Multi-beam satellite transmission method, electronic equipment and storage medium

Abstract

The invention provides a multi-beam satellite transmission method, electronic equipment and a storage medium. The method comprises the following steps: acquiring a link state key index and environment data; inputting the link state key index and the environment data into an embedded AI module, and outputting a link score in the future N seconds; and determining an availability judgment result of the link according to the link score, and sending the availability judgment result of the link and the link score to the aggregation router, so that the aggregation router sends the availability judgment result of the link to the aggregation router when receiving a target service signal encoded by a secure and reliable transport protocol SRT encoder. And determining a load weight corresponding to each available satellite portable station according to the link availability judgment result and the link score of the at least two satellite portable stations, and performing link aggregation based on the load weight to transmit the target service signal. According to the embodiment of the invention, fine and efficient utilization of satellite link spectrum resources is realized, and the bandwidth utilization rate and the dynamic aggregation capability of multi-beam satellite transmission are greatly improved.

Description

Technical Field

[0001] This disclosure relates to the field of satellite communication technology, and in particular to a multi-beam satellite transmission method, electronic device, and storage medium. Background Technology

[0002] High-throughput satellites (HTS) have significantly improved bandwidth capabilities through technologies such as multi-beaming and frequency reuse. Total capacity has increased from less than 10Gbps in the first generation to over 200Gbps in the fourth generation with all-digital beamforming technology, providing fundamental support for the long-distance transmission of high-bandwidth services such as high-definition video streaming. With the development of phased array technology, Ka / Ku band portable satellite stations have achieved miniaturization, with antenna apertures reduced to 0.5m, and also feature one-click automatic satellite acquisition, meeting the portability requirements of emergency communication scenarios. However, limited by the hardware transmission capabilities of a single terminal, the uplink rate of Ka band portable stations is capped at only 15Mbps, and the downlink rate at 60Mbps, making it difficult to support the stable transmission requirements of ultra-high-definition video streams.

[0003] To overcome the limitations of single-terminal bandwidth, existing technologies attempt to improve total throughput by using multi-beam parallel transmission, but the actual application results are still unsatisfactory. The core problems are concentrated in the following two aspects:

[0004] (1) Low bandwidth utilization and insufficient dynamic aggregation capability: Existing technologies mostly adopt fixed frequency band reuse or single beam independent transmission modes, lacking the ability to aggregate multi-beam resources in real time. These schemes pre-allocate the frequency band, time slot, and transmission load ratio of each beam during the link planning stage, and the allocation strategy cannot be dynamically adjusted during transmission. In highly dynamic satellite communication environments, factors such as rain attenuation and atmospheric turbulence can cause random fluctuations in beam signal quality. Traditional load balancing algorithms rely on post-event monitoring data for adjustment, resulting in significant response lag and an inability to optimize resource allocation in advance based on changes in link status. This directly leads to a bandwidth fluctuation rate as high as 30%, with some beams in a high-load congestion state and others in a low-load idle state, resulting in serious waste of spectrum resources. This situation makes it difficult to meet the stable transmission requirements of high-bandwidth services such as high-definition video streaming and large file transmission.

[0005] (2) Poor adaptability of transmission protocols to satellite multi-beam scenarios: Traditional transmission protocols (such as UDP) lack effective error control and congestion management mechanisms in unreliable network environments with high latency and high jitter of satellite links, which can easily lead to data packet loss and timing disorder. Summary of the Invention

[0006] This disclosure provides a multi-beam satellite transmission method, electronic device, and storage medium to solve the problems of low bandwidth utilization, insufficient dynamic aggregation capability, and poor adaptability of transmission protocols to satellite multi-beam scenarios in existing multi-beam satellite transmission methods.

[0007] In a first aspect, this disclosure provides a multi-beam satellite transmission method applied to a portable satellite station, the method comprising:

[0008] Acquire key link status indicators and environmental data;

[0009] The key indicators of the link status and environmental data are input into the embedded artificial intelligence (AI) module, which outputs the link score for the next N seconds, where N≥1;

[0010] The availability of a link is determined based on the link score, and the availability of the link and the link score are sent to the aggregation router. When the aggregation router receives the target service signal encoded by the Secure and Reliable Transmission Protocol (SRT) encoder, it determines the load weight corresponding to each available satellite portable station based on the availability of at least two satellite portable stations and the link score, and performs link aggregation based on the load weight to transmit the target service signal.

[0011] Furthermore, before acquiring key link status indicators and environmental data, the method further includes:

[0012] When the satellite portable station is started, the embedded AI module is used to analyze historical ephemeris data and predict the optimal beam.

[0013] The satellite beam is locked according to the optimal beam to complete the satellite search.

[0014] Furthermore, the key link status indicators include signal strength, round-trip time (RTT), packet loss rate, and bandwidth utilization. The environmental data includes latitude and longitude and corresponding weather codes. The embedded AI module adopts a bidirectional long short-term memory (LSTM) network model. The process of inputting the key link status indicators and environmental data into the embedded AI module and outputting a link score for the next N seconds specifically includes:

[0015] The signal strength, RTT, packet loss rate, bandwidth utilization, latitude and longitude, and corresponding weather codes are input into the bidirectional LSTM network model to obtain the link score for the next N seconds output by the bidirectional LSTM network model.

[0016] Furthermore, determining the availability of a link based on the link score specifically includes:

[0017] If the link score is greater than or equal to a preset score threshold, and each of the key indicators of the link status meets the corresponding preset threshold, then the link availability is determined to be available; otherwise, the link availability is determined to be unavailable.

[0018] Secondly, this disclosure provides a multi-beam satellite transmission method applied to an aggregation router, the method comprising:

[0019] The system receives link availability determination results and link scores from at least two portable satellite stations. The link score is a score for the next N seconds, where N≥1, output by the portable satellite station after acquiring key link status indicators and environmental data and inputting them into an embedded artificial intelligence (AI) module. The link availability determination result is determined by the portable satellite station based on the link score.

[0020] In response to receiving the target service signal encoded by the Secure and Reliable Transmission Protocol (SRT) encoder, the load weight corresponding to each available satellite portable station is determined based on the link availability determination results and link scores of at least two satellite portable stations.

[0021] Link aggregation is performed based on the load weights to transmit the target service signals.

[0022] Furthermore, the SRT encoder is connected to the aggregation router via the LAN port of the local area network, and the SRT encoder adaptively adjusts the buffer size within the range of 500ms to 2000ms based on the real-time measured RTT and the link latency jitter mode fed back by the aggregation router.

[0023] Furthermore, determining the load weight corresponding to each available satellite portable station based on the link availability determination results and link scores of at least two satellite portable stations specifically includes:

[0024] Based on the link availability determination results of at least two satellite portable stations, the available satellite portable stations are determined;

[0025] Based on the link score of each available satellite portable station, determine the load weight corresponding to each available satellite portable station;

[0026] The link aggregation based on the load weight to transmit the target service signal specifically includes:

[0027] The data packets corresponding to the target service signal are split according to the load weight, and the split data packets are sent to the corresponding available satellite portable stations to transmit the target service signal.

[0028] Furthermore, the method also includes:

[0029] If an anomaly flag is received from any available satellite portable station, the traffic corresponding to the available satellite portable station that reported the anomaly flag will be migrated to other available satellite portable stations.

[0030] Thirdly, this disclosure provides an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores one or more computer programs executable by the at least one processor, the one or more computer programs being executed by the at least one processor to enable the at least one processor to perform the multi-beam satellite transmission method described in the first or second aspect above.

[0031] Fourthly, this disclosure provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the multi-beam satellite transmission method described in the first or second aspect above.

[0032] The multi-beam satellite transmission method, electronic equipment, and storage medium disclosed herein acquire key link status indicators and environmental data through a satellite portable station. An embedded AI module outputs a link score for the next N seconds and determines link availability. An aggregation router then accurately calculates the load weight of each available satellite portable station based on the link availability determination results and link scores of at least two satellite portable stations. Link aggregation is then performed based on this load weight to transmit the target service signal encoded by the SRT encoder. This achieves refined and efficient utilization of satellite link spectrum resources, significantly improving bandwidth utilization and dynamic aggregation capabilities in multi-beam satellite transmission. Furthermore, relying on the deep adaptation of the SRT protocol to the multi-beam satellite transmission scenario, combined with standardized link support for link aggregation, it effectively optimizes the transmission protocol adaptation effect in multi-beam satellite scenarios, ensuring the stability and smoothness of target service signal transmission. This solves the problems of low bandwidth utilization, insufficient dynamic aggregation capabilities, and poor adaptability of transmission protocols to multi-beam satellite scenarios in existing multi-beam satellite transmission methods. Attached Figure Description

[0033] The accompanying drawings are provided to further illustrate the present disclosure and form part of the specification. They are used together with the embodiments of the present disclosure to explain the disclosure and do not constitute a limitation thereof. In the drawings:

[0034] Figure 1 A flowchart illustrating a multi-beam satellite transmission method provided in this embodiment of the disclosure;

[0035] Figure 2 This is a schematic diagram of the structure of a multi-beam satellite transmission system provided in an embodiment of the present disclosure;

[0036] Figure 3 A configuration flowchart for the aggregation router provided in this embodiment of the disclosure;

[0037] Figure 4 A flowchart illustrating yet another multi-beam satellite transmission method provided in this disclosure embodiment;

[0038] Figure 5 This is a block diagram of an electronic device provided in an embodiment of the present disclosure. Detailed Implementation

[0039] To enable those skilled in the art to better understand the technical solutions of this disclosure, exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments of this disclosure to aid understanding. These should be considered merely exemplary. Therefore, those skilled in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0040] Where there is no conflict, the various embodiments of this disclosure and the features thereof in the embodiments may be combined with each other.

[0041] As used herein, the term “and / or” includes any and all combinations of one or more related enumerated entries.

[0042] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. As used herein, the singular forms “a” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that when the terms “comprising” and / or “made of” are used in this specification, the presence of the stated feature, integral, step, operation, element, and / or component is specified, but the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof is not excluded. Words such as “connected” or “linked” are not limited to physical or mechanical connections but can include electrical connections, whether direct or indirect.

[0043] Unless otherwise specified, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and this disclosure, and will not be interpreted as having an idealized or overly formal meaning, unless expressly so defined herein.

[0044] Figure 1 This is a flowchart illustrating a multi-beam satellite transmission method provided in an embodiment of this disclosure, applied to a portable satellite station. (Refer to...) Figure 1 The method includes:

[0045] Step S101: Obtain key indicators of link status and environmental data.

[0046] Specifically, the portable satellite station connects to the WAN interface of the aggregation router via an Ethernet port and a Cat6 shielded network cable. The aggregation router configures consistent communication parameters (modulation method, symbol rate, forward error correction) for each connected portable satellite station to ensure data packet transmission format compatibility across satellite links. Each portable satellite station periodically or non-periodically acquires key link status indicators and environmental data based on this communication connection.

[0047] Step S102: Input the key indicators of the link status and environmental data into the embedded AI (Artificial Intelligence) module and output the link score for the next N seconds, where N≥1.

[0048] Specifically, the embedded AI module is pre-trained using historical link status key indicators and environmental data, with N preferably being 10, and the link score ranging from 0 to 100.

[0049] In some embodiments, prior to acquiring key link status indicators and environmental data, the method further includes:

[0050] When the satellite portable station is started, the embedded AI module is used to analyze historical ephemeris data and predict the optimal beam.

[0051] The satellite beam is locked according to the optimal beam to complete the satellite search.

[0052] Specifically, when the satellite portable station is activated, it automatically searches for available satellite beams using its satellite antenna. Utilizing a built-in embedded AI module, it analyzes historical ephemeris data to predict the optimal beam. Based on this, it filters and locks onto the azimuth, elevation, and polarization angles that meet signal quality requirements, and then fixes them in place. Compared to traditional satellite acquisition methods, this reduces acquisition time by 40%. The historical ephemeris data includes basic satellite orbit and beam coverage data, beam signal quality correlation data, historical satellite acquisition and link adaptation data of the portable station, and environmental and link correlation auxiliary data.

[0053] In some embodiments, the key link status indicators include signal strength, RTT (Round Trip Time), packet loss rate, and bandwidth utilization. The environmental data includes latitude and longitude and corresponding weather codes. The embedded AI module adopts a bidirectional LSTM (Long Short-Term Memory) network model. The process of inputting the key link status indicators and environmental data into the embedded AI module and outputting a link score for the next N seconds specifically includes:

[0054] The signal strength, RTT, packet loss rate, bandwidth utilization, latitude and longitude, and corresponding weather codes are input into the bidirectional LSTM network model to obtain the link score for the next N seconds output by the bidirectional LSTM network model.

[0055] Specifically, the embedded AI module adopts a bidirectional LSTM network model. The input data includes key link status indicators and environmental data. The key link status indicators include signal strength (dBm), RTT (ms), packet loss rate (%), and bandwidth utilization (%). The environmental data includes latitude and longitude and weather codes (0-5 level rain attenuation). The prediction model architecture adopts the structure of "input layer → bidirectional LSTM layer → attention layer → fully connected layer". The input layer has 60 time steps (corresponding to 60 seconds of historical data). The LSTM layer has 128 neurons and adopts a bidirectional structure. The output layer outputs the link score (0-100 points) for the next N seconds (e.g., 10 seconds).

[0056] Step S103: Determine the availability of the link based on the link score, and send the link availability determination result and the link score to the aggregation router, so that when the aggregation router receives the target service signal encoded by the Secure and Reliable Transmission Protocol (SRT) encoder, it determines the load weight corresponding to each available satellite portable station based on the link availability determination results and link scores of at least two satellite portable stations, and performs link aggregation based on the load weight to transmit the target service signal.

[0057] Specifically, if the link score is greater than or equal to a preset score threshold (e.g., 60 points), and each of the key indicators of the link status meets the corresponding preset threshold, then the link availability is determined to be available; otherwise, the link availability is determined to be unavailable.

[0058] Specifically, after receiving the link availability determination results and link availability scores sent by at least two connected satellite portable stations, the aggregation router, upon receiving the target service signal encoded by the SRT (Secure Reliable Transport) encoder, first determines the available satellite portable stations based on the link availability determination results of the at least two satellite portable stations, and then determines the load weight corresponding to each available satellite portable station based on the link score of each available satellite portable station, with the sum of the load weights of all available satellite portable stations being 100%. Subsequently, the data packets corresponding to the target service signal are split according to the load weights, and the split data packets are sent to the corresponding available satellite portable stations to transmit the target service signal.

[0059] The SRT encoder is connected to the aggregation router via a LAN (Local Area Network) port, and the SRT encoder adaptively adjusts the buffer size within a range of 500ms to 2000ms based on the real-time measured RTT and the link latency jitter mode fed back by the aggregation router.

[0060] Specifically, when a satellite portable station detects a sudden abnormality in a key link status indicator or reaches a preset alarm threshold, it immediately generates and reports an abnormality identifier to the aggregation router. If the aggregation router receives an abnormality identifier reported by any available satellite portable station, it will migrate the traffic corresponding to the available satellite portable station that reported the abnormality identifier to other available satellite portable stations.

[0061] In one specific embodiment, a multi-beam satellite transmission system is provided, such as Figure 2 As shown, the system mainly includes an SRT codec, an aggregation router (supporting Eth-Trunk link aggregation and AI dynamic load balancing algorithms), two portable satellite stations A and B (supporting Ka / Ku bands, with built-in AI real-time link status awareness modules based on LSTM models and cross-beam synchronization modules), a signal source, and an internet link. Its main operating procedures are as follows:

[0062] 1) The signal source inputs the signal to the SRT encoder, and the SRT encoder's network port is connected to the LAN port of the aggregation router using a network cable;

[0063] 2) Connect the network interfaces of satellite portable stations A and B to WAN port 1 and WAN port 2 of the aggregation router respectively using network cables;

[0064] 3) Satellite portable stations A and B perform satellite acquisition operations, aligning with the satellite and then connecting to the Internet;

[0065] 4) Turn on the SRT encoder to start streaming;

[0066] 5) The other end uses an SRT decoder to decode and obtain the original push signal.

[0067] Based on the above system, the multi-beam satellite transmission method specifically includes the following steps:

[0068] Step 1: Satellite Portable Station Initialization

[0069] 1. AI-assisted beam scanning and locking

[0070] When the two portable satellite stations (portable satellite stations A and B) are started, they automatically search for available satellite beams through satellite antennas. They use the built-in embedded AI module (LSTM network) to analyze historical ephemeris data, predict the optimal beam, and then select and lock the azimuth, elevation and polarization angles that meet the signal quality requirements and fix them. Compared with the traditional satellite search method, the satellite search time is shortened by 40%.

[0071] The historical ephemeris data for predicting the optimal beam includes the following:

[0072] a) Basic data on satellite orbit and beam coverage: satellite orbit type; beam coverage range, number and direction, overlapping area; beam operating frequency band, frequency reuse scheme, symbol rate configuration.

[0073] b) Beam signal quality correlation data: beam operating status, signal stability percentage, signal-to-noise ratio; optimal polarization angle and signal quality feedback for each beam.

[0074] c) Portable station historical satellite acquisition and link adaptation data: beam number and angle parameters of previous successful satellite acquisitions by similar portable stations; satellite acquisition duration, number of adjustments, lock success rate and signal quality threshold; beam usage records and transmission effects in different scenarios.

[0075] d) Environmental and link-related auxiliary data: correlation data between rain attenuation level and beam signal quality; beam signal fluctuation patterns at different dates and times.

[0076] 2. AI-powered real-time link status awareness and reporting

[0077] After satellite acquisition is completed, the portable satellite station uses an AI real-time link status perception module. This module continuously monitors signal strength, link latency fluctuations, and data transmission packet loss rate. It uses the AI ​​module to train link data in real time, predicts the status in the next 10 seconds, dynamically adjusts and determines link availability based on preset thresholds, and collects indicators such as signal strength, link latency, and packet loss rate, recording the latency jitter patterns of each link.

[0078] The AI ​​module is an embedded bidirectional LSTM network model, and its specific deployment details are shown in Table 1. Input data includes real-time metrics (i.e., key link status metrics) and environmental data. Real-time metrics include signal strength (dBm), RTT (ms), packet loss rate (%), and bandwidth utilization (%). Environmental data includes latitude and longitude, and weather codes (0-5 level rain attenuation). The prediction model architecture adopts a structure of "input layer → bidirectional LSTM layer → attention layer → fully connected layer." The input layer has 60 time steps (corresponding to 60 seconds of historical data), the LSTM layer has 128 neurons and adopts a bidirectional structure, and the output layer outputs the link score (0-100 points) for the next 10 seconds. For training and deployment, the model uses 30 days of satellite link historical data as training data, employs MAE (mean absolute error) as the loss function, and uses an INT8 precision quantization model embedded in a portable station ARM processor during the inference deployment stage to achieve lightweight and high-efficiency real-time inference.

[0079] Table 1: Deployment details of the bidirectional LSTM network model

[0080]

[0081] The link availability determination employs a dual verification mechanism of AI link scoring and key indicator thresholds. This comprehensive assessment ensures the link status meets the stability requirements for high-definition video streaming. Specifically: 1) The AI-outputted "link score for the next 10 seconds" is based on predictions from the embedded AI module. The link score ranges from 0 to 100 points, with the following criteria: a score ≥ 60 points corresponds to "medium availability" or higher; a score ≥ 80 points indicates optimal availability, with a stable link status and priority allocation of high load; a score < 60 points indicates unavailability, with a risk of severe fluctuations or interruptions. 2) The hard threshold verification of key indicators is a rigid constraint. Based on a satisfactory link score, further verification is required to check whether the predicted values ​​of four core indicators for the next 10 seconds meet preset thresholds. Specific indicators and thresholds are as follows: Signal strength (dBm) ≥ -85dBm (normal scenario); Packet loss rate (%) < 1%; RTT (bidirectional latency) < 800ms; Bandwidth utilization < 90%.

[0082] Step 2: Configure the aggregation router

[0083] The configuration flowchart for the aggregation router is as follows: Figure 3As shown: Connect the two satellite links to the WAN1 and WAN2 interfaces of the aggregation router via network cables. Configure the communication parameters of the two links to be consistent (modulation method, symbol rate, forward error correction). Then, create a Layer 3 logical aggregation interface, enable Layer 3 routing mode, assign logical IPs, and declare the specific value of the aggregation bandwidth. Next, bind WAN1 and WAN2 to the Eth-Trunk aggregation group. Finally, dynamically calculate the load weight based on the link prediction results (signal strength trend, latency jitter mode). Detailed explanation follows:

[0084] 1. Hardware connection

[0085] Connect the Ethernet ports of satellite portable stations A and B to the WAN1 and WAN2 interfaces of the aggregation router, respectively (Cat6 shielded network cables are recommended). Configure the communication parameters of the two links to be consistent (modulation method, symbol rate, forward error correction) to ensure data packet transmission format compatibility.

[0086] 2. AI Dynamic Load Balancing Protocol Configuration

[0087] A Layer 3 logical aggregation interface is created in the aggregation router, Layer 3 routing mode is enabled, logical IPs are assigned, and specific aggregation bandwidth values ​​are declared. WAN1 and WAN2 interfaces are bound to the Eth-Trunk aggregation group, and the AI ​​dynamic load balancing protocol is enabled. The aggregation router receives the "link score for the next 10 seconds" reported by the satellite portable station and dynamically calculates the load weight based on the link prediction results. Links with higher scores are allocated a larger proportion of traffic, thereby reducing load migration response time and improving bandwidth utilization. The purpose of this algorithm is to configure two satellite links for transmission aggregation to enhance transmission capabilities.

[0088] The core logic of dynamically calculating load weights is based on the "link score for the next 10 seconds." Load weights essentially represent the proportion of data transmission handled by each satellite link (totaling 100%). For example, link A has a weight of 0.6 and link B has a weight of 0.4, meaning link A transmits 60% of the high-definition video data stream, and link B transmits 40%. Ultimately, the aggregation router merges the traffic from both links, achieving the goal of "breaking through single-link bandwidth limitations and increasing throughput by more than 2 times."

[0089] It should be noted that the main entity responsible for link sensing is the portable satellite station, while the aggregation router acts only as the "decision-making and execution entity," receiving the link status data periodically reported by the portable satellite station to achieve load balancing and failover. Since the aggregation router is the entity responsible for executing link aggregation, load distribution, and failover, the portable satellite station needs to report the sensing results to the aggregation router in real time, forming a closed loop of "sensing-reporting-decision-execution."

[0090] Specifically, the data reported by the AI ​​real-time link status awareness module of the satellite portable station to the aggregation router falls into two categories:

[0091] 1) Link quality details (supporting dynamic load calculation for aggregation routers):

[0092] Real-time monitoring metrics: signal strength (dBm), link RTT (bidirectional latency, ms), packet loss rate (%), bandwidth utilization (%).

[0093] AI prediction data includes: a link score (0-100 points, quantifying link stability) for the next 10 seconds, and prediction sequences for various core indicators (such as packet loss rate and RTT prediction value for each second in the next 10 seconds). It should be noted that during the real-time inference phase, the bidirectional LSTM network model takes "historical data from the last 60 seconds + current real-time indicators + environmental data" as input and outputs a link score for the next 10 seconds.

[0094] 2) Link availability determination result: Based on the dual verification of "link score ≥ 60 points + key indicators meet the standards", the clear conclusion is "available" or "unavailable"; if it is "unavailable", a brief anomaly type (such as "packet loss rate exceeds the standard", "signal strength is insufficient", "latency exceeds the limit") is attached to help the aggregation router quickly locate the problem.

[0095] Data transmission timing includes regular periodic reporting and emergency reporting of anomalies. The frequency of regular periodic reporting is completely synchronized with the link prediction cycle of the AI ​​module, for example, once every 1 second. Emergency reporting of anomalies is reported immediately (without delay) when the satellite portable station detects a "sudden change" in the link indicator (triggers a preset alarm threshold), without waiting for the regular cycle.

[0096] It should be noted that this embodiment uses an embedded AI module (with a bidirectional LSTM network as the core) to achieve two major functions: "optimal beam prediction" and "link scoring for the next 10 seconds" by accessing input data from different scenarios.

[0097] Step 3: SRT codec settings

[0098] 1. Encoder parameter settings

[0099] Connect the encoder using the SRT protocol to the aggregation router via the LAN port, and configure the encoder parameters by connecting the local management terminal to the aggregation router's LAN port:

[0100] (1) Set the handshake mode to caller mode and fill in the public IP address and port of the receiving end;

[0101] (2) Enable transmission buffer delay adaptive function: dynamically measure RTT (satellite two-way delay of about 500ms), and adjust the buffer (range of 500-2000ms) according to the predicted jitter, which is not a fixed value.

[0102] (3) Enable cross-beam synchronization module: The module synchronously collects the link RTT of the two portable stations and calculates the delay difference. Through unified timestamp calibration and data packet delay compensation mechanism, it ensures that the data packets of the two beams arrive at the receiving end synchronously, eliminating the multi-beam delay difference;

[0103] (4) Set detailed encoder parameters: encoding format, encoding rate, bit rate control method, encoding profile, and sampling accuracy.

[0104] (5) Enable FEC forward error correction and ARQ automatic retransmission to enhance the link's ability to resist packet loss.

[0105] 2. Decoder parameter matching

[0106] The receiver's SRT decoder is set to listener mode, and the listening port is configured to match that of the encoder. The decoder's encoding format, rate control method, sampling precision, and other parameters are fully matched to the encoder to ensure proper decoding.

[0107] Step 4: Aggregated Streaming Transmission

[0108] Connect the streaming signal source (e.g., a high-definition video signal) to the input of the SRT encoder. Turn on the SRT encoder streaming switch. The data enters the aggregated satellite link through the aggregation router and then enters the Internet. It reaches the receiving end's SRT decoder via the receiver's IP address. The SRT decoder decodes the signal to restore the high-definition video signal. Detailed explanation follows:

[0109] 1. The SRT encoder completes encoding encapsulation and protocol adaptation.

[0110] (1) The high-definition video signal is input to the SRT encoder input terminal, and the preset encoding parameters (such as H.265 encoding format, 20Mbps encoding rate, CBR bit rate control mode, etc.) are called to compress the original high-definition audio and video signal into a standardized media stream to adapt to the bandwidth requirements of satellite transmission.

[0111] (2) Encapsulate the media stream into data packets conforming to the SRT protocol, enable FEC forward error correction and ARQ automatic retransmission, embed redundant error correction codes in the data packets and reserve ARQ retransmission identifiers (to deal with possible packet loss in satellite links).

[0112] (3) Carry the public IP and port of the receiver in caller mode, and prepare to initiate SRT handshake connection (the receiver decoder needs to be reached through the link between the aggregation router and the satellite portable station). At the same time, the SRT encoder starts dynamic RTT measurement, and a buffer of 500-2000ms is preset based on the satellite bidirectional reference delay of 500ms. Wait for the aggregation router to feed back link jitter data to adjust the buffer.

[0113] 2. The SRT encoder and the aggregation router complete data distribution and configuration linkage.

[0114] (1) The SRT encoder sends SRT data packets in batches to the aggregation router through the LAN port. The transmission is based on a wired connection to ensure low latency and interference-free transmission.

[0115] (2) The aggregation router provides a foundation for data distribution based on the configured Layer 3 logical aggregation interface, Eth-Trunk aggregation group and AI dynamic load balancing protocol;

[0116] (3) The SRT encoder synchronizes the buffer delay adaptive control logic to the aggregation router. The aggregation router provides real-time feedback on the delay jitter mode of the two links, supporting the SRT encoder to dynamically adjust the buffer (for example, if the aggregation router reports that the jitter of link A reaches 120ms, the encoder will increase the buffer from 800ms to 1000ms).

[0117] 3. The aggregation router and satellite portable station complete load distribution and status closure.

[0118] (1) After receiving the SRT data packet, the aggregation router calculates the load weight based on the AI ​​dynamic load balancing algorithm according to the “link score in the next 10 seconds” reported by the satellite portable station (the higher the score, the greater the weight), splits the data packet and sends it to the satellite portable station through the corresponding WAN port (e.g., satellite portable station A has a score of 85 and a weight of 0.57, and satellite portable station B has a score of 65 and a weight of 0.43, respectively transmitting 57% and 43% of the data packets). When sending it, it ensures that the communication parameters of the two links (modulation method such as QPSK, symbol rate such as 2Mbps, forward error correction such as LDPC) are completely consistent, and ensures that the SRT data packet transmission format is compatible in different links and there are no parsing abnormalities.

[0119] (2) After receiving the SRT data packets from the aggregation router, the satellite portable stations A / B modulate the signal according to the unified communication parameters, and upload the SRT data packets to the satellite through the locked satellite beam. Then, they access the Internet via the satellite link and transmit them to the decoder at the receiving end. At the same time, they continuously monitor indicators such as signal strength, packet loss rate, and link RTT. Combined with the LSTM model, they output the "link score for the next 10 seconds" and feed back the link quality details and availability conclusions to the aggregation router at a cycle of 1 second. In case of an anomaly (such as packet loss rate ≥ 2%), an emergency report is triggered:

[0120] a) Typical scenario: Feedback of "link score + indicator details" to support the aggregation router in dynamically adjusting the load weight (e.g., if the signal strength of satellite portable station A drops from -80dBm to -88dBm and the score drops from 85 to 72, the aggregation router will reduce its weight from 0.57 to 0.51).

[0121] b) Abnormal scenarios: If a sudden increase in packet loss rate (≥2%) is detected, an emergency report will be triggered with an "abnormal indicator" (such as "packet loss rate exceeds the standard"), and the aggregation router will immediately start the fault switching preparation logic.

[0122] (3) Satellite portable stations A and B feed back their respective real-time link RTT data to the aggregation router. The aggregation router synchronizes the data to the SRT encoder cross-beam synchronization module. This module calculates the time delay difference between the two links (e.g., RTT_A=550ms, RTT_B=620ms, with a time delay difference of 70ms). After that, it ensures that the two data packets arrive at the receiving end synchronously through unified timestamp calibration and data packet delay compensation (e.g., delaying the data packet transmission of satellite portable station A by 70ms). This eliminates cross-beam timing deviation.

[0123] Step 5: Predictive Fault Handling

[0124] Link interruption detection: Faults are determined based on continuous packet loss, employing an AI predictive mechanism: the model identifies abnormal patterns (such as a sudden increase in packet loss rate) and proactively migrates traffic to healthy links, with a switchover time of less than 50ms. This step achieves rapid fault handling through the collaborative logic of "satellite portable station AI prediction + aggregation router verification," as detailed below:

[0125] 1. The portable satellite station's AI predicts anomalies and urgently reports them to the aggregation router.

[0126] (1) The AI ​​real-time link status perception module of the satellite portable station continuously monitors link indicators such as packet loss rate, signal strength, and RTT, and analyzes the data in real time through an embedded LSTM model;

[0127] (2) If “continuous packet loss reaches the threshold” (e.g., packet loss rate ≥ 5% for 300ms) is detected, or “abnormal pattern” is identified (e.g., packet loss rate suddenly increases from 0.3% to 2.5%), it is immediately determined as “link failure warning”;

[0128] (3) Trigger emergency reporting of anomalies (no need to wait for the 1-second normal cycle), send a "fault warning data packet" to the aggregation router through a Cat6 shielded network cable, which contains 3 types of core information: ① anomaly type identifier (such as continuous packet loss fault, packet loss rate surge warning); ② real-time indicator details (current packet loss rate, signal strength, RTT, link score); ③ the link status prediction for the next 2 seconds output by the LSTM model (such as predicting that the packet loss rate will rise to 8% and the link will be interrupted).

[0129] 2. The aggregation router receives alerts and quickly cross-verifies faults.

[0130] After receiving an emergency report from a satellite portable station (such as station A), the aggregation router does not directly trigger a handover, but completes "dual verification" within 10ms to avoid misjudgment and adapt to the requirements of a highly dynamic satellite environment.

[0131] (1) Local data verification: retrieve the most recent 3 routine data reports (within 1 second) of this link (site A) to confirm the consistency of abnormal trends (e.g., the packet loss rate had increased from 0.2% to 1.8% in the previous two reports, and then suddenly increased to 2.6% this time, which is consistent with the trend).

[0132] (2) Cross-link verification: Synchronously query the real-time status of another healthy link (B station) (already reported and cached through regular reporting), confirm that the B station link score is ≥70 points and the core indicators (packet loss rate <1%, signal strength ≥-85dBm) meet the availability requirements, and ensure that there is an available link to carry traffic.

[0133] 3. The aggregation router detects the fault and initiates traffic migration.

[0134] After successful dual verification, the aggregation router completes the final fault determination within 15ms, marks satellite portable station A as a "faulty link," and immediately initiates the "emergency load migration logic" of AI dynamic load balancing:

[0135] (1) Adjust load weight: Instantly reduce the load weight of the faulty link (site A) from the current value (e.g., 0.53) to 0, and at the same time increase the weight of the healthy link (site B) from the current value (e.g., 0.47) to 100% (Eth-Trunk aggregation group supports millisecond-level weight adjustment).

[0136] (2) Data forwarding switching: The aggregation router shuts down the data packet forwarding channel of WAN1 interface (corresponding to station A) and redirects all subsequent received SRT data packets (from SRT encoder) to WAN2 interface (corresponding to station B) to avoid data transmission to the faulty link;

[0137] (3) Synchronize SRT encoder: Send "link switching notification" to SRT encoder to trigger SRT encoder to start FEC redundancy enhancement function, temporarily increase redundancy code rate by 10% to avoid packet loss due to traffic concentration during switching.

[0138] 4. The aggregation router confirms the switchover is complete and provides status feedback.

[0139] After traffic migration is initiated, the aggregation router completes the switchover confirmation within 20ms:

[0140] (1) Monitor the bandwidth utilization of the healthy link (B station): If the utilization rate is <90% (link availability hard threshold), it is determined that "switching is successful"; if the utilization rate is ≥90%, the "adaptive bit rate adjustment" function of the SRT encoder is temporarily triggered to reduce the encoding rate by 5%-10% to ensure stable transmission.

[0141] (2) Send a “fault link isolation notification” to satellite portable station A, instructing it to suspend data transmission, retain only link status monitoring, and report the fault recovery status once every 500ms;

[0142] (3) Output fault switching logs to the local management terminal (laptop terminal), including fault type, switching time, current link status and other information, to facilitate operation and maintenance monitoring.

[0143] It should be noted that the multi-beam satellite transmission method provided in this disclosure has the following beneficial effects:

[0144] a) Improve bandwidth aggregation efficiency and break through single-link bandwidth limitations: Based on the link prediction model of LSTM network, the system monitors the status of two satellite links in real time, optimizes load weights and dynamically allocates traffic, breaking through the physical bandwidth limit of a single satellite channel for the first time, and achieving efficient utilization of spectrum resources without manual intervention; in actual tests, the total transmission bandwidth of the system reaches more than twice that of a single link, and the bandwidth fluctuation rate is significantly reduced. Especially when transmitting high-definition video in remote areas such as ocean-going ships and uninhabited areas, it can greatly improve the smoothness of the picture and completely solve the pain point of limited single-channel bandwidth in traditional satellite communication.

[0145] b) Reduce end-to-end transmission latency and jitter to meet the requirements of smooth transmission: Based on the SRT protocol, the adaptive rate control and cross-beam synchronization mechanism eliminates the need for manual parameter modification. It can adaptively adjust the transmission latency according to the dynamic changes of the satellite link, compressing the end-to-end transmission latency to within 800ms. This effectively reduces the impact of network jitter on real-time streaming media, ensuring smooth real-time streaming of high-definition video and meeting the low latency requirements of satellite multi-beam collaborative transmission scenarios.

[0146] c) Achieve rapid predictive failover and ensure transmission continuity: Adopt an AI model to predict the risk of link interruption. Combined with a dynamic load migration mechanism, and through the dual verification logic of the KA portable station AI early warning module and the aggregation router, the fault can be quickly identified and traffic migration can be triggered in the early stage of link anomaly (such as a sudden increase in packet loss rate or continuous packet loss). The switching time is strictly controlled within 50ms to avoid transmission lag or interruption caused by link interruption.

[0147] The multi-beam satellite transmission method provided in this disclosure acquires key link status indicators and environmental data through a satellite portable station. An embedded AI module outputs a link score for the next N seconds and determines link availability. An aggregation router then accurately calculates the load weight of each available satellite portable station based on the link availability determination results and link scores of at least two satellite portable stations. Link aggregation is then performed based on this load weight to transmit the target service signal encoded by the SRT encoder. This achieves refined and efficient utilization of satellite link spectrum resources, significantly improving bandwidth utilization and dynamic aggregation capabilities in multi-beam satellite transmission. Furthermore, relying on the deep adaptation of the SRT protocol to the multi-beam satellite transmission scenario, combined with standardized link support for link aggregation, it effectively optimizes the transmission protocol adaptation effect in multi-beam satellite scenarios, ensuring the stability and smoothness of target service signal transmission. This solves the problems of low bandwidth utilization, insufficient dynamic aggregation capabilities, and poor adaptability of transmission protocols to multi-beam satellite scenarios in existing multi-beam satellite transmission methods.

[0148] It is understood that the various method embodiments mentioned above in this disclosure can be combined with each other to form combined embodiments without violating the principle and logic. Due to space limitations, this disclosure will not elaborate further. Those skilled in the art will understand that in the above methods of specific implementation, the specific execution order of each step should be determined by its function and possible internal logic.

[0149] Figure 4 A flowchart of yet another multi-beam satellite transmission method provided in this disclosure embodiment.

[0150] Reference Figure 4 This disclosure provides a multi-beam satellite transmission method applied to an aggregation router, the method comprising:

[0151] Step S201: Receive link availability determination results and link scores sent by at least two satellite portable stations, wherein the link score is a score for the next N seconds output by the satellite portable station after obtaining key link status indicators and environmental data and inputting the key link status indicators and environmental data into the embedded artificial intelligence AI module, where N≥1; the link availability determination result is determined by the satellite portable station based on the link score;

[0152] Specifically, the satellite portable station is connected to the WAN interface of the aggregation router via an Ethernet port and a Cat6 shielded network cable. The aggregation router configures consistent communication parameters (modulation method, symbol rate, forward error correction) for each connected satellite portable station to ensure that the data packet transmission format of each satellite link is compatible.

[0153] Step S203: In response to receiving the target service signal encoded by the Secure and Reliable Transmission Protocol (SRT) encoder, determine the load weight corresponding to each available satellite portable station based on the link availability determination results and link scores of at least two satellite portable stations;

[0154] Specifically, the target service is a high-bandwidth service such as high-definition video streaming and large file transfer. The SRT encoder is connected to the aggregation router via a local area network (LAN) port. When the target service signal is input to the SRT encoder, the encoder uses preset encoding parameters (such as H.265 encoding format, 20Mbps encoding rate, CBR bitrate control mode, etc.) to compress and encode the target service signal into a standardized media stream to meet the bandwidth requirements of satellite transmission. After receiving the encoded target service signal, the aggregation router determines the load weight corresponding to each available satellite portable station based on the link availability judgment results and link scores of at least two satellite portable stations.

[0155] In some embodiments, the SRT encoder adaptively adjusts the buffer size within a range of 500ms to 2000ms based on the real-time measured RTT and the link latency jitter pattern fed back by the aggregation router.

[0156] Specifically, the SRT encoder synchronizes the buffer delay adaptive control logic to the aggregation router. The aggregation router collects and feeds back the delay jitter mode of each satellite link to the SRT encoder in real time, providing data support for the dynamic adjustment of the buffer of the SRT encoder. For example, when the aggregation router reports that the jitter amplitude of a certain satellite link reaches 120ms, the SRT encoder increases the transmission buffer from 800ms to 1000ms.

[0157] In some embodiments, determining the load weight corresponding to each available satellite portable station based on the link availability determination results and link scores of at least two satellite portable stations specifically includes:

[0158] Based on the link availability determination results of at least two satellite portable stations, the available satellite portable stations are determined;

[0159] Based on the link score of each available satellite portable station, determine the load weight corresponding to each available satellite portable station;

[0160] The link aggregation based on the load weight to transmit the target service signal specifically includes:

[0161] The data packets corresponding to the target service signal are split according to the load weight, and the split data packets are sent to the corresponding available satellite portable stations to transmit the target service signal.

[0162] Specifically, the aggregation router first verifies the link availability results of at least two satellite portable stations one by one, selecting the satellite portable stations with usable results as valid transmission nodes. Then, it performs quantitative calculations based on the link availability score of each valid transmission node, allocating corresponding load weights according to the score, with higher scores receiving a larger share of the allocated load weight, and the sum of the load weights of all available satellite portable stations being 100%. After completing the load weight allocation, the aggregation router proportionally splits the SRT protocol data packets corresponding to the target service signal, which are encoded and encapsulated by the SRT encoder, according to the load weight proportion of each available satellite portable station. Then, through the WAN interface corresponding to each available satellite portable station, the split data packets are distributed to the corresponding satellite portable stations. Each satellite portable station then completes the uplink transmission of the target service signal through the locked satellite beam, achieving aggregated transmission of multiple satellite links.

[0163] In some embodiments, the method further includes:

[0164] If an anomaly flag is received from any available satellite portable station, the traffic corresponding to the available satellite portable station that reported the anomaly flag will be migrated to other available satellite portable stations.

[0165] Specifically, when a satellite portable station detects a sudden abnormality in a key link status indicator or reaches a preset alarm threshold, it immediately generates and reports an abnormality identifier to the aggregation router. If the aggregation router receives an abnormality identifier reported by any available satellite portable station, it will migrate the traffic corresponding to the available satellite portable station that reported the abnormality identifier to other available satellite portable stations.

[0166] Figure 5 This is a block diagram of an electronic device provided in an embodiment of the present disclosure.

[0167] Reference Figure 5 This disclosure provides an electronic device, which includes: at least one processor 701; at least one memory 702; and one or more I / O interfaces 703 connected between the processor 701 and the memory 702; wherein the memory 702 stores one or more computer programs that can be executed by the at least one processor 701, and the one or more computer programs are executed by the at least one processor 701 to enable the at least one processor 701 to perform the above-described multi-beam satellite transmission method.

[0168] This disclosure also provides a computer-readable storage medium storing a computer program thereon, wherein the computer program, when executed by a processor, implements the above-described multi-beam satellite transmission method. The computer-readable storage medium may be volatile or non-volatile.

[0169] In summary, the multi-beam satellite transmission method, electronic device, and storage medium provided in this disclosure acquire key link status indicators and environmental data through a satellite portable station. An embedded AI module outputs a link score for the next N seconds and determines link availability. Then, an aggregation router accurately calculates the load weight of each available satellite portable station based on the link availability determination results and link scores of at least two satellite portable stations. Link aggregation is then performed based on this load weight to transmit the target service signal encoded by the SRT encoder. This achieves refined and efficient utilization of satellite link spectrum resources, significantly improving bandwidth utilization and dynamic aggregation capabilities in multi-beam satellite transmission. Furthermore, relying on the deep adaptation of the SRT protocol to the multi-beam satellite transmission scenario, combined with standardized link support for link aggregation, it effectively optimizes the transmission protocol adaptation effect in multi-beam satellite scenarios, ensuring the stability and smoothness of target service signal transmission. This solves the problems of low bandwidth utilization, insufficient dynamic aggregation capabilities, and poor adaptability of transmission protocols to multi-beam satellite scenarios in existing multi-beam satellite transmission methods.

[0170] Those skilled in the art will understand that all or some of the steps, systems, and apparatuses disclosed above, and their functional modules / units, can be implemented as software, firmware, hardware, or suitable combinations thereof. In hardware implementations, the division between functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software can be distributed on a computer-readable storage medium, which may include computer storage media (or non-transitory media) and communication media (or transient media).

[0171] As is known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable program instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), static random access memory (SRAM), flash memory or other memory technologies, portable compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, it is known to those skilled in the art that communication media typically contain computer-readable program instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0172] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0173] Computer program instructions used to perform the operations of this disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may execute 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 a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing the status information of the computer-readable program instructions to implement various aspects of this disclosure.

[0174] This disclosure has disclosed exemplary embodiments, and although specific terminology has been used, it is for general illustrative purposes only and should not be construed as limiting. In some instances, it will be apparent to those skilled in the art that features, characteristics, and / or elements described in conjunction with particular embodiments may be used alone, or in combination with features, characteristics, and / or elements described in conjunction with other embodiments, unless otherwise expressly indicated. Therefore, those skilled in the art will understand that various changes in form and detail may be made without departing from the scope of this disclosure as set forth by the appended claims.

Claims

1. A multi-beam satellite transmission method, characterized in that, Applied to a portable satellite station, the method includes: Acquire key link status indicators and environmental data; The key indicators of the link status and environmental data are input into the embedded artificial intelligence (AI) module, which outputs the link score for the next N seconds, where N≥1; The availability of a link is determined based on the link score, and the availability of the link and the link score are sent to the aggregation router. When the aggregation router receives the target service signal encoded by the Secure and Reliable Transmission Protocol (SRT) encoder, it determines the load weight corresponding to each available satellite portable station based on the availability of at least two satellite portable stations and the link score, and performs link aggregation based on the load weight to transmit the target service signal.

2. The method according to claim 1, characterized in that, Before acquiring key link status indicators and environmental data, the method further includes: When the satellite portable station is started, the embedded AI module is used to analyze historical ephemeris data and predict the optimal beam. The satellite beam is locked according to the optimal beam to complete the satellite search.

3. The method according to claim 1, characterized in that, The key link status indicators include signal strength, round-trip time (RTT), packet loss rate, and bandwidth utilization. The environmental data includes latitude and longitude and corresponding weather codes. The embedded AI module adopts a bidirectional long short-term memory (LSTM) network model. The key link status indicators and environmental data are input into the embedded AI module, which outputs a link score for the next N seconds, specifically including: The signal strength, RTT, packet loss rate, bandwidth utilization, latitude and longitude, and corresponding weather codes are input into the bidirectional LSTM network model to obtain the link score for the next N seconds output by the bidirectional LSTM network model.

4. The method according to claim 1, characterized in that, The step of determining the availability of a link based on the link score specifically includes: If the link score is greater than or equal to a preset score threshold, and each of the key indicators of the link status meets the corresponding preset threshold, then the link availability is determined to be available; otherwise, the link availability is determined to be unavailable.

5. A multi-beam satellite transmission method, characterized in that, Applied to an aggregation router, the method includes: The system receives link availability determination results and link scores from at least two portable satellite stations. The link score is a score for the next N seconds, where N≥1, output by the portable satellite station after acquiring key link status indicators and environmental data and inputting them into an embedded artificial intelligence (AI) module. The link availability determination result is determined by the portable satellite station based on the link score. In response to receiving the target service signal encoded by the Secure and Reliable Transmission Protocol (SRT) encoder, the load weight corresponding to each available satellite portable station is determined based on the link availability determination results and link scores of at least two satellite portable stations. Link aggregation is performed based on the load weights to transmit the target service signals.

6. The method according to claim 5, characterized in that, The SRT encoder is connected to the aggregation router via the LAN port of the local area network, and the SRT encoder adaptively adjusts the buffer size within the range of 500ms to 2000ms based on the real-time measured RTT and the link latency jitter mode fed back by the aggregation router.

7. The method according to claim 5, characterized in that, The determination of the load weight corresponding to each available satellite portable station based on the link availability determination results and link scores of at least two satellite portable stations specifically includes: Based on the link availability determination results of at least two satellite portable stations, the available satellite portable stations are determined; Based on the link score of each available satellite portable station, determine the load weight corresponding to each available satellite portable station; The link aggregation based on the load weight to transmit the target service signal specifically includes: The data packets corresponding to the target service signal are split according to the load weight, and the split data packets are sent to the corresponding available satellite portable stations to transmit the target service signal.

8. The method according to claim 5, characterized in that, The method further includes: If an anomaly flag is received from any available satellite portable station, the traffic corresponding to the available satellite portable station that reported the anomaly flag will be migrated to other available satellite portable stations.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores one or more computer programs that can be executed by the at least one processor, the one or more of the computer programs being executed by the at least one processor to enable the at least one processor to perform the multi-beam satellite transmission method as described in any one of claims 1-4, or to perform the multi-beam satellite transmission method as described in any one of claims 5-8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the multi-beam satellite transmission method as described in any one of claims 1-4, or the multi-beam satellite transmission method as described in any one of claims 5-8.

Images