task request of a traffic routing type or a state migration type, it is added to the task queue. When the low-orbit satellite is in a standby state, the state is updated to a service state to ensure that the low-orbit satellite responds quickly after receiving the task request, thereby improving the real-time and efficiency of task processing; and when the standby state duration of the low-orbit satellite exceeds the preset standby time threshold, its state is updated to a closed state, saving satellite resources, especially computing and power resources, and improving the resource utilization of the system. When the low-orbit satellite is in a closed state and the number of task requests in the task queue is greater than or equal to the preset request number threshold, its state is updated to a set state, and the state migration of the task request is performed, so as to effectively manage and allocate computing resources by dynamically adjusting the satellite state, ensure the smoothness and efficiency of the task migration process, and reduce service interruptions caused by satellite switching. In this process, the target low-orbit satellite is determined by minimizing the total delay optimization model, and the task request is sent to the target low-orbit satellite to ensure that the task request is processed under the conditions of minimum delay and maximum resource utilization, thereby improving the performance of the entire system. Therefore, based on the method of the embodiment of the present application, not only the delay of service migration and traffic routing is significantly reduced, but also by dynamically managing the computing resources of the satellite, resource utilization is optimized, and the continuity and efficiency of the user-plane services of the onboard core network are ensured. The problems of frequent interruptions and excessive resource consumption of the user-plane services of the onboard core network of low-orbit satellites in the existing technology are solved, and the service quality and reliability of satellite Internet are improved.

[0182] like Fig.11 As shown, the embodiment of the present application further discloses a satellite-borne core network user plane service providing device 61, which is applied to a local low-orbit satellite, including:

[0183] The queue module 611 is used to respond to the task request of the traffic routing type or the state migration type, add the task request to the task queue of the local low-orbit satellite, and update the local low-orbit satellite to the service state when the local low-orbit satellite is in the standby state;

[0184] A service module 612 is used to execute a task request in a task queue when the local low-orbit satellite is in a service state;

[0185] A shutdown module 613 is used to update the local low-orbit satellite to a shutdown state when the continuous standby time of the local low-orbit satellite in the standby state exceeds a preset standby time threshold;

[0186] The setting module 614 is used to update the local low-orbit satellite to the setting state when the local low-orbit satellite is in the closed state and the number of task requests in the task queue is greater than or equal to the preset request number threshold; the setting state is used to state migrate the task requests in the task queue, and update the local low-orbit satellite to the service state to execute the remaining task requests in the task queue after the state migration.

[0187] Optionally, the device 61 further includes:

[0188] A status sending module is used to send the operating status data of the local low-orbit satellite to the task management device of the low-orbit satellite network in response to a task request, so that the task management device determines the target low-orbit satellite among all the low-orbit satellites based on the minimum total delay optimization model of the low-orbit satellite network established according to the operating status data sent by each low-orbit satellite in the low-orbit satellite network, and sends the task request received by the task management device to the target low-orbit satellite, so that the target low-orbit satellite executes the task request.

[0189] Optionally, the device 61 further includes:

[0190] A threshold update module is used to receive a standby time threshold update value and / or a request quantity threshold update value sent from a task management device of a low-orbit satellite network to update the standby time threshold to the standby time threshold update value and / or update the request quantity threshold to the request quantity threshold update value.

[0191] like Fig.12 As shown, the embodiment of the present application also discloses a satellite core network user plane service providing device 62, which is applied to a mission management device of a low-orbit satellite:

[0192] The state acquisition module 621 is used to obtain the operation state data of each low-orbit satellite in the low-orbit satellite network in response to the task request of the traffic routing type or the state migration type; each low-orbit satellite processes the task request of the low-orbit satellite by executing the onboard core network user plane service provision method disclosed in the above embodiment;

[0193] A target decision module 622 is used to determine a target low-orbit satellite from all low-orbit satellites according to a minimum total delay optimization model of the low-orbit satellite network established by all operating status data;

[0194] The decision sending module 623 is used to send the task request to the target low-orbit satellite, so that the target low-orbit satellite executes the task request.

[0195] Optionally, the target decision module 622 includes the following submodules:

[0196] An input submodule is used to input all the operation status data into the strategy model to obtain a probability vector of the low-orbit satellite network; the probability vector is used to characterize the probability value of each low-orbit satellite in the low-orbit satellite network being a target low-orbit satellite;

[0197] The selection submodule is used to select the executable low-orbit satellite with the largest corresponding probability value in the low-orbit satellite network as the target low-orbit satellite; the executable low-orbit satellite is a low-orbit satellite whose current state is in the service phase or the standby phase.

[0198] Optionally, the device 62 further includes:

[0199] A threshold updating module, used to determine a standby time threshold update value and / or a request quantity threshold update value of the low-orbit satellite through a greedy algorithm according to all received operation status data;

[0200] An update sending module is used to send a standby time threshold update value and / or a request quantity threshold update value to a low-orbit satellite, so that the low-orbit satellite updates the standby time threshold of the low-orbit satellite to the standby time threshold update value and / or updates the request quantity threshold of the low-orbit satellite to the request quantity threshold update value.

[0201] like Fig.13 As shown, the embodiment of the present application further discloses a strategy model training device 63, which is used to train the strategy model disclosed by the above embodiment, and is characterized by comprising:

[0202] An initial setting module 631 is used to initially set the strategy model according to the switch control parameters of the low-orbit satellite in the low-orbit satellite network;

[0203] The function generation module 632 is used to input a preset target training low-orbit satellite into the strategy model after the initial setting, so as to obtain the cross entropy loss function of the strategy model under the target training low-orbit satellite;

[0204] The network training module 633 is used to update the parameter gradient of the cross entropy loss function through back propagation, and obtain the trained policy model when the parameter gradient reaches the minimum value.

[0205] In summary, in the embodiment of the present application, when the low-orbit satellite receives a task request of a traffic routing type or a state migration type, it is added to the task queue. When the low-orbit satellite is in a standby state, the state is updated to a service state to ensure that the low-orbit satellite responds quickly after receiving the task request, thereby improving the real-time and efficiency of task processing; and when the standby state duration of the low-orbit satellite exceeds the preset standby time threshold, its state is updated to a closed state, saving satellite resources, especially computing and power resources, and improving the resource utilization of the system. When the low-orbit satellite is in a closed state and the number of task requests in the task queue is greater than or equal to the preset request number threshold, its state is updated to a set state, and the state migration of the task request is performed, so as to effectively manage and allocate computing resources by dynamically adjusting the satellite state, ensure the smoothness and efficiency of the task migration process, and reduce service interruptions caused by satellite switching. In this process, the target low-orbit satellite is determined by minimizing the total delay optimization model, and the task request is sent to the target low-orbit satellite to ensure that the task request is processed under the conditions of minimum delay and maximum resource utilization, thereby improving the performance of the entire system. Therefore, based on the method of the embodiment of the present application, not only the delay of service migration and traffic routing is significantly reduced, but also by dynamically managing the computing resources of the satellite, resource utilization is optimized, and the continuity and efficiency of the user-plane services of the onboard core network are ensured. The problems of frequent interruptions and excessive resource consumption of the user-plane services of the onboard core network of low-orbit satellites in the existing technology are solved, and the service quality and reliability of satellite Internet are improved.

[0206] The embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, each process of the embodiment of the method provided in the embodiment of the present application is implemented, and the same technical effect can be achieved. To avoid repetition, it is not repeated here. The computer-readable storage medium is, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0207] Fig.14 700 is a block diagram of an electronic device 700 provided in an embodiment of the present application. For example, the electronic device 700 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0208] Reference Fig.14, the electronic device 700 may include one or more of the following components: a processing component 702 , a memory 704 , a power component 706 , a multimedia component 708 , an audio component 710 , an input / output (I / O) interface 712 , a sensor component 714 , and a communication component 716 .

[0209] The processing component 702 generally controls the overall operation of the electronic device 700, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 702 may include one or more processors 720 to execute instructions to complete all or part of the steps of the method provided by the above embodiment. In addition, the processing component 702 may include one or more modules to facilitate the interaction between the processing component 702 and other components. For example, the processing component 702 may include a multimedia module to facilitate the interaction between the multimedia component 708 and the processing component 702.

[0210] The memory 704 is used to store various types of data to support the operation of the electronic device 700. Examples of such data include instructions for any application or method operating on the electronic device 700, contact data, phone book data, messages, pictures, multimedia, etc. The memory 704 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, magnetic disk or optical disk.

[0211] The power supply component 706 provides power to the various components of the electronic device 700. The power supply component 706 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device 700.

[0212] The multimedia component 708 includes a screen that provides an output interface between the electronic device 700 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the demarcation of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 708 includes a front camera and / or a rear camera. When the electronic device 700 is in an operating mode, such as a shooting mode or a multimedia mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0213] The audio component 710 is used to output and / or input audio signals. For example, the audio component 710 includes a microphone (MIC), and when the electronic device 700 is in an operation mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is used to receive an external audio signal. The received audio signal can be further stored in the memory 704 or sent via the communication component 716. In some embodiments, the audio component 710 also includes a speaker for outputting audio signals.

[0214] I / O interface 712 provides an interface between processing component 702 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0215] The sensor assembly 714 includes one or more sensors for providing various aspects of status assessment for the electronic device 700. For example, the sensor assembly 714 can detect the open / closed state of the electronic device 700, the relative positioning of components, such as the display and keypad of the electronic device 700, and the sensor assembly 714 can also detect the position change of the electronic device 700 or a component of the electronic device 700, the presence or absence of user contact with the electronic device 700, the orientation or acceleration / deceleration of the electronic device 700, and the temperature change of the electronic device 700. The sensor assembly 714 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 714 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 714 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0216] The communication component 716 is used to facilitate wired or wireless communication between the electronic device 700 and other devices. The electronic device 700 can access a wireless network based on a communication standard, such as WiFi, a carrier network (such as 2G, 3G, 4G or 7G), or a combination thereof. In an exemplary embodiment, the communication component 716 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 716 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0217] In an exemplary embodiment, the electronic device 700 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to implement the steps of the method provided in the embodiments of the present application.

[0218] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 704 including instructions, and the above instructions can be executed by a processor 720 of an electronic device 700 to complete the steps of the method provided in the embodiment of the present application. For example, the non-transitory storage medium can be a ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

[0219] Fig.15 8 is a block diagram of an electronic device 800 according to an exemplary embodiment. For example, the electronic device 800 may be provided as a server. Fig.15 The electronic device 800 includes a processing component 822, which further includes one or more processors, and a memory resource represented by a memory 832 for storing instructions that can be executed by the processing component 822, such as an application. The application stored in the memory 832 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 822 is configured to execute instructions to perform the steps of the method provided in the embodiment of the present application.

[0220] The electronic device 800 may also include a power supply component 826 configured to perform power management of the electronic device 800, a wired or wireless network interface 850 configured to connect the electronic device 800 to a network, and an input / output (I / O) interface 858. The electronic device 800 may operate based on an operating system stored in the memory 832, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™ or the like.

[0221] The embodiment of the present application also provides a computer program product, including a computer program, which implements the method provided in the embodiment of the present application when the computer program is executed by a processor.

[0222] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the application disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0223] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

[0224] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0225] It is easy for a person skilled in the art to think that any combination of the above embodiments is feasible, so any combination of the above embodiments is an implementation scheme of the present application. However, due to space limitations, this specification will not describe them in detail here.

[0226] The method provided in the embodiment of the present application is not inherently related to any specific computer, virtual system or other equipment. Various general systems can also be used together with the teaching based on this. According to the above description, it is obvious that the structure required by the system with the scheme of the present application is constructed. In addition, the application is not directed to any specific programming language either. It should be understood that the content of the present application described herein can be realized by various programming languages, and the description made to specific languages ​​above is for disclosing the best mode of implementation of the present application.

[0227] In the description provided herein, a large number of specific details are described. However, it is understood that the embodiments of the present application can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0228] Similarly, it should be understood that in order to streamline the present application and aid in understanding one or more of the various application aspects, in the above description of the exemplary embodiments of the present application, the various features of the present application are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting the following intention: the claimed application requires more features than the features explicitly recited in each claim. More specifically, as reflected in the claims, the application aspects lie in less than all the features of the single embodiment disclosed above. Therefore, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, with each claim itself serving as a separate embodiment of the present application.

[0229] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and further may be divided into a plurality of submodules or subunits or subcomponents. All features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device so disclosed may be combined in any combination, except that at least some of such features and / or processes or units are mutually exclusive. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature that provides the same, equivalent or similar purpose.

[0230] In addition, those skilled in the art will appreciate that, although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present application and form different embodiments. For example, in the claims, any one of the claimed embodiments can be used in any combination.

[0231] The various component embodiments of the present application may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or a digital signal processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components in the method provided according to the embodiment of the present application. The present application may also be implemented as a device or apparatus program (e.g., a computer program and a computer program product) for executing part or all of the methods described herein. Such a program implementing the present application may be stored on a computer-readable medium, or may be in the form of one or more signals. Such a signal may be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0232] It should be noted that the above embodiments illustrate the present application rather than limit the present application, and that those skilled in the art may design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets should not be constructed as a limitation to the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of multiple such elements. The present application may be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In a unit claim that lists several devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc. does not indicate any order. These words may be interpreted as names.

Claims

1. A method for providing user plane services of a satellite core network, characterized in that: Local LEO satellites for LEO satellite networks include: In response to a task request of a traffic routing type or a state migration type, the task request is added to a task queue of the local low-orbit satellite, and when the local low-orbit satellite is in a standby state, the local low-orbit satellite is updated to a service state; the task request of the state migration type is used to migrate the context state of a user equipment from one onboard core network user plane function to another onboard core network user plane function; When the local low-orbit satellite is in service state, executing the task request in the task queue; When the continuous standby time of the standby state of the local low-orbit satellite exceeds a preset standby time threshold, updating the local low-orbit satellite to a shutdown state; When the local low-orbit satellite is in a closed state and the number of task requests in the task queue is greater than or equal to a preset request number threshold, the local low-orbit satellite is updated to a setting state; the setting state is used to process task requests of the state migration type in the task queue, and the local low-orbit satellite is updated to a service state to execute the remaining task requests in the task queue after the state migration.

2. A method for providing user plane services of a satellite core network, characterized in that: Mission management equipment for low-orbit satellite networks, including: In response to a task request of a traffic routing type or a state migration type, the operation status data of each low-orbit satellite in the low-orbit satellite network is obtained; each of the low-orbit satellites processes the task request of the low-orbit satellite by executing the onboard core network user plane service providing method as claimed in claim 1; the task request of the state migration type is used to migrate the context state of the user equipment from one onboard core network user plane function to another onboard core network user plane function; Determine a target low-orbit satellite from among all the low-orbit satellites according to a total delay minimization optimization model of the low-orbit satellite network established by all the operation status data; The mission request is sent to the target low-orbit satellite, so that the target low-orbit satellite executes the mission request.

3. The method according to claim 2, characterized in that Determining a target low-orbit satellite from among all the low-orbit satellites according to a total delay minimization optimization model of the low-orbit satellite network established by all the operating status data comprises: Inputting all of the operating status data into a strategy model to obtain a probability vector of the low-orbit satellite network; the probability vector is used to characterize the probability value of each low-orbit satellite in the low-orbit satellite network being a target low-orbit satellite; The executable low-orbit satellite with the largest probability value corresponding to the low-orbit satellite network is selected as the target low-orbit satellite; the executable low-orbit satellite is a low-orbit satellite whose current state is a service state or a standby state.

4. The method according to claim 3, characterized in that The method further comprises: Determine, according to all the received operating status data, a standby time threshold update value and / or a request quantity threshold update value of the low-orbit satellite by a greedy algorithm; The standby time threshold update value and / or the request quantity threshold update value are sent to the low-orbit satellite, so that the low-orbit satellite updates the standby time threshold of the low-orbit satellite to the standby time threshold update value and / or updates the request quantity threshold of the low-orbit satellite to the request quantity threshold update value.

5. A method for training a policy model, for training a policy model as claimed in claim 4, characterized in that: include: Initially setting the strategy model according to the switch control parameters of the low-orbit satellite in the low-orbit satellite network; The switch control parameters include a standby time threshold and a request quantity threshold of the low-orbit satellite; For the strategy model that has been initially set, a preset target training low-orbit satellite is input to obtain a cross entropy loss function of the strategy model under the target training low-orbit satellite; The parameter gradient of the cross entropy loss function is updated through back propagation, and when the parameter gradient reaches a minimum value, the trained policy model is obtained.

6. The method according to claim 5, characterized in that The cross entropy loss function is: ； in, represents the cross entropy loss function value, It is a representative element of the onboard core network user plane service of the low-orbit satellite. is the label vector of the target low-orbit satellite training, is the output value of the policy model.

7. A low-orbit satellite network system, characterized in that: Includes multiple low-orbit satellites and a mission management device; The low-orbit satellite is used to respond to a task request of a traffic routing type or a state migration type, add the task request to a task queue of a local low-orbit satellite in the low-orbit satellite, and when the local low-orbit satellite is in a standby state, update the local low-orbit satellite to a service state, and when the local low-orbit satellite is in a service state, execute the task request in the task queue, and when the local low-orbit satellite is in a standby state, if the continuous standby time of the standby state of the local low-orbit satellite exceeds a preset standby time threshold, update the local low-orbit satellite to a shutdown state, and when the local low-orbit satellite is in a shutdown state and the number of task requests in the task queue is greater than or equal to a preset request number threshold, update the local low-orbit satellite to a setting state; The setting state is used to process the task requests of the state migration type in the task queue, and update the local low-orbit satellite to the service state to execute the remaining task requests in the task queue after the state migration; The task request of the state migration type is used to migrate the context state of the user equipment from one onboard core network user plane function to another onboard core network user plane function; The task management device is used to respond to a task request of a traffic routing type or a state migration type, obtain the operating status data of each low-orbit satellite in the low-orbit satellite network, and determine the target low-orbit satellite among all the low-orbit satellites based on a total delay minimization optimization model of the low-orbit satellite network established by all the operating status data, and send the task request to the target low-orbit satellite so that the target low-orbit satellite executes the task request.

8. An electronic device, characterized in that: include: A processor, a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the method as claimed in any one of claims 1 to 6.

10. A computer program product, characterized in that The computer program product stores a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images