Anti-interference method for LEO satellite system

Abstract

The invention relates to the technical field of satellite communication, in particular to an LEO satellite system-oriented anti-interference method, which comprises the following steps of: performing spectrum prediction on a plurality of LEO satellite systems in a current spectrum management block chain network by utilizing a preset prediction model, and taking a spectrum with the highest spectrum efficiency as a used spectrum of the LEO satellite system based on a prediction result, and performing signal-to-noise ratio evaluation, determining a target LEO satellite system of which the signal-to-noise ratio is smaller than a preset threshold value, and after the influence coefficient of the signal-to-noise ratio is reduced, performing the step of performing spectrum prediction on the LEO satellite system by using the preset prediction model again until the signal-to-noise ratio of the LEO satellite system is greater than or equal to the preset threshold value. Therefore, the problems of serious mutual interference and insufficient anti-interference capability among satellite systems in emergency in the background technology are solved, and efficient and intelligent spectrum management and improvement of the anti-interference capability are realized by combining the block chain and the deep learning technology.

Description

Technical Field

[0001] The present invention relates to the field of satellite communication technology, and in particular to an anti-interference method for a LEO satellite system. Background Art

[0002] With the rapid development of mobile Internet, Internet of Things (IoT) and 5G networks, people's growing demand for communications has promoted the development of low Earth Orbit (LEO) communication systems. Due to its low orbit, low latency and high coverage, LEO satellite systems have become a hot spot in the current satellite communication field, and countries and commercial companies have also joined the wave of low-orbit satellite construction. However, with the continuous increase in the number of LEO satellites, spectrum and orbital resources have become increasingly tight. The rational and efficient use of spectrum resources is crucial to promoting the sustainable construction and development of LEO satellite systems. In order to achieve efficient use of spectrum and orbital resources, it is increasingly important to effectively suppress mutual interference between LEO satellite systems.

[0003] As a distributed ledger technology, blockchain technology records all transactions and data in a decentralized manner, ensuring the transparency and immutability of data. In spectrum management, blockchain technology can be used to record spectrum usage to ensure data transparency and security. At the same time, smart contracts, as automated programs deployed on blockchains, can automatically execute contract content according to predefined rules and conditions, thereby achieving dynamic allocation and automated management of spectrum resources and ensuring efficient use of spectrum resources among different users.

[0004] As the number of LEO satellites in space increases, spectrum resources become a key resource to support wireless communications. A cognitive LEO system may be affected by emergencies when detecting GEO (Geostationary Earth Orbit) systems (such as ground microwave interference, propagation fade and sun outage, ionosphere scintillation and aerosphere scintillation, unauthorized use and malicious interference, and many other environmental factors), which may lead to further interference from other LEO satellite systems, thereby seriously affecting the spectrum and causing it to change.

[0005] Although the existing LEO satellite systems have made significant progress in spectrum management and anti-environmental interference, there are still deficiencies in the LEO satellite system's anti-mutual interference system under sudden conditions and how to resist attacks from other attacking satellites without affecting the transmission of information. As a result, the robustness of the LEO giant satellite constellation composed of multiple satellite orbital planes and hundreds of small satellites is low, and the satellite-to-ground link transmission rate (Bit Rate), bit error rate (Bit Error Rate, BER) and spectrum efficiency (Spectral Efficiency) need to be improved. Summary of the invention

[0006] The present invention provides an anti-interference method for LEO satellite systems to solve the problems of serious mutual interference and insufficient anti-interference ability between satellite systems in emergency situations in the background technology. By combining blockchain and deep learning technology, efficient and intelligent spectrum management and anti-interference ability improvement are achieved.

[0007] The first aspect of the present invention provides an anti-interference method for a LEO satellite system, comprising the following steps: Acquire multiple LEO satellite systems of the current spectrum management blockchain network; Performing spectrum prediction on the multiple LEO satellite systems using a preset prediction model, and selecting a spectrum with the highest spectrum efficiency based on the prediction result, and using the spectrum with the highest spectrum efficiency as a use spectrum of the multiple LEO satellite systems, and performing signal-to-noise ratio evaluation when the multiple LEO satellite systems transmit signals to obtain an evaluation result; Based on the evaluation result, a target LEO satellite system having a signal-to-noise ratio less than a preset threshold is determined, and after reducing an influence coefficient of the signal-to-noise ratio of the target LEO satellite system, the step of performing spectrum prediction on the multiple LEO satellite systems using a preset prediction model is re-executed until the signal-to-noise ratios of the multiple LEO satellite systems are greater than or equal to the preset threshold.

[0008] According to one embodiment of the present invention, before using the preset prediction model to perform spectrum prediction on the multiple LEO satellite systems, the method further includes: obtaining historical spectrum usage data of the plurality of LEO satellite systems; The deep learning-based prediction model is trained using the historical spectrum usage data to obtain the preset prediction model, and the preset prediction model is deployed to the current spectrum management blockchain network.

[0009] According to one embodiment of the present invention, the anti-interference method for the LEO satellite system further includes: Determining whether any LEO satellite system among the plurality of LEO satellite systems is in a full spectrum suppression environment; If any of the LEO satellite systems is in the full spectrum suppression environment, the suppressed signal is restored based on a pre-trained neural network model, and the restored signal is output.

[0010] According to one embodiment of the present invention, after outputting the restored signal, the method further includes: Determine whether the current malicious interference is co-track interference; If the current malicious interference is not co-orbit interference, the orbit of any LEO satellite system or the attitude of the LEO satellite system is adjusted based on the satellite attitude control system to achieve anti-interference.

[0011] According to the anti-interference method for LEO satellite systems of the embodiment of the present invention, a preset prediction model is used to predict the spectrum of multiple LEO satellite systems in the current spectrum management blockchain network, and the spectrum with the highest spectrum efficiency is used as the use spectrum of the LEO satellite system based on the prediction result, and the signal-to-noise ratio is evaluated to determine the target LEO satellite system whose signal-to-noise ratio is less than the preset threshold, and after reducing the influence coefficient of the signal-to-noise ratio, the step of using the preset prediction model to predict the spectrum of the LEO satellite system is re-executed until the signal-to-noise ratio of the LEO satellite system is greater than or equal to the preset threshold. Thus, the problem of serious mutual interference and insufficient anti-interference ability between satellite systems in emergency situations in the background technology is solved, and by combining blockchain and deep learning technology, efficient and intelligent spectrum management and anti-interference ability improvement are achieved.

[0012] A second aspect of the present invention provides an anti-interference device for a LEO satellite system, comprising: An acquisition module, used to acquire multiple LEO satellite systems of the current spectrum management blockchain network; a spectrum optimization and evaluation module, configured to perform spectrum prediction on the multiple LEO satellite systems using a preset prediction model, and screen out the spectrum with the highest spectrum efficiency based on the prediction result, and use the spectrum with the highest spectrum efficiency as the use spectrum of the multiple LEO satellite systems, and perform signal-to-noise ratio evaluation when the multiple LEO satellite systems transmit signals to obtain an evaluation result; an adaptive adjustment module, configured to determine, based on the evaluation result, a target LEO satellite system whose signal-to-noise ratio is less than a preset threshold, and after reducing an influence coefficient of the signal-to-noise ratio of the target LEO satellite system, re-execute the step of performing spectrum prediction on the multiple LEO satellite systems using a preset prediction model until the signal-to-noise ratios of the multiple LEO satellite systems are all greater than or equal to the preset threshold.

[0013] According to one embodiment of the present invention, before using the preset prediction model to perform spectrum prediction on the multiple LEO satellite systems, the spectrum optimization and evaluation module is further used to: obtaining historical spectrum usage data of the plurality of LEO satellite systems; The deep learning-based prediction model is trained using the historical spectrum usage data to obtain the preset prediction model, and the preset prediction model is deployed to the current spectrum management blockchain network.

[0014] According to one embodiment of the present invention, the anti-interference device for the LEO satellite system is further used for: Determining whether any LEO satellite system among the plurality of LEO satellite systems is in a full spectrum suppression environment; If any of the LEO satellite systems is in the full spectrum suppression environment, the suppressed signal is restored based on a pre-trained neural network model, and the restored signal is output.

[0015] According to one embodiment of the present invention, after outputting the recovered signal, the anti-interference device for the LEO satellite system is further used to: Determine whether the current malicious interference is co-track interference; If the current malicious interference is not co-orbit interference, the orbit of any LEO satellite system or the attitude of the LEO satellite system is adjusted based on the satellite attitude control system to achieve anti-interference.

[0016] According to the anti-interference device for LEO satellite systems of the embodiment of the present invention, a preset prediction model is used to predict the spectrum of multiple LEO satellite systems in the current spectrum management blockchain network, and the spectrum with the highest spectrum efficiency is used as the use spectrum of the LEO satellite system based on the prediction result, and the signal-to-noise ratio is evaluated to determine the target LEO satellite system whose signal-to-noise ratio is less than the preset threshold, and after reducing the influence coefficient of the signal-to-noise ratio, the step of using the preset prediction model to predict the spectrum of the LEO satellite system is re-executed until the signal-to-noise ratio of the LEO satellite system is greater than or equal to the preset threshold. Thus, the problem of serious mutual interference and insufficient anti-interference ability between satellite systems in emergency situations in the background technology is solved, and by combining blockchain and deep learning technology, efficient and intelligent spectrum management and anti-interference ability improvement are achieved.

[0017] A third aspect of the present invention provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the anti-interference method for LEO satellite systems as described in the above embodiment.

[0018] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, the program being executed by a processor to implement the anti-interference method for a LEO satellite system as described in the above embodiment.

[0019] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which: Figure 1 A flowchart of an anti-interference method for a LEO satellite system provided according to an embodiment of the present invention; Figure 2 A schematic diagram of a flow chart of an anti-interference method for a LEO satellite system according to an embodiment of the present invention; Figure 3 A block diagram of an anti-interference device for a LEO satellite system according to an embodiment of the present invention; Figure 4 FIG. 4 is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0021] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0022] The following describes an anti-interference method for a LEO satellite system according to an embodiment of the present invention with reference to the accompanying drawings. In view of the problem that most of the existing technical methods mentioned in the above background technology only consider the transmission loss model of the satellite-to-ground link, atmospheric absorption, cloud attenuation and the influence of the antenna angle, and do not take the mutual interference between LEO systems into consideration, the present invention provides an anti-interference method for a LEO satellite system, which effectively suppresses the mutual interference between LEO satellite systems in emergency situations, solves the problem of serious mutual interference between satellite systems and insufficient anti-interference capability in emergency situations in the background technology, and realizes efficient and intelligent spectrum management and improved anti-interference capability by combining blockchain and deep learning technology.

[0023] Specifically, Figure 1 A schematic flow chart of an anti-interference method for a LEO satellite system provided in an embodiment of the present invention.

[0024] like Figure 1As shown, the anti-interference method for the LEO satellite system includes the following steps: In step S101, multiple LEO satellite systems of the current spectrum management blockchain network are obtained.

[0025] Specifically, in the initial stage, the embodiment of the present invention connects all LEO satellite systems that agree to the blockchain network protocol (i.e., comply with non-interference and are willing to provide their own historical data) to the current spectrum management blockchain network through the blockchain client, and obtains the initial network configuration information and receives the necessary blockchain network access information.

[0026] Furthermore, LEO satellite communication equipment establishes a connection with the blockchain network access node via a satellite link, ensuring that all communication devices can participate in the blockchain network and download smart contract logic and other necessary spectrum management configuration data.

[0027] In step S102, spectrum prediction is performed on multiple LEO satellite systems using a preset prediction model, and the spectrum with the highest spectrum efficiency is screened out based on the prediction results. The spectrum with the highest spectrum efficiency is used as the spectrum used by the multiple LEO satellite systems, and a signal-to-noise ratio evaluation is performed during signal transmission of the multiple LEO satellite systems to obtain an evaluation result.

[0028] Among them, in some embodiments, before using a preset prediction model to perform spectrum prediction on multiple LEO satellite systems, it also includes: obtaining historical spectrum usage data of multiple LEO satellite systems; using the historical spectrum usage data to train a deep learning-based prediction model to obtain a preset prediction model, and deploying the preset prediction model to the current spectrum management blockchain network.

[0029] Each LEO satellite system participating in the blockchain network runs a lightweight blockchain client on its device to collect and record satellite data. When each satellite uses the spectrum, the client records the spectrum usage information (such as frequency band, time, location, interference situation and user ID) in the blockchain network. At the same time, the spectrum usage information is pre-processed (including data cleaning, denoising and normalization) to ensure data consistency and quality.

[0030] Exemplarily, the specific recorded spectrum usage information can be represented by the following vector:

[0031] in, For spectrum usage information, is the frequency band, For time, For location, For interference situations, is the user ID.

[0032] Therefore, various LEO satellite systems are connected through blockchain technology, and the ledgers are collaboratively maintained to ensure the transparency and non-tamperability of historical data, thereby providing a reliable data foundation. At the same time, it can also be called in real time to ensure the timeliness of the data.

[0033] Furthermore, when a cognitive LEO satellite system in the blockchain network is affected by an emergency (such as ground microwave interference, abnormal radio wave fading and solar eclipse interference, ionospheric scintillation and atmospheric scintillation, unauthorized use and malicious interference) when detecting a GEO system, the unstable satellite is regarded as an interfering LEO satellite system, and the signal-to-noise ratio (SNR) of the interfering LEO satellite system to the normal LEO satellite system is recorded, where the calculation formula of the signal-to-noise ratio is:

[0034] in, is the signal-to-noise ratio, is the signal power, is the noise power.

[0035] Furthermore, according to the new signal-to-noise ratio (the signal-to-noise ratio of the LEO satellite system after being interfered by the sudden situation) and the original signal-to-noise ratio (the signal-to-noise ratio of the LEO satellite system before being interfered by the sudden situation, that is, the signal-to-noise ratio under normal conditions without interference), the influence coefficient of the interfering LEO satellite system on the signal-to-noise ratio of the normal LEO satellite system can be obtained. ( ):

[0036] in, is the influence coefficient of the interference LEO satellite system on the signal-to-noise ratio of the normal LEO satellite system, is the new signal-to-noise ratio, is the original signal-to-noise ratio.

[0037] Furthermore, the obtained influence coefficient of the interfering LEO satellite system on the signal-to-noise ratio of the normal LEO satellite system is recorded in the blockchain network as historical data.

[0038] Furthermore, after experiencing "enough" "emergencies", that is, after collecting enough historical spectrum usage data of LEO satellite systems, the historical spectrum usage data is extracted from the blockchain network, and the extracted historical spectrum usage data is used to train the prediction model based on deep learning, and the spectrum usage prediction is performed based on the trained preset prediction model. The specific steps are as follows: The first step is to select and train a prediction model based on deep learning. Select a suitable time series prediction model, such as using a bidirectional long short-term memory network model (Bi-LSTM) to capture the temporal characteristics of spectrum usage, and use the pre-processed historical spectrum usage data to train the Bi-LSTM model.

[0039] Among them, the structure of the internal unit of the Bi-LSTM model includes the input gate gating unit , Forget gate gating unit , output gate gating unit , the cell state at the current time step , the cell state at the previous time step , the hidden state at the current time step , the hidden state of the previous time step , the input of the current time step , candidate memory state at the current time step , activation function , activation function φ and activation function ћ.

[0040] Furthermore, the update formula of the Bi-LSTM model is as follows:

[0041]

[0042]

[0043]

[0044]

[0045]

[0046] in, is the Hadamard product operator, is the input weight of the input gate, is the hidden state weight of the input gate, is the input weight of the forget gate, is the hidden state weight of the forget gate, is the input weight of the output gate, is the hidden state weight of the output gate, is the input weight of the cell state, is the hidden state weight of the cell state, is the bias term, and .

[0047] Secondly, the trained model is verified and deployed. Specifically, some data from the historical spectrum usage data is used to verify the model, and the model parameters are adjusted and optimized to improve the accuracy of the prediction, thereby obtaining the preset prediction model. Finally, the trained preset prediction model is deployed on the current spectrum management blockchain network so that the smart contract can call the preset prediction model for spectrum prediction, and by calculating the spectrum efficiency of the remaining selectable spectrum, the spectrum with the least interference to the LEO satellite system signal transmission is selected, thereby suppressing the interference of other satellites to itself.

[0048] Therefore, in addition to the basic smart contract functions (such as registration of satellite and its spectrum information, query of spectrum usage, update of spectrum information, and deletion of spectrum that can no longer be used), the embodiment of the present invention adds a function to avoid the spectrum information of the prediction results of other preset prediction models (such as the above-mentioned Bi-LSTM model) that interfere with the LEO satellite system, and simultaneously performs spectrum efficiency screening, wherein the calculation formula of spectrum efficiency is:

[0049] in, is the spectrum efficiency, R is the data transmission rate in bps, and B is the signal bandwidth in Hz.

[0050] Furthermore, the spectrum with the highest spectrum efficiency is selected within the scope of the smart contract, and the spectrum with the highest spectrum efficiency is used as the spectrum used by multiple LEO satellite systems for communication between the LEO satellite system and the GEO system. In addition, for multiple LEO satellite systems after the entire set of smart contracts are enabled, the signal-to-noise ratio is evaluated during signal transmission to obtain an evaluation result.

[0051] In step S103, based on the evaluation result, a target LEO satellite system whose signal-to-noise ratio is less than a preset threshold is determined, and after reducing the influence coefficient of the signal-to-noise ratio of the target LEO satellite system, the step of performing spectrum prediction on multiple LEO satellite systems using a preset prediction model is re-executed until the signal-to-noise ratios of the multiple LEO satellite systems are greater than or equal to the preset threshold.

[0052] The preset threshold may be a threshold preset by a person skilled in the art, such as 30 db, and is not specifically limited here.

[0053] Specifically, in the embodiment of the present invention, a LEO satellite system with a signal-to-noise ratio greater than or equal to a preset threshold is recorded as superior, and for a target LEO satellite system with a signal-to-noise ratio less than the preset threshold, the influence coefficient of the signal-to-noise ratio is reduced. After the value is obtained, the influence coefficient of the reduced signal-to-noise ratio is input into the database of the preset prediction model for self-circular adjustment until the signal-to-noise ratios of multiple LEO satellite systems are greater than or equal to the preset threshold.

[0054] Therefore, the present invention adopts a model based on artificial intelligence deep learning (such as Bi-LSTM and CNN) and combines it with a machine learning algorithm to predict spectrum usage, thereby improving the accuracy of the prediction. The feature dimension is reduced by the maximum pooling or average pooling layer, important information is retained, and the extracted features are mapped to the output signal through the fully connected layer. The neural network model training uses the original signal and its suppressed version for supervised learning, and optimizes the CNN parameters so that it can recover an output close to the original signal from the suppressed signal. In addition, the neural network model evaluation stage ensures the effectiveness of the neural network model in practical applications through group signal-to-noise ratio evaluation. The application of this deep learning model not only improves the anti-interference ability of the LEO satellite system in emergency situations, but also provides new ideas for technological progress in the field of satellite communications.

[0055] Furthermore, in some embodiments, the anti-interference method for LEO satellite systems also includes: determining whether any LEO satellite system among multiple LEO satellite systems is in a full-spectrum suppression environment; if any LEO satellite system is in a full-spectrum suppression environment, recovering the suppressed signal based on a pre-trained neural network model, and outputting the recovered signal.

[0056] Specifically, when the LEO satellite system within the blockchain network is maliciously interfered with by satellite systems outside the blockchain network (such as spy satellites of other countries, unilateral breaking of satellite agreements caused by extreme periods such as war, etc.), in order to suppress the interference and ensure the normal connection between the LEO satellite system and other satellites, the malicious interference sources can be divided into uplink satellites (such as MEO (Medium Earth Orbit), GEO), satellites in the same orbit (LEO) and ground satellite signal jammers.

[0057] In malicious interference, a common method is "full spectrum suppression", and how to effectively recover signals and defend against them in a full spectrum suppression environment is particularly important. This is the prerequisite for ensuring the coordinated operation of the system.

[0058] Based on this, the present invention proposes a method for applying convolutional neural networks (CNN) and smart contract synchronous update in a full spectrum suppression environment to enhance signal recovery and anti-malicious interference capabilities, which specifically includes the following steps: First, a large amount of original signal and corresponding suppressed signal data are collected, wherein the data can be generated by simulation tools or obtained from actual environments.

[0059] Secondly, the collected data is preprocessed. Since the original sequence data has many inconsistencies for the deep neural network learning process, in order to better reflect the influence of certain characteristics of the space target itself on the trend of the photometric sequence data change, preprocessing is required to remove the discontinuity and measurement deviation in the original data. Among them, the preprocessing process can include normalization, distance correction, phase angle correction, smoothing filtering (noise reduction) and frame processing, which are not specifically limited here.

[0060] Next, the neural network model is established. The preprocessed data is input into the input layer of the neural network model. The main information in the input layer, that is, the baseband waveform of the signal, can be expressed as:

[0061] in, is the baseband waveform of the signal, is the time variable, is the symbol sequence sent by the transmitter, is the index of the symbol sequence, is additive white Gaussian noise, It is an equivalent filter, including shaping filter, channel filter and matched filter.

[0062] Furthermore, multiple convolutional layers are used to extract local features, such as different frequencies and amplitude changes:

[0063] in, is the output feature map, represents the value of position (i, j) in the output feature map, X is the input signal (such as time series, baseband waveform, etc.), K is the convolution kernel, is the row offset of the convolution kernel K, is the column offset of the convolution kernel K.

[0064] Furthermore, we add activation functions such as ReLU (Rectified Linear Unit, linear rectification function) ( ) introduces nonlinear features and imports the pooling layer, so that the neural network model reduces the feature dimension through the maximum pooling or average pooling layer, thereby retaining important information. Among them, the maximum pooling operation is defined as:

[0065] The above formula represents the maximum value selected in each 2 x 2 area.

[0066] Furthermore, activation functions such as ReLU are added to introduce nonlinear features, and after importing the pooling layer, the extracted features are mapped to the output signal through the fully connected layer, thereby realizing the establishment of a neural network model.

[0067] Then, the established neural network model is trained. The original signal and its compressed version are used for supervised learning, and a loss function, such as mean square error (MSE), is used to optimize the parameters of the CNN so that the neural network model can recover an output close to the original signal from the compressed signal. The mean square error of the embodiment of the present invention can be expressed as:

[0068] in, is the mean square error, is the original signal, is the restored signal output by the neural network model, and N is the total number of samples.

[0069] Finally, the trained neural network model is evaluated. The embodiment of the present invention can evaluate the group signal-to-noise ratio of the trained neural network model, that is:

[0070] Therefore, according to the evaluation results of the neural network model after training, the signals that meet the preset conditions (such as the group signal-to-noise ratio is higher than a certain threshold) are retained, and the above data collection, preprocessing, model building, model training and model evaluation operations are repeated for the signals that do not meet the preset conditions.

[0071] After completing the above operations, this CNN signal recovery system is integrated into the original smart contract to realize a new collaborative system, thereby improving the anti-interference capability of the LEO satellite system.

[0072] Furthermore, in some embodiments, after the recovered signal is output, it also includes: determining whether the current malicious interference is co-orbit interference; if the current malicious interference is not co-orbit interference, adjusting the orbit of any LEO satellite system or the attitude of the LEO satellite system based on the satellite attitude control system to achieve anti-interference.

[0073] Specifically, for long-range signal directional interference such as uplink satellite and ground satellite signal jammers, since this type of malicious interference is fixed and difficult to steer, further methods can be taken to resist interference independently of the same orbit satellite (LEO), that is, using the satellite attitude control system to adjust the thrusters or reaction wheels to change the orbit or attitude, thereby achieving anti-interference in a physical sense.

[0074] Specifically, the embodiments of the present invention can avoid interfering with the radar signals of satellites by pre-setting the target attitude and orbit; at the same time, multiple sensors can be used for data fusion to improve the accuracy of state estimation; and the degree of anti-interference should be monitored, such as setting a threshold. When the attitude or orbit deviation exceeds the threshold, the anti-interference mechanism is triggered to select appropriate thrusters and reaction wheels for adjustment, and the adjusted state is continuously monitored, thereby optimizing the control strategy and improving the anti-interference capability at the physical position.

[0075] It should be noted that when using the satellite attitude control system to adjust the thrusters or reaction wheels to change the orbit or attitude, attention should be paid to power consumption management, that is, balancing the adjustment frequency with fuel consumption, and managing the heat and vibration caused by the thruster and reaction wheel operation to avoid component damage.

[0076] Therefore, the embodiment of the present invention sets attitude and orbit deviation thresholds, triggers the anti-interference mechanism when the threshold is exceeded, and uses the thrusters and reaction wheels for adjustment, thereby effectively improving the anti-interference capability of the LEO satellite system. By continuously monitoring and optimizing the control strategy, the system can respond to external interference in real time and reduce the impact on communication quality. In addition, the method also takes into account power consumption management, balances the relationship between adjustment frequency and fuel consumption, and manages the heat and vibration generated by the operation of the thrusters and reaction wheels to avoid component damage and ensure stable operation of the system.

[0077] In order to facilitate those skilled in the art to more clearly and intuitively understand the anti-interference method for the LEO satellite system proposed in the present invention, the following is a Figure 2 Provide detailed explanation.

[0078] like Figure 2 As shown, the anti-interference method for the LEO satellite system includes the following steps: S201, link blockchain network.

[0079] S202, collect historical data and perform preprocessing.

[0080] S203, establish a deep learning model (Bi-LSTM model).

[0081] S204, establishing association between the smart contract and the Bi-LSTM model.

[0082] S205, perform signal-to-noise ratio (SNR) evaluation, if the SNR is less than 30 db, execute S206, if the SNR is greater than or equal to 30 db, execute S207.

[0083] S206, reducing the influence coefficient by modification, and updating the Bi-LSTM model system in real time.

[0084] S207, further introduce an anti-malicious interference collaborative system.

[0085] S208, applying convolutional neural network to establish and train a neural network model.

[0086] S209, determining whether the malicious interference is co-track interference, if yes, executing S211, otherwise, executing S210.

[0087] S210, using the satellite attitude control system to change the orbit or attitude.

[0088] S211, add the neural network model to the original smart contract.

[0089] S212, end.

[0090] Therefore, the anti-interference method for LEO satellite systems proposed in the present invention solves the problem of other LEO satellite systems occupying spectrum resources and interfering with transmission results when the LEO satellite system transmits signals to the GEO system, thereby improving the bit rate, bit error rate and spectrum efficiency of the satellite-to-ground link.

[0091] According to the anti-interference method for LEO satellite systems of the embodiment of the present invention, a preset prediction model is used to predict the spectrum of multiple LEO satellite systems in the current spectrum management blockchain network, and the spectrum with the highest spectrum efficiency is used as the use spectrum of the LEO satellite system based on the prediction result, and the signal-to-noise ratio is evaluated to determine the target LEO satellite system whose signal-to-noise ratio is less than the preset threshold, and after reducing the influence coefficient of the signal-to-noise ratio, the step of using the preset prediction model to predict the spectrum of the LEO satellite system is re-executed until the signal-to-noise ratio of the LEO satellite system is greater than or equal to the preset threshold. Thus, the problem of serious mutual interference and insufficient anti-interference ability between satellite systems in emergency situations in the background technology is solved, and by combining blockchain and deep learning technology, efficient and intelligent spectrum management and anti-interference ability improvement are achieved.

[0092] Next, the anti-interference device for a LEO satellite system proposed according to an embodiment of the present invention will be described with reference to the accompanying drawings.

[0093] Figure 3 It is a block diagram of an anti-interference device for a LEO satellite system according to an embodiment of the present invention.

[0094] like Figure 3 As shown, the anti-interference device 10 for the LEO satellite system includes: an acquisition module 100 , a spectrum optimization and evaluation module 200 and an adaptive adjustment module 300 .

[0095] Among them, the acquisition module 100 is used to acquire multiple LEO satellite systems of the current spectrum management blockchain network; the spectrum optimization and evaluation module 200 is used to perform spectrum prediction on multiple LEO satellite systems using a preset prediction model, and screen out the spectrum with the highest spectrum efficiency based on the prediction results, and use the spectrum with the highest spectrum efficiency as the use spectrum of multiple LEO satellite systems, and perform signal-to-noise ratio evaluation when multiple LEO satellite systems transmit signals to obtain evaluation results; the adaptive adjustment module 300 is used to determine a target LEO satellite system whose signal-to-noise ratio is less than a preset threshold based on the evaluation results, and after reducing the influence coefficient of the signal-to-noise ratio of the target LEO satellite system, re-execute the step of performing spectrum prediction on multiple LEO satellite systems using a preset prediction model until the signal-to-noise ratios of multiple LEO satellite systems are greater than or equal to the preset threshold.

[0096] Furthermore, in some embodiments, before using a preset prediction model to perform spectrum prediction on multiple LEO satellite systems, the spectrum optimization and evaluation module 200 is also used to: obtain historical spectrum usage data of multiple LEO satellite systems; use the historical spectrum usage data to train a deep learning-based prediction model to obtain a preset prediction model, and deploy the preset prediction model to the current spectrum management blockchain network.

[0097] Furthermore, in some embodiments, the anti-interference device 10 for the LEO satellite system is also used to: determine whether any LEO satellite system among multiple LEO satellite systems is in a full-spectrum suppression environment; if any LEO satellite system is in a full-spectrum suppression environment, restore the suppressed signal based on a pre-trained neural network model, and output the restored signal.

[0098] Furthermore, in some embodiments, after the recovered signal is output, the anti-interference device 10 for the LEO satellite system is also used to: determine whether the current malicious interference is co-orbit interference; if the current malicious interference is not co-orbit interference, then adjust the orbit of any LEO satellite system or the attitude of the LEO satellite system based on the satellite attitude control system to achieve anti-interference.

[0099] It should be noted that the aforementioned explanation of the embodiment of the anti-interference method for the LEO satellite system is also applicable to the anti-interference device for the LEO satellite system of this embodiment, and will not be repeated here.

[0100] According to the anti-interference device for LEO satellite systems of the embodiment of the present invention, a preset prediction model is used to predict the spectrum of multiple LEO satellite systems in the current spectrum management blockchain network, and the spectrum with the highest spectrum efficiency is used as the use spectrum of the LEO satellite system based on the prediction result, and the signal-to-noise ratio is evaluated to determine the target LEO satellite system whose signal-to-noise ratio is less than the preset threshold, and after reducing the influence coefficient of the signal-to-noise ratio, the step of using the preset prediction model to predict the spectrum of the LEO satellite system is re-executed until the signal-to-noise ratio of the LEO satellite system is greater than or equal to the preset threshold. Thus, the problem of serious mutual interference and insufficient anti-interference ability between satellite systems in emergency situations in the background technology is solved, and by combining blockchain and deep learning technology, efficient and intelligent spectrum management and anti-interference ability improvement are achieved.

[0101] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. The electronic device may include: Memory 401 , processor 402 , and a computer program stored in the memory 401 and executable on the processor 402 .

[0102] When the processor 402 executes the program, the anti-interference method for the LEO satellite system provided in the above embodiment is implemented.

[0103] Furthermore, the electronic device further comprises: The communication interface 403 is used for communication between the memory 401 and the processor 402 .

[0104] The memory 401 is used to store computer programs that can be run on the processor 402 .

[0105] The memory 401 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0106] If the memory 401, the processor 402 and the communication interface 403 are implemented independently, the communication interface 403, the memory 401 and the processor 402 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0107] Optionally, in a specific implementation, if the memory 401, the processor 402 and the communication interface 403 are integrated on a chip, the memory 401, the processor 402 and the communication interface 403 can communicate with each other through an internal interface.

[0108] The processor 402 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention.

[0109] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, and when the program is executed by a processor, the anti-interference method for a LEO satellite system as described above is implemented.

[0110] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0111] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0112] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. An anti-interference method for a LEO satellite system, characterized in that: The following steps are involved: Acquire multiple LEO satellite systems of the current spectrum management blockchain network; Performing spectrum prediction on the multiple LEO satellite systems using a preset prediction model, and selecting a spectrum with the highest spectrum efficiency based on the prediction result, and using the spectrum with the highest spectrum efficiency as a use spectrum of the multiple LEO satellite systems, and performing signal-to-noise ratio evaluation when the multiple LEO satellite systems transmit signals to obtain an evaluation result; Based on the evaluation result, a target LEO satellite system having a signal-to-noise ratio less than a preset threshold is determined, and after reducing an influence coefficient of the signal-to-noise ratio of the target LEO satellite system, the step of performing spectrum prediction on the multiple LEO satellite systems using a preset prediction model is re-executed until the signal-to-noise ratios of the multiple LEO satellite systems are greater than or equal to the preset threshold.

2. The anti-interference method for LEO satellite system according to claim 1, characterized in that: Before using the preset prediction model to perform spectrum prediction on the multiple LEO satellite systems, the method further includes: obtaining historical spectrum usage data of the plurality of LEO satellite systems; The deep learning-based prediction model is trained using the historical spectrum usage data to obtain the preset prediction model, and the preset prediction model is deployed to the current spectrum management blockchain network.

3. The anti-interference method for LEO satellite system according to claim 1, characterized in that: Also includes: Determining whether any LEO satellite system among the plurality of LEO satellite systems is in a full spectrum suppression environment; If any of the LEO satellite systems is in the full spectrum suppression environment, the suppressed signal is restored based on a pre-trained neural network model, and the restored signal is output.

4. The anti-interference method for LEO satellite system according to claim 3, characterized in that: After outputting the restored signal, it also includes: Determine whether the current malicious interference is co-track interference; If the current malicious interference is not co-orbit interference, the orbit of any LEO satellite system or the attitude of the LEO satellite system is adjusted based on the satellite attitude control system to achieve anti-interference.

5. An anti-interference device for a LEO satellite system, characterized in that: include: An acquisition module, used to acquire multiple LEO satellite systems of the current spectrum management blockchain network; a spectrum optimization and evaluation module, configured to perform spectrum prediction on the multiple LEO satellite systems using a preset prediction model, and screen out the spectrum with the highest spectrum efficiency based on the prediction result, and use the spectrum with the highest spectrum efficiency as the use spectrum of the multiple LEO satellite systems, and perform signal-to-noise ratio evaluation when the multiple LEO satellite systems transmit signals to obtain an evaluation result; an adaptive adjustment module, configured to determine, based on the evaluation result, a target LEO satellite system whose signal-to-noise ratio is less than a preset threshold, and after reducing an influence coefficient of the signal-to-noise ratio of the target LEO satellite system, re-execute the step of performing spectrum prediction on the multiple LEO satellite systems using a preset prediction model until the signal-to-noise ratios of the multiple LEO satellite systems are all greater than or equal to the preset threshold.

6. The anti-interference device for LEO satellite system according to claim 5, characterized in that: Before using the preset prediction model to perform spectrum prediction on the multiple LEO satellite systems, the spectrum optimization and evaluation module is further used to: obtaining historical spectrum usage data of the plurality of LEO satellite systems; The deep learning-based prediction model is trained using the historical spectrum usage data to obtain the preset prediction model, and the preset prediction model is deployed to the current spectrum management blockchain network.

7. The anti-interference device for LEO satellite system according to claim 5, characterized in that: Also used for: Determining whether any LEO satellite system among the plurality of LEO satellite systems is in a full spectrum suppression environment; If any of the LEO satellite systems is in the full spectrum suppression environment, the suppressed signal is restored based on a pre-trained neural network model, and the restored signal is output.

8. The anti-interference device for LEO satellite system according to claim 7, characterized in that: After outputting the restored signal, the anti-interference device for the LEO satellite system is further used to: Determine whether the current malicious interference is co-track interference; If the current malicious interference is not co-orbit interference, the orbit of any LEO satellite system or the attitude of the LEO satellite system is adjusted based on the satellite attitude control system to achieve anti-interference.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the anti-interference method for a LEO satellite system as described in any one of claims 1 to 4.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the anti-interference method for a LEO satellite system as described in any one of claims 1 to 4.

Images