Communication channel intelligent prediction method and device under atmospheric disturbance

Abstract

The invention discloses a communication channel intelligent prediction method and device under atmospheric disturbance, and relates to the technical field of communication, and the method comprises the steps: obtaining the atmospheric feature data and corresponding height information between a satellite and a ground end, determining the atmospheric disturbance data of the corresponding height based on the atmospheric feature data and the height information, and carrying out the intelligent prediction of a communication channel based on the height information. The method comprises the following steps: generating a prediction scale, fusing the prediction scale with atmospheric disturbance data, generating an atmospheric stratification model, determining a communication channel interval between a satellite and a ground end, determining a corresponding channel interval atmospheric model in the atmospheric stratification model according to the communication channel interval, generating an atmospheric change trend based on the prediction scale and the channel interval atmospheric model, and enabling the communication channel parameters to act on an atmospheric change trend, generating a channel quality change curve, and determining a quality prediction result of the communication channel based on the prediction scale and the channel quality change curve. Through the above mode, the problem of real-time prediction of the communication channel performance in a complex atmospheric environment is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of communication, in particular to a communication channel intelligent prediction method and device under atmospheric disturbance. BACKGROUND

[0002] The rapid development of wireless communication technology makes the influence of atmospheric disturbance on communication channels a research hotspot. In a complex atmospheric environment, the performance of a communication channel can be significantly disturbed, leading to a decline or even interruption of signal transmission quality. Current research on signal disturbance mainly uses adversarial networks and variational autoencoders to learn interference characteristics and dynamically generate anti-interference strategies. However, the anti-interference strategy of the adversarial network relies on historical data statistics, and has limitations in dealing with sudden atmospheric events. In addition, atmospheric disturbance is usually coupled with multiple physical fields, and the frequency domain filtering strategy generated by the adversarial network may not fully consider the combined effect of turbulence and thermal blooming, thereby affecting the compensation effect and making it difficult to accurately predict the communication channel under atmospheric disturbance.

[0003] The above content is only used to assist in understanding the technical solutions of the present application and does not represent the acknowledgement of the above content as prior art. SUMMARY

[0004] The main purpose of the present application is to provide a communication channel intelligent prediction method and device under atmospheric disturbance, aiming to solve the technical problem that the performance of a communication channel under a complex atmospheric environment cannot be predicted in real time in the prior art.

[0005] To achieve the above-mentioned purpose, the present application provides a communication channel intelligent prediction method under atmospheric disturbance, the method comprising: obtaining atmospheric characteristic data between a satellite and a ground terminal and corresponding height information, determining atmospheric disturbance data corresponding to the height based on the atmospheric characteristic data and the height information; fusing the atmospheric disturbance data based on the height information to generate an atmospheric layered model; determining a communication channel interval between the satellite and the ground terminal, and determining a corresponding channel interval atmospheric model in the atmospheric layered model according to the communication channel interval; generating an atmospheric change trend based on a prediction scale and the channel interval atmospheric model, applying the communication channel parameter to the atmospheric change trend to generate a channel quality change curve, and determining a quality prediction result of the communication channel based on the prediction scale and the channel quality change curve.

[0006] In an embodiment, the step of obtaining atmospheric characteristic data between a satellite and a ground terminal and corresponding height information, and determining atmospheric disturbance data corresponding to the height based on the atmospheric characteristic data and the height information comprises: Collecting atmospheric temperature, humidity, wind speed and turbulence intensity data between the satellite and the ground terminal at different altitudes as initial atmospheric characteristic data; Obtaining the spatial distribution characteristics of each altitude point to form altitude correlation data; Performing multi-dimensional interpolation calculation on the initial atmospheric characteristic data and the altitude correlation data to determine the atmospheric disturbance coefficient of each altitude point; Mapping the atmospheric disturbance coefficient to the corresponding altitude to generate altitude-matched atmospheric disturbance data.

[0007] In an embodiment, the step of generating an atmospheric layered model by fusing the atmospheric disturbance data based on the altitude information includes: Segmenting the altitude information to divide multiple altitude intervals; For each altitude interval, extracting its corresponding atmospheric disturbance data and performing normalization processing on the atmospheric disturbance data; Inputting the normalized data into a deep learning model to train and generate a disturbance feature vector of the altitude interval; Based on the disturbance feature vector, a layered structure is constructed, and the disturbance feature vectors of each altitude interval are superimposed to generate an atmospheric layered model.

[0008] In an embodiment, the step of determining the communication channel interval of the satellite and the ground terminal, and determining the corresponding channel interval atmospheric model in the atmospheric layered model according to the communication channel interval includes: According to the communication frequency band and signal propagation path of the satellite and the ground terminal, the communication channel interval is divided; Locating the spatial region covered by the communication channel interval in the atmospheric layered model; Extracting the disturbance feature vector in the spatial region and projecting the disturbance feature vector to the frequency domain space of the communication channel interval to obtain a projection result; Generating a channel interval atmospheric model based on the projection result.

[0009] In an embodiment, the step of generating an atmospheric change trend based on a prediction scale and the channel interval atmospheric model includes: According to the prediction scale, a prediction time window is set, and based on the prediction time window, the time series data of the channel interval atmospheric model is divided into multiple sub-intervals; Performing time series analysis on the disturbance feature vectors in each sub-interval to extract the change law of the disturbance feature vectors in the sub-interval; Modeling the change law using a convolutional neural network to generate a time evolution trend of atmospheric disturbance; The time evolution trend of the atmospheric disturbance is combined with atmospheric characteristics to generate an atmospheric change trend.

[0010] In an embodiment, the step of applying the communication channel parameter to the atmospheric change trend to generate a channel quality change curve comprises: The communication channel parameter is mapped to a channel transmission function, and the disturbance intensity in the atmospheric change trend is subjected to matrix multiplication to generate a channel attenuation factor; The channel attenuation factor is cumulatively integrated in a prediction time window as a step to output an instantaneous signal-to-noise ratio sequence; The time distribution of the instantaneous signal-to-noise ratio sequence is fitted to generate a signal quality change curve with a confidence interval, wherein the horizontal axis is the time scale and the vertical axis is the relative change rate of channel capacity.

[0011] In an embodiment, the step of determining the quality prediction result of the communication channel based on the prediction scale and the channel quality change curve comprises: According to the fluctuation range of the instantaneous signal-to-noise ratio sequence in the channel quality change curve, and according to the instantaneous signal-to-noise ratio, three levels of state are determined; The steep drop point and the duration of the instantaneous signal-to-noise ratio in the channel quality change curve are identified, and the time period corresponding to the steep drop point and the duration is marked as a communication interruption warning period; The time proportion of each level state in the prediction scale is calculated, and the quality prediction result is generated in the communication interruption warning period.

[0012] In an embodiment, after the step of determining the quality prediction result of the communication channel based on the prediction scale and the channel quality change curve, the method further comprises: Obtaining a real-time monitored communication channel quality indicator, calculating an error distribution of the communication channel quality indicator and the quality prediction result; Determining a time period in which the error distribution exceeds a threshold, and extracting abnormal atmospheric disturbance data features corresponding to the time period; The abnormal features are fed back to a deep learning model to update the weight parameters of the disturbance feature vector online; Based on the updated model, a channel quality change curve with a narrowed confidence interval is regenerated.

[0013] In an embodiment, the intelligent prediction method of the communication channel under the atmospheric disturbance further comprises: According to the position and duration of the communication interruption warning period, a backup transmission strategy is preloaded in the satellite-ground end link; When the instantaneous signal-to-noise ratio steep drop point is predicted, the modulation and coding scheme is dynamically switched based on the relative change rate of channel capacity; In the communication interruption early warning period, multi-path redundant transmission is triggered, specifically: the data is shunted to at least two independent channels, and the independent channels are generated by the orthogonality of the disturbance characteristic vector in the atmospheric stratification model; Real-time matching of channel quality change curve and execution result of transmission strategy, generation of strategy optimization coefficient and iterative update of standby transmission strategy.

[0014] In addition, to achieve the above-mentioned purpose, the present application also provides an intelligent prediction device for a communication channel under atmospheric disturbance, which comprises: A data acquisition module is configured to acquire atmospheric feature data and corresponding height information between a satellite and a ground terminal, and determine atmospheric disturbance data at a corresponding height based on the atmospheric feature data and the height information; A model generation module is configured to fuse the atmospheric disturbance data based on the height information, and generate an atmospheric stratification model; A model division module is configured to determine a communication channel interval of the satellite and the ground terminal, and determine a corresponding channel interval atmospheric model in the atmospheric stratification model according to the communication channel interval; An intelligent prediction module is configured to generate an atmospheric change trend based on a prediction scale and the channel interval atmospheric model, apply the communication channel parameter to the atmospheric change trend, generate a channel quality change curve, and determine a quality prediction result of the communication channel based on the prediction scale and the channel quality change curve.

[0015] In addition, to achieve the above-mentioned purpose, the present application also provides an intelligent prediction device for a communication channel under atmospheric disturbance, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the intelligent prediction method for a communication channel under atmospheric disturbance as described above.

[0016] In addition, to achieve the above-mentioned purpose, the present application also provides a storage medium, which is a computer-readable storage medium, and the storage medium stores a computer program, which is executed by a processor to implement the steps of the intelligent prediction method for a communication channel under atmospheric disturbance as described above.

[0017] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to implement the steps of the intelligent prediction method for a communication channel under atmospheric disturbance as described above.

[0018] The application provides a communication channel intelligent prediction method under atmospheric disturbance. By obtaining atmospheric characteristic data and corresponding height information between a satellite and a ground terminal, atmospheric characteristics corresponding to each height in the interval between the satellite and the ground terminal can be obtained. Different atmospheric characteristics have different interference on wireless communication. Therefore, after determining atmospheric characteristics corresponding to different heights, the interference degree of each region on communication can be determined, that is, atmospheric disturbance data corresponding to the height is obtained. Therefore, the height information and the atmospheric disturbance data can be fused to obtain the influence of any point in the space domain between the satellite and the ground terminal on communication. The product obtained is an atmospheric layering model. However, when the satellite and the ground terminal are determined, the communication channel is also determined. Therefore, in order to more accurately determine the quality of the channel, the corresponding channel interval can be separated from the atmospheric layering model to determine the atmospheric model of the corresponding channel interval. Then, the atmospheric change trend is generated according to the prediction scale and the atmospheric model of the channel interval, so as to determine the disturbance data change of the channel interval in the future moment or time period, and determine the channel quality change curve, and then the channel quality prediction result can be determined. The effect of real-time prediction of communication channel performance in a complex atmospheric environment is realized. BRIEF DESCRIPTION OF DRAWINGS

[0019] The accompanying drawings, which are incorporated into and form a part of the specification, illustrate an embodiment consistent with the present application and, together with the description, serve to explain the principles of the application.

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, for those skilled in the art, other drawings can also be obtained without creative labor based on these drawings.

[0021] Figure 1 The flowchart of the first embodiment of the communication channel intelligent prediction method under atmospheric disturbance of the present application is shown. Figure 2 The satellite-ground terminal communication relationship diagram of the first embodiment of the communication channel intelligent prediction method under atmospheric disturbance of the present application is shown. Figure 3 The communication channel interval diagram of the first embodiment of the communication channel intelligent prediction method under atmospheric disturbance of the present application is shown. Figure 4 The module structure diagram of the communication channel intelligent prediction device under atmospheric disturbance of the embodiment of the present application is shown. Figure 5 The device structure diagram of the hardware running environment involved in the communication channel intelligent prediction method under atmospheric disturbance in the embodiment of the present application is shown.

[0022] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0023] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0024] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0025] The main solution of this application embodiment is as follows: acquiring atmospheric characteristic data and corresponding altitude information between the satellite and the ground end; determining atmospheric disturbance data at the corresponding altitude based on the atmospheric characteristic data and the altitude information; fusing the altitude information with the atmospheric disturbance data to generate an atmospheric stratification model; determining the communication channel interval between the satellite and the ground end, and determining the corresponding channel interval atmospheric model in the atmospheric stratification model according to the communication channel interval; generating an atmospheric change trend based on the prediction scale and the channel interval atmospheric model; applying the communication channel parameters to the atmospheric change trend to generate a channel quality change curve; and determining the communication channel quality prediction result based on the prediction scale and the channel quality change curve.

[0026] Currently, the rapid development of wireless communication technology has made the impact of atmospheric disturbances on communication channels a research hotspot. In complex atmospheric environments, communication channel performance can be significantly interfered with, leading to a decline in signal transmission quality or even interruption. Current research on signal disturbances mainly utilizes adversarial networks (ANNs) and variational autoencoders to learn interference characteristics and dynamically generate anti-interference strategies. However, the anti-interference strategies of ANFs rely on historical data statistics, which has limitations in responding to sudden atmospheric events. Furthermore, atmospheric disturbances are often coupled with multiple physics fields, and the frequency domain filtering strategies generated by ANFs may not fully consider the combined effects of turbulence and thermal corona, thus affecting the compensation effect and making it difficult to accurately predict communication channels under atmospheric disturbances.

[0027] This application provides a solution that, by acquiring atmospheric characteristic data and corresponding altitude information between a satellite and a ground station, can obtain the atmospheric characteristics at each altitude within this interval. Different atmospheric characteristics cause different levels of interference to wireless communication. Therefore, after determining the atmospheric characteristics at different altitudes, the degree of interference to communication in each region can be naturally determined, i.e., atmospheric disturbance data at the corresponding altitude can be obtained. Thus, by fusing altitude information and atmospheric disturbance data, the impact of any point in this spatial domain between the satellite and the ground station on communication can be obtained, and the resulting product is the atmospheric stratification model. However, when the satellite and ground station are determined, their communication channels are also determined. Therefore, to more accurately determine channel quality, the corresponding channel interval can be separated from the atmospheric stratification model to determine the corresponding channel interval atmospheric model. Then, based on the prediction scale and the channel interval atmospheric model, an atmospheric change trend is generated to determine the disturbance data changes in the channel interval at future times or time periods, and a channel quality change curve is determined accordingly, thereby determining the channel quality prediction result. This achieves the effect of real-time prediction of communication channel performance in complex atmospheric environments.

[0028] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device capable of performing the above functions, such as an intelligent prediction device for communication channels under atmospheric disturbances. This embodiment does not specifically limit this. The following uses an intelligent prediction device for communication channels under atmospheric disturbances as an example to describe this embodiment and the following embodiments.

[0029] All actions involving the acquisition of signals, information, or data in this application are carried out in accordance with the relevant data protection laws and policies of the country where the application is located, and with the authorization of the owner of the relevant device.

[0030] This application provides an intelligent prediction method for communication channels under atmospheric disturbances, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the intelligent prediction method for communication channels under atmospheric disturbances according to this application.

[0031] In this embodiment, the intelligent prediction method for communication channels under atmospheric disturbances includes steps S10 to S40: Step S10: Obtain atmospheric characteristic data and corresponding altitude information between the satellite and the ground, and determine atmospheric disturbance data at the corresponding altitude based on the atmospheric characteristic data and the altitude information; It should be noted that a satellite is a man-made spacecraft orbiting the Earth or other celestial bodies, used for tasks such as communication, navigation, remote sensing, and meteorological observation. Ground-based facilities refer to receiving / transmitting facilities on the Earth's surface, used to establish two-way communication links with satellites, including but not limited to airborne mobile stations, local stations, land-based mobile stations, sea-based mobile stations, communication hubs, and central stations. (See reference...) Figure 2 , Figure 2 This diagram illustrates the satellite-to-ground communication relationship. Atmospheric characteristic data is a set of parameters describing the physical state of the atmosphere, typically including: temperature, air pressure, humidity, wind speed / direction, ionospheric electron density, aerosol concentration, etc. Data sources include radiosondes, meteorological satellites, and low-level remote sensing equipment. Atmospheric disturbance data describes random fluctuations in atmospheric parameters that deviate from their average state; core characteristics include refractive index structure constant, wind shear, ionospheric scintillation index, and gravity wave activity.

[0032] Understandably, atmospheric characteristic data, including parameters such as temperature, humidity, air pressure, and wind speed, are collected between meteorological satellites, ground-based detection equipment (such as weather radar and radiosondes), or meteorological databases, and the corresponding altitude information is recorded simultaneously. Using the obtained atmospheric characteristic data and altitude information, the atmospheric refractive index at different altitudes is calculated. Based on parameter fluctuations and turbulence models, key disturbance indicators are calculated to obtain atmospheric disturbance data.

[0033] In one feasible implementation, the step of acquiring atmospheric characteristic data and corresponding altitude information between the satellite and the ground, and determining atmospheric disturbance data at the corresponding altitude based on the atmospheric characteristic data and the altitude information, includes: Data on atmospheric temperature, humidity, wind speed, and turbulence intensity at different altitudes between the satellite and the ground are collected as initial atmospheric characteristic data. Obtain the spatial distribution characteristics of each elevation point to form elevation correlation data; Multidimensional interpolation calculations are performed on the initial atmospheric characteristic data and the altitude-related data to determine the atmospheric disturbance coefficient at each altitude point; The atmospheric disturbance coefficients are mapped to corresponding altitudes to generate altitude-matched atmospheric disturbance data.

[0034] In the specific implementation, raw atmospheric parameters at different altitudes along the satellite-to-ground path are obtained, including atmospheric temperature. ,humidity Wind speed and turbulence intensity data This data is used as the raw atmospheric feature data. Since the corresponding data differs at different altitudes, a spatial mapping relationship between atmospheric parameters and altitude can be established to form altitude-related data. During the mapping process, each altitude point can be... Atmospheric characteristic data It is bound to its spatial location to form a dataset. Then, multidimensional interpolation calculations are performed on the initial atmospheric characteristic data and altitude-related data. Based on the discrete data, a continuously vertically distributed atmospheric disturbance coefficient is generated using three-dimensional spline interpolation. This determines the specific interpolated data corresponding to the target altitude and, based on this, generates the refractive index structure constant. .

[0035]

[0036] in, This is an empirical coefficient. For air pressure, For water vapor pressure, For the vertical temperature gradient, The humidity vertical gradient For target altitude.

[0037] The refractive index structure constant Mapping to continuous height layers to determine the vertical profile function Atmospheric disturbance data with high altitude matching are generated based on altitude.

[0038] Step S20: Based on the altitude information, fuse it with the atmospheric disturbance data to generate an atmospheric layering model; It should be noted that the atmospheric stratification model is a mathematical model that divides the atmosphere into several continuous altitude layers in the vertical direction, each layer having uniform or gradually changing atmospheric physical properties. This model is determined by fusing altitude information and atmospheric disturbance data.

[0039] It is understood that the steps of fusing the altitude information with the atmospheric disturbance data to generate an atmospheric stratification model include: segmenting the altitude information to divide it into multiple altitude intervals; extracting the corresponding atmospheric disturbance data for each altitude interval and normalizing the atmospheric disturbance data; inputting the normalized data into a deep learning model to train and generate disturbance feature vectors for the altitude intervals; constructing a stratified structure based on the disturbance feature vectors, and superimposing the disturbance feature vectors of each altitude interval to generate an atmospheric stratification model.

[0040] In the specific implementation, the altitude information is segmented. The original altitude information is divided according to atmospheric physical characteristics, such as the boundary layer, troposphere, and stratosphere. During the segmentation, equal intervals are determined as the segmentation precision to output several altitude intervals. Within each altitude interval, the corresponding atmospheric disturbance data is normalized. Atmospheric disturbance data within the interval Its normalization formula is:

[0041] in, For interval The mean of the disturbance, , For interval The standard value, .

[0042] Once normalized data is obtained, it can be input into a deep learning model to determine the normalization perturbation. to feature vector The mapping is as follows:

[0043] The mapping relationship automatically captures the spatiotemporal correlations of disturbance data, such as the intermittency of turbulence and the propagation of gravity waves, generating low-dimensional dense vectors while preserving essential physical characteristics. Subsequently, a hierarchical structure is constructed based on the disturbance feature vectors, and the disturbance feature vectors of each altitude range are superimposed to generate an atmospheric stratification model. Finally, the feature vectors of all ranges are vertically superimposed to construct an altitude feature matrix. ,

[0044] And for each interval Binding model layer properties: The perturbation feature vectors of each altitude range are superimposed to generate an atmospheric stratification model.

[0045] Step S30: Determine the communication channel interval between the satellite and the ground terminal, and determine the corresponding channel interval atmospheric model in the atmospheric layering model based on the communication channel interval; It should be noted that, referring to Figure 3 , Figure 3 This is a schematic diagram of a communication channel interval. The communication channel interval refers to the physical spatial range of signal propagation between the satellite and the ground station, which is a three-dimensional cone-shaped region determined by the satellite position, the ground station position, and the electromagnetic wave propagation path.

[0046] It is understandable that the communication channel interval refers to the cone-shaped signal propagation area between the satellite and the ground end, which is determined by the antenna beamwidth and spatial geometry. By calculating the spatial intersection of this interval with the pre-built atmospheric layering model (including vertically divided perturbation data layers), the perturbation feature vectors and turbulence parameters corresponding to the overlapping height layers are extracted to generate an atmospheric model of the channel interval that is only for the actual signal path, thereby achieving accurate and localized modeling of the propagation effect of the satellite-to-ground link.

[0047] It should be understood that the step of determining the communication channel interval between the satellite and the ground end, and determining the corresponding channel interval atmospheric model in the atmospheric layering model based on the communication channel interval includes: dividing the communication channel interval according to the communication frequency band and signal propagation path between the satellite and the ground end; locating the spatial region covered by the communication channel interval in the atmospheric layering model; extracting the disturbance feature vector in the spatial region, and projecting the disturbance feature vector onto the frequency domain space of the communication channel interval to obtain the projection result; and generating the channel interval atmospheric model based on the projection result.

[0048] In practical implementation, communication channel intervals are divided based on the communication frequency bands and signal propagation paths of satellites and low-end devices. The spatial region covered by the current communication channel interval can be located from the atmospheric stratification model; that is, the communication channel interval is a segment of the atmospheric stratification model. When determining the communication channel interval, the center frequency band can be used as a reference. Antenna half-power beamwidth satellite coordinates and ground coordinates This allows us to determine the path distance based on satellite coordinates and ground-based coordinates. The Fresnel zone radius is determined based on the center frequency band and path distance. Determine the effective signal area. ,

[0049] in, For signal transmission speed, At the current altitude, λ is the wavelength.

[0050] The coverage area of ​​a communication channel interval is determined by its cross-sectional radius. Determine and output the corresponding channel space domain. The channel spatial domain is composed of points within this cross-section.

[0051]

[0052]

[0053] In the atmospheric layering model, locate the spatial region covered by the communication channel interval, and extract the disturbance feature vector within the spatial region. The disturbance feature vector is then projected onto the frequency domain space of the communication channel interval to obtain the projection result. The projection is performed using a Fourier transform, and can be expressed as follows:

[0054] Then, frequency band filtering is used to match the communication frequency band. After filtering, it can be represented as:

[0055] The frequency domain perturbation intensity is:

[0056] in, For frequency, For communication bandwidth, This is a rectangular window function for the frequency band.

[0057] Based on the projection results, a channel interval atmospheric model is generated. The structure of the channel interval atmospheric model is as follows:

[0058] in, , The turbulence-frequency domain coupling coefficient is... The fundamental attenuation constant for the frequency band. The frequency decay exponent, For turbulent terms, This is the frequency band attenuation term.

[0059] Step S40: Generate an atmospheric change trend based on the prediction scale and the channel interval atmospheric model; apply the communication channel parameters to the atmospheric change trend to generate a channel quality change curve; and determine the communication channel quality prediction result based on the prediction scale and the channel quality change curve.

[0060] It should be noted that atmospheric change trends refer to the predicted evolution of atmospheric conditions within the communication channel range over a future period, including changes in turbulence intensity, temperature and humidity fluctuations, and extreme time probabilities. Channel quality change curves refer to the time-performance relationship generated after applying communication channel parameters to atmospheric change trends. Quality prediction results refer to the quantitative communication reliability conclusions output based on the channel quality change curves and prediction scales.

[0061] It is understood that the step of generating atmospheric change trends based on the prediction scale and the channel interval atmospheric model includes: setting a prediction time window according to the prediction scale; dividing the time series data of the channel interval atmospheric model into multiple sub-intervals based on the prediction time window; performing time series analysis on the disturbance feature vectors in each sub-interval to extract the variation patterns of the disturbance feature vectors in the sub-intervals; using a convolutional neural network to model the variation patterns to generate the temporal evolution trend of atmospheric disturbances; and combining the temporal evolution trend of atmospheric disturbances with atmospheric features to generate atmospheric change trends.

[0062] In practical implementation, the prediction time window can be determined based on the prediction scale. The time interval corresponding to the prediction scale and the prediction time window is the same; that is, if the prediction scale is 1 second, the corresponding prediction time window is also 1 second. Then, the time series of the atmospheric model is divided into multiple sub-intervals according to the prediction time window. The original time series data of the atmospheric model in the channel interval... It can be represented as:

[0063] in, This is the sequence data corresponding to the current time scale. For time series scale, This represents the original observation dimension.

[0064] Divided by sliding window Subintervals, subintervals It can be represented as:

[0065] in, For the prediction time window.

[0066] A time-series analysis is performed on the disturbance feature vectors within each sub-interval to extract the variation patterns of the disturbance feature vectors within the sub-intervals. A convolutional neural network is used to model these variation patterns to generate a temporal evolution trend of atmospheric disturbances. This temporal evolution trend of atmospheric disturbances is then combined with atmospheric features to generate an atmospheric change trend. Sub-intervals are determined. eigenvector sequence within , When extracting patterns of change, the trend is determined using the first-order difference: Then through the correlation coefficient Determine the periodic characteristics:

[0067] Based on its periodic characteristics, the variation pattern of the disturbance feature vector within the sub-interval can be determined. Then, a convolutional neural network is used to model the variation pattern, forming the temporal evolution trend of atmospheric disturbance. The temporal evolution trend of atmospheric disturbance is then combined with atmospheric characteristics to generate the atmospheric change trend.

[0068] In one feasible implementation, the step of applying the communication channel parameters to the atmospheric change trend to generate a channel quality change curve includes: The communication channel parameters are mapped to the channel transmission function, and the disturbance intensity in the atmospheric change trend is multiplied by matrix to generate the channel attenuation factor. Using the prediction time window as the step size, the channel attenuation factor is cumulatively integrated to output the instantaneous signal-to-noise ratio sequence; The temporal distribution of the instantaneous signal-to-noise ratio sequence is fitted to generate a signal quality change curve with confidence intervals, where the horizontal axis represents the time scale and the vertical axis represents the relative rate of change of channel capacity.

[0069] In practical implementation, when electromagnetic waves pass through the atmosphere, they are subject to interference such as gas absorption and precipitation loss, leading to energy attenuation. The channel attenuation factor is a quantitative indicator used to describe the energy loss of wireless signals caused by atmospheric disturbances. Let the communication channel parameter vector be... ,in, For channel bandwidth, For transmit and receive antenna gain, For fixed loss, the channel transmission function is defined as follows: ,in, To fix the propagation delay, This is the atmospheric attenuation factor. In the... Within a single prediction time window, the intensity of atmospheric disturbances can be determined. and perturbation attenuation-mapping matrix . The empirical weights of the disturbance components on the attenuation. This is the frequency response factor. Its channel attenuation factor is... It can be represented as , The model error is represented by the prediction time window. The channel attenuation factor is cumulatively integrated with the prediction time window as the step size, and the instantaneous signal-to-noise ratio (SNR) sequence is output. The time distribution of the instantaneous SNR sequence is fitted to generate a signal quality change curve with confidence intervals, where the horizontal axis is the time scale and the vertical axis is the relative rate of change of channel capacity.

[0070] In one feasible implementation, the step of determining the quality prediction result of the communication channel based on the prediction scale and the channel quality change curve includes: The three-level status is determined based on the fluctuation range of the instantaneous signal-to-noise ratio sequence in the channel quality change curve and the instantaneous signal-to-noise ratio. Identify the steep drop point and duration of the instantaneous signal-to-noise ratio in the channel quality change curve, and mark the time period corresponding to the steep drop point and duration as the communication interruption warning period; Calculate the time percentage of each level of state within the prediction scale, and generate quality prediction results for the communication interruption warning period.

[0071] In practical implementation, the instantaneous signal-to-noise ratio (SNR) is determined into three levels based on the fluctuation range of the instantaneous SNR sequence in the channel quality change curve. Depending on the specific terminology, this embodiment uses three levels: excellent, medium, and poor. Excellent corresponds to an SNR consistently above the upper threshold, indicating near-lossless communication. Medium corresponds to an SNR in the middle range, indicating the link is still usable but performance has degraded. Poor corresponds to an SNR approaching the lower threshold, with a significantly increased bit error rate, barely maintaining its current state. A "sharp drop" is identified in the state sequence, where the SNR instantly plummets from a high / medium level to a low level, and remains at the low level for a duration exceeding a set threshold. This "sharp drop point + duration" is marked as a communication interruption warning period. During this period, the system issues an early warning, indicating potential link unavailability or severe quality degradation. Within a prediction scale (e.g., the next 6 hours), the time percentage for each level is calculated, resulting in "Excellent level percentage XX%, Medium level percentage YY%, Poor level percentage ZZ%". Simultaneously, the start and end times and durations of all communication interruption warning periods are listed. These two types of information combined constitute the final quality prediction result.

[0072] In one feasible implementation, after the step of determining the quality prediction result of the communication channel based on the prediction scale and the channel quality change curve, the method further includes: Obtain real-time monitored communication channel quality indicators, and calculate the error distribution between the communication channel quality indicators and the quality prediction results; Determine the time period in which the error distribution exceeds the threshold, and extract the atmospheric disturbance data anomaly features for the corresponding time period; The abnormal features are fed back to the deep learning model to update the weight parameters of the perturbation feature vector online; The channel quality change curve with narrowed confidence intervals is regenerated based on the updated model.

[0073] In its implementation, the system continuously receives real-time channel quality indicators during operation, compares them point by point with previously generated quality prediction results to obtain the error distribution, and locks the corresponding time period once the error exceeds a set threshold. It then backtracks to extract atmospheric disturbance anomaly features within that time period and immediately inputs these anomaly features into a deep learning model using incremental learning, fine-tuning the weight parameters of the disturbance feature vector online. After the model is updated, the signal-to-noise ratio sequence is re-derived, and its confidence interval is significantly narrowed because the parameters are closer to reality, thus forming a more accurate new channel quality change curve.

[0074] The intelligent prediction method for communication channels under atmospheric disturbances also includes: Based on the location and duration of the communication interruption warning period, a backup transmission strategy is preloaded into the satellite-to-ground link; When the instantaneous signal-to-noise ratio drops sharply, the modulation and coding scheme is dynamically switched based on the relative rate of change of channel capacity; During the communication interruption warning period, multi-path redundant transmission is triggered, specifically by diverting data to at least two independent channels, which are generated by orthogonality selection of disturbance feature vectors in the atmospheric layering model. The system matches the channel quality change curve with the execution results of the transmission strategy in real time, generates strategy optimization coefficients, and iteratively updates the backup transmission strategy.

[0075] In practical implementation, within the satellite-to-ground link, once a communication interruption warning period is locked, the system immediately writes the start and end times and duration of that period into the link controller's policy table and preloads the corresponding backup transmission policy. When a sudden drop in the instantaneous signal-to-noise ratio is detected in real time, the controller adjusts the modulation and coding scheme online based on the current relative rate of change of channel capacity to ensure maximum spectral efficiency within the available signal-to-noise ratio range. After entering the warning period, the link layer triggers multi-path redundant transmission: data is dynamically diverted to two or more independent channels. These channels are generated by orthogonality determination of the disturbance feature vectors output by the atmospheric layering model, ensuring that the probability of them being affected by the same disturbance event is minimized. During transmission, the ground station continuously compares the real-time channel quality curve with the policy execution results, calculates policy optimization coefficients (such as redundancy gain, handover delay, and actual effective throughput), and iteratively updates the backup policy in real time, making the handover during the next round of interruption warnings smoother and resource utilization higher.

[0076] This embodiment provides an intelligent prediction method for communication channels under atmospheric disturbances. By acquiring atmospheric characteristic data and corresponding altitude information between the satellite and the ground station, the atmospheric characteristics corresponding to each altitude within this interval can be obtained. Different atmospheric characteristics cause different levels of interference to wireless communication. Therefore, after determining the atmospheric characteristics corresponding to different altitudes, the degree of interference to communication in each region can be naturally determined, i.e., atmospheric disturbance data at the corresponding altitude can be obtained. Thus, the altitude information and atmospheric disturbance data can be fused to obtain the impact of any point in this spatial domain between the satellite and the ground station on communication, and the resulting product is the atmospheric stratification model. However, when the satellite and ground station are determined, their communication channels are also determined. Therefore, in order to more accurately determine the channel quality, the corresponding channel interval can be separated from the atmospheric stratification model to determine the corresponding channel interval atmospheric model. Then, based on the prediction scale and the channel interval atmospheric model, an atmospheric change trend is generated to determine the change of disturbance data in the channel interval at future times or time periods, and a channel quality change curve is determined accordingly, thereby determining the channel quality prediction result. This achieves the effect of real-time prediction of communication channel performance in complex atmospheric environments.

[0077] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the intelligent prediction method for communication channels under atmospheric disturbances in this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0078] This application also provides a smart prediction device for communication channels under atmospheric disturbances. Please refer to [link / reference]. Figure 4 The intelligent prediction device for communication channels under atmospheric disturbances includes: Data acquisition module 10 is used to acquire atmospheric characteristic data and corresponding altitude information between the satellite and the ground, and to determine atmospheric disturbance data at the corresponding altitude based on the atmospheric characteristic data and the altitude information; The model generation module 20 is used to generate an atmospheric layering model by fusing the altitude information with the atmospheric disturbance data. The model partitioning module 30 is used to determine the communication channel interval between the satellite and the ground end, and to determine the corresponding channel interval atmospheric model in the atmospheric layering model according to the communication channel interval; The intelligent prediction module 40 is used to generate an atmospheric change trend based on the prediction scale and the channel interval atmospheric model, apply the communication channel parameters to the atmospheric change trend, generate a channel quality change curve, and determine the quality prediction result of the communication channel based on the prediction scale and the channel quality change curve.

[0079] In one feasible implementation, the data acquisition module 10 is also used to acquire atmospheric temperature, humidity, wind speed and turbulence intensity data at different altitudes between the satellite and the ground, as initial atmospheric characteristic data; Obtain the spatial distribution characteristics of each elevation point to form elevation correlation data; Multidimensional interpolation calculations are performed on the initial atmospheric characteristic data and the altitude-related data to determine the atmospheric disturbance coefficient at each altitude point; The atmospheric disturbance coefficients are mapped to corresponding altitudes to generate altitude-matched atmospheric disturbance data.

[0080] In one feasible implementation, the model generation module 20 is further used to segment the height information to divide it into multiple height intervals; For each altitude range, extract the corresponding atmospheric disturbance data and normalize the atmospheric disturbance data. The normalized data is input into a deep learning model to train and generate perturbation feature vectors in the height range; A hierarchical structure is constructed based on the disturbance feature vectors, and the disturbance feature vectors of each altitude range are superimposed to generate an atmospheric stratification model.

[0081] In one feasible implementation, the model partitioning module 30 is further configured to partition communication channel intervals based on the communication frequency band and signal propagation path between the satellite and the ground terminal; Locate the spatial region covered by the communication channel interval in the atmospheric layering model; Extract the disturbance feature vector within the spatial region and project the disturbance feature vector onto the frequency domain space of the communication channel interval to obtain the projection result; An atmospheric model for the channel interval is generated based on the projection results.

[0082] In one feasible implementation, the intelligent prediction module 40 is further configured to set a prediction time window according to the prediction scale, and divide the time series data of the channel interval atmospheric model into multiple sub-intervals based on the prediction time window. Perform time-series analysis on the disturbance feature vectors within each sub-interval to extract the variation patterns of the disturbance feature vectors within the sub-intervals; The changes were modeled using a convolutional neural network to generate a temporal evolution trend of atmospheric disturbances. By combining the temporal evolution trend of the atmospheric disturbance with atmospheric characteristics, an atmospheric change trend is generated.

[0083] In one feasible implementation, the intelligent prediction module 40 is further configured to map the communication channel parameters to a channel transfer function, perform matrix multiplication on the disturbance intensity in the atmospheric change trend, and generate a channel attenuation factor. Using the prediction time window as the step size, the channel attenuation factor is cumulatively integrated to output the instantaneous signal-to-noise ratio sequence; The temporal distribution of the instantaneous signal-to-noise ratio sequence is fitted to generate a signal quality change curve with confidence intervals, where the horizontal axis represents the time scale and the vertical axis represents the relative rate of change of channel capacity.

[0084] In one feasible implementation, the intelligent prediction module 40 is further configured to determine the three-level status based on the fluctuation range of the instantaneous signal-to-noise ratio sequence in the channel quality change curve and the instantaneous signal-to-noise ratio. Identify the steep drop point and duration of the instantaneous signal-to-noise ratio in the channel quality change curve, and mark the time period corresponding to the steep drop point and duration as the communication interruption warning period; Calculate the time percentage of each level of state within the prediction scale, and generate quality prediction results for the communication interruption warning period.

[0085] In one feasible implementation, the intelligent prediction module 40 is further configured to acquire real-time monitored communication channel quality indicators and calculate the error distribution between the communication channel quality indicators and the quality prediction results. Determine the time period in which the error distribution exceeds the threshold, and extract the atmospheric disturbance data anomaly features for the corresponding time period; The abnormal features are fed back to the deep learning model to update the weight parameters of the perturbation feature vector online; The channel quality change curve with narrowed confidence intervals is regenerated based on the updated model.

[0086] In one feasible implementation, the intelligent prediction module 40 is further configured to preload a backup transmission strategy in the satellite-to-ground link based on the location and duration of the communication interruption warning period. When the instantaneous signal-to-noise ratio drops sharply, the modulation and coding scheme is dynamically switched based on the relative rate of change of channel capacity; During the communication interruption warning period, multi-path redundant transmission is triggered, specifically by diverting data to at least two independent channels, which are generated by orthogonality selection of disturbance feature vectors in the atmospheric layering model. The system matches the channel quality change curve with the execution results of the transmission strategy in real time, generates strategy optimization coefficients, and iteratively updates the backup transmission strategy.

[0087] The intelligent prediction device for communication channels under atmospheric disturbances provided in this application employs the intelligent prediction method for communication channels under atmospheric disturbances described in the above embodiments, which can solve the technical problem of being unable to perform real-time prediction and dynamic compensation of communication channel performance under complex atmospheric environments. Compared with the prior art, the beneficial effects of the intelligent prediction device for communication channels under atmospheric disturbances provided in this application are the same as those of the intelligent prediction method for communication channels under atmospheric disturbances provided in the above embodiments, and other technical features in the intelligent prediction device for communication channels under atmospheric disturbances are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0088] This application provides a communication channel intelligent prediction device under atmospheric disturbance. The communication channel intelligent prediction device under atmospheric disturbance includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the communication channel intelligent prediction method under atmospheric disturbance in the above embodiment 1.

[0089] The following is for reference. Figure 5This document illustrates a structural schematic diagram of a communication channel intelligent prediction device suitable for implementing embodiments of this application under atmospheric disturbances. The communication channel intelligent prediction device under atmospheric disturbances in embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The intelligent prediction device for communication channels under atmospheric disturbances shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0090] like Figure 5 As shown, the intelligent prediction device for communication channels under atmospheric disturbances may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in ROM (Read Only Memory) 1002 or a program loaded from storage device 1003 into RAM (Random Access Memory) 1004. RAM 1004 also stores various programs and data required for the operation of the intelligent prediction device for communication channels under atmospheric disturbances. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via bus 1005. Input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, LCDs (Liquid Crystal Displays), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the intelligent prediction device for communication channels under atmospheric disturbances to exchange data wirelessly or via wired communication with other devices. Although the figure shows an intelligent prediction device for communication channels under atmospheric disturbances with various systems, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems can be implemented alternatively.

[0091] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0092] The intelligent prediction device for communication channels under atmospheric disturbances provided in this application employs the intelligent prediction method for communication channels under atmospheric disturbances described in the above embodiments, and can solve the technical problem of intelligent prediction of communication channels under atmospheric disturbances. Compared with the prior art, the beneficial effects of the intelligent prediction device for communication channels under atmospheric disturbances provided in this application are the same as the beneficial effects of the intelligent prediction method for communication channels under atmospheric disturbances provided in the above embodiments, and other technical features of the intelligent prediction device for communication channels under atmospheric disturbances are the same as those disclosed in the method of the previous embodiment, and will not be repeated here.

[0093] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0094] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0095] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the intelligent prediction method for communication channels under atmospheric disturbances in the above embodiments.

[0096] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable Read Only Memory or Flash Memory), optical fibers, CD-ROM (CD-Read Only Memory), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0097] The aforementioned computer-readable storage medium may be included in the intelligent prediction device for communication channels under atmospheric disturbances; or it may exist independently and not assembled into the intelligent prediction device for communication channels under atmospheric disturbances.

[0098] The aforementioned computer-readable storage medium carries one or more programs. When these programs are executed by the intelligent prediction device for communication channels under atmospheric disturbances, the intelligent prediction device for communication channels under atmospheric disturbances: acquires atmospheric characteristic data and corresponding altitude information between the satellite and the ground terminal; determines atmospheric disturbance data at the corresponding altitude based on the atmospheric characteristic data and the altitude information; fuses the altitude information with the atmospheric disturbance data to generate an atmospheric stratification model; determines the communication channel interval between the satellite and the ground terminal, and determines the corresponding channel interval atmospheric model in the atmospheric stratification model according to the communication channel interval; generates an atmospheric change trend based on the prediction scale and the channel interval atmospheric model; applies the communication channel parameters to the atmospheric change trend to generate a channel quality change curve; and determines the communication channel quality prediction result based on the prediction scale and the channel quality change curve.

[0099] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including LAN (Local Area Network) or WAN (Wide Area Network)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0100] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0101] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0102] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described intelligent prediction method for communication channels under atmospheric disturbances, thereby solving the technical problem of intelligent prediction of communication channels under atmospheric disturbances. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the intelligent prediction method for communication channels under atmospheric disturbances provided in the above embodiments, and will not be repeated here.

[0103] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the intelligent prediction method for communication channels under atmospheric disturbances as described above.

[0104] The computer program product provided in this application can solve the technical problem of intelligent prediction of communication channels under atmospheric disturbances. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the intelligent prediction method of communication channels under atmospheric disturbances provided in the above embodiments, and will not be repeated here.

[0105] The above are only some embodiments of this application and do not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A method for intelligent prediction of communication channels under atmospheric disturbances, characterized in that, The intelligent prediction method for communication channels under atmospheric disturbances includes: Acquire atmospheric characteristic data and corresponding altitude information between the satellite and the ground, and determine atmospheric disturbance data at the corresponding altitude based on the atmospheric characteristic data and the altitude information; Based on the altitude information, it is fused with the atmospheric disturbance data to generate an atmospheric stratification model; Determine the communication channel interval between the satellite and the ground terminal, and determine the corresponding channel interval atmospheric model in the atmospheric layering model based on the communication channel interval; Based on the prediction scale and the atmospheric model of the channel interval, an atmospheric change trend is generated. The communication channel parameters are applied to the atmospheric change trend to generate a channel quality change curve. Based on the prediction scale and the channel quality change curve, the quality prediction result of the communication channel is determined.

2. The method as described in claim 1, characterized in that, The step of acquiring atmospheric characteristic data and corresponding altitude information between the satellite and the ground, and determining atmospheric disturbance data at the corresponding altitude based on the atmospheric characteristic data and the altitude information, includes: Data on atmospheric temperature, humidity, wind speed, and turbulence intensity at different altitudes between the satellite and the ground are collected as initial atmospheric characteristic data. Obtain the spatial distribution characteristics of each elevation point to form elevation correlation data; Multidimensional interpolation calculations are performed on the initial atmospheric characteristic data and the altitude-related data to determine the atmospheric disturbance coefficient at each altitude point; The atmospheric disturbance coefficients are mapped to corresponding altitudes to generate altitude-matched atmospheric disturbance data.

3. The method as described in claim 1, characterized in that, The step of fusing the altitude information with the atmospheric disturbance data to generate an atmospheric layering model includes: The height information is segmented to divide it into multiple height intervals; For each altitude range, extract the corresponding atmospheric disturbance data and normalize the atmospheric disturbance data. The normalized data is input into a deep learning model to train and generate perturbation feature vectors in the height range; A hierarchical structure is constructed based on the disturbance feature vectors, and the disturbance feature vectors of each altitude range are superimposed to generate an atmospheric stratification model.

4. The method as described in claim 1, characterized in that, The steps of determining the communication channel interval between the satellite and the ground terminal, and determining the corresponding channel interval atmospheric model in the atmospheric layering model based on the communication channel interval, include: Based on the communication frequency band and signal propagation path between the satellite and the ground terminal, the communication channel interval is divided; Locate the spatial region covered by the communication channel interval in the atmospheric layering model; Extract the disturbance feature vector within the spatial region and project the disturbance feature vector onto the frequency domain space of the communication channel interval to obtain the projection result; An atmospheric model for the channel interval is generated based on the projection results.

5. The method as described in claim 1, characterized in that, The steps for generating atmospheric change trends based on the prediction scale and the channel interval atmospheric model include: A prediction time window is set according to the prediction scale, and the time series data of the channel interval atmospheric model is divided into multiple sub-intervals based on the prediction time window. Perform time-series analysis on the disturbance feature vectors within each sub-interval to extract the variation patterns of the disturbance feature vectors within the sub-intervals; The changes were modeled using a convolutional neural network to generate a temporal evolution trend of atmospheric disturbances. By combining the temporal evolution trend of the atmospheric disturbance with atmospheric characteristics, an atmospheric change trend is generated.

6. The method as described in claim 1, characterized in that, The step of applying the communication channel parameters to the atmospheric change trend to generate a channel quality change curve includes: The communication channel parameters are mapped to the channel transmission function, and the disturbance intensity in the atmospheric change trend is multiplied by matrix to generate the channel attenuation factor. Using the prediction time window as the step size, the channel attenuation factor is cumulatively integrated to output the instantaneous signal-to-noise ratio sequence; The temporal distribution of the instantaneous signal-to-noise ratio sequence is fitted to generate a signal quality change curve with confidence intervals, where the horizontal axis represents the time scale and the vertical axis represents the relative rate of change of channel capacity.

7. The method as described in claim 1, characterized in that, The step of determining the quality prediction result of the communication channel based on the prediction scale and the channel quality change curve includes: The three-level status is determined based on the fluctuation range of the instantaneous signal-to-noise ratio sequence in the channel quality change curve and the instantaneous signal-to-noise ratio. Identify the steep drop point and duration of the instantaneous signal-to-noise ratio in the channel quality change curve, and mark the time period corresponding to the steep drop point and duration as the communication interruption warning period; Calculate the time percentage of each level of state within the prediction scale, and generate quality prediction results for the communication interruption warning period.

8. The method as described in claim 1, characterized in that, After the step of determining the quality prediction result of the communication channel based on the prediction scale and the channel quality change curve, the method further includes: Obtain real-time monitored communication channel quality indicators, and calculate the error distribution between the communication channel quality indicators and the quality prediction results; Determine the time period in which the error distribution exceeds the threshold, and extract the atmospheric disturbance data anomaly features for the corresponding time period; The abnormal features are fed back to the deep learning model to update the weight parameters of the perturbation feature vector online; The channel quality change curve with narrowed confidence intervals is regenerated based on the updated model.

9. The method according to any one of claims 1 to 8, characterized in that, The intelligent prediction method for communication channels under atmospheric disturbances also includes: Based on the location and duration of the communication interruption warning period, a backup transmission strategy is preloaded into the satellite-to-ground link; When the instantaneous signal-to-noise ratio drops sharply, the modulation and coding scheme is dynamically switched based on the relative rate of change of channel capacity; During the communication interruption warning period, multi-path redundant transmission is triggered, specifically by diverting data to at least two independent channels, which are generated by orthogonality selection of disturbance feature vectors in the atmospheric layering model. The system matches the channel quality change curve with the execution results of the transmission strategy in real time, generates strategy optimization coefficients, and iteratively updates the backup transmission strategy.

10. A smart prediction device for communication channels under atmospheric disturbances, characterized in that, The intelligent prediction device for communication channels under atmospheric disturbances includes: The data acquisition module is used to acquire atmospheric characteristic data and corresponding altitude information between the satellite and the ground, and to determine atmospheric disturbance data at the corresponding altitude based on the atmospheric characteristic data and the altitude information. The model generation module is used to fuse the altitude information with the atmospheric disturbance data to generate an atmospheric stratification model. The model segmentation module is used to determine the communication channel interval between the satellite and the ground terminal, and to determine the corresponding channel interval atmospheric model in the atmospheric layering model based on the communication channel interval; The intelligent prediction module is used to generate an atmospheric change trend based on the prediction scale and the channel interval atmospheric model, apply the communication channel parameters to the atmospheric change trend to generate a channel quality change curve, and determine the quality prediction result of the communication channel based on the prediction scale and the channel quality change curve.

Images