Satellite service traffic prediction method and device

Abstract

The invention relates to the technical field of satellites, in particular to a satellite service traffic prediction method and device. The method comprises the following steps: acquiring geographic feature data of a wave position; acquiring coverage time data of the satellite for the wave position in a historical time period; constructing first feature data of the satellite according to the geographic feature data and the coverage time data; the first feature data is used for representing geographic features accumulated and covered by the satellite in the historical time period; acquiring second feature data, wherein the second feature data is used for representing the service traffic of the satellite in the historical time period; and predicting the future service flow of the satellite according to the first feature data and the second feature data. The embodiment of the invention can improve the prediction accuracy.

Description

Technical Field

[0001] This specification relates to the field of satellite technology, and in particular to a method and device for predicting satellite service traffic. Background Art

[0002] With the rapid advancement of aerospace and communications technologies, satellite internet has become a crucial component of integrated space-space-ground networks. Widely used in military, aerospace, communications, meteorology, and other fields, satellite internet provides critical support for remote sensing data transmission, emergency communications, and global coverage. Forecasting satellite internet traffic can help optimize satellite network performance, resource allocation, and security management. Therefore, satellite traffic forecasting is essential.

[0003] Related technologies often use the same approach to predicting terrestrial network traffic to predict satellite traffic. For example, machine learning algorithms are used to predict satellite traffic based directly on historical traffic data.

[0004] However, due to the highly dynamic nature of satellite motion, satellite internet services and traffic characteristics differ significantly from terrestrial networks. Compared to terrestrial networks, satellite internet traffic exhibits more complex temporal and spatial characteristics and fluctuations. The aforementioned technologies are unable to accurately predict satellite traffic. Summary of the Invention

[0005] The embodiments of this specification provide a method and apparatus for predicting satellite service traffic to improve the accuracy of prediction.

[0006] According to a first aspect of an embodiment of this specification, a satellite service flow prediction method is provided, comprising:

[0007] Obtain geographical feature data of wave positions;

[0008] Obtaining coverage time data of the satellite for the wave position in a historical period;

[0009] Constructing first feature data of the satellite based on the geographic feature data and the coverage time data; the first feature data is used to represent the geographic features cumulatively covered by the satellite during the historical period;

[0010] Acquire second characteristic data, where the second characteristic data is used to represent the service flow of the satellite during the historical period;

[0011] The future service traffic of the satellite is predicted based on the first characteristic data and the second characteristic data.

[0012] According to a second aspect of the embodiments of this specification, a satellite service flow prediction device is provided, comprising:

[0013] A first acquisition unit is used to acquire geographic feature data of wave positions;

[0014] A second acquiring unit is configured to acquire coverage time data of the satellite for the wave position in a historical period;

[0015] A construction unit, configured to construct first characteristic data of the satellite based on the geographic characteristic data and the coverage time data; the first characteristic data is used to represent the geographic characteristics cumulatively covered by the satellite during the historical period;

[0016] a third acquiring unit, configured to acquire second characteristic data, where the second characteristic data is used to represent the service flow of the satellite during the historical period;

[0017] A prediction unit is used to predict the future service traffic of the satellite based on the first characteristic data and the second characteristic data.

[0018] The technical solutions of the embodiments of this specification, in response to the highly dynamic nature of satellite movement, can construct the first characteristic data of the satellite based on the geographic feature data of the wave position and the coverage time data of the wave position during the satellite movement. The first characteristic data is used to represent the geographical features cumulatively covered by the satellite during a historical period. In addition, the second characteristic data of the satellite can also be obtained. The second characteristic data is used to represent the service traffic of the satellite during a historical period. The future service traffic of the satellite can be predicted based on the first characteristic data and the second characteristic data. Therefore, in response to the highly dynamic nature of satellite movement, the embodiments of this specification predict the future service traffic of the satellite by integrating the geographical features covered during the satellite movement and the characteristics of the carried service traffic. This greatly improves the accuracy and prediction effect of satellite Internet traffic prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. The drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0020] Figure 1 Schematic diagram of the flow of satellite service flow prediction method in the embodiment of this specification;

[0021] Figure 2 A schematic diagram of the wave positions covered by satellites in a historical period in an embodiment of this specification;

[0022] Figure 3Schematic diagram of the construction process of the time series matrix in the embodiment of this specification;

[0023] Figure 4 A schematic diagram of a time series matrix in an embodiment of this specification;

[0024] Figure 5 Schematic diagram of the functional structure of the satellite service flow prediction device in the embodiment of this specification. DETAILED DESCRIPTION

[0025] The technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of this specification, rather than all of the embodiments. The specific embodiments described here are only used to explain the present disclosure, rather than to limit the present disclosure. Based on the described embodiments of the present disclosure, all other embodiments obtained by those of ordinary skill in the art fall within the scope of protection of the present disclosure. In addition, relational terms such as "first" and "second" are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0026] The present invention provides a satellite traffic flow prediction method. The method can be applied to computer devices such as portable computers, desktop computers, and servers. Figure 1 The method may include the following steps.

[0027] Step 11: Obtain the geographic feature data of the wave position.

[0028] Step 12: Obtain the satellite's coverage time data for the wave position during the historical period.

[0029] Step 13: Construct first characteristic data of the satellite based on the geographic characteristic data and the coverage time data; the first characteristic data is used to represent the geographic characteristics accumulated by the satellite in the historical period.

[0030] Step 14: Acquire second characteristic data, where the second characteristic data is used to represent the service traffic of the satellite in a historical period.

[0031] Step 15: Predict the future service traffic of the satellite based on the first characteristic data and the second characteristic data.

[0032] In some embodiments, there are one or more satellites. Each satellite has a corresponding satellite identifier. The satellite identifier is used to identify the satellite. The one or more satellites may include low Earth orbit (LEO) satellites, medium Earth orbit (MEO) satellites, or any combination thereof. Low Earth orbit and medium Earth orbit satellites move relative to the Earth during their orbital motion. Due to the highly dynamic nature of satellite motion, the spatiotemporal characteristics and volatility of satellite internet traffic are more complex. Therefore, using the same approach to predicting terrestrial network traffic, the accuracy of satellite service traffic prediction is low. In embodiments of this specification, first satellite feature data can be constructed based on the geographic feature data of the satellite and the time data of the satellite's coverage of the satellite during its motion. This first feature data represents the cumulative geographic features covered by the satellite over a historical period. In addition, second satellite feature data can be obtained. This second feature data represents the service traffic of the satellite over a historical period. Future satellite service traffic can be predicted based on the first and second feature data. Therefore, to address the highly dynamic nature of satellite motion, embodiments of this specification predict future satellite service traffic by integrating the geographic features covered during satellite motion and the characteristics of the service traffic carried. This will greatly improve the accuracy and prediction effect of satellite Internet traffic prediction.

[0033] In some embodiments, see Figure 2 . A wavelet, also known as a ground wavelet, refers to a geographical unit with a specific geographical range and communication characteristics divided according to factors such as business requirements and beam characteristics. A wavelet is a spatial unit for satellite resource allocation and business scheduling. By dividing the preset geographical range, one or more wavelets can be obtained. Each wavelet corresponds to a wavelet identifier. The wavelet identifier is used to identify the wavelet. The satellite forms a signal coverage area on the ground through the beam. The beam coverage area includes one or more wavelets. The periodic motion of the satellite in orbit causes the wavelets covered by the satellite to change.

[0034] In some embodiments, satellite services are strongly correlated with geographic location. To this end, beamline planning data can be obtained. This beamline planning data includes geographic feature data for one or more beamlines. Geographic feature data represents the geographic characteristics of the beamline. The geographic feature data for a beamline can include indicator data for one or more geographic features. Geographic features can include landform types and specific services. Landform types can include one or more of oceanic, desert, urban, and forest landforms. Indicators for landform types can include landform area. For example, telemetry data can be used to calculate the surface area corresponding to each landform type using methods such as the Normalized Difference Water Index (NDWI) and the Normalized Difference Vegetation Index (NDVI). Specific services can include key services. Key services are core services that require priority communication continuity and stability during satellite operation, such as forest fire prevention, maritime search and rescue, and earthquake emergency command. Indicators for specific services can include the number of specific services, such as the number of key services.

[0035] For example, the preset geographical range can be divided into W1, W2, ..., W i 、......、W w There are w wave positions. w is an integer greater than or equal to 0. Each wave position (for example, wave position W i ) can include geographic feature data A. Geographic feature data A can include five data elements: a1, a2, a3, a4, and a5. a1 represents the area of ​​oceanic landforms, a2 represents the area of ​​desert and Gobi landforms, a3 represents the area of ​​urban landforms, a4 represents the area of ​​forest landforms, and a5 represents the number of key security services.

[0036] In some embodiments, the duration of a historical period can be, for example, 5 minutes, 6 minutes, 30 minutes, etc. There can be one or more historical periods. The duration of the one or more historical periods can be the same or different. Each historical period can be understood as a statistical cycle used to collect statistical data on the satellite's characteristics within that historical period, such as the satellite's first characteristic data, second characteristic data, etc. The multiple historical periods can be continuous. For example, the historical time interval before a certain moment can be divided into multiple continuous historical periods. Based on the characteristic data of the satellite in these multiple historical periods, the future traffic flow of the satellite after that moment can be predicted. For example, the historical time interval is 15 days. The duration of a historical period can be 5 minutes. The historical time interval can be divided into 4320 continuous historical periods. Based on the characteristic data of these 4320 historical periods, the traffic flow of the satellite in 864 periods within the next three days can be predicted.

[0037] In some embodiments, coverage time data for each satellite during each historical period can be obtained. A satellite can cover one or more beamspots during a historical period. Coverage time data includes the percentage of the satellite's coverage duration for each beamspot. Coverage duration percentage includes the ratio of the satellite's coverage duration for the beamspot during the historical period to the duration of the historical period. Coverage duration includes the duration of the satellite's presence at the beamspot. Coverage duration percentage can indicate the intensity of the satellite's resource allocation to the beamspot.

[0038] For each satellite, the satellite's coverage duration for one or more beam positions during each historical period can be obtained. The coverage duration for each beam position can be divided by the duration of the historical period to obtain the coverage duration percentage for the beam position. The satellite's coverage time data for the historical period can include the coverage duration percentage of the one or more beam positions.

[0039] Each satellite can cover one or more of the planned wave positions in a historical period, and the duration of the satellite's presence in the one or more wave positions can be the same or different. To this end, as an example, for each satellite, the one or more wave positions covered by the satellite in each historical period can be determined; the coverage duration of each wave position can be divided by the duration of the historical period to obtain the coverage duration ratio of the wave position. The coverage time data of the satellite in the historical period includes the coverage duration ratio of the one or more wave positions. As another example, for each satellite, the coverage duration of the satellite for all planned wave positions in each historical period can be obtained; the coverage duration of each wave position can be divided by the duration of the historical period to obtain the coverage duration ratio of the wave position. The coverage time data of the satellite in the historical period can include the coverage duration ratio of all planned wave positions. Among all planned wave positions, for the wave positions covered by the satellite, the coverage duration of the satellite for the wave position can be obtained; for the wave positions not covered by the satellite, the coverage duration of the wave position is 0.

[0040] In some scenario examples, the satellites to be predicted include S1, S2, ..., S i 、......、S s There are s satellites. All planned wave positions include W1, W2, ..., W i 、......、W w There are w wave positions. The historical periods include T1, T2, ..., T i 、......、T t Wait for t historical periods. You can get satellite S i In the historical period T i For each of the w wave positions, the coverage time of the wave position can be compared with the historical period T i Divide the duration of the satellite S to get the coverage duration ratio of the wave position. i In the historical period T i The coverage time data includes the coverage time ratio of the w wave positions.

[0041] Optionally, a matrix SWS can also be constructed. The matrix SWS represents the coverage time data of s satellites in t historical periods. The dimensions of the matrix SWS can be expressed as (s, t, w). w represents the number of wave bits. The data elements SWS in the matrix SWS are ijk Satellite S i In the historical period T j The inner relative wave position W k The coverage duration ratio is 1≤i≤s, 1≤j≤t, 1≤k≤w.

[0042] In some embodiments, first characteristic data can be obtained for each satellite in each historical period. A satellite can cover one or more locations in a historical period. These one or more locations can correspond to geographic feature data. The first characteristic data can include the geographic features cumulatively covered by the satellite in the historical period. The geographic feature data for a location can include index data for one or more geographic features. The first characteristic data can include the accumulated index data for the satellite for one or more geographic features. The accumulated index data can represent the actual accumulated index data for the geographic features as the satellite moves during the statistical period. The coverage duration ratio can represent the intensity of the satellite's resource allocation to the location. Therefore, the resource allocation intensity can be used as a weight to calculate the actual accumulated index data for various geographic features during the satellite's movement to obtain accumulated index data for each geographic feature. Furthermore, the first characteristic data of a satellite in multiple historical periods can also represent the dynamic changes in the geographic features of the locations covered by the satellite during its movement. For example, it can represent the dynamic changes in one or more geographic features of the locations covered by the satellite.

[0043] For each satellite, the satellite's coverage time data for each historical period can be obtained. The satellite's coverage time data for this historical period includes the coverage duration percentage of one or more wavebands. The index data for each waveband under each geographic feature is multiplied by the coverage duration percentage of the waveband to obtain the product corresponding to the geographic feature for the waveband. The products corresponding to the same geographic feature for the one or more wavebands are added together to obtain the cumulative index data for the geographic feature. The first feature data for the satellite during this historical period may include the cumulative index data for one or more geographic features.

[0044] In some example scenarios, satellite S i In the historical period T i The coverage time data includes the coverage time ratio of w wave positions. Each wave position (for example, wave position W i) can include geographic feature data such as a1, a2, a3, a4, and a5. a1 represents the area of ​​oceanic landforms, a2 represents the area of ​​desert and Gobi landforms, a3 represents the area of ​​urban landforms, a4 represents the area of ​​forest landforms, and a5 represents the number of key services. For each of the w wave positions, a1 for that wave position can be multiplied by the coverage time percentage of that wave position to obtain the product corresponding to a1; a2 for that wave position can be multiplied by the coverage time percentage of that wave position to obtain the product corresponding to a2; a3 for that wave position can be multiplied by the coverage time percentage of that wave position to obtain the product corresponding to a3; a4 for that wave position can be multiplied by the coverage time percentage of that wave position to obtain the product corresponding to a4; and a5 for that wave position can be multiplied by the coverage time percentage of that wave position to obtain the product corresponding to a5. The products of w wave positions corresponding to a1 can be added together to obtain the cumulative index data corresponding to a1 (cumulative ocean landform area); the products of w wave positions corresponding to a2 can be added together to obtain the cumulative index data corresponding to a2 (cumulative desert Gobi landform area); the products of w wave positions corresponding to a3 can be added together to obtain the cumulative index data corresponding to a3 (cumulative urban landform area); the products of w wave positions corresponding to a4 can be added together to obtain the cumulative index data corresponding to a4 (cumulative forest landform area); the products of w wave positions corresponding to a5 can be added together to obtain the cumulative index data corresponding to a5 (cumulative number of key security services). Satellite S i In the historical period T i The first characteristic data may include the cumulative marine landform area, the cumulative desert Gobi landform area, the cumulative urban landform area, the cumulative forest landform area, and the cumulative number of key security services. Among them, the cumulative marine landform area can represent the cumulative marine landform area in the historical period T i Inside, with satellite S i The movement of the actual cumulative coverage of marine landforms. The cumulative desert Gobi landform area can be characterized in the historical period T i Inside, with satellite S i The movement of the actual cumulative coverage of desert Gobi landforms. The cumulative urban landform area can be characterized in the historical period T i Inside, with satellite S i The movement of the actual cumulative urban landform area. The cumulative forest landform area can be characterized in the historical period T i Inside, with satellite S i The actual cumulative forest landform area covered by the movement. The cumulative number of key protection operations can be characterized in the historical period T i Inside, with satellite S i The actual cumulative number of key support services. iThe first characteristic data in t historical periods can also characterize the dynamic changes of various geographical features of the wave positions covered by the satellite during its movement.

[0045] Optionally, a matrix SW can also be constructed. The matrix SW represents the geographic feature data of w wave positions. The dimension of the matrix SW can be expressed as (w, a). a represents the number of types of geographic features, for example, 5. The data elements SW in the matrix SW are km For wave position W k Indicator data for geographic feature m. 1≤k≤w, 1≤m≤a.

[0046] The matrix SW can be multiplied by the matrix SWS to obtain the matrix GFT. The matrix GFT represents the first characteristic data of s satellites in t historical periods. The dimension of the matrix GFT can be expressed as (s, t, a). The data elements GFT in the matrix GFT are ijm Satellite S i In the historical period T j Cumulative indicator data under the intrinsic geographical feature m. .

[0047] In some embodiments, second characteristic data can be obtained for each satellite during each historical period. This second characteristic data is used to represent the service traffic of the satellite during the historical period. The second characteristic data of a satellite over multiple historical periods can also characterize the dynamic changes in service traffic of one or more service types during the satellite's motion.

[0048] Based on an analysis of traffic service application characteristics, the internet services to which the traffic belongs can be categorized to obtain one or more service types for satellite internet services. Service types can include one or more of broadband access, mobile communications, emergency communications, professional applications, and narrowband access. Broadband access can include enterprise private networks and mobile broadband. Mobile communications can include voice services and SMS services. Emergency communications can include emergency rescue services. Professional applications can include remote sensing mapping, environmental monitoring, and meteorological monitoring. Narrowband access can include Internet of Things services. The second characteristic data can then include first traffic data for one or more service types.

[0049] Optionally, a matrix FL can be constructed. The matrix FL represents the second characteristic data of s satellites in t historical periods. The dimension of the matrix FL can be expressed as (s, t, b). b represents the number of service types. The data elements FL in the matrix FL are ijn Satellite S i In the historical period T j The first traffic data of intrinsic service type n. 1≤i≤s, 1≤j≤t, 1≤n≤b.

[0050] In some embodiments, future satellite traffic volume can be predicted based on first and second feature data. The first feature data represents the geographic features covered by the satellite over a historical period. The second feature data represents the satellite's traffic volume over that period. This allows for a comprehensive forecast of future satellite traffic volume by combining geographic and traffic volume characteristics. This significantly improves the accuracy and effectiveness of satellite internet traffic forecasts.

[0051] In some embodiments, a machine learning model can be used to predict the future business traffic of the satellite. The machine learning model can be trained using sample data to obtain a trained machine learning model. The trained machine learning model can be used to predict the future business traffic of the satellite. The machine learning model may include a time series model. A time series model is a machine learning model used to analyze and predict time series data. A time series model can explore the changing patterns of data in the time dimension and infer future data based on these patterns. Time series models may include ARIMA models, LSTM models, Informer models, etc. Among them, the Informer model is a machine learning model for efficient time series prediction. By improving the self-attention mechanism, the Informer model can effectively process long time series data, overcoming the problems of high computational complexity and poor performance of traditional methods when processing long series.

[0052] The first feature data and the second feature data can be input into a machine learning model to obtain an output of the machine learning model. The output of the machine learning model may include the service traffic of the satellite in one or more future time periods. The duration of each future time period may be the same or different. The service traffic of each future time period may include multiple first traffic data of a satellite. Each first traffic data corresponds to a service type. Alternatively, the service traffic of each future time period may also include second traffic data of a satellite. The second traffic data may include the sum of the first traffic data of multiple service types.

[0053] As an example, the first and second feature data of a satellite over a historical period can be input into a machine learning model to obtain the output of the machine learning model. The output of the machine learning model may include the service traffic of the satellite over one or more future periods. The first and second feature data can be input into the machine learning model separately. Alternatively, the first and second feature data can be fused, and the fused feature data can be input into the machine learning model. Fusion methods may include concatenating the first and second feature data.

[0054] As another example, the first feature data and second feature data of a satellite over multiple historical time periods can be input into a machine learning model to obtain the output of the machine learning model. The output of the machine learning model may include the service traffic of the satellite over one or more future time periods. Specifically, time series data of the satellite can be constructed based on the first feature data and second feature data of multiple historical time periods; the time series data can be input into the machine learning model. For example, the first feature data and second feature data of each historical time period can be fused to obtain fused feature data for that historical time period; or the fused feature data of multiple historical time periods can be fused to obtain the time series data of the satellite. The fusion method can include splicing. For example, the first feature data and second feature data can be spliced; or the fused feature data of multiple historical time periods can be spliced. Of course, the first feature data and second feature data of multiple historical time periods can also be input into the machine learning model separately. Alternatively, the first feature data and second feature data of each historical time period can be fused; or the fused feature data of multiple historical time periods can be input into the machine learning model separately.

[0055] As another example, first feature data and second feature data for multiple satellites over a historical period can be input into a machine learning model to obtain an output of the machine learning model. The output of the machine learning model may include traffic flow for the multiple satellites over one or more future periods. For each satellite, traffic flow for one or more future periods can be output.

[0056] As another example, first feature data and second feature data for multiple satellites over multiple historical time periods can be input into a machine learning model to obtain an output of the machine learning model. The output of the machine learning model includes traffic flow for the multiple satellites over one or more future time periods. Each of the multiple satellites has first feature data and second feature data for multiple historical time periods. The machine learning model can output traffic flow for each satellite over one or more future time periods.

[0057] Satellite time series data can be constructed based on the first and second feature data of multiple satellites over multiple historical periods. This time series data can then be input into a machine learning model. For example, the first and second feature data of each satellite in each historical period can be fused to obtain sub-fused feature data for that satellite in that historical period. The sub-fused feature data of a satellite over multiple historical periods can be fused to obtain fused feature data for that satellite. The fused feature data of multiple satellites can also be fused to obtain time series data. Of course, the first and second feature data of multiple satellites over multiple historical periods can also be input into a machine learning model separately.

[0058] Alternatively, the matrix GFT and the matrix FL may be concatenated to obtain a concatenated matrix. The concatenated matrix can be interpreted as time series data. The concatenated matrix can be input into a machine learning model to obtain the output of the machine learning model.

[0059] In some embodiments, third characteristic data of a satellite can also be obtained. This third characteristic data represents the satellite's second traffic data over a historical period. The second traffic data comprises the sum of the first traffic data for each service type. The second characteristic data of a satellite over multiple historical periods can characterize the dynamic changes in the overall service traffic of the satellite during its motion.

[0060] Third characteristic data can be obtained for each satellite for each historical period. For example, second characteristic data can be obtained for each satellite for each historical period. The second characteristic data can include first traffic data for one or more service types. The first traffic data within the second characteristic data can be summed to obtain the second traffic data for the satellite for the historical period.

[0061] Optionally, a matrix Ff may be constructed. The matrix Ff represents the third characteristic data of s satellites in t historical periods. The dimension of the matrix Ff may be (s, t). The data elements Ff in the matrix Ff are ij Satellite S i In the historical period T j The second flow data within.

[0062] Based on the first, second, and third characteristic data, the satellite's future traffic volume can be predicted. This allows for a comprehensive analysis of geographic characteristics, traffic characteristics for each service type, and overall traffic volume to predict future satellite traffic volume. This further improves the accuracy and effectiveness of satellite Internet traffic predictions.

[0063] A machine learning model can be used to predict future satellite traffic. First feature data, second feature data, and third feature data can be input into the machine learning model to obtain an output from the machine learning model. The output of the machine learning model can include the satellite's traffic in one or more future time periods. The durations of each future time period can be the same or different. The traffic in each future time period can include multiple first traffic data sets for a satellite. Each first traffic data set corresponds to a service type. Alternatively, the traffic in each future time period can also include second traffic data sets for a satellite. The second traffic data sets can include the sum of the first traffic data sets for multiple service types.

[0064] As an example, the first, second, and third feature data of a satellite over a historical period can be input into a machine learning model to obtain the output of the machine learning model. The output of the machine learning model can include the traffic volume of the satellite over one or more future periods. The first, second, and third feature data can be input into the machine learning model separately. Alternatively, the first, second, and third feature data can be fused, and the fused feature data can be input into the machine learning model.

[0065] As another example, the first, second, and third feature data of a satellite over multiple historical time periods can be input into a machine learning model to obtain the output of the machine learning model. The output of the machine learning model may include the service traffic of the satellite over one or more future time periods. Here, time series data of the satellite can be constructed based on the first, second, and third feature data of multiple historical time periods; the time series data can be input into the machine learning model. For example, the first, second, and third feature data of each historical time period can be fused to obtain fused feature data for that historical time period; the fused feature data of multiple historical time periods can be fused to obtain the time series data of the satellite. Fusion methods may include splicing, etc.

[0066] As another example, first feature data, second feature data, and third feature data for multiple satellites over a historical period can be input into a machine learning model to obtain an output of the machine learning model. The output of the machine learning model can include traffic flow for the multiple satellites over one or more future periods. For each satellite, traffic flow for one or more future periods can be output.

[0067] As another example, first feature data, second feature data, and third feature data for multiple satellites over multiple historical time periods can be input into a machine learning model to obtain an output of the machine learning model. The output of the machine learning model includes traffic flow for the multiple satellites over one or more future time periods. Each of the multiple satellites has first feature data, second feature data, and third feature data for multiple historical time periods. The machine learning model can output traffic flow for each satellite over one or more future time periods.

[0068] Satellite time series data can be constructed based on the first, second, and third feature data of multiple satellites over multiple historical time periods. This time series data can then be input into a machine learning model. For example, the first, second, and third feature data of each satellite in each historical time period can be fused to obtain sub-fused feature data for that satellite in that historical time period. The sub-fused feature data of a satellite over multiple historical time periods can be fused to obtain fused feature data for that satellite. The fused feature data of multiple satellites can also be fused to obtain time series data. Fusion methods can include splicing. Of course, the first, second, and third feature data of multiple satellites over multiple historical time periods can also be input into the machine learning model separately.

[0069] Optionally, the matrix GFT, the matrix FL, and the matrix Ff can be concatenated to obtain a concatenated matrix. The concatenated matrix can be understood as time series data. The concatenated matrix can be input into a machine learning model.

[0070] In some embodiments, the fourth characteristic data of the satellite can also be obtained. The fourth characteristic data is used to represent the number of wave bits covered by the satellite in the historical period. The fourth characteristic data of the satellite in multiple historical periods can characterize the dynamic changes in the number of wave bits covered by the satellite during movement. The fourth characteristic data of each satellite in each historical period can be obtained. For example, for each satellite, one or more wave bits covered by the satellite in each historical period can be determined; the number of wave bits covered by the satellite in the historical period can be counted. Optionally, a matrix Fwn can be constructed. The matrix Fwn represents the fourth characteristic data of s satellites in t historical periods. The dimension of the matrix Fwn can be expressed as (s, t). The data element Fwn in the matrix Fwn ij Satellite S i In the historical period T j The number of wave positions covered.

[0071] Based on the first, second, and fourth characteristic data, the satellite's future service traffic can be predicted. This allows for a comprehensive analysis of geographic characteristics, traffic characteristics for each service type, and overall wavenumber characteristics to predict future satellite service traffic. This further improves the accuracy and effectiveness of satellite Internet traffic predictions.

[0072] A machine learning model can be used to predict future satellite traffic. The first feature data, second feature data, and fourth feature data can be input into the machine learning model to obtain an output of the machine learning model. The output of the machine learning model can include the satellite's traffic in one or more future time periods. The durations of each future time period can be the same or different. The traffic in each future time period can include multiple first traffic data for a satellite. Each first traffic data corresponds to a service type. Alternatively, the traffic in each future time period can also include second traffic data for a satellite. The second traffic data can include the sum of the first traffic data for multiple service types.

[0073] The process of making predictions based on the first feature data, the second feature data, and the fourth feature data is similar to the process of making predictions based on the first feature data, the second feature data, and the third feature data, and they can be referred to each other and will not be repeated.

[0074] In some embodiments, the first, second, third, and fourth characteristic data can be used to predict future satellite traffic. This allows for a comprehensive forecast of future satellite traffic by integrating geographic characteristics, traffic characteristics for each service type, overall traffic characteristics, and overall wavenumber characteristics. This further improves the accuracy and effectiveness of satellite Internet traffic forecasts.

[0075] A machine learning model can be used to predict future satellite traffic. First feature data, second feature data, third feature data, and fourth feature data can be input into the machine learning model to obtain an output from the machine learning model. The output of the machine learning model can include the satellite's traffic in one or more future time periods. The durations of each future time period can be the same or different. The traffic in each future time period can include multiple first traffic data for a satellite. Each first traffic data corresponds to a service type. Alternatively, the traffic in each future time period can also include second traffic data for a satellite. The second traffic data can include the sum of the first traffic data for multiple service types.

[0076] As an example, the first, second, third, and fourth feature data of a satellite over a historical period can be input into a machine learning model to obtain the output of the machine learning model. The output of the machine learning model includes the service traffic of the satellite over one or more future periods. The first, second, third, and fourth feature data can be input into the machine learning model separately. Alternatively, the first, second, third, and fourth feature data can be fused, and the fused feature data can be input into the machine learning model.

[0077] As another example, the first, second, third, and fourth feature data of a satellite over multiple historical time periods can be input into a machine learning model to obtain the output of the machine learning model. The output of the machine learning model includes the service traffic of the satellite over one or more future time periods. Time series data for the satellite can be constructed based on the first, second, third, and fourth feature data of the multiple historical time periods; the time series data can be input into the machine learning model. For example, the first, second, third, and fourth feature data of each historical time period can be fused to obtain fused feature data for that historical time period; and the fused feature data of multiple historical time periods can be fused to obtain time series data for the satellite.

[0078] As another example, first feature data, second feature data, third feature data, and fourth feature data for multiple satellites over a historical period can be input into a machine learning model to obtain an output of the machine learning model. The output of the machine learning model can include traffic flow for the multiple satellites over one or more future periods. Traffic flow for each satellite over one or more future periods can be output.

[0079] As another example, first feature data, second feature data, third feature data, and fourth feature data for multiple satellites over multiple historical time periods can be input into a machine learning model to obtain an output of the machine learning model. The output of the machine learning model can include traffic flow for the multiple satellites over one or more future time periods. Each of the multiple satellites has first feature data, second feature data, third feature data, and fourth feature data for multiple historical time periods. The machine learning model can output traffic flow for each satellite over one or more future time periods.

[0080] Satellite time series data can be constructed based on the first, second, third, and fourth feature data of multiple satellites over multiple historical time periods. This time series data can then be input into a machine learning model. For example, the first, second, third, and fourth feature data of each satellite over each historical time period can be fused to obtain sub-fused feature data for that satellite over that historical time period. The sub-fused feature data for a satellite over multiple historical time periods can be fused to obtain fused feature data for that satellite. The fused feature data of multiple satellites can also be fused to obtain time series data. Fusion methods can include splicing. Of course, the first, second, third, and fourth feature data of multiple satellites over multiple historical time periods can also be input into the machine learning model separately.

[0081] Optionally, see Figure 3. The matrix GFT, matrix FL, matrix Ff, and matrix Fwn can be concatenated to obtain matrix M. Matrix M can be time series data. Matrix M can be input into the machine learning model. The dimension of matrix GFT is (s, t, a). The dimension of matrix FL is (s, t, b). The dimension of matrix Ff is (s, t, 1). The dimension of matrix Fwn is (s, t, 1). Considering that matrix GFT, matrix FL, matrix Ff, and matrix Fwn all have satellite dimensions (dimensions corresponding to s) and historical period dimensions (dimensions corresponding to t), the geographic feature dimension of matrix GFT (dimensions corresponding to a), the service type dimension of matrix FL (dimensions corresponding to b), the service traffic dimension of matrix Ff (dimensions corresponding to 1), and the wave position dimension of matrix Fwn (dimensions corresponding to 1) can be concatenated to obtain matrix M. The dimension of matrix M can be expressed as (s, t, f). f=a+1+1+b. For example, the value of a can be 5, the value of b can be 5, and f=17. Please refer to Figure 4 The first dimension of matrix M (the dimension corresponding to s) represents satellites. The second dimension of matrix M (the dimension corresponding to t) represents historical time periods. The third dimension of matrix M (the dimension corresponding to f) represents satellite characteristics. Each data element in the third dimension represents a satellite characteristic for a historical time period. This satellite characteristic can be represented by the first, second, third, and fourth characteristic data of the satellite during that historical time period.

[0082] The embodiment of this specification also provides a satellite service flow prediction device. The device can be applied to computer equipment such as portable computers, desktop computers, servers, etc. Figure 5 The device may include the following units.

[0083] A first acquisition unit 51 is used to acquire geographic feature data of wave positions;

[0084] A second acquiring unit 52 is configured to acquire the coverage time data of the satellite for the wave position in a historical period;

[0085] A construction unit 53 is configured to construct first characteristic data of the satellite based on the geographic characteristic data and the coverage time data; the first characteristic data is used to represent the geographic characteristics cumulatively covered by the satellite during the historical period;

[0086] A third acquiring unit 54 is configured to acquire second characteristic data, where the second characteristic data is used to represent the service flow of the satellite during the historical period;

[0087] The prediction unit 55 is configured to predict the future service traffic of the satellite based on the first characteristic data and the second characteristic data.

[0088] An embodiment of this specification also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned satellite service traffic prediction method when executing the computer program.

[0089] The embodiments of this specification also provide a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned satellite service traffic prediction method is implemented.

[0090] The embodiments of this specification also provide a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the above-mentioned satellite service traffic prediction method.

[0091] Those skilled in the art will appreciate that this specification may be provided as a method, system, or computer program product. Thus, this specification may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0092] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products of the embodiments of this specification. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. The computer can be a personal computer, a laptop computer, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0093] The various functional units in the embodiments of this specification may be integrated into one processing unit, or each functional unit may exist physically separately, or two or more functional units may be integrated into one processing unit.

[0094] Those skilled in the art will understand that this specification describes each embodiment with different emphases. For portions not described in detail in a particular embodiment, reference can be made to the relevant descriptions of other embodiments. Furthermore, it is understood that after reading this specification, those skilled in the art may, without inventive effort, conceive of any combination of some or all of the embodiments listed in this specification, and such combinations are also within the scope of disclosure and protection of this specification.

[0095] Although this specification has been described through examples, those skilled in the art will appreciate that the above examples are merely intended to facilitate understanding of the core concepts of this specification. Those skilled in the art will appreciate that this specification is susceptible to numerous variations and modifications. It is intended that the appended claims encompass such variations and modifications without departing from the spirit of this specification.

Claims

1. A satellite traffic flow prediction method, characterized in that: include: Obtain geographical feature data of wave positions; Obtaining coverage time data of the satellite for the wave position in a historical period; Constructing first feature data of the satellite based on the geographic feature data and the coverage time data; the first feature data is used to represent the geographic features cumulatively covered by the satellite during the historical period; Acquire second characteristic data, where the second characteristic data is used to represent the service flow of the satellite during the historical period; The future service traffic of the satellite is predicted based on the first characteristic data and the second characteristic data.

2. The method according to claim 1, characterized in that The number of the wave positions is multiple; The geographical feature data includes index data of each wave position under multiple geographical features; The coverage time data includes the coverage time ratio of each wave position; The coverage duration ratio includes the ratio of the satellite's coverage duration for the wave position to the duration of the historical period.

3. The method according to claim 2, characterized in that The constructing the first characteristic data of the satellite includes: Multiply the multiple indicator data of each wave position by the coverage time ratio of the wave position; Add the products of multiple wave positions corresponding to the same geographical feature to obtain the cumulative index data of the geographical feature; The first characteristic data includes accumulated index data of the satellite under various geographical characteristics.

4. The method according to claim 1, wherein The method further comprises: determining one or more service types of the satellite's Internet service; The second characteristic data includes first traffic data of the satellite under various service types.

5. The method according to claim 4, characterized in that The method further comprises: Acquire third characteristic data of the satellite, where the third characteristic data is used to represent second traffic data of the satellite in the historical period, where the second traffic data includes the sum of first traffic data under various service types; The prediction of future service traffic of the satellite includes: The future service traffic of the satellite is predicted based on the first characteristic data, the second characteristic data and the third characteristic data.

6. The method according to claim 1, wherein The method further comprises: Acquire fourth characteristic data, where the fourth characteristic data is used to indicate the number of wave bits covered by the satellite during the historical period; The prediction of future service traffic of the satellite includes: The future service traffic of the satellite is predicted based on the first characteristic data, the second characteristic data and the fourth characteristic data.

7. The method according to claim 1, characterized in that The number of the historical periods is multiple; The prediction of future service traffic of the satellite includes: constructing time series data based on first feature data and second feature data of multiple historical periods; Inputting the time series data into a time series model to obtain an output of the time series model; The output of the time series model includes the traffic flow of the satellite in one or more future time periods.

8. The method according to claim 7, characterized in that The number of the satellites is multiple; The constructing of time series data includes: constructing time series data based on first characteristic data and second characteristic data of each satellite in multiple historical periods; The output of the time series model includes the traffic flow of each satellite in one or more future time periods.

9. The method according to claim 1, characterized in that The satellites include one or more of low earth orbit satellites and medium earth orbit satellites.

10. A satellite service flow prediction device, characterized in that: include: A first acquisition unit is used to acquire geographic feature data of wave positions; A second acquiring unit is configured to acquire coverage time data of the satellite for the wave position in a historical period; A construction unit, configured to construct first characteristic data of the satellite based on the geographic characteristic data and the coverage time data; the first characteristic data is used to represent the geographic characteristics cumulatively covered by the satellite during the historical period; a third acquiring unit, configured to acquire second characteristic data, where the second characteristic data is used to represent the service flow of the satellite during the historical period; A prediction unit is used to predict the future service traffic of the satellite based on the first characteristic data and the second characteristic data.

Images