Star-ground cooperative resource scheduling method and device based on digital twin model, electronic equipment, storage medium and computer program product

Abstract

The application relates to the technical field of satellite communication and ground mobile communication fusion network, and provides a satellite-ground cooperation resource scheduling method and device based on a digital twin model, electronic equipment, a storage medium and a computer program product. The method comprises the following steps: determining the positions of communication satellites, model communication parameters and user densities of each communication area based on a digital twin model of a communication scene, wherein the communication scene comprises a plurality of communication areas; determining target interference parameters of the communication areas in a future preset time period by using a time sequence prediction model according to the positions of the satellites, the model communication parameters and the user densities; and performing resource scheduling on the communication areas according to the target interference parameters. The real-time performance of resource regulation is improved, so that the communication quality of satellite-ground communication is improved. Moreover, the model input parameters are obtained through the digital twin model, the timeliness of the model input parameters can be greatly improved, and the difficulty and cost of parameter acquisition are reduced.

Description

Technical Field

[0001] This application relates to the field of converged network technology of satellite communication and terrestrial mobile communication, and in particular to a satellite-ground cooperative resource scheduling method, device, electronic equipment, storage medium and computer program product based on a digital twin model. Background Technology

[0002] With the maturity of fifth-generation mobile communication technology (5G) and the deepening research on sixth-generation mobile communication technology (6G), building a seamless global coverage network integrating air, space, and ground has become an important development trend in the communications field. Among these, low-Earth orbit (LEO) satellites, with their advantages of low transmission latency, low path loss, and ease of achieving global coverage through large-scale constellation networking, are considered a key component for collaborative operation with terrestrial 5G / 6G base station networks. In space-ground collaboration scenarios, LEO satellites, acting as airborne base stations or relay nodes, can effectively compensate for coverage blind spots of terrestrial base stations in remote areas such as oceans, deserts, and mountains, achieving ubiquitous connectivity across all regions.

[0003] In existing satellite-ground cooperative communication systems, resource scheduling strategies typically rely heavily on Channel State Information (CSI) to maximize spectral efficiency and system throughput. Specifically, User Equipment (UE) or satellite gateways measure the downlink Signal-to-Interference-plus-Noise Ratio (SINR) in real time and dynamically adjust the Modulation and Coding Scheme (MCS), beamforming weights, or power allocation schemes based on the measurement results.

[0004] However, this resource scheduling mechanism based on real-time SINR measurement has significant limitations in scenarios where low-Earth orbit satellites move at high speeds. From the equipment measuring SINR and reporting the measurement report to the base station or satellite processing the data and issuing new scheduling instructions, this closed-loop control process inevitably involves processing and transmission delays. As low-Earth orbit satellites move at high speeds relative to the ground, their communication conditions change within these delays due to changes in their position, resulting in a lag in adjustments and thus affecting the communication quality of satellite-to-ground communication. Summary of the Invention

[0005] This application provides a method, apparatus, electronic device, storage medium, and computer program product for satellite-ground collaborative resource scheduling based on a digital twin model, in order to improve the communication quality of satellite-ground communication.

[0006] In a first aspect, embodiments of this application provide a satellite-ground collaborative resource scheduling method based on a digital twin model, including: The digital twin model based on the communication scenario determines the location of communication satellites, the model communication parameters of each communication area, and the user density, wherein the communication scenario includes multiple communication areas; Based on the satellite location, the model communication parameters, and the user density, the target interference parameters of the communication area in the future preset time period are determined using a time-series prediction model. Resource scheduling is performed on the communication area based on the target interference parameters.

[0007] In one embodiment, the method further includes: Acquire communication satellite data, ground base station data, and obstacle data in the communication scenario; Based on communication satellite data, establish a communication satellite model; The communication scenario is divided into multiple communication regions, and a communication region model for each communication region is established based on the ground base station data and the obstacle data. Based on communication satellite data and ground base station data, establish a satellite-to-ground network neighbor cell topology model; Establish a dynamic interference source model; By combining the satellite model, the communication area model, the satellite-to-ground network neighbor cell topology model, and the dynamic interference source model, a digital twin model of the communication scenario is obtained.

[0008] In one embodiment, the dynamic interference source model includes at least one of the following: a drone swarm model, a temporary base station model, a weather radar model, and a satellite portable station model.

[0009] In one embodiment, the method further includes: Obtain the actual scenario parameters of the communication scenario; The actual scene parameters are aligned in time and in position to obtain the target actual scene parameters; The state of the digital twin model is updated using the actual scene parameters of the target. The actual scenario parameters include at least one of the following: communication quality parameters of the satellite-to-ground link, load parameters of the ground base station, communication beam parameters of the ground base station, user location parameters, environmental parameters, and dynamic interference source parameters.

[0010] In one embodiment, the step of performing time and position alignment on the actual scene parameters to obtain the target actual scene parameters includes: According to the coordinate position of the actual scene parameters, the actual scene parameters are divided into corresponding communication areas; Using the time of the communication satellite as a reference, the actual scene parameters in each of the aforementioned communication areas are sliced ​​and sampled to obtain the actual scene parameters of the target.

[0011] In one embodiment, the target real-world scenario parameters include fusionable real-world scenario parameters and non-fusionable real-world scenario parameters; updating the state of the digital twin model using the target real-world scenario parameters includes: For each communication region, calculate the distance from the coordinate position of the same type of aggregable real-world scene parameter in the communication region to the center of the communication region; calculate the initial weight of the corresponding aggregable real-world scene parameter based on the distance, wherein, for any aggregable real-world scene parameter, the magnitude of its initial weight is inversely proportional to the magnitude of its distance; For each communication region, the initial weights of the same type of aggregable real-world scene parameters in the communication region are scaled to obtain the target weights of the aggregable real-world scene parameters, wherein the sum of the target weights of the same type of aggregable real-world scene parameters in the communication region is 1. For each communication region, the aggregateable actual scene parameters of the same type in the communication region are weighted and summed according to the target weight to obtain the regional scene parameters of the communication region. The state of the digital twin model is updated according to the parameters of each region scene and the parameters of the non-integrable actual scene.

[0012] In one embodiment, determining the target interference parameters of the communication area within a future preset time period using a time-series prediction model based on the satellite location, the model communication parameters, and the user density includes: Based on the model communication parameters, determine the signal-to-interference-plus-noise ratio and interference power of satellite-to-ground communication in the communication area; The satellite position, the signal-to-interference-plus-noise ratio, interference power, and user density of each communication area are input into the time series prediction model to obtain the target interference level, target interference probability, and target interference time slot for each communication area within a preset time period in the future. The target interference parameters include the target interference level, the target interference probability, and the target interference time slot.

[0013] In one embodiment, the step of scheduling resources in the communication area according to the target interference parameters includes: The terminals in the communication area are scheduled according to the target interference parameters, and / or the transmission beams of the communication satellites are adjusted according to the target interference parameters.

[0014] In one embodiment, the target interference parameters include the target interference level, the target interference probability, and the target interference time slot; the step of scheduling resources in the communication area according to the target interference parameters includes: For each communication area, the resource scheduling method for that communication area is determined based on the target interference level and target interference probability of that communication area. When the resource scheduling mode in the communication area indicates that user migration is not required, the communication beam of the target communication satellite is adjusted in the target interference time slot of the communication area, wherein the target communication satellite is the expected service satellite in the target interference time slot of the communication area; When the resource scheduling mode in the communication area indicates that users need to be migrated, the terminal in the communication area is switched from the target communication satellite to other communication satellites or ground base stations in the target interference time slot of the communication area, and the communication beam of the target communication satellite is adjusted.

[0015] In one embodiment, when the resource scheduling mode in the communication area indicates that user migration is not required, adjusting the communication beam of the target communication satellite in the target interference time slot of the communication area includes: When the resource scheduling mode in the communication area indicates that user migration is not required, the modulation and coding strategy level of the target communication beam of the target communication satellite is reduced and the transmission power of the target communication beam is increased in the target interference time slot of the communication area. The target communication beam is the communication beam of the target communication satellite for the communication area.

[0016] In one embodiment, when the resource scheduling mode in the communication area indicates that user migration is required, the terminal in the communication area is switched from the target communication satellite to other communication satellites or ground base stations during the target interference time slot in the communication area, and the communication beam of the target communication satellite is adjusted, including: When the resource scheduling method in the communication area indicates that a user needs to be migrated, the target device is obtained by selecting a device whose signal-to-interference-plus-noise ratio meets the preset quality requirements from the neighboring communication satellites or neighboring ground base stations corresponding to the communication area. In the target interference time slot of the communication area, the bandwidth, transmit power, modulation and coding strategy level of the target communication beam of the target communication satellite are reduced, and the terminal in the communication area is switched from the target communication satellite to the target device, wherein the target communication beam is the communication beam of the target communication satellite for the communication area.

[0017] In one embodiment, the method further includes: Obtain the actual communication parameters of each communication area in the communication scenario, and calculate the error value between the model communication parameters and the actual communication parameters; If the error value is greater than a preset error threshold, the parameters of the digital twin model are adjusted, wherein the parameters of the digital twin model include at least one of the following: path loss coefficient of the satellite-to-ground link, user mobility parameters, and simulation intensity of interference sources.

[0018] In one embodiment, the method further includes: After the predetermined future time period is reached, the actual interference parameters of the communication scenario within the predetermined future time period are obtained. The model loss of the time series prediction model is calculated based on the actual interference parameters and the target interference parameters. The time series prediction model is fine-tuned online based on the model loss.

[0019] Secondly, embodiments of this application provide a satellite-ground cooperative resource scheduling based on a digital twin model, including: The digital twin model invocation module is used to determine the location of communication satellites, the model communication parameters of each communication area, and the user density based on the digital twin model of the communication scenario, wherein the communication scenario includes multiple communication areas; The interference parameter prediction module is used to determine the target interference parameters of the communication area in a future preset time period based on the satellite position, the model communication parameters and the user density using a time-series prediction model. The resource scheduling module is used to schedule resources in the communication area according to the target interference parameters.

[0020] Thirdly, embodiments of this application provide an electronic device, including a processor and a memory storing a computer program, wherein the processor executes the program to implement the steps of the satellite-ground cooperative resource scheduling method based on a digital twin model as described in the first aspect.

[0021] Fourthly, embodiments of this application provide a non-transitory computer-readable storage medium storing a computer program thereon, wherein the computer program, when executed by a processor, implements the steps of the satellite-ground cooperative resource scheduling method based on a digital twin model as described in the first aspect.

[0022] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the steps of the satellite-ground cooperative resource scheduling method based on a digital twin model as described in the first aspect.

[0023] The satellite-ground collaborative resource scheduling method, apparatus, electronic device, storage medium, and computer program product based on a digital twin model provided in this application determine the location of communication satellites, model communication parameters for each communication area, and user density based on a digital twin model of a communication scenario, wherein the communication scenario includes multiple communication areas. Based on the satellite location, model communication parameters, and user density, a time-series prediction model is used to determine the target interference parameters for the communication areas within a future preset time period. Resource scheduling is then performed on the communication areas based on the target interference parameters. By determining the location of communication satellites, model communication parameters for each communication area, and user density based on the digital twin model, and then using a time-series prediction model to obtain the target interference parameters for the communication areas within a future preset time period, interference conditions within the future time period can be predicted in advance. When the predicted future time period is reached, resource scheduling is performed on the communication areas based on the predicted target interference parameters without the need for real-time SINR measurement, improving the real-time performance of resource adjustment and thus improving the communication quality of satellite-ground communication. Furthermore, compared to directly obtaining model output parameters from the actual communication scenario, obtaining model input parameters through a digital twin model significantly increases the timeliness of model input parameters and reduces the difficulty and cost of parameter acquisition. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a schematic flowchart of a satellite-ground collaborative resource scheduling method based on a digital twin model provided in an embodiment of this application; Figure 2 This is a flowchart illustrating a digital twin model construction method provided in an embodiment of this application; Figure 3 This is a schematic diagram of a possible implementation of step S102 in an embodiment of this application; Figure 4 This is a schematic diagram of a possible implementation of step S106 in an embodiment of this application; Figure 5 This is a schematic diagram of a satellite-ground collaborative resource scheduling device based on a digital twin model provided in an embodiment of this application; Figure 6 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0027] Existing resource scheduling mechanisms based on real-time SINR measurements have significant limitations in scenarios involving high-speed movement of low-Earth orbit (LEO) satellites. Signaling processing and transmission both involve delays. As LEO satellites move at high speeds relative to the ground, changes in their position within these delays alter communication conditions, resulting in lags in resource adjustments and consequently impacting the quality of satellite-to-ground communication.

[0028] To address at least one of the aforementioned problems, this application proposes a method, apparatus, electronic device, storage medium, and computer program product for satellite-ground cooperative resource scheduling based on a digital twin model. The following is in conjunction with... Figures 1 to 6 Please provide a detailed explanation.

[0029] Reference Figure 1 This application provides a satellite-ground collaborative resource scheduling method based on a digital twin model, which may include: S101, Based on the digital twin model of the communication scenario, determine the location of the communication satellite, the model communication parameters of each communication area, and the user density, wherein the communication scenario includes multiple communication areas.

[0030] A digital twin model is a digitized model of a real-world satellite-ground cooperative communication scenario (hereinafter referred to as the communication scenario). The digital twin model can digitally represent the communication situation within the scenario. For ease of calculation, the entire communication scenario is divided into multiple grids, each grid representing a communication region. Based on the digital twin model, the positions of communication satellites, the model communication parameters for each communication region, and the user density are determined. The model communication parameters are the communication parameters for each communication region within the digital twin model, and these parameters may include at least one of interference power, signal power, and noise.

[0031] S102, based on the satellite position, the model communication parameters, and the user density, the target interference parameters of the communication area within a future preset time period are determined using a time-series prediction model.

[0032] The time-series prediction model is used to predict interference parameters for each communication area within a preset future time period. The model is trained using sample satellite locations, sample model communication parameters, sample user density, and corresponding ground truth interference parameters. The duration of the preset future time period can be customized based on actual conditions; for example, it can be set to any duration within the future 200ms to 5s. Interference parameters characterize the interference situation between satellites and user terminals within the communication area and can include at least one of interference level, interference probability, and interference time slots. The interference time slots refer to the time slots within the preset future time period where interference occurs.

[0033] S103, perform resource scheduling on the communication area according to the target interference parameters.

[0034] In step S102, the target interference parameters for the communication area within a future preset time period are predicted, and a corresponding resource scheduling method can be determined based on these parameters. When the corresponding time period (the future preset time period) is reached, resource scheduling for the communication area can be performed according to the corresponding resource scheduling method. This resource scheduling may include: scheduling terminals in the communication area according to the target interference parameters, and / or adjusting the transmission beams of communication satellites according to the target interference parameters. Adjusting the transmission beams of communication satellites refers to adjusting the transmission beams of communication satellites serving the communication area; scheduling terminals refers to scheduling terminals to a service set of ground base stations or neighboring satellites.

[0035] In this embodiment, the location of communication satellites, model communication parameters for each communication area, and user density are determined based on a digital twin model. This allows for the use of a time-series prediction model to obtain target interference parameters for the communication area within a preset future time period, enabling advance prediction of future interference conditions. When the predicted future time period arrives, resource scheduling for the communication area is performed based on the predicted target interference parameters without requiring real-time SINR measurement, thus improving the real-time performance of resource adjustment and consequently enhancing the communication quality of satellite-to-ground communication. Furthermore, compared to directly obtaining model output parameters from actual communication scenarios, using a digital twin model to obtain model input parameters significantly increases the timeliness of model input parameters and reduces the difficulty and cost of parameter acquisition.

[0036] The following describes the process of establishing a digital twin model. (See also...) Figure 2 , Figure 2 This is a schematic diagram of a digital twin model establishment method in an embodiment of this application, including: S201, acquires communication satellite data, ground base station data, and obstacle data in the communication scenario.

[0037] Communication satellite data includes satellite motion-related parameters and communication beam-related parameters. For example, communication satellite data may include at least one of the following parameters: satellite altitude, satellite orbit, satellite speed, number of two-line element sets (TLE), satellite type, number of beams, single beam power, and antenna pattern parameters.

[0038] Ground base station data includes the location of the ground base station and related parameters of the communication beam. For example, ground base station data may include at least one of the following parameters: latitude and longitude of the ground base station, number of beams, single beam power, antenna pattern parameters, etc.

[0039] Obstacle data is used to describe the characteristics of obstacles such as buildings and vegetation that obstruct satellite signals in a communication scenario. For example, obstacle data may include at least one of the following parameters: the three-dimensional spatial location and geometric contour of the obstacle, its physical thickness, and signal blocking parameters reflecting material properties.

[0040] S202, Based on communication satellite data, establish a communication satellite model.

[0041] A digital communication satellite model is built based on communication satellite data, representing the satellite's motion and communication status. For example, using the Satellite Tool Kit (STK) and orbital dynamics engine, the satellite's position, velocity, elevation, and azimuth can be calculated in 100ms increments to determine its motion. Furthermore, a multi-beam pointing mechanism can be precisely constructed within the model based on communication beam parameters. Through digital mapping, the model not only supports beam hopping and beamforming but also dynamically simulates the scanning process of point beams. This process deeply couples the satellite's radio frequency parameters with its spatial geometric attitude, realistically reproducing the satellite's dynamic coverage characteristics and signal transmission status during on-orbit operation.

[0042] S203, the communication scenario is divided into multiple communication areas, and a communication area model for each communication area is established based on the ground base station data and the obstacle data.

[0043] The communication scenario is divided into multiple geographic grids, each representing a communication region. The size and shape of the communication region can be customized according to the actual situation; for example, the communication region can be set as a rectangle. Each communication region independently stores data such as terrain height, occlusion angle, diffraction loss, and the number of direct / reflected paths, thereby obtaining a communication region model for each region.

[0044] S204. Based on communication satellite data and ground base station data, establish a satellite-to-ground network neighbor cell topology model.

[0045] Based on data such as satellite beam neighbor cell relationships, satellite-to-ground base station neighbor cell relationships, and ground base station neighbor cell relationships, a satellite-to-ground network neighbor cell topology model is constructed.

[0046] S205, Establish a dynamic interference source model.

[0047] A template library is established, including at least one of the following interference sources: UAV swarms, temporary base stations, weather radar, and portable satellite stations, to obtain dynamic interference source models. The dynamic interference source models include at least one of the following: UAV swarm model, temporary base station model, weather radar model, and portable satellite station model. Each model supports configuration of parameters such as location, transmit power, operating frequency band, occupied bandwidth, and activation time period.

[0048] S206. By combining the satellite model, the communication area model, the satellite-to-ground network neighbor cell topology model, and the dynamic interference source model, a digital twin model of the communication scenario is obtained.

[0049] Establish the relationships between satellite models, communication area models, satellite-to-ground network neighbor cell topology models, and dynamic interference source models, and combine them into a digital twin model of the communication scenario.

[0050] In this embodiment of the application, the process of establishing a digital twin model is given. Through the dynamic interference source model, the signal interference situation in the satellite-to-ground communication process can be effectively simulated, thereby providing a model basis for subsequent prediction of target interference parameters.

[0051] The state of the digital twin model can be updated periodically. In one possible implementation, the method further includes: Step A1: Obtain the actual scenario parameters of the communication scenario.

[0052] The actual scenario parameters include at least one of the following: communication quality parameters of the satellite-to-ground link, load parameters of the ground base station, communication beam parameters of the ground base station, user location parameters, environmental parameters, and dynamic interference source parameters.

[0053] Communication quality parameters for the satellite-to-ground link can include measured SINR, Received Signal Strength Indicator (RSSI), and Block Error Rate (BLER). Ground base station load parameters represent the load on the ground base station, such as the number of connected users and handover failure rate. Ground base station communication beam parameters can include Physical Resource Block (PRB) utilization, uplink and downlink channel power, etc. User location parameters represent the location of users in each communication area, which can be obtained through location signals reported by user terminals; user location parameters can include the user's latitude, longitude, speed, and direction of movement. Environmental parameters represent natural environmental factors affecting communication, such as rainfall rate, cloud thickness, and solar flare index. Dynamic interference source parameters represent the situation of dynamic interference sources such as UAV swarms, temporary base stations, weather radars, and portable satellite stations.

[0054] Step A2: Perform time and position alignment on the actual scene parameters to obtain the target actual scene parameters.

[0055] The acquisition period and acquisition time of various types of actual scene parameters may differ. Therefore, it is necessary to align the time of each type of actual scene parameter to facilitate subsequent collaborative processing. Location alignment refers to classifying each actual scene parameter into its corresponding communication area in terms of geographical location.

[0056] In one example, the actual scene parameters can be divided into corresponding communication areas according to their coordinate positions. Using the communication satellite's time as a reference, the actual scene parameters in each communication area are sliced ​​and sampled to obtain the target actual scene parameters. The coordinate positions of the actual scene parameters refer to the location where the parameters are collected, affected, or occur. For example, the coordinate position of the measured SINR of the satellite-to-ground link is the coordinate position of the terminal testing the SINR; the coordinate position of the physical resource block utilization rate of the ground base station is the coordinate position of the ground base station; the coordinate position of the cloud thickness is the coordinate position of the area where the cloud layer is located; and the coordinate position of the solar flare index is the coordinate position of the area affected by the solar flare. Classifying the actual scene parameters into specific communication areas according to their coordinate positions facilitates management by communication area. Because satellites are in high-speed motion and the communication environment is dynamically changing, the actual scene parameters are sliced ​​using the communication satellite's operating time as a reference to extract parameters at specific times / periods, thus obtaining the target actual scene parameters.

[0057] Step A3: Update the state of the digital twin model using the actual target scene parameters.

[0058] The state of the digital twin model is updated using parameters from the actual target scenario, thereby making the state of the digital twin model closer to the state of the actual communication scenario.

[0059] The target real-world scenario parameters include fusionable real-world scenario parameters and non-fusionable real-world scenario parameters. Fusionable real-world scenario parameters refer to target real-world scenario parameters that need to be fused based on the communication area, while non-fusionable real-world scenario parameters refer to target real-world scenario parameters that do not require fusion. In one example, communication quality parameters of the satellite-to-ground link, load parameters of the ground base station, and communication beam parameters of the ground base station are fusionable real-world scenario parameters, while user location parameters, environmental parameters, and dynamic interference source parameters are non-fusionable real-world scenario parameters. In one example, step A3 includes: Step A31: For each communication area, calculate the distance from the coordinate position of the same type of aggregable real-world scene parameter in the communication area to the center of the communication area; calculate the initial weight of the corresponding aggregable real-world scene parameter based on the distance, wherein the initial weight of any aggregable real-world scene parameter is inversely proportional to the magnitude of its distance.

[0060] For aggregable real-world scene parameters of the same type within the current communication area, determine the distance between the coordinates of each aggregable real-world scene parameter and the center of the current communication area. The greater the distance, the smaller the initial weight of the aggregable real-world scene parameter. In one example, the reciprocal of the square of the distance can be used as the initial weight, i.e. a i =1 / d i 2 ,in, a i Let d be the initial weight of the i-th SINR in the current communication area. i It represents the distance between the user terminal corresponding to the i-th SINR and the center of its communication area.

[0061] Step A32: For each communication region, scale the initial weights of the same type of aggregable real-world scene parameters in the communication region to obtain the target weights of the aggregable real-world scene parameters, wherein the sum of the target weights of the same type of aggregable real-world scene parameters in the communication region is 1.

[0062] We can first calculate the scaling factor for aggregable real-world scene parameters of the same type, and then use the scaling factor to scale each initial weight to obtain the target weight. In one example, the scaling factor can be calculated using the following formula: ; Where k is the scaling factor, N is the total number of aggregable real-scene parameters of the same type in the current communication region, and ai is the initial weight of the i-th aggregable real-scene parameter of the same type in the current communication region. Then the target weight of the i-th aggregable real-scene parameter is... Scaling parameters are calculated separately for different types of aggregateable real-world scene parameters.

[0063] Step A33: For each communication region, perform a weighted summation of the same type of aggregable actual scene parameters in the communication region according to the target weight to obtain the region scene parameters of the communication region.

[0064] Taking SINR as an example of an aggregateable real-world scenario parameter, the regional scenario parameter corresponding to the SINR of the current communication region can be calculated using the following formula: ; in, Let be the regional scene parameter corresponding to the SINR of the current communication region at time t, and N be the total number of SINRs in the current communication region. Let i be the target weight of the i-th SINR in the current communication area. Let be the parameter value of the i-th SINR in the current communication area at time t. It is understandable that different types of aggregable real-world scenario parameters need to be calculated separately, and the aggregable real-world scenario parameters of different types in different communication areas also need to be calculated separately.

[0065] Step A34: Update the state of the digital twin model according to the scene parameters of each region and the parameters of the non-integrable actual scene.

[0066] The system will use a high-speed channel to write regional scene parameters and non-integrable actual scene parameters into the communication area and time slot corresponding to the digital twin model in the form of a data stream, thereby updating the state of the digital twin model.

[0067] In this embodiment, updating the digital twin model using actual scenario parameters enables synchronization between the digital twin model and the actual communication scenario, significantly improving the fidelity and dynamic response capability of the digital twin model. This ensures that the digital twin model accurately reflects changes in the actual communication environment, providing highly reliable data support for subsequent prediction and resource scheduling. Furthermore, dividing the target actual scenario parameters into fusionable and non-fusionable parameters, and merging fusionable parameters of the same type within the same communication area into regional scenario parameters, and updating the state of the digital twin model according to these regional and non-fusionable parameters, can significantly reduce the data volume of the digital twin model while effectively representing the state of each communication area. This saves on the operating costs of the digital twin model and reduces the computational load of subsequent interference parameter predictions, improving the prediction speed of interference parameters.

[0068] In addition to updating the state of the digital twin model, the parameters of the digital twin model can also be updated. In one possible implementation, the method further includes: Step B1: Obtain the actual communication parameters of each communication area in the communication scenario, and calculate the error value between the model communication parameters and the actual communication parameters.

[0069] The actual communication parameters are obtained by acquiring the communication parameters of each communication area in the real communication scenario, and the model communication parameters are obtained by acquiring the communication parameters of each communication area in the digital twin model. The error value between the model communication parameters and the actual communication parameters at the same time is calculated.

[0070] Step B2: If the error value is greater than a preset error threshold, adjust the parameters of the digital twin model, wherein the parameters of the digital twin model include at least one of the following: path loss coefficient of the satellite-to-ground link, user mobility parameters, and simulation intensity of interference sources.

[0071] The preset error threshold can be set according to the actual situation. In an example, taking the model SINR and the actual SINR as an example, the error value can be expressed as: ; in, This is the error value. For the model SINR, This is the actual SINR. The preset error threshold is 3dB. When the value exceeds 3dB, the parameters of the digital twin model are adjusted. The adjustment step for the path loss coefficient is ±0.5dB, the adjustment step for the simulation intensity of the interference source is ±1dB, and the adjustment of user movement parameters includes adjusting the user's movement speed and turning probability.

[0072] In this embodiment, when the communication parameters of the model differ significantly from the actual communication parameters, adjusting the parameters of the digital twin model can synchronize the state of the digital twin model with that of the actual communication scenario, significantly improving the fidelity and dynamic response capability of the digital twin model; ensuring that the digital twin model can accurately reflect changes in the actual communication environment, and providing highly reliable data support for subsequent prediction and resource scheduling.

[0073] based on Figure 1 The illustrated embodiment, in one possible implementation, see [link to example]. Figure 3 Step S102, based on the satellite position, the model communication parameters, and the user density, uses a time-series prediction model to determine the target interference parameters of the communication area within a future preset time period, including: S1021, Determine the signal-to-interference-plus-noise ratio and interference power of satellite-to-ground communication in the communication area based on the model communication parameters.

[0074] Interference power represents the interference power received by a user terminal during communication with a communication satellite in a communication area. The calculation methods for the signal-to-interference-plus-noise ratio and interference power can be found in relevant technologies. For example, based on the satellite's position and velocity, the precise slant range and Doppler shift between the satellite and the ground can be calculated. The path loss is then calculated using the line-of-sight spatial loss formula, combined with the transmission frequency of the communication beam. Furthermore, rain attenuation, atmospheric attenuation, and the loss from the interference source must be added. By combining the effective radiated power of the interference source, the gain of the receiving antenna in the interference direction, and the path loss, the interference power during communication between the user terminal and the communication satellite can be calculated.

[0075] S1022, the satellite position, the signal-to-interference-plus-noise ratio, interference power, and user density of each communication area are input into the time series prediction model to obtain the target interference level, target interference probability, and target interference time slot of each communication area within a future preset time period, wherein the target interference parameters include the target interference level, the target interference probability, and the target interference time slot.

[0076] The inputs to the time series prediction model are the satellite positions, SINR of each communication area, interference power, and user density over a past period. The outputs of the time series prediction model are the target interference level, target interference probability, and target interference time slot for each communication area within a preset future time period. The target interference probability can be the confidence level of the target interference level occurring in the target interference time slot.

[0077] A time series prediction model can specifically be a state-space model (SSM), which needs to be trained beforehand using sample data. In one example, the training steps for a time series prediction model might include: Step C1: Obtain the actual data of the communication scenario as sample data and the truth label of the sample data.

[0078] The sample data may include satellite location, SINR of each communication area, interference power, and user density. The ground truth label may include the actual interference level and actual interference time slot of each communication area within a preset future time period. The interference level represents the interference intensity, which can be divided into multiple numerical intervals, each corresponding to an interference level. The numerical intervals can be divided according to actual conditions, and are not limited in this application.

[0079] Step C2: Input the sample data into the time series prediction model to obtain the prediction interference parameters output by the time series prediction model.

[0080] The predicted interference parameters include the predicted interference level, predicted interference probability, and predicted interference time slot. In one example, the input to the time-series prediction model is the SINR, interference power, user density, and satellite position over a past period. The past period can be set according to actual conditions; for example, it could be 100 past time slots, with each time slot being 100ms. The output is the predicted interference level, predicted interference probability, and predicted interference time slot for each communication area within a preset future time period. The interference time slot represents the time slot where interference will occur. The preset future time period can be set according to actual conditions; for example, it could be a period from 0.2s to 5s in the future. The predicted interference probability is the confidence level that interference of the predicted interference level will occur within the predicted interference time slot.

[0081] Step C3: Calculate the model loss based on the predicted interference parameters and the true value labels, and adjust the parameters of the time series prediction model based on the model loss.

[0082] Calculate the model loss based on the actual interference level, actual interference time slot, predicted interference level, and predicted interference time slot, and adjust the parameters of the time series prediction model based on the model loss. Return to step C1 above and continue execution until the preset number of training iterations is reached or the model loss converges, resulting in the pre-trained time series prediction model.

[0083] In this embodiment, a time-series prediction model is used to predict the target interference parameters of each communication area within a preset future time period, allowing for advance prediction of interference conditions in the future. When the predicted future time period is reached, resource scheduling is performed on the communication area based on the predicted target interference parameters, without the need for real-time SINR measurement. This improves the real-time performance of resource adjustment and thus enhances the communication quality of satellite-to-ground communication.

[0084] To further improve the accuracy of the time series forecasting model, it can be updated through online learning. In one possible implementation, the method further includes: Step D1: After reaching the preset future time period, obtain the actual interference parameters of the communication scenario within the preset future time period.

[0085] The actual data of the communication scenario within a "preset future time" is collected to obtain the true interference parameters. The true interference parameters may include the actual interference level and actual interference time slots of each communication area.

[0086] Step D2: Calculate the model loss of the time series prediction model based on the actual interference parameters and the target interference parameters.

[0087] The model loss is calculated based on the actual interference level, actual interference time slot, target interference level, and target interference time slot.

[0088] Step D3: Fine-tune the time series prediction model online based on the model loss.

[0089] In this embodiment of the application, after reaching the future preset time period corresponding to the target interference parameter, the actual interference parameters of the communication scenario within that future preset time period are obtained. Based on the actual interference parameters and the target interference parameters, the time series prediction model is fine-tuned online, which can increase the accuracy of the time series prediction model.

[0090] based on Figure 1 In one possible implementation of the illustrated embodiment, the target interference parameters include the target interference level, the target interference probability, and the target interference time slot; see also Figure 4 Step S103, which involves resource scheduling in the communication area based on the target interference parameters, includes: S1031, For each communication area, determine the resource scheduling method of the communication area based on the target interference level and target interference probability of the communication area.

[0091] The resource scheduling method for a communication area indicates whether resource scheduling is required for that communication area, and whether users in that communication area need to be migrated if resource scheduling is required.

[0092] In one example, for any target interference time slot in a communication area, if the target interference level of the target interference time slot is lower than a first preset level and the target interference probability is lower than a first preset probability value, it is determined that no resource scheduling is required for the communication area in that target interference time slot. If the target interference level of the target interference time slot reaches the first preset level (≥ the first preset level) and / or the target interference probability is not lower than the first preset probability value, it is determined that resource scheduling is required for the communication area in that target interference time slot. If resource scheduling is required for the communication area in a target interference time slot, it is further determined whether users in that communication area need to be relocated. If the target interference level of the target interference time slot reaches a second preset level (≥ the second preset level) and the target interference probability is not lower than the second preset probability value, it is determined that users in that communication area need to be relocated. If the target interference level does not reach the second preset level and / or the target interference probability is lower than the second preset probability value, it is determined that users in that communication area do not need to be relocated. Here, the second preset level is higher than the first preset level, and the second preset probability value is greater than the first preset probability value.

[0093] In one example, for any target interference time slot in the communication area, the product of the target interference level and the target interference probability of the target interference time slot is calculated. If the product is less than a first preset value, it is determined that no resource scheduling is required for the communication area in the target interference time slot; if the first preset value is less than or equal to the product and less than a second preset value, it is determined that resource scheduling is required for the communication area in the target interference time slot, but user migration is not required; if the second preset value is less than or equal to the product, it is determined that resource scheduling is required for the communication area in the target interference time slot, but user migration is required.

[0094] S1032, when the resource scheduling mode in the communication area indicates that user migration is not required, the communication beam of the target communication satellite is adjusted in the target interference time slot of the communication area, wherein the target communication satellite is the expected service satellite in the target interference time slot of the communication area.

[0095] The target communication satellite is the intended service satellite for the communication area within the target interference time slot; that is, the communication satellite planned for the communication area based on its communication coverage area when no user migration is required. When resource scheduling is needed in the communication area but user migration is not required, the modulation and coding scheme (MCS) level of the target communication beam of the target communication satellite is reduced in the target interference time slot within the communication area, for example, adjusted from QAM256 to QAM64; and the transmit power of the target communication beam is increased, for example, by 3dB to 6dB. The target communication beam is the communication beam of the target communication satellite for the communication area.

[0096] S1033, when the resource scheduling mode in the communication area indicates that users need to be migrated, the terminal in the communication area is switched from the target communication satellite to other communication satellites or ground base stations in the target interference time slot of the communication area, and the communication beam of the target communication satellite is adjusted.

[0097] When the resource scheduling method in the communication area indicates that user migration is required, a device whose SINR meets the preset quality requirements is selected from the neighboring communication satellites or ground base stations corresponding to the communication area to obtain the target device. During the target interference time slot in the communication area, the bandwidth, transmit power, and modulation and coding scheme level of the target communication beam of the target communication satellite are reduced. For example, the MCS is adjusted from QAM256 to QAM64, the transmit power of the target communication beam is reduced by 3dB~6dB, and the bandwidth of the target communication beam is reduced by 20%. Furthermore, the terminals in the communication area are switched from the target communication satellite to the target device.

[0098] In this embodiment, when interference is not severe, users are not migrated; instead, the SINR of satellite-to-ground communication is improved by increasing the transmit power and reducing the MCS level. When interference is severe, user migration is performed while reducing the bandwidth, transmit power, and MCS level of the original target communication beam. This reduces the impact of the original target communication beam on the migrated users, thereby improving the SINR of the communication.

[0099] The following describes the satellite-ground collaborative resource scheduling device based on the digital twin model provided in the embodiments of this application. The satellite-ground collaborative resource scheduling device based on the digital twin model described below can be referred to in correspondence with the satellite-ground collaborative resource scheduling method based on the digital twin model described above.

[0100] See Figure 5 This application provides a satellite-ground collaborative resource scheduling device based on a digital twin model, comprising: The digital twin model invocation module 501 is used to determine the location of communication satellites, model communication parameters of each communication area, and user density based on the digital twin model of the communication scenario, wherein the communication scenario includes multiple communication areas; The interference parameter prediction module 502 is used to determine the target interference parameters of the communication area in a future preset time period based on the satellite position, the model communication parameters and the user density using a time series prediction model. The resource scheduling module 503 is used to perform resource scheduling on the communication area according to the target interference parameters.

[0101] In one possible implementation, the device further includes: a digital twin model building module, used to acquire communication satellite data, ground base station data, and obstacle data of the communication scenario; build a communication satellite model based on the communication satellite data; divide the communication scenario into multiple communication areas, and build a communication area model for each of the communication areas based on the ground base station data and the obstacle data; build a satellite-to-ground network neighbor cell topology model based on the communication satellite data and the ground base station data; build a dynamic interference source model; and combine the satellite model, the communication area model, the satellite-to-ground network neighbor cell topology model, and the dynamic interference source model to obtain a digital twin model of the communication scenario.

[0102] In one possible implementation, the dynamic interference source model includes at least one of the following: a drone swarm model, a temporary base station model, a weather radar model, and a satellite portable station model.

[0103] In one possible implementation, the apparatus further includes: a digital twin model update module, configured to acquire actual scene parameters of the communication scenario; perform time and location alignment on the actual scene parameters to obtain target actual scene parameters; and update the state of the digital twin model using the target actual scene parameters; wherein the actual scene parameters include at least one of the following: communication quality parameters of the satellite-to-ground link, load parameters of the ground base station, communication beam parameters of the ground base station, user location parameters, environmental parameters, and dynamic interference source parameters.

[0104] In one possible implementation, the digital twin model update module is specifically used to divide the actual scene parameters into corresponding communication areas according to the coordinate positions of the actual scene parameters; and to perform slice sampling of the actual scene parameters in each of the communication areas based on the time of the communication satellite to obtain the target actual scene parameters.

[0105] In one possible implementation, the target real-world scene parameters include fusionable real-world scene parameters and non-fusionable real-world scene parameters; the digital twin model update module is specifically used to calculate, for each communication region, the distance from the coordinate position of the fusionable real-world scene parameter of the same type in the communication region to the center of the communication region; calculate the initial weight of the corresponding fusionable real-world scene parameter based on the distance, wherein, for any fusionable real-world scene parameter, its initial weight is inversely proportional to the distance; for each communication region, scale the initial weight of the fusionable real-world scene parameters of the same type in the communication region to obtain the target weight of the fusionable real-world scene parameter, wherein the sum of the target weights of all fusionable real-world scene parameters of the same type in the communication region is 1; for each communication region, perform a weighted summation of the fusionable real-world scene parameters of the same type in the communication region according to the target weight to obtain the regional scene parameters of the communication region; and update the state of the digital twin model according to each regional scene parameter and the non-fusionable real-world scene parameter.

[0106] In one possible implementation, the interference parameter prediction module 502 is specifically used to: determine the signal-to-interference-plus-noise ratio and interference power of satellite-to-ground communication in the communication area according to the model communication parameters; input the satellite position, the signal-to-interference-plus-noise ratio, interference power, and user density of each of the communication areas into the time series prediction model to obtain the target interference level, target interference probability, and target interference time slot of each of the communication areas in a future preset time period, wherein the target interference parameters include the target interference level, the target interference probability, and the target interference time slot.

[0107] In one possible implementation, the resource scheduling module 503 is specifically used to: schedule terminals in the communication area according to the target interference parameters, and / or adjust the transmission beam of the communication satellite according to the target interference parameters.

[0108] In one possible implementation, the target interference parameters include the target interference level, the target interference probability, and the target interference time slot; the resource scheduling module 503 is specifically used to determine the resource scheduling mode for each communication area based on the target interference level and the target interference probability of the communication area; when the resource scheduling mode of the communication area indicates that user migration is not required, the communication beam of the target communication satellite is adjusted in the target interference time slot of the communication area, wherein the target communication satellite is the expected service satellite in the target interference time slot of the communication area; when the resource scheduling mode of the communication area indicates that user migration is required, the terminal in the communication area is switched from the target communication satellite to other communication satellites or ground base stations in the target interference time slot of the communication area, and the communication beam of the target communication satellite is adjusted.

[0109] In one possible implementation, the resource scheduling module 503 is specifically used to reduce the modulation and coding strategy level of the target communication beam of the target communication satellite and increase the transmission power of the target communication beam in the target interference time slot of the communication area when the resource scheduling mode of the communication area indicates that user migration is not required, wherein the target communication beam is the communication beam of the target communication satellite for the communication area.

[0110] In one possible implementation, the resource scheduling module 503 is specifically used to select a device whose signal-to-interference-plus-noise ratio meets a preset quality requirement from neighboring communication satellites or neighboring ground base stations corresponding to the communication area when the resource scheduling mode of the communication area indicates that a user needs to be migrated; and to reduce the bandwidth, transmit power, modulation and coding strategy level of the target communication beam of the target communication satellite in the target interference time slot of the communication area, and to switch the terminal in the communication area from the target communication satellite to the target device, wherein the target communication beam is the communication beam of the target communication satellite for the communication area.

[0111] In one possible implementation, the device further includes: a digital twin model update module, configured to acquire actual communication parameters of each communication area in the communication scenario, calculate the error value between the model communication parameters and the actual communication parameters; and adjust the parameters of the digital twin model when the error value is greater than a preset error threshold, wherein the parameters of the digital twin model include at least one of the following: path loss coefficient of the satellite-to-ground link, user mobility parameters, and interference source simulation intensity.

[0112] In one possible implementation, the apparatus further includes: a time-series prediction model update module, configured to, after reaching the future preset time period, acquire the actual interference parameters of the communication scenario within the future preset time period; calculate the model loss of the time-series prediction model based on the actual interference parameters and the target interference parameters; and fine-tune the time-series prediction model online based on the model loss.

[0113] The terminal / user terminal involved in the embodiments of this application can be a device that provides voice and / or data connectivity to a user, a handheld device with wireless connectivity, or other processing devices connected to a wireless modem, etc. The name of the user terminal may differ in different systems; for example, in a 5G system, the user terminal can be called User Equipment (UE).

[0114] The ground base stations involved in the embodiments of this application may include multiple cells that provide services to terminals. Depending on the specific application, a base station may also be called an access point, or a device in an access network that communicates with wireless terminal devices through one or more sectors on the air interface, or other names.

[0115] Figure 6 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 6 As shown, the electronic device may include a processor 610, a communication interface 620, a memory 630, and a communication bus 640, wherein the processor 610, the communication interface 620, and the memory 630 communicate with each other through the communication bus 640. The processor 610 can call the computer program in the memory 630 to execute the steps of the space-ground cooperative resource scheduling method based on the digital twin model.

[0116] Furthermore, the logical instructions in the aforementioned memory 630 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0117] On the other hand, this application also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can perform the steps of the satellite-ground cooperative resource scheduling method based on the digital twin model provided in the above embodiments.

[0118] On the other hand, embodiments of this application also provide a processor-readable storage medium storing a computer program for causing a processor to execute the steps of the satellite-ground cooperative resource scheduling method based on a digital twin model provided in the above embodiments.

[0119] The processor-readable storage medium can be any available medium or data storage device that the processor can access, including but not limited to magnetic memory (e.g., floppy disk, hard disk, magnetic tape, magneto-optical disk (MO)), optical memory (e.g., CD, DVD, BD, HVD), and semiconductor memory (e.g., ROM, EPROM, EEPROM, non-volatile memory (NAND FLASH), solid-state drive (SSD)).

[0120] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0121] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0122] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A satellite-ground collaborative resource scheduling method based on a digital twin model, characterized in that, include: The digital twin model based on the communication scenario determines the location of communication satellites, the model communication parameters of each communication area, and the user density, wherein the communication scenario includes multiple communication areas; Based on the satellite location, the model communication parameters, and the user density, the target interference parameters of the communication area in the future preset time period are determined using a time-series prediction model. Resource scheduling is performed on the communication area based on the target interference parameters.

2. The method according to claim 1, characterized in that, The method further includes: Acquire communication satellite data, ground base station data, and obstacle data in the communication scenario; Based on communication satellite data, establish a communication satellite model; The communication scenario is divided into multiple communication regions, and a communication region model for each communication region is established based on the ground base station data and the obstacle data. Based on communication satellite data and ground base station data, establish a satellite-to-ground network neighbor cell topology model; Establish a dynamic interference source model; By combining the satellite model, the communication area model, the satellite-to-ground network neighbor cell topology model, and the dynamic interference source model, a digital twin model of the communication scenario is obtained.

3. The method according to claim 2, characterized in that, The dynamic interference source model includes at least one of the following: UAV swarm model, temporary base station model, weather radar model, and satellite portable station model.

4. The method according to claim 1, characterized in that, The method further includes: Obtain the actual scenario parameters of the communication scenario; The actual scene parameters are aligned in time and in position to obtain the target actual scene parameters; The state of the digital twin model is updated using the actual scene parameters of the target. The actual scenario parameters include at least one of the following: communication quality parameters of the satellite-to-ground link, load parameters of the ground base station, communication beam parameters of the ground base station, user location parameters, environmental parameters, and dynamic interference source parameters.

5. The method according to claim 4, characterized in that, The step of aligning the actual scene parameters by time and position to obtain the target actual scene parameters includes: According to the coordinate position of the actual scene parameters, the actual scene parameters are divided into corresponding communication areas; Using the time of the communication satellite as a reference, the actual scene parameters in each of the aforementioned communication areas are sliced ​​and sampled to obtain the actual scene parameters of the target.

6. The method according to claim 4, characterized in that, The target real-world scene parameters include fusionable real-world scene parameters and non-fusionable real-world scene parameters; The step of updating the state of the digital twin model using the target actual scene parameters includes: For each communication region, calculate the distance from the coordinate position of the same type of aggregable real-world scene parameter in the communication region to the center of the communication region; calculate the initial weight of the corresponding aggregable real-world scene parameter based on the distance, wherein, for any aggregable real-world scene parameter, the magnitude of its initial weight is inversely proportional to the magnitude of its distance; For each communication region, the initial weights of the same type of aggregable real-world scene parameters in the communication region are scaled to obtain the target weights of the aggregable real-world scene parameters, wherein the sum of the target weights of the same type of aggregable real-world scene parameters in the communication region is 1. For each communication region, the aggregateable actual scene parameters of the same type in the communication region are weighted and summed according to the target weight to obtain the regional scene parameters of the communication region. The state of the digital twin model is updated according to the parameters of each region scene and the parameters of the non-integrable actual scene.

7. The method according to claim 1, characterized in that, The step of determining the target interference parameters of the communication area within a future preset time period using a time-series prediction model based on the satellite position, the model communication parameters, and the user density includes: Based on the model communication parameters, determine the signal-to-interference-plus-noise ratio and interference power of satellite-to-ground communication in the communication area; The satellite position, the signal-to-interference-plus-noise ratio, interference power, and user density of each communication area are input into the time series prediction model to obtain the target interference level, target interference probability, and target interference time slot for each communication area within a preset time period in the future. The target interference parameters include the target interference level, the target interference probability, and the target interference time slot.

8. The method according to claim 1, characterized in that, The step of scheduling resources in the communication area according to the target interference parameters includes: The terminals in the communication area are scheduled according to the target interference parameters, and / or the transmission beams of the communication satellites are adjusted according to the target interference parameters.

9. The method according to claim 1, characterized in that, The target interference parameters include the target interference level, the target interference probability, and the target interference time slot; the step of scheduling resources in the communication area according to the target interference parameters includes: For each communication area, the resource scheduling method for that communication area is determined based on the target interference level and target interference probability of that communication area. When the resource scheduling mode in the communication area indicates that user migration is not required, the communication beam of the target communication satellite is adjusted in the target interference time slot of the communication area, wherein the target communication satellite is the expected service satellite in the target interference time slot of the communication area; When the resource scheduling mode in the communication area indicates that users need to be migrated, the terminal in the communication area is switched from the target communication satellite to other communication satellites or ground base stations in the target interference time slot of the communication area, and the communication beam of the target communication satellite is adjusted.

10. The method according to claim 9, characterized in that, When the resource scheduling mode in the communication area indicates that user migration is not required, adjusting the communication beam of the target communication satellite in the target interference time slot of the communication area includes: When the resource scheduling mode in the communication area indicates that user migration is not required, the modulation and coding strategy level of the target communication beam of the target communication satellite is reduced and the transmission power of the target communication beam is increased in the target interference time slot of the communication area. The target communication beam is the communication beam of the target communication satellite for the communication area.

11. The method according to claim 9, characterized in that, When the resource scheduling mode in the communication area indicates that user migration is required, the terminal in the communication area is switched from the target communication satellite to other communication satellites or ground base stations during the target interference time slot in the communication area, and the communication beam of the target communication satellite is adjusted, including: When the resource scheduling method in the communication area indicates that a user needs to be migrated, the target device is obtained by selecting a device whose signal-to-interference-plus-noise ratio meets the preset quality requirements from the neighboring communication satellites or neighboring ground base stations corresponding to the communication area. In the target interference time slot of the communication area, the bandwidth, transmit power, modulation and coding strategy level of the target communication beam of the target communication satellite are reduced, and the terminal in the communication area is switched from the target communication satellite to the target device, wherein the target communication beam is the communication beam of the target communication satellite for the communication area.

12. The method according to claim 1, characterized in that, The method further includes: Obtain the actual communication parameters of each communication area in the communication scenario, and calculate the error value between the model communication parameters and the actual communication parameters; If the error value is greater than a preset error threshold, the parameters of the digital twin model are adjusted, wherein the parameters of the digital twin model include at least one of the following: path loss coefficient of the satellite-to-ground link, user mobility parameters, and simulation intensity of interference sources.

13. The method according to claim 1, characterized in that, The method further includes: After the predetermined future time period is reached, the actual interference parameters of the communication scenario within the predetermined future time period are obtained; The model loss of the time series prediction model is calculated based on the actual interference parameters and the target interference parameters. The time series prediction model is fine-tuned online based on the model loss.

14. A satellite-ground collaborative resource scheduling device based on a digital twin model, characterized in that, include: The digital twin model invocation module is used to determine the location of communication satellites, the model communication parameters of each communication area, and the user density based on the digital twin model of the communication scenario, wherein the communication scenario includes multiple communication areas; The interference parameter prediction module is used to determine the target interference parameters of the communication area in a future preset time period based on the satellite position, the model communication parameters and the user density using a time-series prediction model. The resource scheduling module is used to schedule resources in the communication area according to the target interference parameters.

15. An electronic device comprising a processor and a memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the satellite-ground cooperative resource scheduling method based on the digital twin model as described in any one of claims 1 to 13.

16. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the satellite-ground cooperative resource scheduling method based on the digital twin model as described in any one of claims 1 to 13.

17. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the satellite-ground cooperative resource scheduling method based on the digital twin model as described in any one of claims 1 to 13.

Images