A method and system for non-terrestrial network communication parameter prediction

Abstract

The application provides a non-ground network communication parameter prediction method and system, and relates to the field of mobile communication, which comprises the following steps: acquiring signal quality information of a currently connected satellite, and simultaneously acquiring operation information of the currently connected satellite and each adjacent satellite; based on the operation information, a pre-trained prediction model is used to predict future motion information and load information of each satellite according to a preset time window, and future motion information of a user equipment is predicted; the channel throughput and the predicted service duration of each satellite in the future are calculated; a target satellite is selected according to the load information, the channel throughput and the predicted service duration; and the time advance (TA) value and the Doppler shift value are calculated according to the relative distance and the relative radial velocity of the target satellite, so as to generate preloaded access signaling, thereby guaranteeing the robustness of the non-ground network system in the case that the global navigation satellite system (GNSS) signal is weak or temporarily unavailable, and reducing the service interruption time during service switching or link reconfiguration.

Description

Technical Field

[0001] This invention relates to the field of mobile communications, and in particular to a method and system for predicting communication parameters in non-terrestrial networks. Background Technology

[0002] Before accessing a satellite cell, ground users need to obtain Global Positioning and Navigation System (GNSS) positioning information and satellite ephemeris broadcast by the satellite to achieve uplink synchronization. Before performing random access, the User Equipment (UE) should autonomously pre-calculate the uplink synchronization timing advance using satellite ephemeris information and calculate the compensated Doppler shift based on the radial velocity between the UE and the satellite. Due to the concept of integrated air-space-ground communication, satellite communication is now considered in non-remote areas. However, if the UE is in an indoor environment, tunnel, or dense urban building complex, satellite signals may attenuate or fail, preventing the UE from obtaining the satellite ephemeris and GNSS information broadcast by the satellite. Furthermore, when the UE is in an indoor environment, tunnel, or dense urban building complex, the method of calculating the timing advance (TA) and Doppler shift value required for satellite access after receiving the broadcast information from the satellite results in communication delays when the UE performs cell handover or reselection in non-terrestrial networks. Therefore, a method is needed to continuously predict communication parameters when GNSS information cannot be received to solve these two problems. Summary of the Invention

[0003] The purpose of this invention is to provide a method and system for predicting communication parameters in non-terrestrial networks, thereby improving the aforementioned problems. To achieve this objective, the technical solution adopted by this invention is as follows:

[0004] In a first aspect, this application provides a method for predicting communication parameters in a non-terrestrial network, comprising:

[0005] Obtain signal quality information of the currently connected satellite, and at the same time obtain operational information of the currently connected satellite and each of its neighboring satellites;

[0006] Whether to re-access or handover is determined based on signal quality. If so, a pre-trained prediction model is used to predict the future motion and load information of each satellite according to a preset time window based on the operation information, and the future motion information of the user equipment is also predicted. The future motion information includes position and radial velocity.

[0007] Based on the future motion information of satellites and user equipment, calculate the relative distance and relative radial velocity between the user equipment and each satellite in the future, and calculate the channel throughput and expected service duration of each satellite in the future;

[0008] Select target satellites based on load information, channel throughput, and expected service duration;

[0009] The TA value and Doppler shift value are calculated based on the relative distance and relative radial velocity of the target satellite.

[0010] Preloaded communication parameters are generated based on the TA value and Doppler shift value.

[0011] Secondly, this application also provides a communication parameter prediction system for non-terrestrial networks, characterized in that it includes:

[0012] The first module is used to obtain the signal quality information of the currently connected satellite, and at the same time obtain the operation information of the currently connected satellite and each of its neighboring satellites;

[0013] The second module is used to determine whether to re-access or switch based on signal quality. If so, it uses a pre-trained prediction model based on the operation information to predict the future motion information and load information of each satellite according to a preset time window, and predicts the future motion information of the user equipment. The future motion information includes position and radial velocity.

[0014] The third module is used to calculate the relative distance and relative radial velocity between the user equipment and each satellite in the future, based on the future motion information of the satellite and the user equipment, and to calculate the channel throughput and expected service duration of each satellite in the future.

[0015] The fourth module is used to select target satellites based on load information, channel throughput, and expected service duration;

[0016] The fifth module is used to calculate the TA value and Doppler shift value based on the relative distance and relative radial velocity of the target satellite;

[0017] The sixth module is used to generate preloaded communication parameters based on the TA value and Doppler frequency shift value.

[0018] The beneficial effects of this invention are as follows:

[0019] This invention selects a suitable switching satellite by predicting the operating trajectories of satellites and users, and preloads access signaling by calculating the required TA value and Doppler shift of the access satellite in advance based on the prediction results and caching it on the user side. This ensures the robustness of the NR NTN system when GNSS signals are weak or temporarily unavailable, reduces service interruption time during service switching or link reconfiguration, and ensures service continuity and low latency.

[0020] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing embodiments of the invention. Attached Figure Description

[0021] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart of a non-terrestrial network communication parameter prediction method according to an embodiment of this application;

[0023] Figure 2 This is a flowchart of the single-UE-side prediction scheme in an embodiment of this application;

[0024] Figure 3 This is a flowchart illustrating the hybrid prediction scheme for the UE side and satellite base station side in an embodiment of this application.

[0025] Figure 4 This is a structural diagram of a communication parameter prediction device for a non-terrestrial network according to an embodiment of this application;

[0026] Symbol explanation: 800 - Communication parameter prediction device for non-terrestrial networks; 801 - Processor; 802 - Memory; 803 - Multimedia component; 804 - I / O interface; 805 - Communication component. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0028] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0029] Example 1:

[0030] See Figure 1 This embodiment provides a method for predicting communication parameters of a non-terrestrial network, including steps S100, S200, S300, S400, S500 and S600.

[0031] S100: Obtain the signal quality information of the currently connected satellite, and at the same time obtain the operational information of the currently connected satellite and each of its neighboring satellites;

[0032] Each low-Earth orbit (LEO) satellite maintains a neighboring satellite set Hs. Each LEO satellite spontaneously sends beacon information (which includes its own ephemeris information, current radial velocity, orbital semi-major axis, inclination, eccentricity, right ascension of the ascending node, and current downlink channel occupancy status) to neighboring LEO satellites within a certain range. After receiving these beacon information, the LEO satellites store their identity information in the neighboring satellite set Hs and update the neighboring satellite set Hs at preset intervals of Δt.

[0033] S200. Determine whether to perform re-access or handover based on signal quality. If so, use a pre-trained prediction model based on the operation information to predict the future motion information and load information of each satellite according to a preset time window, and predict the future motion information of the user equipment; the future motion information includes position and radial velocity.

[0034] When the UE detects a sharp decline in the quality of the received satellite signal or when the quality of the received satellite signal is below a threshold for an extended period of time, it will initiate re-access or handover.

[0035] Get preset time window For example, 50 seconds; divide the time window into... t Each time slot The pre-trained prediction model is used to predict the future motion and payload information of each satellite according to a preset time window.

[0036] Specifically, the steps for building the prediction model are as follows:

[0037] S210. Obtain a collection of low-Earth orbit satellites, and use the K-Means clustering algorithm to classify all low-Earth orbit satellites in the collection according to their orbital parameters to obtain multiple satellite clusters;

[0038] The orbital parameters include semi-major axis, inclination, eccentricity, right ascension of the ascending node, etc., and orbital features are constructed based on the orbital parameters. K-Means clustering is performed on the orbital features, and a corresponding prediction model is trained using the satellite historical information in each cluster.

[0039] S220. For each satellite cluster, obtain the historical operation information and historical channel occupancy information of the satellites within it;

[0040] Historical operational information includes longitude, latitude, altitude, horizontal velocity, velocity direction, radial velocity, horizontal acceleration, acceleration direction, and radial acceleration acquired in chronological order.

[0041] S230. Calculate the historical load status based on the historical channel occupancy information;

[0042] Load status is represented by the ratio of occupied channels to the maximum number of available channels, as shown in the formula: , Each satellite has a maximum number of channels that can be provided. Number of channels occupied; Under load;

[0043] S240. Based on the satellite's historical operation information and historical load status, construct the first matrix training set, and use the first matrix training set to train the gated recurrent neural network to obtain the first prediction model;

[0044] Concatenate historical operation information and historical load status to construct the first matrix training set. The shape of the input matrix is: (Time step) × 10 (Feature dimension);

[0045] The output labels (future true values) are set as follows: [future longitude, future latitude, future altitude, future horizontal velocity, future velocity direction, load status]. The shape of the output matrix is: (Prediction steps) × 6 (feature dimensions);

[0046] The model is trained using a gated recurrent neural network (GRU model), which employs an encoder-decoder structure. The encoder compresses sequence information about position, velocity, and load status obtained from past measurements into a "context vector," and the decoder then uses this "context vector" to generate future time information step by step. A sequence of information per second over a given time period.

[0047] S250. Obtain historical operating information of user equipment, construct a second matrix training set, and train a gated recurrent neural network using the first matrix training set to obtain a second prediction model.

[0048] The historical operational information of user equipment includes the same parameters as the historical operational information of satellites, and the training of its prediction model is the same as that of the first prediction model.

[0049] S300. Based on the future motion information of satellites and user equipment, calculate the relative distance and relative radial velocity between the user equipment and each satellite in the future, and calculate the channel throughput and expected service duration of each satellite in the future;

[0050] For each future time t :

[0051] ;

[0052] in:

[0053] :time The relative distance between user equipment and satellites;

[0054] , , Predicted satellite time Three-dimensional coordinates with the Earth's center as the origin;

[0055] Predicted UE in time Three-dimensional coordinates with the Earth's center as the origin;

[0056] To predict the relative radial velocity, the relative velocity vector and unit direction vector between the UE and the satellite must first be calculated, using the formula shown below:

[0057] Relative velocity vector calculation: ;

[0058] in:

[0059] :time t The relative velocity vector between user equipment and satellite

[0060] :time t The satellite velocity vector;

[0061] :time t UE velocity vector;

[0062] Formula for calculating the unit direction vector:

[0063] ;

[0064] in, This is the distance vector between the satellite and the user equipment in three dimensions;

[0065] : The unit direction vector from the UE to the satellite;

[0066] Finally, the relative radial velocity was actually calculated: ;

[0067] The steps for calculating satellite channel throughput and estimated service duration are as follows:

[0068] Channel throughput between UE and satellite Based on downlink carrier-to-noise ratio According to Shannon's formula, the path loss is assumed to be mainly caused by free space fading. Influence:

[0069] Based on the relative distance between the user equipment and the satellite Calculate free space path loss;

[0070] Free space path loss :

[0071] ;

[0072] in, For carrier frequency, It is the speed of light.

[0073] Obtain satellite transmission power Satellite transmitting antenna gain and user receiving antenna gain The received signal power is calculated by combining the free space path loss.

[0074] Received signal power:

[0075] ;

[0076] in, These are fixed losses other than free space losses, and this assumption is a constant factor.

[0077] Calculate the downlink carrier-to-noise ratio based on the received signal power;

[0078] Received signal noise power is Therefore, the downlink carrier-to-noise ratio It can be expressed by the following formula:

[0079] ;

[0080] The channel throughput is calculated based on the downlink carrier-to-noise ratio.

[0081] by This represents the fixed parameters mentioned earlier. Therefore, the channel throughput can be simplified to:

[0082] ;

[0083] in, Channel bandwidth; Channel throughput;

[0084] Expected service duration This refers to the original satellite and the satellite's ability to continuously monitor the target UE for a duration of [duration missing]. The service time is used to avoid frequent handovers, and this value is calculated based on the UE's elevation angle to the satellite.

[0085] Calculate the channel throughput and expected service duration for each satellite in the future, including:

[0086] Transform the positions of the satellite and user equipment to the geocentric-ground-fixed coordinate system (ECEF) and calculate the position vector of the user equipment.

[0087] The Earth-centered, Earth-fixed coordinate system consists of three coordinate axes (X, Y, Z), which are perpendicular to each other, forming a right-handed coordinate system. The specific definition is as follows:

[0088] X-axis: The point from the Earth's center of mass to the intersection of the Greenwich Meridian and the Earth's equator.

[0089] Y-axis: Perpendicular to the X-axis, located on the Earth's equatorial plane, pointing eastward.

[0090] Z-axis: from the Earth's center of mass to the Earth's North Pole.

[0091] In the geocentric coordinate system, the UE position vector is represented as The satellite position vector is represented as ; For the UE's three-dimensional coordinates; For satellite three-dimensional coordinates;

[0092] A user coordinate system is established with the user equipment location as the origin, and the normal vector of the horizontal plane at the location of the user equipment is obtained; wherein, the three axes of the user coordinate system are determined based on the user equipment location vector;

[0093] Establish an XYZ coordinate system with the user's location as the origin, as follows:

[0094] The formula for calculating the unit vector along the X-axis is:

[0095] ;

[0096] in, It is the Z-axis unit vector in the geocentric-fixed coordinate system;

[0097] The formula for calculating the unit vector along the Y-axis is:

[0098] ;

[0099] The formula for calculating the unit vector along the Z-axis is:

[0100] ;

[0101] That is, the normal vector of the horizontal plane where the UE is currently located.

[0102] The satellite is transformed from the geocentric coordinate system to the user coordinate system, the satellite's trajectory in the user coordinate system is modeled, and a formula for calculating the satellite's elevation angle is constructed.

[0103] The relative position of the satellite is obtained with the user equipment as the origin. for: and satellite relative velocity v .

[0104] In short-term (e.g., a few minutes) predictions, assuming the UE and satellite move at a constant velocity in a straight line for a short period, the satellite's motion in the user coordinate system can be modeled as follows:

[0105] ;

[0106]

[0107] for t The position of the time satellite in the user coordinate system; Let t be the three-dimensional coordinates of the satellite in the user coordinate system at time t;

[0108] Formula for calculating satellite elevation angle:

[0109] ;

[0110] in, This refers to the satellite's elevation angle;

[0111] Based on the satellite elevation angle calculation formula, the elevation angle between the satellite and the user equipment is equal to the preset minimum elevation angle. The corresponding time of time The estimated service duration of the satellite is calculated based on the corresponding time.

[0112] make ;

[0113] ；

[0114] Two real roots can be obtained by solving. , ,in The expected satellite service duration is... ;

[0115] As an optional implementation, since signal transmission can be affected by terrain or building obstructions in densely built-up urban areas or mountainous regions, this step performs terrain obstruction correction when determining the minimum elevation angle, as detailed below:

[0116] Obtain the digital elevation model (DEM) within a preset range based on the location of the user equipment, such as a range of 5km;

[0117] Calculate the line-of-sight path parameters of the satellite in the user coordinate system. The line-of-sight path parameters include the ground projection vector of the line-of-sight path and the elevation angle of the line-of-sight path.

[0118] Along the ground projection direction of the satellite line of sight, uniformly sample at least two terrain points in the digital elevation model; here, uniform sampling can be performed according to the grid resolution of the DEM (e.g., 30m);

[0119] Obtain the relative elevation of each sampled terrain point relative to the user device;

[0120] Calculate the line-of-sight path height corresponding to each sampled terrain point, and determine whether the sampled terrain point will obstruct the satellite's line-of-sight path based on the relative elevation. If so, calculate the satellite's effective minimum elevation angle based on the relative elevation.

[0121] If the relative elevation is greater than the line-of-sight height corresponding to the terrain point, it means the satellite will be obstructed. In this case, the minimum unobstructed elevation angle needs to be calculated based on the relative elevation of the obstruction point. This angle is used as the effective minimum elevation angle. When the line-of-sight path is unobstructed, the minimum elevation angle uses a preset value, such as 10°.

[0122] In addition, the terrain undulation within a preset range surrounding the UE can be analyzed based on the digital elevation model; the proportion of areas with a slope greater than 20° can be calculated to obtain the terrain complexity.

[0123] The effective service duration is adjusted based on the complexity of the terrain; the more complex the terrain, the shorter the effective service duration.

[0124] S400: Select target satellites based on load information, channel throughput, and expected service duration;

[0125] Calculation t The value of each satellite selection :

[0126] ;

[0127] in, , and These are constant weight values, used to describe the trade-off between expected satellite service duration, channel throughput, and satellite load. The satellite with the highest value is selected as the target satellite for access based on the calculation results.

[0128] S500: The TA value and Doppler shift value are calculated based on the relative distance and relative radial velocity of the target satellite.

[0129] The calculation formulas for both are as follows:

[0130]

[0131] Where c is the speed of light. Sampling rate, This represents the sampling interval.

[0132]

[0133] in, The carrier frequency used by the local UE.

[0134] S600: Generate preloaded communication parameters based on TA value and Doppler frequency shift value;

[0135] The pre-loaded communication parameters are stored in the user equipment. When the UE determines that the signal quality of the best access satellite cell reaches the access threshold, it confirms the satellite information and the corresponding TA value and Doppler frequency shift value of the cached satellite based on the broadcast information sent by the satellite, and generates access signaling to complete the access with the satellite base station.

[0136] This method also includes:

[0137] Access to the target satellite is achieved by preloading communication parameters;

[0138] Obtain the actual access time consumed by the satellite. ;

[0139] Calculate the actual access duration The difference D between the current value and the preset window is calculated. If the difference is positive, the difference is multiplied by a preset first coefficient to obtain the first adjustment amount; this indicates the prediction time window. Since the internal UE has not accessed the target satellite, the prediction time window needs to be extended and used in the next prediction.

[0140] If the difference is negative, multiply the difference by a preset second coefficient to obtain the second adjustment amount; this indicates that within the prediction time window... Once the UE successfully accesses the target satellite, the prediction window can be appropriately shortened to reduce the computational load.

[0141] Adjust the preset window based on the first or second adjustment amount, and then make the next prediction.

[0142] For situations where the received satellite signal is detected to be below an acceptable threshold for an extended period, two prediction schemes are designed: one uses only the UE side for prediction, and the other uses a hybrid prediction scheme using both the UE side and the satellite side. The choice between these two schemes can be made based on the UE's performance.

[0143] 1. Prediction is performed using only the UE side. The specific prediction process is as follows: Figure 2 As shown, the specific steps are as follows:

[0144] B1. The UE monitors whether the received satellite signal remains below an acceptable threshold for an extended period, which can be set to several seconds. The UE then reports the measurement results to the serving satellite (the currently connected satellite). The serving satellite makes a conditional handover decision (whether to perform re-access or handover). If a handover is decided, it sends a handover request to neighboring satellites. The neighboring satellites determine admission control, send a handover request confirmation message to the serving satellite, and send the configuration information and ephemeris information of the original serving satellite and neighboring satellites to the UE via an RRC reconfiguration message. The UE then sends an RRC reconfiguration complete message to the serving satellite.

[0145] B2. After receiving ephemeris information, the UE initiates a prediction model to predict the satellite-UE relative distance and relative radial velocity, as well as the load status of the original serving satellite and neighboring satellite cells, every second for a future period. It also calculates the TA value and Doppler offset value of the access satellite cell per second for the future period. The UE preloads and caches access signaling based on the calculated TA value and Doppler shift value. Subsequently, the UE monitors whether the satellite signal meets the handover conditions. When the satellite signal received power and signal quality reach the threshold, it determines the optimal access satellite cell (target cell) covering the UE at this time based on the predicted and saved optimal access satellite cell sequence, applies the cached target cell configuration and security context, and completes the connection.

[0146] 2. The specific prediction process using a hybrid prediction method combining UE-side and satellite-side prediction is as follows: Figure 3 As shown, the specific steps are as follows:

[0147] C1. After receiving the measurement report from the UE and preparing to initiate conditional handover, the satellite uses the first prediction model stored on the satellite to perform the first round of basic predictions for itself and neighboring satellites, predicting future... Within a given second, the system records the position, velocity, and load status of itself and neighboring satellites every ΔT seconds (ΔT > 1). After deciding to switch, it sends a switch request to neighboring satellites. The neighboring satellites then determine admission control and send a switch request confirmation message to the serving satellite.

[0148] C2. The serving satellite sends an RRC reconfiguration message to the UE. This message contains an empty ta-Command field (to be filled by the UE) and its own and neighboring satellite configuration information, as well as the satellite's predicted future position, velocity information and load status of itself and neighboring satellites.

[0149] C3. UE performs more refined local predictions (future) The system predicts the satellite's position and velocity per second within a ΔT-second interval using basic information about the target and candidate satellites. ΔT seconds are not included in the dynamically adjusted prediction time window. For the UE's own position and velocity prediction, a second prediction model on the UE side is used. Based on the prediction results, the most suitable access satellite cell is selected, and precise timing advance and Doppler offset values ​​are calculated. The UE monitors whether the satellite signal meets the handover conditions. When the satellite signal received power and signal quality reach the thresholds, the cached target cell configuration and security context are applied to complete the connection.

[0150] Example 2:

[0151] This embodiment provides a communication parameter prediction system for non-terrestrial networks, including:

[0152] The first module is used to obtain the signal quality information of the currently connected satellite, and at the same time obtain the operation information of the currently connected satellite and each of its neighboring satellites;

[0153] The second module is used to determine whether to re-access or switch based on signal quality. If so, it uses a pre-trained prediction model based on the operation information to predict the future motion information and load information of each satellite according to a preset time window, and predicts the future motion information of the user equipment. The future motion information includes position and radial velocity.

[0154] The third module is used to calculate the relative distance and relative radial velocity between the user equipment and each satellite in the future, based on the future motion information of the satellite and the user equipment, and to calculate the channel throughput and expected service duration of each satellite in the future.

[0155] The fourth module is used to select target satellites based on load information, channel throughput, and expected service duration;

[0156] The fifth module is used to calculate the TA value and Doppler shift value based on the relative distance and relative radial velocity of the target satellite;

[0157] The sixth module is used to generate preloaded communication parameters based on the TA value and Doppler frequency shift value.

[0158] As an optional implementation, the system further includes:

[0159] The seventh module is used to obtain a collection of low-Earth orbit satellites. The K-Means clustering algorithm is used to classify all low-Earth orbit satellites in the collection according to their orbital parameters, resulting in multiple satellite clusters.

[0160] The eighth module is used to obtain historical operational information and historical channel occupancy information of the satellites in each satellite cluster;

[0161] The ninth module is used to calculate the historical load status based on historical channel occupancy information;

[0162] The tenth module is used to construct the first matrix training set based on the satellite's historical operational information and historical load status, and to train the gated recurrent neural network using the first matrix training set to obtain the first prediction model;

[0163] The eleventh module is used to obtain historical operating information of user equipment, construct a second matrix training set, and train a gated recurrent neural network using the first matrix training set to obtain a second prediction model.

[0164] As an optional implementation, the third module includes:

[0165] The first unit is used to calculate the free space path loss based on the relative distance between the user equipment and the satellite;

[0166] The second unit is used to obtain the satellite transmit power, satellite transmit antenna gain and user receive antenna gain, and calculate the received signal power in combination with free space path loss;

[0167] The third unit is used to calculate the downlink carrier-to-noise ratio based on the received signal power.

[0168] The fourth unit is used to calculate the channel throughput based on the downlink carrier-to-noise ratio.

[0169] As an optional implementation, the channel throughput and expected service duration for each satellite in the future are calculated, including:

[0170] The fifth unit is used to transform the positions of satellites and user equipment to the geocentric coordinate system and calculate the position vector of the user equipment.

[0171] The sixth unit is used to establish a user coordinate system with the user equipment position as the origin and obtain the normal vector of the horizontal plane where the user equipment is located; wherein, the three axes of the user coordinate system are determined based on the user equipment position vector.

[0172] Unit 7 is used to transform the satellite from the geocentric coordinate system to the user coordinate system, model the satellite's trajectory in the user coordinate system, and construct the formula for calculating the satellite's elevation angle.

[0173] The eighth unit is used to calculate the time when the elevation angle between the satellite and the user equipment is equal to the preset minimum elevation angle, based on the satellite elevation angle calculation formula, and to calculate the expected service duration of the satellite based on the corresponding time.

[0174] Example 3:

[0175] Corresponding to the above method embodiments, this embodiment also provides a communication parameter prediction device for non-terrestrial networks. The communication parameter prediction device for non-terrestrial networks described below can be referred to in correspondence with the communication parameter prediction method for non-terrestrial networks described above.

[0176] Figure 4 This is a block diagram illustrating a communication parameter prediction device 800 for a non-terrestrial network according to an exemplary embodiment. Figure 4 As shown, the non-terrestrial network communication parameter prediction device 800 includes a processor 801 and a memory 802. The non-terrestrial network communication parameter prediction device 800 may also include one or more of a multimedia component 803, an input / output (I / O) interface 804, and a communication component 805. The processor 801 controls the overall operation of the non-terrestrial network communication parameter prediction device 800 to complete all or part of the steps in the aforementioned non-terrestrial network communication parameter prediction method. The memory 802 stores various types of data to support the operation of the non-terrestrial network communication parameter prediction device 800. This data may include, for example, commands for any application or method operating on the non-terrestrial network communication parameter prediction device 800, and application-related data such as contact data, sent and received messages, images, audio, video, etc. The memory 802 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 storage, flash memory, magnetic disk or optical disk.

[0177] Multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals.

[0178] The received audio signal can be further stored in memory 802 or transmitted via communication component 805. The audio component also includes at least one speaker for outputting audio signals. I / O interface 804 provides an interface between processor 801 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons can be virtual or physical. Communication component 805 is used for wired or wireless communication between the non-terrestrial network communication parameter prediction device 800 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, 5G, or 6G, or a combination thereof, is used. Therefore, the corresponding communication component 805 may include a Wi-Fi module, a Bluetooth module, or an NFC module.

[0179] Example 4:

[0180] Corresponding to the above embodiment of the method for predicting communication parameters of non-terrestrial networks, this embodiment also provides a readable storage medium. The readable storage medium described below can be referred to in correspondence with the above-described method for predicting communication parameters of non-terrestrial networks.

[0181] A readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described embodiment of the communication parameter prediction method for non-terrestrial networks.

[0182] Specifically, the readable storage medium can be a USB flash drive, external hard drive, read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk, or any other readable storage medium capable of storing program code.

[0183] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0184] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for predicting communication parameters in a non-terrestrial network, characterized in that, include: Obtain signal quality information of the currently connected satellite, and at the same time obtain operational information of the currently connected satellite and each of its neighboring satellites; Whether to re-access or handover is determined based on signal quality. If so, a pre-trained prediction model is used to predict the future motion and load information of each satellite according to a preset time window based on the operation information, and the future motion information of the user equipment is also predicted. The future motion information includes position and radial velocity. Based on the future motion information of satellites and user equipment, calculate the relative distance and relative radial velocity between the user equipment and each satellite in the future, and calculate the channel throughput and expected service duration of each satellite in the future; Select target satellites based on load information, channel throughput, and expected service duration; The TA value and Doppler shift value are calculated based on the relative distance and relative radial velocity of the target satellite. Preloaded communication parameters are generated based on the TA value and Doppler shift value.

2. The method for predicting communication parameters of non-terrestrial networks according to claim 1, characterized in that, The method includes: A collection of low-Earth orbit satellites is obtained, and the K-Means clustering algorithm is used to classify all low-Earth orbit satellites in the collection according to their orbital parameters, resulting in multiple satellite clusters; For each satellite cluster, obtain the historical operational information and historical channel occupancy information of the satellites within it; Calculate historical load status based on historical channel occupancy information; Based on the satellite's historical operational information and historical load status, a first matrix training set is constructed, and a gated recurrent neural network is trained using the first matrix training set to obtain the first prediction model. Historical operating information of user equipment is obtained, a second matrix training set is constructed, and a gated recurrent neural network is trained using the first matrix training set to obtain a second prediction model.

3. The method for predicting communication parameters in non-terrestrial networks according to claim 1, characterized in that, Calculate the channel throughput and expected service duration for each satellite in the future, including: Calculate free space path loss based on the relative distance between the user equipment and the satellite; Obtain the satellite transmit power, satellite transmit antenna gain, and user receive antenna gain, and calculate the received signal power by combining the free space path loss; Calculate the downlink carrier-to-noise ratio based on the received signal power; The channel throughput is calculated based on the downlink carrier-to-noise ratio.

4. The method for predicting communication parameters in non-terrestrial networks according to claim 1, characterized in that, Calculate the channel throughput and expected service duration for each satellite in the future, including: Transform the positions of the satellite and user equipment to a geocentric-ground-fixed coordinate system, and calculate the position vector of the user equipment. A user coordinate system is established with the user equipment location as the origin, and the normal vector of the horizontal plane at the location of the user equipment is obtained; wherein, the three axes of the user coordinate system are determined based on the user equipment location vector; The satellite is transformed from the geocentric coordinate system to the user coordinate system, the satellite's trajectory in the user coordinate system is modeled, and a formula for calculating the satellite's elevation angle is constructed. Based on the satellite elevation angle calculation formula, the corresponding time when the elevation angle between the satellite and the user equipment equals the preset minimum elevation angle is determined, and the expected service duration of the satellite is calculated based on the corresponding time.

5. The method for predicting communication parameters of non-terrestrial networks according to claim 1, characterized in that, The method includes: Access to the target satellite is achieved by preloading communication parameters; Obtain the actual access time consumed by the satellite; Calculate the difference between the actual access duration and the preset window. If the difference is positive, multiply the difference by a preset first coefficient to obtain the first adjustment amount; if the difference is negative, multiply the difference by a preset second coefficient to obtain the second adjustment amount. Adjust the preset window based on the first or second adjustment amount, and then make the next prediction.

6. The method for predicting communication parameters in a non-terrestrial network according to claim 4, characterized in that, The method includes: Obtain the digital elevation model within the corresponding preset range based on the location of the user equipment; Calculate the line-of-sight path parameters of the satellite in the user coordinate system. The line-of-sight path parameters include the ground projection vector of the line-of-sight path and the elevation angle of the line-of-sight path. Along the ground projection direction of the satellite line of sight path, at least two terrain points are uniformly sampled in the digital elevation model; Obtain the relative elevation of each sampled terrain point relative to the user device; Calculate the line-of-sight path height corresponding to each sampled terrain point, and determine whether the sampled terrain point will obstruct the satellite's line-of-sight path based on the relative elevation. If so, calculate the satellite's effective minimum elevation angle based on the relative elevation.

7. A communication parameter prediction system for non-terrestrial networks, characterized in that, include: The first module is used to obtain the signal quality information of the currently connected satellite, and at the same time obtain the operation information of the currently connected satellite and each of its neighboring satellites; The second module is used to determine whether to re-access or switch based on signal quality. If so, it uses a pre-trained prediction model based on the operation information to predict the future motion information and load information of each satellite according to a preset time window, and predicts the future motion information of the user equipment. The future motion information includes position and radial velocity. The third module is used to calculate the relative distance and relative radial velocity between the user equipment and each satellite in the future, based on the future motion information of the satellite and the user equipment, and to calculate the channel throughput and expected service duration of each satellite in the future. The fourth module is used to select target satellites based on load information, channel throughput, and expected service duration; The fifth module is used to calculate the TA value and Doppler shift value based on the relative distance and relative radial velocity of the target satellite; The sixth module is used to generate preloaded communication parameters based on the TA value and Doppler frequency shift value.

8. The communication parameter prediction system for non-terrestrial networks according to claim 1, characterized in that, The system also includes: The seventh module is used to obtain a collection of low-Earth orbit satellites. The K-Means clustering algorithm is used to classify all low-Earth orbit satellites in the collection according to their orbital parameters, resulting in multiple satellite clusters. The eighth module is used to obtain historical operational information and historical channel occupancy information of the satellites in each satellite cluster; The ninth module is used to calculate the historical load status based on historical channel occupancy information; The tenth module is used to construct the first matrix training set based on the satellite's historical operational information and historical load status, and to train the gated recurrent neural network using the first matrix training set to obtain the first prediction model; The eleventh module is used to obtain historical operating information of user equipment, construct a second matrix training set, and train a gated recurrent neural network using the first matrix training set to obtain a second prediction model.

9. The communication parameter prediction system for non-terrestrial networks according to claim 1, characterized in that, The third module includes: The first unit is used to calculate the free space path loss based on the relative distance between the user equipment and the satellite; The second unit is used to obtain the satellite transmit power, satellite transmit antenna gain and user receive antenna gain, and calculate the received signal power in combination with free space path loss; The third unit is used to calculate the downlink carrier-to-noise ratio based on the received signal power. The fourth unit is used to calculate the channel throughput based on the downlink carrier-to-noise ratio.

10. The method for predicting communication parameters of a non-terrestrial network according to claim 1, characterized in that, Calculate the channel throughput and expected service duration for each satellite in the future, including: The fifth unit is used to transform the positions of satellites and user equipment to the geocentric coordinate system and calculate the position vector of the user equipment. The sixth unit is used to establish a user coordinate system with the user equipment position as the origin and obtain the normal vector of the horizontal plane where the user equipment is located; wherein, the three axes of the user coordinate system are determined based on the user equipment position vector. Unit 7 is used to transform the satellite from the geocentric coordinate system to the user coordinate system, model the satellite's trajectory in the user coordinate system, and construct the formula for calculating the satellite's elevation angle. The eighth unit is used to calculate the time when the elevation angle between the satellite and the user equipment is equal to the preset minimum elevation angle, based on the satellite elevation angle calculation formula, and to calculate the expected service duration of the satellite based on the corresponding time.

Images