A data collaborative transmission method and system for low-orbit satellite Internet of Things terminals

Abstract

The present invention discloses a data collaborative transmission method and system for a low-orbit satellite Internet of Things terminal, the method specifically comprising: classifying and cutting environmental data to form multiple environmental data subsets; determining the optimal communication paths of several collaborative transmission terminals and the first low-orbit satellite Internet of Things terminal and each collaborative transmission terminal based on the communication topology relationship between each low-orbit satellite Internet of Things terminal in the self-organizing network; transmitting environmental data subsets of different priorities to the corresponding collaborative transmission terminals through different optimal communication paths; receiving environmental data subsets sent by each collaborative transmission terminal according to the low-orbit satellite, splicing each environmental data subset and forwarding it to a target terminal or a ground station or a data center. The present invention can make full use of the synergy between multiple low-orbit satellite Internet of Things terminals to achieve stable and reliable data transmission under large data volume and high real-time requirements.

Description

Technical Field

[0001] The present invention relates to the technical field of satellite Internet of Things, and in particular to a data collaborative transmission method and system for a low-orbit satellite Internet of Things terminal. Background Art

[0002] With the continuous advancement of IoT technology, its application in various fields is becoming more and more extensive, especially in data collection and transmission in complex scenarios such as large-scale, cross-regional, and harsh environments. IoT technology has shown great potential and value. However, traditional ground IoT has many limitations in these scenarios, such as difficulty in base station construction, limited communication distance, and susceptibility to natural disasters, resulting in a serious mismatch between service capabilities and demand. Especially in vast uninhabited areas such as oceans and deserts, ground IoT can hardly provide effective services, which greatly limits the application scope and effect of IoT technology.

[0003] In order to solve the application limitations of the ground-based Internet of Things in complex scenarios, the low-orbit satellite Internet of Things came into being. With its advantages such as wide coverage, no restrictions on weather and geographical conditions, and strong system anti-destruction, the low-orbit satellite Internet of Things has become an effective supplement and extension of the ground-based Internet of Things. By deploying a low-orbit satellite network, seamless coverage can be achieved around the world, providing stable and reliable communication services for various smart terminal devices. This not only greatly expands the application scope of the Internet of Things technology, but also improves the stability and reliability of data transmission.

[0004] However, despite the many advantages of low-orbit satellite IoT, it still faces some challenges in data transmission. First, due to the limited bandwidth of satellite communications and the increasingly diversified and high-volume data transmission needs of smart terminal devices, how to improve transmission efficiency while ensuring data transmission stability has become an urgent problem to be solved. Traditional data transmission methods are often limited to the data transmission optimization of a single terminal device, while ignoring the synergy between multiple terminal devices, resulting in transmission performance that is difficult to meet actual needs when facing complex scenarios such as large data volumes and high real-time requirements.

[0005] Secondly, the computing power and energy supply of smart terminal devices also limit the performance of data transmission. Especially in some harsh environments and difficult energy supply scenarios, such as marine environmental monitoring, the energy supply of floating smart terminal devices is very limited, making it difficult to support long-term, high-frequency data collection and transmission. At the same time, wireless signals in marine environments are easily interfered by factors such as waves and tides, resulting in unstable data transmission and high packet loss rate, which further affects the reliability and efficiency of data transmission.

[0006] In addition, the wide distribution range and low density of smart terminal devices are also a major problem facing data transmission. In vast uninhabited areas such as the ocean, the distribution of smart terminal devices is often sparse and uneven, making it difficult to form an effective self-organizing network, resulting in unreliable data transmission paths, and it is difficult to ensure the timeliness and reliability of data transmission. Summary of the invention

[0007] The purpose of the present invention is to provide a data collaborative transmission method and system for low-orbit satellite Internet of Things terminals, which can make full use of the synergy between multiple low-orbit satellite Internet of Things terminals, realize stable and reliable data transmission under large data volumes and high real-time requirements, overcome the data transmission limitations in complex scenarios such as marine environments, and promote the further development and application of low-orbit satellite Internet of Things technology to solve at least one of the above-mentioned prior art problems.

[0008] In a first aspect, the present invention provides a data collaborative transmission method for a low-orbit satellite Internet of Things terminal, the method specifically comprising:

[0009] According to the device distribution and network topology of multiple low-orbit satellite IoT terminals, a self-organizing network among multiple low-orbit satellite IoT terminals is formed;

[0010] Acquire environmental data collected by the first low-orbit satellite Internet of Things terminal, and if the environmental data is larger than a preset data size threshold, classify and cut the environmental data to form multiple environmental data subsets;

[0011] Based on the communication topology relationship between each low-orbit satellite Internet of Things terminal in the self-organizing network, determine the optimal communication path between a plurality of coordinated transmission terminals and the first low-orbit satellite Internet of Things terminal and each coordinated transmission terminal;

[0012] Prioritizing the plurality of environmental data subsets, and transmitting environmental data subsets of different priorities to corresponding cooperative sending terminals through different optimal communication paths;

[0013] The environmental data subset sent by each cooperative transmitting terminal is received by the low-orbit satellite, and each environmental data subset is spliced ​​and forwarded to the target terminal or ground station or data center.

[0014] In a second aspect, the present invention provides a data collaborative transmission system for a low-orbit satellite Internet of Things terminal, the system specifically comprising:

[0015] The first data collaborative transmission module is used to form a self-organizing network among multiple low-orbit satellite Internet of Things terminals according to the device distribution and network topology of multiple low-orbit satellite Internet of Things terminals;

[0016] A second data collaborative transmission module is used to obtain environmental data collected by the first low-orbit satellite Internet of Things terminal, and if the environmental data is larger than a preset data size threshold, the environmental data is classified and cut to form multiple environmental data subsets;

[0017] A third data cooperative transmission module is used to determine the optimal communication path between a plurality of cooperative transmission terminals and the first low-orbit satellite Internet of Things terminal and each cooperative transmission terminal based on the communication topology relationship between each low-orbit satellite Internet of Things terminal in the ad hoc network;

[0018] A fourth data cooperative transmission module, used to prioritize the plurality of environmental data subsets, and transmit environmental data subsets of different priorities to corresponding cooperative sending terminals through different optimal communication paths;

[0019] The fifth data collaborative transmission module is used to receive the environmental data subset sent by each collaborative sending terminal according to the low-orbit satellite, splice each environmental data subset and forward it to the target terminal or ground station or data center.

[0020] In a third aspect, the present invention provides a computer device comprising: a memory and a processor and a computer program stored in the memory. When the computer program is executed on the processor, a data collaborative transmission method for a low-orbit satellite Internet of Things terminal as described in any one of the above methods is implemented.

[0021] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for collaborative data transmission of a low-orbit satellite Internet of Things terminal as described in any of the above methods is implemented.

[0022] Compared with the prior art, the present invention has at least one of the following technical effects:

[0023] 1. The present invention can make full use of the synergy between multiple low-orbit satellite Internet of Things terminals to achieve stable and reliable data transmission under large data volumes and high real-time requirements, overcome the data transmission limitations in complex scenarios such as marine environments, and promote the further development and application of low-orbit satellite Internet of Things technology.

[0024] 2. The present invention realizes collaborative work among terminals and improves the reliability and efficiency of data transmission by forming a self-organizing network among multiple low-orbit satellite Internet of Things terminals.

[0025] 3. The present invention classifies and cuts the environmental data and transmits them separately, which reduces the amount of data transmitted in a single time and helps to reduce the delay and packet loss rate of data transmission.

[0026] 4. The present invention utilizes the optimal communication path to transmit environmental data subsets of different priorities, thereby ensuring the priority transmission of key data and improving the real-time and accuracy of data transmission.

[0027] 5. The present invention calculates the distance matrix between devices and uses the K-means clustering algorithm to group them, determines the main node and relay node of each terminal group, realizes the reasonable distribution and efficient management of low-orbit satellite Internet of Things terminals, optimizes the network topology, and improves the stability and efficiency of data transmission.

[0028] 6. The present invention realizes adaptive optimization of the self-organizing network and improves network performance and resource utilization by periodically detecting the operating status and device movement of the self-organizing network and making dynamic adjustments based on the Q-Learning algorithm.

[0029] 7. The present invention preprocesses and classifies the environmental data, uses a logistic regression model for modeling training, forms a classifier discrimination model, effectively tests and optimizes the classification accuracy of the environmental data subset, and improves the accuracy, efficiency and reliability of data processing.

[0030] 8. The present invention achieves optimal selection of data transmission paths and reduces data transmission delays and costs by constructing a routing table within each terminal group and determining the optimal communication path based on the Dijkstra shortest path algorithm.

[0031] 9. The present invention matches the environmental data subset and the optimal communication path according to the priority evaluation index and the path performance evaluation index, thereby ensuring that the key data can be transmitted through the optimal path and improving the real-time and accuracy of data transmission.

[0032] 10. The present invention constructs a signal interference change trend prediction model and predicts the signal interference intensity within a future preset time period, thereby achieving dynamic adjustment and optimization of transmission parameters, improving data transmission rate and reducing bit error rate.

[0033] 11. The present invention establishes an equipment health monitoring model to evaluate the equipment operating status of the low-orbit satellite Internet of Things terminal in real time, predict and prevent equipment failures in advance, and improve the reliability and service life of the equipment.

[0034] 12. The present invention determines the risk level of physical damage to the equipment according to the number of times the equipment protection mechanism is triggered, and uses a genetic algorithm to adjust the equipment position, thereby optimizing the equipment layout and improving the stability of the self-organizing network and the data transmission efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0036] Figure 1 It is a flowchart of a data collaborative transmission method for a low-orbit satellite Internet of Things terminal provided by an embodiment of the present invention;

[0037] Figure 2 It is a structural schematic diagram of a data collaborative transmission system for a low-orbit satellite Internet of Things terminal provided by an embodiment of the present invention;

[0038] Figure 3 It is a structural schematic diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0039] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0040] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0041] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0042] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0043] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0044] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0045] In the embodiment of the present application, the execution subject of the process includes a terminal device, which includes but is not limited to: a server, a computer, a smart phone, a tablet computer, and other devices capable of executing the method disclosed in the present application. Figure 1 A schematic flow chart of a data collaborative transmission method for a low-orbit satellite IoT terminal disclosed in an embodiment of the present invention is shown, and the details are as follows:

[0046] S101, forming a self-organizing network among multiple low-orbit satellite Internet of Things terminals according to the device distribution and network topology of multiple low-orbit satellite Internet of Things terminals.

[0047] In this embodiment, low-orbit satellite IoT terminals are reasonably deployed according to the geographical location of the environment. These terminals have the ability to access the low-orbit satellite network and can realize data transmission and reception. A stable network topology is constructed, such as a Manhattan network or a ring network. These network topologies have the advantages of strong stability, low latency, and high anti-destruction capability, which can ensure stable connection and communication between low-orbit satellite IoT terminals.

[0048] S102, obtaining environmental data collected by a first low-orbit satellite Internet of Things terminal. If the environmental data is larger than a preset data size threshold, the environmental data is classified and cut to form multiple environmental data subsets.

[0049] In this embodiment, a first low-orbit satellite Internet of Things terminal (hereinafter referred to as "terminal A") is deployed, which is equipped with various environmental sensors for real-time collection of environmental data. Terminal A packages the collected environmental data regularly or on demand, and prepares for transmission. A preset data size threshold is set inside terminal A to determine whether the environmental data packet is too large. When the size of the environmental data packet collected by terminal A exceeds the preset threshold, a classification and cutting operation is triggered. According to the type of environmental data (such as temperature, humidity, air pressure, etc.) or dimensions such as timestamp, the large data packet is cut into multiple smaller environmental data subsets. The size of each subset should be less than or equal to the preset data size threshold to ensure smooth transmission through the satellite communication link.

[0050] Furthermore, the first low-orbit satellite IoT terminal is a floating intelligent terminal for ocean monitoring. When collecting environmental data through the floating intelligent terminal, the initial data sampling frequency and data volume threshold can be determined according to the characteristics of the data and business needs. Adaptive sampling algorithms, such as adaptive multi-resolution sampling algorithms, are used to dynamically adjust the data sampling strategy according to the changes in the data volume and the acquisition frequency. By real-time monitoring of the data volume and the acquisition frequency, it is determined whether it exceeds the preset threshold. If the data volume exceeds the preset threshold, the adaptive sampling algorithm is triggered, and the amplitude of reducing the sampling frequency is calculated according to the degree of exceeding the threshold, and the energy consumption of data collection and transmission is reduced by reducing the sampling frequency. The collected environmental data is compressed, and an adaptively selected data compression algorithm, such as an adaptive Huffman coding algorithm, is used to further reduce the energy consumption of data transmission while ensuring data quality. Based on the compressed data, feature extraction and pattern recognition are performed on the data through data analysis and machine learning algorithms, such as support vector machine algorithms, to find key information and abnormal conditions in the data. According to the analysis results, the data collection strategy and threshold settings are dynamically adjusted, such as adjusting the data sampling frequency and data volume threshold. Adopt incremental learning algorithms, such as online sequence extreme learning machine algorithms, to continuously update and optimize machine learning models based on newly collected data, improve the accuracy of data analysis and anomaly detection, adapt to changes in environmental data, and maintain the timeliness of the model. According to the results of adaptive sampling and data analysis, dynamically adjust the working mode and parameter configuration of the floating intelligent terminal, such as adjusting the sampling rate and data transmission interval of the floating intelligent terminal, and through intelligent control and adaptive adjustment, minimize energy consumption and extend the working time of the equipment.

[0051] S103, based on the communication topology relationship between each low-orbit satellite Internet of Things terminal in the self-organizing network, determine a plurality of cooperative sending terminals and the optimal communication path between the first low-orbit satellite Internet of Things terminal and each cooperative sending terminal.

[0052] In this embodiment, first, the communication topology of the entire ad hoc network is constructed through the communication links between the low-orbit satellite Internet of Things terminals. This includes determining the location, communication capabilities and connection relationship between each terminal. Terminal A, as the starting point for data transmission, needs to establish a communication link with other terminals in order to transmit data. According to the communication topology, factors such as the quality, distance and capacity of the communication link between terminal A and other terminals are analyzed. Several terminals with good communication link quality, close distance and sufficient capacity with terminal A are selected as cooperative transmission terminals. These terminals will assist terminal A in data transmission and improve the communication efficiency of the overall network. For terminal A and each cooperative transmission terminal, a path selection algorithm (such as Dijkstra algorithm, Bellman-Ford algorithm, etc.) is used to determine the optimal communication path. These algorithms can find the shortest path or optimal path from the starting point to the end point based on the weight of the link (such as delay, packet loss rate, etc.). When determining the optimal communication path, the stability and reliability of the link also need to be considered to ensure the smooth progress of data transmission. In the actual communication process, the optimal communication path may change due to changes in the network topology and the instability of the communication link. Therefore, the optimal communication path needs to be optimized and adjusted regularly or on demand to adapt to network changes and ensure the reliability of data transmission.

[0053] In this embodiment, by determining the coordinated transmission terminal and the optimal communication path, the communication resources of the low-orbit satellite Internet of Things can be fully utilized, the efficiency of data transmission can be improved, the delay and packet loss rate of data transmission can be reduced, and the communication performance of the overall network can be improved. By selecting a coordinated transmission terminal with good communication link quality, short distance and sufficient capacity, the reliability of the network can be enhanced, which helps to reduce possible faults and errors in the data transmission process and improve the success rate of data transmission.

[0054] S104, prioritizing the plurality of environment data subsets, and transmitting environment data subsets of different priorities to corresponding cooperative sending terminals through different optimal communication paths.

[0055] In this embodiment, first, according to the importance, urgency and timeliness of environmental data, multiple environmental data subsets are prioritized. Priorities can be divided into different levels such as high, medium and low, and the specific classification criteria can be set according to actual needs. For example, for disaster warning data monitored in real time, it can be set to high priority; and for conventional environmental data collected periodically, it can be set to medium or low priority. According to the optimal communication path determined previously, the corresponding transmission path is selected for environmental data subsets of different priorities. The high-priority data subset should choose the optimal path with the best communication quality and the lowest delay for transmission to ensure the timeliness and accuracy of the data. The medium and low priority data subsets can choose other suboptimal paths for transmission to make full use of network resources and reduce transmission costs. According to the priority and optimal communication path of the environmental data subset, the data subsets of different priorities are allocated to the corresponding collaborative sending terminal. The collaborative sending terminal should have sufficient communication capabilities and storage resources to ensure that the data can be received and forwarded smoothly. At the same time, in order to avoid data conflicts and losses, it should be ensured that data subsets of the same priority are not allocated to the same collaborative sending terminal at the same time. In order of priority, the environmental data subsets are transmitted to the cooperative sending terminal through the corresponding optimal communication path. During the transmission process, the status of the communication link and the progress of data transmission should be monitored in real time to ensure the smooth progress of data transmission. In the event of communication link failure or data loss, remedial measures should be taken in a timely manner, such as reselecting the path or requesting the cooperative sending terminal to retransmit the data.

[0056] In this embodiment, by prioritizing and selecting the optimal communication path, it is possible to ensure that high-priority data is transmitted first, improve the efficiency and response speed of data transmission, and help obtain key data in an emergency in a timely manner to provide support for decision-making. Selecting communication paths and collaborative sending terminals based on data priority can make full use of network resources and avoid unnecessary waste, which helps reduce network operating costs and improve the overall network efficiency.

[0057] S105, receiving the environmental data subset sent by each cooperative transmitting terminal according to the low-orbit satellite, splicing each environmental data subset and forwarding it to the target terminal or ground station or data center.

[0058] In this embodiment, each environmental monitoring terminal is equipped with a sensor and a data acquisition module, which is responsible for collecting environmental data in real time. After the data collection is completed, the terminal packages the data into an environmental data subset and prepares to send it through the low-orbit satellite communication network. The terminal predicts the satellite transit time and orbit based on the pre-stored satellite ephemeris, and controls the antenna servo tracking to point to the satellite. During the satellite transit, the terminal sends the environmental data subset to the low-orbit satellite through the satellite communication module. The low-orbit satellite receives the environmental data subset from each terminal through its transceiver. The received data is verified to ensure the integrity and accuracy of the data. The data processing module on the low-orbit satellite splices the received multiple environmental data subsets to form a complete data set. During the splicing process, the data needs to be synchronized in time, spatial continuity verification and other operations to ensure the consistency and continuity of the data. The spliced ​​data set is forwarded to the target terminal, ground station or data center through the low-orbit satellite communication network. During the forwarding process, the low-orbit satellite network selects the optimal transmission path and strategy according to the location and needs of the target.

[0059] In this embodiment, through the low-orbit satellite communication network, centralized data processing and forwarding of multiple environmental monitoring terminals can be achieved, which improves the efficiency of data transmission and realizes real-time, efficient, wide-coverage, reliable and cost-effective data transmission services.

[0060] In some embodiments, in the above step S101, forming an ad hoc network among multiple low-orbit satellite Internet of Things terminals according to the device distribution and network topology of the multiple low-orbit satellite Internet of Things terminals specifically includes:

[0061] According to the location coordinate information of each low-orbit satellite IoT terminal, the inter-device distance matrix is ​​obtained by calculating the Euclidean distance between every two low-orbit satellite IoT terminals;

[0062] Based on the inter-device distance matrix, a K-means clustering algorithm is used to group multiple low-orbit satellite IoT terminals to determine a number of terminal groups;

[0063] According to the network topology of each low-orbit satellite IoT terminal in each terminal group, determine the master node and several relay nodes of each terminal group;

[0064] According to the relationship between each terminal group and the relationship between the main node and several relay nodes in each terminal group, a self-organizing network among multiple low-orbit satellite Internet of Things terminals is formed.

[0065] In this embodiment, the location coordinate information of the low-orbit satellite Internet of Things terminal is obtained, and the longitude and latitude coordinates of each terminal are determined by GPS positioning or triangulation positioning. According to the obtained terminal location coordinate information, the Euclidean distance formula is used to calculate the distance between each two terminals to generate an inter-device distance matrix. If the coordinates of terminal A are (x1, y1) and the coordinates of terminal B are (x2, y2), the Euclidean distance between the two terminals is √((x1-x2)^2+(y1-y2)^2). The generated inter-device distance matrix is ​​used as the input of the K-means clustering algorithm, and the terminals are divided into several cluster centers by iterative optimization. The number of cluster centers K can be preset according to business needs, or it can be adaptively determined by the elbow method and other methods. In each iteration of K-means clustering, the Euclidean distance from each terminal to each cluster center is calculated, and the terminal is divided into the cluster with the closest cluster center. The position of the cluster center is continuously updated until the clustering result converges or the maximum number of iterations is reached. For terminals divided into the same cluster, it is determined that they belong to the same terminal group. According to the clustering results, the low-orbit satellite IoT terminals are divided into several terminal groups, and the terminals in each terminal group are relatively close.

[0066] Obtain the network topology information of all low-orbit satellite IoT terminals in each terminal group, and determine the master node and relay node of each terminal group according to the network structure characteristics. Analyze the logical relationship between each terminal group to determine whether there is a path that can be connected between different terminal groups. If so, establish a virtual link between terminal groups. In each terminal group, obtain the network topology relationship between the master node and each relay node, and plan the optimal transmission path between nodes through the routing algorithm. Integrate the virtual link between terminal groups and the optimal path of nodes within the group to build an ad hoc network topology covering all low-orbit satellite IoT terminals. According to the ad hoc network topology, a distributed network addressing scheme is used to assign a unique network address identifier to each terminal node. Through the dynamic routing protocol, the network topology changes are discovered and updated in real time, the data transmission path is adaptively adjusted, and the network connectivity is maintained. Obtain the satellite orbit position and the terminal geographic location information, combine the ad hoc network topology structure, optimize the satellite communication link, and improve the network transmission efficiency.

[0067] Exemplarily, first, the inter-device distance matrix is ​​constructed by calculating the Euclidean distance between terminals. For example, assuming that there are 5 terminals with coordinates of (1, 2, 3), (4, 5, 6), (7, 8, 9), (2, 3, 4) and (5, 6, 7), a 5x5 distance matrix can be calculated, in which each element represents the distance between two terminals. Next, the terminals are grouped using the K-means clustering algorithm. The K-means algorithm clusters similar terminals together through iterative optimization. For example, the above 5 terminals may be divided into two groups: {(1, 2, 3), (2, 3, 4)} and {(4, 5, 6), (5, 6, 7), (7, 8, 9)}. This grouping method helps to improve the efficiency and reliability of the network because terminals with close geographical locations are more likely to establish stable communication links. After the terminal groups are determined, it is necessary to select a master node and a relay node for each group. The master node is usually the terminal with the strongest communication capability or the best location within the group, responsible for coordinating communication within the group and interaction with other groups. The relay nodes assist the master node and expand the network coverage. For example, in the group {(4,5,6), (5,6,7), (7,8,9)}, (5,6,7) may be selected as the master node because it is located in the center, and the other two terminals are set as relay nodes. Finally, based on the relationship between groups and the relationship between nodes within the group, a self-organizing network is formed. This network structure can adapt to the dynamic characteristics of low-orbit satellites and achieve efficient data transmission. For example, a direct communication link can be established between the master nodes of the two groups, and the relay nodes within the group are responsible for transmitting data from the edge terminal to the master node. This hierarchical network structure not only ensures the overall connectivity of the network, but also reduces unnecessary communication overhead. The formation process of this self-organizing network has important technical significance. It can adaptively handle the dynamic changes in network topology caused by the changes in the orbit of low-orbit satellites and improve the robustness and reliability of the network. At the same time, through grouping and hierarchical management, the complexity of the network is greatly reduced, making it possible to manage and optimize large-scale low-orbit satellite Internet of Things. This is of great significance for achieving global Internet of Things coverage and providing high-quality communication services.

[0068] Furthermore, the method further comprises:

[0069] Using the network topology of the ad hoc network as a state space, using the adjustable communication parameters of the ad hoc network as an action space, and using the network performance evaluation index as a reward function;

[0070] Periodically detecting the operation status and device movement of the self-organizing network, and judging whether the self-organizing network has reached an adjustment critical point according to the operation status and device movement status;

[0071] When it is determined that the ad hoc network has reached an adjustment critical point, a Q-Learning algorithm is used to readjust the terminal grouping situation and communication parameters of the ad hoc network based on the state space, the action space and the reward function.

[0072] In this embodiment, according to the network topology of the ad hoc network, the state space of the reinforcement learning algorithm is constructed, and the state space includes network topology information such as network node location and link status. According to the adjustable communication parameters of the ad hoc network, the action space of the reinforcement learning algorithm is constructed, and the action space includes adjustable communication parameters such as channel allocation, power control, and routing selection. According to the network performance evaluation indicators of the ad hoc network, the reward function of the reinforcement learning algorithm is constructed, and the reward function comprehensively considers performance indicators such as network throughput, delay, and reliability. The operating status of the ad hoc network is periodically detected, and the operating status information such as the traffic volume and queue length of the network nodes is obtained to determine whether the network is in a congested state. The movement of the devices in the ad hoc network is periodically detected, and the mobile status information such as the location and speed of the devices is obtained to determine whether the network topology has changed significantly. According to the operating status of the network and the movement of the devices, it is comprehensively judged whether the ad hoc network has reached the adjustment critical point. If the adjustment critical point is reached, the network reconstruction is triggered. When the self-organizing network reaches the adjustment critical point, the Q-Learning algorithm is used to learn the optimal terminal grouping scheme and communication parameter configuration through exploration and utilization according to the current state space, action space and reward function, so as to reconstruct and optimize the self-organizing network and improve network performance.

[0073] Exemplarily, the state space can be represented by an adjacency matrix in graph theory, where the matrix elements represent the connection status and link quality between nodes. The action space contains adjustable communication parameters, such as transmission power, channel allocation, and routing strategy. For example, the transmission power can be discretized into multiple levels, each level corresponds to an action, channel allocation can be represented as the selection of available frequency bands, and routing strategy can include selecting different relay nodes or changing data forwarding paths. The design of the reward function is directly related to the goal of network optimization. Common performance evaluation indicators include network throughput, delay, energy consumption, and coverage. For example, throughput and delay can be combined into a comprehensive indicator, while considering energy consumption factors to form a multi-objective optimization problem. The reward function can be designed as the weighted sum of these indicators, and the weights can be adjusted according to the specific application scenario. Periodic detection of network operation status and device mobility is the key to maintaining efficient network operation. This can be achieved by regularly collecting the location information, link quality, and data transmission statistics of each terminal. For example, a time threshold can be set, and when a certain proportion of terminal position changes exceed a preset distance, network adjustment is triggered. The application of the Q-Learning algorithm in this scenario reflects the advantages of reinforcement learning in a dynamic environment. The algorithm gradually learns the optimal strategy by constantly trying different actions (adjusting communication parameters) and observing the results (changes in network performance). For example, when network congestion is detected, Q-Learning may try to increase the transmission power of certain key nodes or change the routing strategy, and then update the Q value table according to the changes in network performance. This adaptive optimization method based on reinforcement learning can effectively cope with dynamic changes in low-orbit satellite networks. It can not only handle topological changes caused by terminal mobility, but also adapt to changes in business traffic patterns and external interference. Through continuous learning and optimization, the system can maintain efficient performance under different operating conditions and improve the robustness and reliability of the network. This is of great significance for achieving stable IoT coverage on a global scale and can support various complex application scenarios such as ocean monitoring, agricultural IoT, and smart cities.

[0074] In some embodiments, in the above step S102, the environmental data is classified and cut to form multiple environmental data subsets, specifically including:

[0075] Performing data preprocessing on the environmental data to obtain key characteristic parameters;

[0076] According to the preset data feature rules, the key feature parameters are classified using a decision tree algorithm, and the optimal partitioning attribute is selected based on the information gain ratio to obtain multiple environmental data subsets;

[0077] Obtaining classified and labeled historical massive environmental data, and using a logistic regression model to perform modeling training based on the historical massive environmental data to form a classifier discrimination model;

[0078] Based on the classifier discrimination model, the classification accuracy of the plurality of environmental data subsets is tested to obtain a test result, and the plurality of environmental data subsets are optimized and adjusted according to the test result.

[0079] In this embodiment, according to preset data feature rules, environmental data is cleaned and features are extracted to obtain key feature parameters; the key feature parameters are reduced in dimension using principal component analysis to remove redundant information and obtain an optimal feature subset; based on the optimal feature subset, a classification model is constructed using a decision tree algorithm, and an optimal partitioning attribute is selected based on the information gain ratio; if the partitioning attribute meets a preset threshold, the current data set is divided into multiple subsets to form child nodes of the decision tree; if the partitioning attribute does not meet the preset threshold, the current data set is used as a leaf node of the decision tree and marked with a corresponding category label; the above partitioning steps are recursively executed until all data are divided into leaf nodes or the preset tree depth limit is reached; based on the generated decision tree model, the newly collected environmental data is classified and predicted, its category is determined, and an environmental status assessment result is obtained, and the environmental status assessment result includes multiple environmental data subsets.

[0080] Obtain classified and labeled historical environmental data, preprocess the data, including data cleaning, feature extraction, and data normalization, to obtain a data set suitable for modeling. Use a logistic regression model to model the preprocessed data set, and iteratively optimize the model parameters to obtain a classifier discriminant model with good performance. Divide the original environmental data into multiple data subsets, each of which contains a certain number of data samples for subsequent model testing. Use the trained classifier discriminant model to perform classification prediction on each data subset to obtain the classification accuracy of each subset. According to the classification accuracy of each data subset, judge the generalization performance of the model on different data. If the accuracy is very different, it means that the model may have overfitting or underfitting problems. According to the model test results, optimize and adjust the data subset, and improve the data quality and feature expression ability through methods such as data enhancement and feature selection. Use the optimized and adjusted data subset to retrain and test the model, and continuously iterate and optimize until a classifier discriminant model with stable performance and strong generalization ability is obtained.

[0081] For example, taking water quality monitoring as an example, a decision tree can be constructed based on indicators such as pH value, dissolved oxygen, and ammonia nitrogen. Information gain ratio as a selection criterion for dividing attributes can effectively avoid the problem of biased multi-valued attributes. Assuming that at a certain node, the information gain ratio of pH value is the highest, the system will select pH value as the division criterion and divide the data into three subsets: acidic, neutral, and alkaline. This method can not only quickly perform a preliminary classification of water quality, but also intuitively show the degree of influence of various indicators on water quality judgment. Logistic regression models play an important role in the classification of environmental data. Taking soil pollution assessment as an example, historical data contains a large number of labeled soil samples, covering multiple features such as heavy metal content and organic matter content, as well as corresponding pollution level labels. Through logistic regression modeling, the system can learn the relationship between different features and pollution levels. For example, the model may find that when the lead content exceeds a certain threshold, the probability of soil being classified as heavily polluted increases significantly. This probability-based classification method can not only give the pollution level, but also provide the confidence of the classification, providing more reference information for decision-making. The inspection and optimization of the classifier discriminant model are key steps to ensure the practicality of the model. Taking forest fire risk prediction as an example, the model needs to be tested on multiple environmental data subsets after training. These subsets may represent different geographical regions or climatic conditions. By calculating the classification accuracy, precision, and recall of each subset, the model performance can be comprehensively evaluated. If it is found that the model performs poorly under certain specific conditions, such as the prediction accuracy in arid areas is significantly lower than in other areas, targeted optimization is required. This may include measures such as increasing relevant training samples, adjusting feature weights, or introducing new relevant features (such as vegetation coverage). Through this iterative optimization, the model can better adapt to different environmental conditions and improve the overall prediction accuracy. The comprehensive application of this environmental data analysis method not only improves the accuracy and efficiency of classification, but also provides a powerful decision-making support tool for environmental monitoring and management. Through continuous data collection, model training and optimization, the system can continuously improve its understanding and prediction capabilities of complex environmental issues, making important contributions to environmental protection and sustainable development.

[0082] In some embodiments, in the above step S103, determining the optimal communication path between a plurality of coordinated transmitting terminals and the first low-orbit satellite Internet of Things terminal and each coordinated transmitting terminal based on the communication topology relationship between each low-orbit satellite Internet of Things terminal in the ad hoc network specifically includes:

[0083] According to the communication connection relationship between the main node and relay node of each terminal group, the shortest path between nodes is calculated by Floyd algorithm to build the routing table within each terminal group;

[0084] Using each master node as a coordinated sending terminal of the first low-orbit satellite Internet of Things terminal;

[0085] Based on the routing table within each terminal group, with minimizing the distance between terminals as the optimization goal and the packet loss rate of the path not lower than the preset packet loss rate threshold as the constraint condition, the Dijkstra shortest path algorithm is used to determine the optimal communication path between the first low-orbit satellite IoT terminal and each collaborative sending terminal.

[0086] In this embodiment, according to the communication connection relationship between the master node and the relay node in each terminal group, the shortest path between the nodes is calculated by the Floyd algorithm, a routing table in the terminal group is constructed, and the routing table is stored in the local database of the master node and the relay node. The location information of the first low-orbit satellite Internet of Things terminal is obtained, and each master node is used as a cooperative sending terminal to obtain the location information of each cooperative sending terminal. According to the routing table in the terminal group, the distance between the first low-orbit satellite Internet of Things terminal and each cooperative sending terminal is calculated. If the distance exceeds the preset threshold, the path is judged to be unavailable and removed from the candidate path. For the remaining candidate paths, the historical packet loss rate data of each path is obtained. If the packet loss rate is lower than the preset packet loss rate threshold, the path is judged to not meet the constraint condition and is removed from the candidate path. The Dijkstra shortest path algorithm is adopted, and the minimization of the distance between terminals is taken as the optimization goal. Among the candidate paths that meet the constraint conditions, the optimal communication path between the first low-orbit satellite Internet of Things terminal and each cooperative sending terminal is determined. The routing information of the optimal communication path is sent to the first low-orbit satellite IoT terminal and each coordinated sending terminal, and the routing table and forwarding rules of the terminal are updated according to the routing information. If the packet loss rate of the path exceeds the preset threshold during the communication process, the above steps are re-executed to dynamically adjust the optimal communication path to ensure the reliability of the communication link.

[0087] Exemplarily, first, the shortest path between nodes is calculated by the Floyd algorithm to construct a routing table within the terminal group. For example, assuming that a terminal group contains 5 nodes, the Floyd algorithm will calculate a 5x5 distance matrix, in which each element represents the shortest distance between two nodes. This globally optimal path information is crucial to improving the overall efficiency of the network. Next, each master node is designated as a cooperative sending terminal. For example, in a network consisting of 20 terminals, 3-5 master nodes may be selected as cooperative sending terminals. These terminals usually have stronger processing capabilities and more stable link quality, and can effectively coordinate and forward data streams. Finally, based on the routing table within the terminal group, the Dijkstra algorithm is used to determine the optimal communication path. This step takes into account two key factors: distance minimization and packet loss rate threshold. Distance minimization helps to reduce transmission delay and energy consumption, while the packet loss rate threshold ensures the reliability of the link. For example, assume that it is necessary to find the best path from the first terminal to the cooperative sending terminal under the condition that the packet loss rate does not exceed 5%. The Dijkstra algorithm evaluates all possible paths, weighs the distance and packet loss rate, and finally selects a path that meets the conditions and has the shortest total distance. The advantage of this method is that it can dynamically adapt to changes in network conditions. For example, when a node exits the network due to a fault, the system can quickly recalculate the route to ensure the continuity of communication. In addition, by optimizing path selection, this method can significantly improve the throughput and response speed of the network. In practical applications, this is particularly important for scenarios that require real-time data transmission (such as environmental monitoring or disaster warning). It is worth noting that the implementation of this routing strategy needs to take into account the high-speed motion characteristics of low-orbit satellites. The rapid change of satellite position will cause frequent changes in network topology, so the routing algorithm must have the ability to converge quickly. In practice, this challenge can be addressed by regularly updating the routing table (such as every few minutes) to ensure the timeliness of routing information. In general, this routing method that combines the Floyd algorithm and the Dijkstra algorithm not only optimizes the utilization of network resources, but also improves the reliability and efficiency of communication. It provides strong technical support for the large-scale deployment and application of low-orbit satellite Internet of Things, and is expected to play an important role in global communications, remote monitoring and other fields.

[0088] In some embodiments, in the above step S104, the prioritization of the plurality of environmental data subsets and transmitting environmental data subsets of different priorities to corresponding cooperative sending terminals through different optimal communication paths specifically includes:

[0089] According to the priority evaluation index, the priority of each environmental data subset is evaluated to determine the priority ranking relationship of all environmental data subsets, wherein the priority evaluation index includes the importance, urgency, data volume and transmission frequency of the environmental data subset;

[0090] Determining path performance scores of different optimal communication paths according to path performance evaluation indicators, wherein the path performance evaluation indicators include topology, bandwidth, latency, and stability of the optimal communication path;

[0091] Matching the priority ranking relationship with the path performance score, determining the most suitable optimal communication path for the environmental data subsets with different priorities, and forming a matching result;

[0092] Based on the matching result, each subset of environmental data is transmitted to the cooperative sending terminal on the optimal communication path through the corresponding optimal communication path.

[0093] In this embodiment, environmental data is obtained, and the environmental data is divided into multiple subsets according to business needs. For each subset, parameters such as importance, urgency, data volume and transmission frequency are obtained from the priority evaluation index, and the priority score of the subset is obtained by weighted calculation. Network topology information is obtained, and parameters such as bandwidth, latency and stability are obtained from the path performance evaluation index for the communication path in the network, and the path performance score of each communication path is obtained by comprehensive evaluation. The priority score of the environmental data subset is matched with the path performance score of the communication path, and the Hungarian algorithm is used to solve the bipartite graph matching problem to obtain the matching result with the highest matching degree between priority and path performance. According to the matching result, the optimal communication path is selected for each environmental data subset. If the remaining bandwidth resources of the path meet the data transmission requirements of the subset, the subset data is packaged and sent to the cooperative sending terminal of the corresponding path. After receiving the data, the cooperative sending terminal uses the priority queue method to sort the data packets according to the priority identifier of the data packet, prioritizes the high-priority data, and feeds back the processing results to the data center. Based on the feedback results, the data center dynamically adjusts the priority score of the environmental data subset and the path performance score of the communication path, and continuously improves the efficiency and reliability of data transmission through iterative optimization. If a communication path is found to be congested or faulty during data transmission, the path switching mechanism is triggered, and the suboptimal path is selected for data transmission based on the path performance score and network topology to ensure the continuity and stability of data transmission.

[0094] For example, for a system that includes meteorological, geological and oceanographic data, typhoon warning data may be considered the highest priority because of its extremely high importance and urgency. In contrast, conventional ocean temperature data, although the data volume is large, may be given a lower priority. Path performance evaluation is the key to optimizing network resource utilization. Evaluation indicators cover topology, bandwidth, latency and stability. In practical applications, a path consisting of three nodes may receive a higher performance score due to its simple topology and low latency. Another path passing through five nodes, although with a larger bandwidth, may receive a lower score due to potential instability. Matching priority sorting with path performance scores is the core of achieving efficient data transmission. High-priority data should be assigned to the path with the best performance. For example, the aforementioned typhoon warning data may be assigned to the three-node low-latency path to ensure rapid transmission of information. Large-capacity but lower-priority ocean temperature data may be arranged for transmission on a five-node path with larger bandwidth. Data transmission based on the matching results is the last step of the whole process. Each subset of environmental data is transmitted to the corresponding cooperative sending terminal through its designated optimal communication path. This approach not only ensures the timely delivery of important data, but also optimizes the overall utilization of network resources. For example, in an actual operation, the system may process multiple data streams at the same time: high-priority earthquake monitoring data is transmitted through the fastest path, medium-priority atmospheric pollution data chooses a path with higher stability, and low-priority daily temperature data uses the remaining network capacity for transmission. The implementation of this optimization strategy can significantly improve the overall performance of the system. It can not only respond quickly in emergency situations (such as natural disaster warnings), but also improve network throughput and resource utilization in daily operations. In addition, this dynamic path allocation mechanism also makes the system more adaptable, and can flexibly adjust the transmission strategy according to the data characteristics and network conditions of different time periods, so as to maintain efficient and stable operation in the complex and changeable low-orbit satellite network environment.

[0095] In some embodiments, in the above steps S101 to S105, the method further includes:

[0096] Obtain signal interference data and transmission parameter setting data during historical data transmission of each optimal communication path;

[0097] Forming a first training data set by performing correlation analysis on the signal interference data and the transmission parameter setting data;

[0098] Taking the first training data set as input, using a support vector machine algorithm for modeling training to construct a signal interference change trend prediction model;

[0099] According to the signal interference change trend prediction model, the change trend of the signal interference intensity of each optimal communication path within a future preset time period is predicted to obtain a signal interference change trend prediction result;

[0100] According to the prediction result of the signal interference change trend, the optimal transmission parameter combination is determined by searching through a particle swarm optimization algorithm with the optimization goal of maximizing the data transmission rate and minimizing the bit error rate;

[0101] According to the optimal transmission parameter combination, the transmission parameter setting data of each optimal communication path is readjusted and optimized.

[0102] In this embodiment, the signal interference data and transmission parameter setting data in the historical data transmission process of the optimal communication path are obtained, and the signal interference data and transmission parameter setting data are preprocessed to remove outliers and missing values ​​to obtain preprocessed data. According to the preprocessed signal interference data and transmission parameter setting data, the Pearson correlation coefficient method is used to perform association analysis, the correlation between each parameter is calculated, and the parameter combination with high correlation is screened to form a first training data set. The first training data set is randomly divided into a training set and a test set, and the training set is modeled and trained using a support vector machine algorithm. The model hyperparameters are optimized by a grid search method to obtain the optimal signal interference change trend prediction model. The test set is predicted using the prediction model, the root mean square error and the mean absolute percentage error between the prediction result and the true value are calculated, and the prediction performance of the model is evaluated. If the prediction performance meets the preset threshold, the prediction model is determined to be the final model.

[0103] According to the signal interference change trend prediction model, the signal interference intensity change trend of each optimal communication path in the future preset time period is predicted to obtain the signal interference change trend prediction result. The maximization of data transmission rate and the minimization of bit error rate are used as optimization goals, and the fitness function of the particle swarm optimization algorithm is constructed. With the signal interference change trend prediction result as input, the particle swarm optimization algorithm is used to search and determine the optimal transmission parameter combination that can meet the optimization goal. If the particle swarm optimization algorithm search reaches the maximum number of iterations, the position of the current optimal particle is used as the optimal transmission parameter combination; otherwise, the particle speed and position are updated, and the search is returned to continue. According to the determined optimal transmission parameter combination, the transmission parameter setting data of each optimal communication path is adjusted and optimized to obtain the optimized transmission parameter setting. The optimized transmission parameter setting is sent to the corresponding communication device, the transmission parameters of the communication device are adjusted, and the data transmission performance of the communication link is improved.

[0104] Exemplarily, first, it is necessary to obtain historical data of each optimal communication path, including signal interference data and transmission parameter setting data, which include indicators such as signal-to-noise ratio, bit error rate, and transmission power in different time periods. For example, a path may record the average signal-to-noise ratio change per hour in the past month, from a higher level in the morning (such as 20dB) to a lower level at night (such as 15dB). Next, the first training data set is formed through association analysis. This step aims to discover the potential relationship between signal interference and transmission parameters. For example, it may be found that under certain specific transmission power settings (such as 30dBm), the signal interference level is low, while under other settings (such as 40dBm), the interference increases significantly. This association analysis helps to understand the impact of parameter adjustment on communication quality. Using the support vector machine algorithm to build a signal interference change trend prediction model is the next key step. The model can learn patterns in historical data and predict future signal interference. For example, the model may predict that the signal interference of a path will increase significantly in a specific season or weather conditions. This predictive capability enables the system to adjust parameters in advance to meet potential communication challenges. Based on the results of the prediction model, the trend of signal interference intensity changes in the future preset time period can be predicted. Assume that the model predicts that in the next 24 hours, the signal interference of a certain path will show a trend of increasing first and then decreasing, and the peak may appear at around 2 pm. In order to maximize the data transmission rate and minimize the bit error rate, the particle swarm optimization algorithm is used to search for the optimal transmission parameter combination. The algorithm simulates swarm intelligence and can quickly find a near-optimal solution in a complex parameter space. For example, the algorithm may find that in the predicted high interference period, reducing the transmission power to 25dBm and increasing the error correction coding strength can significantly reduce the bit error rate while maintaining a high transmission rate. Finally, according to the optimal parameter combination obtained by the optimization algorithm, the transmission parameters of each communication path are dynamically adjusted. This adjustment may include changing the modulation mode, adjusting the transmission power, updating the error correction coding scheme, etc. In this way, the system can adapt to the changing communication environment and always maintain the best performance. For example, during the night time when the signal interference is predicted to be low, the system may automatically switch to a higher-order modulation mode to increase data throughput. This dynamic optimization method based on historical data analysis and machine learning can not only improve the overall performance of the low-orbit satellite IoT system, but also significantly enhance its adaptability to complex environmental changes. Through continuous learning and optimization, the system can maintain stable and efficient communications under various challenging conditions, providing reliable data transmission for key applications such as earth observation and disaster monitoring.

[0105] In some embodiments, in the above steps S101 to S105, the method further includes:

[0106] Obtain historical equipment failure data of several low-orbit satellite IoT terminals, and use machine learning algorithms for training based on the historical equipment failure data to establish an equipment health monitoring model;

[0107] Acquire the device operation status data of each low-orbit satellite IoT terminal in real time, evaluate the device operation status data according to the device health monitoring model, and obtain the device health evaluation result;

[0108] Determine the equipment failure rate of each low-orbit satellite IoT terminal based on the equipment health assessment results;

[0109] By comparing the device failure rate with a preset device failure rate threshold, it is determined whether a device failure event is about to occur in each low-orbit satellite Internet of Things terminal.

[0110] In this embodiment, historical equipment failure data of low-orbit satellite IoT terminals is obtained, the failure data is preprocessed, the failure features are extracted, and a failure feature set is constructed. According to the failure feature set, a support vector machine algorithm or a random forest algorithm is used for training to establish an equipment health monitoring model. The model parameters are optimized by cross-validation and grid search to improve the accuracy and generalization ability of the model. The equipment operation status data of each low-orbit satellite IoT terminal is obtained in real time, and the data is feature extracted to obtain a real-time operation feature vector. The real-time operation feature vector is input into the equipment health monitoring model, and the equipment health assessment result is obtained through model prediction to determine the health status of the equipment. According to the equipment health assessment result, the frequency of failures within a certain time range is counted, and the equipment failure rate of each terminal is calculated. A preset equipment failure rate threshold is set, and by comparing the size relationship between the equipment failure rate of each terminal and the threshold, it is determined whether the terminal is in a high-risk state of an impending failure. If the equipment failure rate of the terminal exceeds the preset threshold, a fault warning is triggered, a fault prediction report is generated, and the operation and maintenance personnel are notified to perform equipment maintenance or fault prevention in advance to avoid service interruption caused by equipment abnormality. At the same time, the real-time data and prediction results of the terminal are fed back to the model training set for incremental learning, and the equipment health monitoring model is continuously optimized and updated.

[0111] For example, first, historical equipment failure data is obtained. These data include various types of failures, frequency of occurrence, environmental conditions and other information. For example, a terminal may have recorded 10 signal interruption failures in the past year, 8 of which occurred in extreme temperature environments. This data helps identify potential failure modes and triggers. The next key step is to train the health monitoring model using machine learning algorithms. Commonly used algorithms include random forests and support vector machines. These algorithms can learn from complex historical data and identify feature combinations that may cause failures. For example, the model may find that when the temperature exceeds 40°C and the humidity is higher than 85%, the probability of signal interruption failure increases significantly. Real-time acquisition of equipment operating status data is the key to model application. These data include multiple parameters such as temperature, humidity, signal strength, and battery power. Assume that the data reported by a terminal in real time shows: temperature 38°C, humidity 82%, signal strength -95dBm, and battery power 20%. The health monitoring model will evaluate based on these data and give quantitative indicators of the health status of the equipment. The equipment health assessment results are usually presented in the form of scores or grades. For example, a 0-100 scoring system may be used, where 90-100 indicates excellent health, 70-89 indicates good, 50-69 indicates attention, 30-49 indicates warning, and 0-29 indicates high risk. Based on the previous real-time data, the model may give an assessment result of 65 points, indicating that the equipment status needs close attention. Determining the equipment failure rate based on the health assessment results is an important part of predictive maintenance. The failure rate can be derived from the assessment score through statistical methods. For example, historical data may show that the probability of failure of equipment with a score between 60-70 in the next 30 days is 15%. Finally, the failure event is judged by comparing the equipment failure rate with the preset threshold. The setting of the threshold requires a balance between system reliability and maintenance cost. For example, if the threshold is set to 20%, the above equipment needs attention but has not yet triggered an alarm for impending failure. This early warning mechanism enables the operation team to take preventive measures in advance, such as adjusting the workload or arranging maintenance, thereby greatly reducing the possibility of actual failure and improving the stability and reliability of the entire low-orbit satellite IoT system.

[0112] In some embodiments, in the above steps S101 to S105, the method further includes:

[0113] Obtain the number of times a device protection mechanism is triggered for each low-orbit satellite IoT terminal, and determine the device physical damage risk level of each low-orbit satellite IoT terminal according to the number of times the device protection mechanism is triggered;

[0114] According to the risk level of physical damage to the equipment, a genetic algorithm is used to adjust the equipment positions of several low-orbit satellite IoT terminals to obtain an equipment layout optimization solution;

[0115] According to the equipment layout optimization plan, the optimal communication paths between the cooperative transmitting terminals in the self-organizing network and the first low-orbit satellite Internet of Things terminal and each cooperative transmitting terminal are re-determined.

[0116] In this embodiment, the number of times the protection mechanism of each low-orbit satellite Internet of Things terminal device is triggered is obtained, and the number of triggers is used as an input parameter. The physical damage risk level of each terminal device is calculated through a preset risk assessment model. The terminal devices are classified according to the physical damage risk level, and the risk level is used as the fitness function of the genetic algorithm. Through genetic operations such as crossover and mutation, the spatial position distribution of the terminal devices is optimized to obtain the device layout optimization scheme. According to the device layout optimization scheme, the Dijkstra algorithm is used to calculate the shortest communication path between the first terminal and each cooperative sending terminal, and the calculated shortest path is used as the optimal communication path. According to the optimal communication path, the routing table of each node in the self-organizing network is updated through the routing protocol to achieve dynamic optimization of the network topology structure and improve the robustness and reliability of the network. During the data transmission process, a convolutional neural network is used to extract and classify the data collected by the terminal device, identify abnormal data, and determine the type and severity of the abnormal data through an abnormal detection algorithm. According to the type and severity of the abnormal data, the protection mechanism parameters of the terminal device are dynamically adjusted, such as adjusting the trigger threshold of the protection mechanism, adjusting the data encryption strength, etc., to improve the security and reliability of the terminal device. Through the reinforcement learning algorithm, the allocation and scheduling of network resources are dynamically optimized according to changes in the network environment and the status of terminal devices, such as optimizing channel allocation and optimizing power control, to improve network performance and efficiency.

[0117] For example, a terminal triggers overvoltage protection 10 times, overcurrent protection 5 times, and temperature protection 3 times within a month. By analyzing these data, a physical damage risk level can be assigned to each terminal. The risk level can be determined by weighted scoring. Assuming that the weight of overvoltage protection is 3, the weight of overcurrent protection is 2, and the weight of temperature protection is 1, then the risk score of the above terminal is 10×3+5×2+3×1=43. 0-20 points can be defined as low risk, 21-40 points as medium risk, and 41 points or more as high risk. Based on this, the terminal is classified as a high risk level. After obtaining the risk level, the next step is to optimize the equipment layout. Genetic algorithm is an effective tool for solving such complex optimization problems. The algorithm simulates the biological evolution process and continuously optimizes the solution through selection, crossover and mutation operations. In this scenario, each possible equipment layout scheme is encoded as a "chromosome". The fitness function may consider multiple factors, such as the dispersion of high-risk equipment, the distance between equipment, signal coverage, etc. For example, suppose there are 10 terminals that need to be laid out, of which 3 are high risk, 4 are medium risk, and 3 are low risk. The initial population may contain 100 randomly generated layout plans. After multiple generations of evolution, the algorithm may come up with an optimized plan: high-risk devices are dispersed at the edge of the area, medium-risk devices are evenly distributed in the middle area, and low-risk devices are concentrated in the center. This layout can minimize the mutual influence between high-risk devices while ensuring the connectivity of the overall network. The optimized device layout will directly affect the network topology, so the cooperative sending terminals and communication paths need to be re-determined. In an ad hoc network, each terminal can serve as both a data source and a relay node. When selecting cooperative sending terminals, devices with low risk levels can be given priority because they are more stable and reliable. For example, in the new layout, a low-risk terminal may be selected as the main cooperative sending node, responsible for forwarding data from multiple high-risk terminals. The optimal communication path can be determined using routing algorithms such as the Dijkstra algorithm. Considering the risk of physical damage, the risk level can be used as a factor in the path cost. For example, a path passing through a high-risk terminal may be assigned a higher cost, thereby reducing the possibility of it being selected as the optimal path. In this way, not only can the network load be balanced, but the stability and reliability of the overall system can also be improved. Through this series of optimizations, the operating efficiency and security of the low-orbit satellite Internet of Things can be significantly improved. The optimization of device layout reduces mutual interference between high-risk devices, and the routing strategy based on risk level further enhances the robustness of the network. This approach can not only extend the life of the equipment, but also improve the reliability of the entire system and provide users with more stable services.

[0118] Reference Figure 2 An embodiment of the present invention provides a data collaborative transmission system 2 for low-orbit satellite Internet of Things terminals, and the system 2 specifically includes:

[0119] The first data collaborative transmission module 201 is used to form an ad hoc network among multiple low-orbit satellite Internet of Things terminals according to the device distribution and network topology of multiple low-orbit satellite Internet of Things terminals;

[0120] The second data collaborative transmission module 202 is used to obtain the environmental data collected by the first low-orbit satellite Internet of Things terminal, and if the environmental data is larger than a preset data size threshold, the environmental data is classified and cut to form multiple environmental data subsets;

[0121] The third data cooperative transmission module 203 is used to determine the optimal communication path between a plurality of cooperative transmission terminals and the first low-orbit satellite Internet of Things terminal and each cooperative transmission terminal based on the communication topology relationship between each low-orbit satellite Internet of Things terminal in the ad hoc network;

[0122] A fourth data cooperative transmission module 204 is used to prioritize the plurality of environmental data subsets and transmit environmental data subsets of different priorities to corresponding cooperative sending terminals through different optimal communication paths;

[0123] The fifth data cooperative transmission module 205 is used to receive the environmental data subset sent by each cooperative sending terminal according to the low-orbit satellite, splice each environmental data subset and forward it to the target terminal or ground station or data center.

[0124] It is understandable that if Figure 1 The contents of the data collaborative transmission method embodiment of the low-orbit satellite Internet of Things terminal shown in the figure are all applicable to the data collaborative transmission system embodiment of the low-orbit satellite Internet of Things terminal. The functions specifically implemented by the data collaborative transmission system embodiment of the low-orbit satellite Internet of Things terminal are similar to those of the embodiment of the low-orbit satellite Internet of Things terminal. Figure 1 The data collaborative transmission method embodiment of the low-orbit satellite Internet of Things terminal shown in FIG. 1 is the same as that of the embodiment of the low-orbit satellite Internet of Things terminal shown in FIG. 1 , and the beneficial effects achieved are the same as those of the embodiment of the low-orbit satellite Internet of Things terminal shown in FIG. Figure 1 The beneficial effects achieved by the embodiment of the data collaborative transmission method for the low-orbit satellite Internet of Things terminal shown are also the same.

[0125] It should be noted that the information interaction, execution process and other contents between the above-mentioned systems are based on the same concept as the embodiment of the method of the present invention. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0126] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0127] Reference Figure 3 The embodiment of the present invention further provides a computer device 3, comprising: a memory 302 and a processor 301 and a computer program 303 stored in the memory 302. When the computer program 303 is executed on the processor 301, a data collaborative transmission method for a low-orbit satellite Internet of Things terminal as described in any one of the above methods is implemented.

[0128] The computer device 3 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The computer device 3 may include, but is not limited to, a processor 301 and a memory 302. Those skilled in the art will appreciate that Figure 3 It is only an example of computer device 3 and does not constitute a limitation on computer device 3. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components, for example, it may also include input and output devices, network access devices, etc.

[0129] The processor 301 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0130] In some embodiments, the memory 302 may be an internal storage unit of the computer device 3, such as a hard disk or memory of the computer device 3. In other embodiments, the memory 302 may also be an external storage device of the computer device 3, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the computer device 3. Further, the memory 302 may also include both an internal storage unit and an external storage device of the computer device 3. The memory 302 is used to store an operating system, an application program, a boot loader, data, and other programs, such as the program code of the computer program. The memory 302 may also be used to temporarily store data that has been output or is to be output.

[0131] An embodiment of the present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the method for collaborative data transmission of a low-orbit satellite Internet of Things terminal as described in any of the above methods is implemented.

[0132] In this embodiment, if the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, USB flash drive, mobile hard disk, disk or optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0133] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0134] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0135] In the embodiments disclosed in the present application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0136] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

Claims

1. A data collaborative transmission method for low-orbit satellite Internet of Things terminals, characterized in that: The method specifically comprises: According to the device distribution and network topology of multiple low-orbit satellite IoT terminals, a self-organizing network among multiple low-orbit satellite IoT terminals is formed; Acquire environmental data collected by the first low-orbit satellite Internet of Things terminal, and if the environmental data is larger than a preset data size threshold, classify and cut the environmental data to form multiple environmental data subsets; Based on the communication topology relationship between each low-orbit satellite Internet of Things terminal in the self-organizing network, determine the optimal communication path between a plurality of coordinated transmission terminals and the first low-orbit satellite Internet of Things terminal and each coordinated transmission terminal; Prioritizing the plurality of environmental data subsets, and transmitting environmental data subsets of different priorities to corresponding cooperative sending terminals through different optimal communication paths; Receiving the environmental data subset sent by each cooperative sending terminal according to the low-orbit satellite, splicing each environmental data subset and forwarding it to the target terminal or ground station or data center; Obtain signal interference data and transmission parameter setting data during historical data transmission of each optimal communication path; Forming a first training data set by performing correlation analysis on the signal interference data and the transmission parameter setting data; Taking the first training data set as input, using a support vector machine algorithm for modeling training to construct a signal interference change trend prediction model; According to the signal interference change trend prediction model, the change trend of the signal interference intensity of each optimal communication path within a future preset time period is predicted to obtain a signal interference change trend prediction result; According to the prediction result of the signal interference change trend, the optimal transmission parameter combination is determined by searching through a particle swarm optimization algorithm with the optimization goal of maximizing the data transmission rate and minimizing the bit error rate; According to the optimal transmission parameter combination, the transmission parameter setting data of each optimal communication path is readjusted and optimized.

2. The method according to claim 1, characterized in that The forming of a self-organizing network among a plurality of low-orbit satellite Internet of Things terminals according to the device distribution and network topology of the plurality of low-orbit satellite Internet of Things terminals specifically includes: According to the location coordinate information of each low-orbit satellite IoT terminal, the inter-device distance matrix is ​​obtained by calculating the Euclidean distance between every two low-orbit satellite IoT terminals; Based on the inter-device distance matrix, a K-means clustering algorithm is used to group multiple low-orbit satellite IoT terminals to determine a number of terminal groups; According to the network topology of each low-orbit satellite IoT terminal in each terminal group, determine the master node and several relay nodes of each terminal group; According to the relationship between each terminal group and the relationship between the main node and several relay nodes in each terminal group, a self-organizing network among multiple low-orbit satellite Internet of Things terminals is formed.

3. The method according to claim 2, characterized in that The method further comprises: Using the network topology of the ad hoc network as a state space, using the adjustable communication parameters of the ad hoc network as an action space, and using the network performance evaluation index as a reward function; Periodically detecting the operation status and device movement of the self-organizing network, and judging whether the self-organizing network has reached an adjustment critical point according to the operation status and device movement status; When it is determined that the ad hoc network has reached an adjustment critical point, a Q-Learning algorithm is used to readjust the terminal grouping situation and communication parameters of the ad hoc network based on the state space, the action space and the reward function.

4. The method according to claim 1, characterized in that: The environmental data is classified and cut into multiple environmental data subsets, specifically including: Performing data preprocessing on the environmental data to obtain key characteristic parameters; According to the preset data feature rules, the key feature parameters are classified using a decision tree algorithm, and the optimal partitioning attribute is selected based on the information gain ratio to obtain multiple environmental data subsets; Obtaining classified and labeled historical massive environmental data, and using a logistic regression model to perform modeling training based on the historical massive environmental data to form a classifier discrimination model; Based on the classifier discrimination model, the classification accuracy of the plurality of environmental data subsets is tested to obtain a test result, and the plurality of environmental data subsets are optimized and adjusted according to the test result.

5. The method according to claim 2, characterized in that: The determining, based on the communication topology relationship between each low-orbit satellite Internet of Things terminal in the ad hoc network, a plurality of coordinated transmission terminals and respective optimal communication paths between the first low-orbit satellite Internet of Things terminal and each coordinated transmission terminal specifically includes: According to the communication connection relationship between the main node and relay node of each terminal group, the shortest path between nodes is calculated by Floyd algorithm to build the routing table within each terminal group; Using each master node as a coordinated sending terminal of the first low-orbit satellite Internet of Things terminal; Based on the routing table within each terminal group, with minimizing the distance between terminals as the optimization goal and the packet loss rate of the path not lower than the preset packet loss rate threshold as the constraint condition, the Dijkstra shortest path algorithm is used to determine the optimal communication path between the first low-orbit satellite IoT terminal and each collaborative sending terminal.

6. The method according to claim 1, characterized in that The prioritizing of the plurality of environment data subsets and transmitting environment data subsets of different priorities to corresponding coordinated sending terminals through different optimal communication paths specifically includes: According to the priority evaluation index, the priority of each environmental data subset is evaluated to determine the priority ranking relationship of all environmental data subsets, wherein the priority evaluation index includes the importance, urgency, data volume and transmission frequency of the environmental data subset; Determining path performance scores of different optimal communication paths according to path performance evaluation indicators, wherein the path performance evaluation indicators include topology, bandwidth, latency, and stability of the optimal communication path; Matching the priority ranking relationship with the path performance score, determining the most suitable optimal communication path for the environmental data subsets with different priorities, and forming a matching result; Based on the matching result, each subset of environmental data is transmitted to the cooperative sending terminal on the optimal communication path through the corresponding optimal communication path.

7. The method according to any one of claims 1 to 6, characterized in that The method further comprises: Obtain historical equipment failure data of several low-orbit satellite IoT terminals, and use machine learning algorithms for training based on the historical equipment failure data to establish an equipment health monitoring model; Acquire the device operation status data of each low-orbit satellite IoT terminal in real time, evaluate the device operation status data according to the device health monitoring model, and obtain the device health evaluation result; Determine the equipment failure rate of each low-orbit satellite IoT terminal based on the equipment health assessment results; By comparing the device failure rate with a preset device failure rate threshold, it is determined whether a device failure event is about to occur in each low-orbit satellite Internet of Things terminal.

8. The method according to any one of claims 1 to 6, characterized in that The method further comprises: Obtain the number of times a device protection mechanism is triggered for each low-orbit satellite IoT terminal, and determine the device physical damage risk level of each low-orbit satellite IoT terminal according to the number of times the device protection mechanism is triggered; According to the risk level of physical damage to the equipment, a genetic algorithm is used to adjust the equipment positions of several low-orbit satellite IoT terminals to obtain an equipment layout optimization solution; According to the equipment layout optimization plan, the optimal communication paths between the cooperative transmitting terminals in the self-organizing network and the first low-orbit satellite Internet of Things terminal and each cooperative transmitting terminal are re-determined.

9. A data collaborative transmission system for low-orbit satellite Internet of Things terminals, characterized in that: The system specifically comprises: The first data collaborative transmission module is used to form a self-organizing network among multiple low-orbit satellite Internet of Things terminals according to the device distribution and network topology of multiple low-orbit satellite Internet of Things terminals; A second data collaborative transmission module is used to obtain environmental data collected by the first low-orbit satellite Internet of Things terminal, and if the environmental data is larger than a preset data size threshold, the environmental data is classified and cut to form multiple environmental data subsets; A third data cooperative transmission module is used to determine the optimal communication path between a plurality of cooperative transmission terminals and the first low-orbit satellite Internet of Things terminal and each cooperative transmission terminal based on the communication topology relationship between each low-orbit satellite Internet of Things terminal in the ad hoc network; A fourth data cooperative transmission module, used to prioritize the plurality of environmental data subsets, and transmit environmental data subsets of different priorities to corresponding cooperative sending terminals through different optimal communication paths; A fifth data cooperative transmission module is used to receive the environmental data subset sent by each cooperative sending terminal according to the low-orbit satellite, splice each environmental data subset and forward it to the target terminal or ground station or data center; The system is also used to obtain signal interference data and transmission parameter setting data during historical data transmission of each optimal communication path; Forming a first training data set by performing correlation analysis on the signal interference data and the transmission parameter setting data; Taking the first training data set as input, using a support vector machine algorithm for modeling training to construct a signal interference change trend prediction model; According to the signal interference change trend prediction model, the change trend of the signal interference intensity of each optimal communication path within a future preset time period is predicted to obtain a signal interference change trend prediction result; According to the prediction result of the signal interference change trend, the optimal transmission parameter combination is determined by searching through a particle swarm optimization algorithm with the optimization goal of maximizing the data transmission rate and minimizing the bit error rate; According to the optimal transmission parameter combination, the transmission parameter setting data of each optimal communication path is readjusted and optimized.

Images