Satellite beam scanning scheduling method, device and storage medium

Abstract

This application discloses a satellite beam scanning scheduling method, apparatus, and storage medium. Belonging to the field of satellite communications, the method involves: acquiring parameter characteristics of the coverage areas of multiple satellite beams; inputting these parameter characteristics into a pre-trained neural network model to determine sub-frequency bands adapted to the multiple beams; initializing chromosome vectors and constructing an initial population, where the chromosome vectors indicate the positions scanned by each satellite beam in each hop beam time slot of the hop beam cycle; constructing an adaptation function; iteratively optimizing the initial population using a genetic algorithm to determine the optimal chromosome vector; and determining the positions scanned by each beam in each hop beam time slot of the hop beam cycle based on the optimal chromosome vector. Thus, this application minimizes coverage overlap and sidelobe leakage interference of co-frequency beams from the scanning timing dimension, simultaneously achieving the dual objectives of sub-frequency band adaptation and interference suppression.

Description

Technical Field

[0001] This application relates to the field of satellite communications, and in particular to a satellite beam scanning scheduling method, apparatus and storage medium. Background Technology

[0002] In satellite communication systems, the beam, as the core carrier of signal coverage and transmission, has performance limited by the physical characteristics of the antenna hardware, making it impossible to achieve an ideal "needle-shaped beam." In practical applications, beams commonly exhibit sidelobe effects and roll-off characteristics: sidelobes cause some signals to deviate from the main coverage area and leak into the coverage range of adjacent beams; roll-off causes the signal strength at the beam coverage boundary to attenuate gradually, forming an ambiguous coverage boundary area. To cope with the continuously growing demand for satellite communication services, the industry widely adopts high-spectrum multiplexing strategies to improve resource utilization. For example, compared to traditional 7-color multiplexing, 4-color multiplexing shortens the spatial spacing of beams at the same frequency through denser frequency allocation.

[0003] For example, CN113852452A, entitled "A Beam Scanning Method and System for a Satellite Communication System," discloses a beam scanning method and system for a satellite communication system. This invention relates to the field of satellite communication systems and solves the problem of long transmission and acquisition delays between satellites and terminals in existing technologies. The key technical points are: beam generation and beam velocity scanning are performed on both the satellite and terminal sides to form a multi-peak beam with multiple peaks; the satellite side receives a UL reference signal based on the multi-peak beam and performs multi-peak calculation to generate the optimal directional beam; the terminal side receives a DL reference signal based on the multi-peak beam and performs multi-peak calculation to generate the optimal directional beam. This invention reduces the number of signaling transmissions between the satellite and terminal during beam scanning, while also reducing the acquisition delay of the optimal beam.

[0004] For example, CN115189748A, entitled "A Beam Management, Reception Method and Apparatus," aims to improve the utilization efficiency of satellite beams and increase system capacity. This application provides a beam management method comprising: determining a first beam and a second beam; configuring the first beam and the second beam to share the same bandwidth portion (BWP) in a time-division multiplexing (TDM) manner; and configuring the time scanning parameters of the first beam such that the first beam occupies all or part of the time-domain resources, wherein the time scanning parameters include a TDM pattern; or, configuring the first beam and the second beam to occupy different BWPs, wherein there is a frequency interval between the first BWP occupied by the first beam and the second BWP occupied by the second beam, and each BWP has a frequency reference point.

[0005] However, while this high-frequency spectrum reuse strategy improves spectrum efficiency, it also significantly reduces the spatial isolation of co-frequency beams, leading to a substantial increase in the probability of overlap between the coverage areas of adjacent beams. Especially in the edge user areas where coverage overlaps, the signals from two co-frequency beams are prone to spatial superposition, causing the receiver to receive both useful and interfering signals simultaneously. This results in a sharp drop in the signal-to-interference-plus-noise ratio (SINR), which in turn leads to problems such as increased bit error rate and transmission rate fluctuations, severely restricting the service stability of satellite communications.

[0006] However, in practical applications, the environmental conditions of the coverage areas of each satellite beam objectively require matching the most suitable sub-frequency band. Therefore, adjacent beams may still objectively use the same sub-frequency band for scanning. This makes co-channel interference difficult to completely avoid, especially in the edge areas of beam coverage, where sidelobe leakage and signal superposition problems are more prominent, seriously affecting communication quality.

[0007] There are currently no effective solutions to the technical problems in the existing technologies mentioned above, such as the difficulty in suppressing interference caused by the co-frequency configuration of adjacent beams while meeting the sub-band adaptation requirements, and the decrease in signal-to-interference-plus-noise ratio caused by high-frequency spectrum reuse and the superposition of beam physical characteristics. Summary of the Invention

[0008] The embodiments of this disclosure provide a satellite beam scanning scheduling method, apparatus, and storage medium to at least solve the technical problems in the prior art that make it difficult to suppress interference caused by the co-frequency configuration of adjacent beams while meeting the sub-band adaptation requirements, and the signal-to-interference-plus-noise ratio reduction caused by high-frequency spectrum reuse and the superposition of beam physical characteristics.

[0009] According to one aspect of the present disclosure, a satellite beam scanning scheduling method is provided, comprising: acquiring parameter features of the coverage area of ​​multiple beams of a satellite, wherein the parameter features are used to characterize the communication link characteristics between the satellite and the coverage area; inputting the parameter features into a pre-trained neural network model, and determining sub-frequency bands adapted to the multiple beams through the neural network model; initializing chromosome vectors and constructing an initial population, wherein the chromosome vectors are used to indicate the wave positions scanned by each beam of the satellite in each hop beam time slot of a hop beam cycle; constructing an fitness function, wherein the function value of the fitness function is related to the severity of co-channel interference in the satellite coverage area; iteratively optimizing the initial population according to a genetic algorithm to determine an optimal chromosome vector; and determining the wave positions scanned by each beam in each hop beam time slot of a hop beam cycle according to the optimal chromosome vector.

[0010] According to another aspect of the present disclosure, a storage medium is also provided, the storage medium including a stored program, wherein, when the program is executed, a processor performs any of the methods described above.

[0011] According to another aspect of the present disclosure, a satellite beam scanning scheduling apparatus is also provided, comprising: an acquisition module for acquiring parameter features of the coverage area of ​​multiple beams of a satellite, wherein the parameter features are used to characterize the communication link characteristics between the satellite and the coverage area; an input module for inputting the parameter features into a pre-trained neural network model, and determining sub-frequency bands adapted to the multiple beams through the neural network model; an initialization module for initializing chromosome vectors and constructing an initial population, wherein the chromosome vectors are used to indicate the positions scanned by each beam of the satellite in each hop beam time slot of the hop beam period; a construction module for constructing an adaptation function, wherein the function value of the adaptation function is related to the severity of co-channel interference in the satellite coverage area; an iteration module for iteratively optimizing the initial population according to a genetic algorithm to determine the optimal chromosome vector; and a determination module for determining the positions scanned by each beam in each hop beam time slot of the hop beam period based on the optimal chromosome vector.

[0012] According to another aspect of the present disclosure, a satellite beam scanning scheduling apparatus is also provided, comprising: a processor; and a memory connected to the processor, configured to provide the processor with instructions for processing the following steps: acquiring parameter features of the coverage area of ​​multiple beams of a satellite, wherein the parameter features are used to characterize the communication link characteristics between the satellite and the coverage area; inputting the parameter features into a pre-trained neural network model, and determining sub-frequency bands adapted to the multiple beams through the neural network model; initializing chromosome vectors and constructing an initial population, wherein the chromosome vectors are used to indicate the positions scanned by each beam of the satellite in each hop beam time slot of the hop beam period; constructing an fitness function, wherein the function value of the fitness function is related to the severity of co-channel interference within the satellite coverage area; iteratively optimizing the initial population according to a genetic algorithm to determine the optimal chromosome vector; and determining the positions scanned by each beam in each hop beam time slot of the hop beam period according to the optimal chromosome vector.

[0013] This application provides a beam scanning scheduling method for a multi-beam satellite communication system. First, the processor collects the characteristic parameters of the ground coverage area corresponding to each satellite beam and inputs the characteristic parameters into a pre-trained neural network model to match the most suitable sub-frequency band for each beam. Then, a chromosome vector (indicating the scanning position of each beam in each time slot of the hopping beam cycle) is defined and an initial population is constructed. At the same time, a fitness function related to the degree of co-channel interference is constructed to quantify the evaluation scheme. Then, the initial population is iteratively optimized through a genetic algorithm (calculating fitness, selecting parents, crossover mutation to generate offspring, and screening to form a new population) to determine the optimal chromosome vector. Finally, the scanning position of each beam in each time slot of the hopping beam cycle is determined accordingly, which minimizes co-channel interference while meeting the sub-frequency band adaptation requirements and improving communication quality. Therefore, this application not only ensures the adaptability of each beam sub-band to the coverage area environment and service requirements through neural networks, but also avoids coverage overlap and sidelobe leakage interference of co-frequency beams to the greatest extent from the scanning timing dimension by using a genetic algorithm combined with an interference quantization adaptation function. It simultaneously achieves the dual goals of sub-band adaptation and interference suppression, thereby solving the technical problems in the prior art that it is difficult to suppress interference caused by co-frequency configuration of adjacent beams while meeting the sub-band adaptation requirements, as well as the signal-to-interference-plus-noise ratio reduction caused by high spectrum reuse and beam physical characteristics superposition. Attached Figure Description

[0014] The accompanying drawings, which are included to provide a further understanding of this disclosure and form part of this application, illustrate exemplary embodiments of this disclosure and are used to explain this disclosure, but do not constitute an undue limitation of this disclosure. In the drawings:

[0015] Figure 1 This is a hardware structure block diagram of a computing device for implementing the method described in Embodiment 1 of this disclosure;

[0016] Figure 2 This is a flowchart illustrating a satellite beam scanning scheduling method according to Embodiment 1 of this disclosure;

[0017] Figure 3 This is a schematic diagram of the satellite beam coverage area of ​​a satellite beam scanning scheduling method according to Embodiment 1 of this disclosure;

[0018] Figure 4 This is a schematic diagram of a neural network model of a satellite beam scanning scheduling method according to Embodiment 1 of this disclosure;

[0019] Figure 5 Each coverage area S according to Embodiment 1 of this disclosure is a satellite beam scanning scheduling method. i A corresponding set of wavelet cluster diagrams;

[0020] Figure 6This is a schematic diagram of the overlapping region of two beams of the same frequency band in a satellite beam scanning scheduling method according to Embodiment 1 of this disclosure;

[0021] Figure 7 This is a schematic diagram of the overlapping region of three beams of the same frequency band in a satellite beam scanning scheduling method according to Embodiment 1 of this disclosure;

[0022] Figure 8 This is a schematic diagram of a satellite beam scanning scheduling device according to Embodiment 2 of this disclosure;

[0023] Figure 9 This is a schematic diagram of a satellite beam scanning scheduling device according to Embodiment 3 of this disclosure. Detailed Implementation

[0024] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this disclosure.

[0025] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0026] Example 1

[0027] According to this embodiment, a method embodiment for satellite beam scanning scheduling is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0028] Figure 1 This is a schematic diagram of the hardware architecture of Satellite-110. (Reference) Figure 1As shown, satellite 110 includes an integrated electronic system, which comprises a processor, a memory, a bus management module, and a communication interface. The memory is connected to the processor, allowing the processor to access the memory, read program instructions stored in the memory, read data from the memory, or write data to the memory. The bus management module is connected to the processor and also to a bus such as a CAN bus. Thus, the processor can communicate with onboard peripherals connected to the bus through the bus managed by the bus management module. These onboard peripherals include: onboard peripheral 1 (GNSS module), onboard peripheral 2 (fiber optic gyroscope), ..., onboard peripheral n (torque flywheel). Furthermore, the processor also communicates with devices such as cameras, star sensors, telemetry and control transponders, and data transmission equipment via the communication interface. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, a satellite system may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0029] It should be noted that, Figure 1 One or more processors and / or other data processing circuits shown herein may generally be referred to as "data processing circuitry". This data processing circuitry may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuitry may be a single, independent processing module, or may be integrated, in whole or in part, into any other element in a computing device. As involved in embodiments of this disclosure, the data processing circuitry serves as processor control (e.g., selection of a variable resistor termination path connected to an interface).

[0030] Figure 1 The memory shown can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the method for determining the communication frequency band corresponding to the beam in the embodiments of this disclosure. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, to implement the above-mentioned method for determining the communication frequency band corresponding to the beam in the application program. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory.

[0031] It should be noted here that, in some optional embodiments, the above... Figure 1 The device shown may include hardware elements (including circuitry), software elements (including computer code stored on a computer-readable medium), or a combination of both hardware and software elements. It should be noted that... Figure 1This is only one instance of a specific particular instance, and is intended to illustrate the types of components that may exist in the aforementioned devices.

[0032] Under the aforementioned operating environment, according to the first aspect of this embodiment, a satellite beam scanning scheduling method is provided, which comprises... Figure 1 The processor implementation shown. Figure 2 A flowchart illustrating the method is shown below. (Refer to...) Figure 2 As shown, the method includes:

[0033] S202: Obtain the parameter characteristics of the coverage area of ​​multiple beams of the satellite, wherein the parameter characteristics are used to characterize the communication link characteristics between the satellite and the coverage area;

[0034] S204: Input the parameter features into a pre-trained neural network model, and determine the sub-band that is compatible with multiple beams through the neural network model;

[0035] S206: Initialize the chromosome vector and construct the initial population, where the chromosome vector is used to indicate the wave positions scanned by each beam of the satellite in each hop beam time slot of the hop beam period;

[0036] S208: Construct an adaptation function, where the function value of the adaptation function is related to the severity of co-channel interference within the satellite coverage area;

[0037] S210: Iteratively optimize the initial population using a genetic algorithm to determine the optimal chromosome vector; and

[0038] S212: Based on the optimal chromosome vector, determine the wave positions scanned by each beam in each hop beam time slot of the hop beam period.

[0039] Specifically, during the operation of a multi-beam satellite communication system, the processor first needs to collect characteristic parameters of the ground coverage areas corresponding to the multiple beams of the satellite. These characteristic parameters must be directly related to core technical aspects such as signal transmission efficiency, resource allocation rationality, and interference control effectiveness during satellite communication, providing data support for the subsequent formulation of beam scheduling strategies (corresponding to step S202). Among these, reference... Figure 3 As shown, satellite 110 can use m beams B1~B1 respectively. m Simultaneously covering multiple coverage areas S1~S mFor example, beam B1 covers area S1, which contains wave positions P1 to P3. Beam B1 is used to scan wave positions P1 to P3 and can provide satellite communication services to these wave positions. Beam B2 covers area S2, which contains wave positions P4 to P6. Beam B2 is used to scan wave positions P4 to P6 and can provide satellite communication services to these wave positions. ... and so on. m The covered area is S m Coverage area S m The inner corresponding wave position P 3m-2 ~P 3m Thus, beam B m Used for wave position P 3m-2 ~P 3m Perform a scan, and beam B m It can be directed to the covered wave position P 3m-2 ~P 3m It provides satellite communication services. Thus, satellite 110 can switch between corresponding positions using m beams and provide satellite communication services to each corresponding position in a time-division manner.

[0040] In embodiments of the present invention, the frequency bands allocated to satellites are multiplexed using a multi-color multiplexing method, such as four-color multiplexing (or seven-color multiplexing). That is, the present invention divides the frequency bands allocated to satellites into four non-overlapping sub-bands N1 to N4, so that satellite 110 selects appropriate sub-bands from N1 to N4 and allocates them to each beam B1 to B2. m Preferably, the frequencies used in sub-bands N1 to N4 increase sequentially.

[0041] However, in practical applications, due to the different beams B1~B m Coverage area S1~S m The environmental conditions objectively necessitate matching the most suitable sub-frequency band. Therefore, it is still possible for adjacent beams to scan using the same sub-frequency band. In this case, it is necessary to allocate the most suitable scanning strategy for each beam to mitigate co-frequency interference between adjacent beams.

[0042] Specifically, the processor inputs the characteristic parameters of each beam's coverage area into a pre-trained neural network model for analysis and calculation, determining the sub-frequency band that best meets the communication needs of each beam's coverage area (corresponding to step S204). This neural network model is trained using a large amount of historical data (such as past cases of parameter matching between different beams and regions and sub-frequency bands, as well as communication quality data after matching), and already possesses the ability to determine "which sub-frequency band is most suitable for this beam" based on parameter characteristics, providing a basis for sub-frequency band allocation in subsequent beam scanning scheduling. For example, for the high user density and high transmission rate demand area covered by beam B1, the neural network model will combine historical data to determine that this area is more suitable for a wider bandwidth sub-frequency band; for the low interference and low traffic volume area covered by beam B2, the neural network model will determine that it is suitable for a narrower bandwidth sub-frequency band.

[0043] Then, the processor defines chromosome vectors for the scanning strategy of each beam in each hop beam slot within a hop beam cycle, and constructs an initial population (corresponding to step S206). The chromosome vectors are used to indicate which beam position to scan (i.e., the specific spatial location pointed to by the beam) in each hop beam slot within the entire hop beam cycle.

[0044] In other words, the chromosome vector needs to include all beams B1~B1 in satellite 110. m The correspondence with all time slots within the hopping beam period: For example, if the hopping beam period is divided into T hopping beam time slots, the chromosome vector needs to record the scanning positions of beam B1 in hopping beam time slots 1 to T, the scanning positions of beam B2 in hopping beam time slots 1 to T, and so on, until beam B... m The scanning wave positions within the hopping beam time slots 1 to T form a complete beam-time slot-wave position mapping relationship.

[0045] Next, the processor constructs an adaptation function to evaluate the merits of the beam scanning scheduling scheme. The function value of this adaptation function has a clear correlation with the severity of co-channel interference in all coverage areas of the satellite (corresponding to step S208). In other words, this adaptation function is used to calculate and output a quantitative value of the severity of co-channel interference in all coverage areas of satellite 110 under this scheduling scheme, providing a comparable quantitative basis for subsequent determination of the merits of the beam scanning scheduling scheme.

[0046] Specifically, co-channel interference occurs when beams corresponding to two coverage areas are assigned the same sub-frequency band, and these two coverage areas have spatial overlap, or when signals cross in space due to beam sidelobe leakage. The adaptation function calls upon previously acquired coverage area characteristic parameters to convert the co-channel interference into a quantifiable value. For example, under a certain beam scanning scheduling scheme, the more overlapping areas of the coverage areas corresponding to beams in the same frequency band, or the larger the area of ​​signal crossing due to sidelobe leakage, the larger the interference quantization value output by the adaptation function, indicating a more severe co-channel interference problem for that beam scanning scheduling scheme. Conversely, the fewer overlapping coverage areas of the coverage areas corresponding to beams in the same frequency band, and the smaller the area of ​​signal crossing due to sidelobe leakage, the smaller the interference quantization value output by the adaptation function, indicating a better interference control effect for that beam scanning scheduling. This adaptation function provides a clear performance criterion for subsequent genetic algorithm iterations to select the optimal beam scanning scheduling scheme.

[0047] Furthermore, following the optimization logic of the genetic algorithm, multiple chromosome vectors (i.e., multiple beam scanning scheduling candidate schemes) in the initial population are iteratively optimized. Through multiple rounds of screening, combination, and improvement, scheduling schemes with lower interference and stronger adaptability are gradually selected, and finally, the chromosome vector with the best performance is determined (corresponding to step S210). That is, first, the parent population is crossovered and mutated to generate corresponding child populations; then, the fitness value of each chromosome vector in the parent and child populations is calculated using the fitness function (the better the fitness value, the lighter the co-frequency interference); a high-quality chromosome vector is selected as the new parent population. The above iterative process is repeated until the termination condition is met (such as reaching the preset number of iterations or the optimal fitness value stabilizing), and the final output optimal chromosome vector is the optimal beam scanning scheduling scheme.

[0048] Finally, based on the optimal chromosome vector obtained through iterative optimization using a genetic algorithm, the specific wave positions to be scanned in each hop beam time slot of satellite 110 during the entire hop beam cycle can be determined (corresponding to step S212). This minimizes co-channel interference while meeting sub-band adaptation requirements.

[0049] This enables the provision of precise and executable beam scanning commands for each beam of Satellite 110 in each time slot of the beam hopping cycle, forming an optimal scheduling scheme that balances sub-band adaptation requirements and interference control. This ensures that the communication link characteristics of each beam's coverage area match the sub-band, while significantly reducing coverage overlap and sidelobe leakage interference of co-frequency beams by optimizing the beam scanning timing. This effectively improves the signal-to-interference-plus-noise ratio and spectrum utilization of the satellite communication system, ultimately guaranteeing the stability of communication quality and the reliability of service transmission within the coverage area.

[0050] As described in the background section, in satellite communication systems, the beam, as the core carrier of signal coverage and transmission, cannot achieve an ideal "needle-shaped beam" due to the limitations of antenna hardware physical characteristics. It commonly exhibits sidelobe effects and edge roll-off characteristics—sidelobes cause signals to leak from the main coverage area into adjacent beam ranges, while edge roll-off causes signal strength gradient attenuation at the coverage boundary, forming an ambiguous boundary region. While the industry's high-spectrum multiplexing strategies (such as 4-color multiplexing shortening the spatial spacing of co-frequency beams through denser frequency allocation compared to traditional 7-color multiplexing) adopted to cope with increasing communication traffic and improve resource utilization improve spectral efficiency, they also significantly compress the spatial isolation of co-frequency beams, significantly increasing the probability of overlapping coverage between adjacent beams. This is especially true in user areas at the coverage boundaries, where spatial superposition of co-frequency beam signals easily occurs, leading to a sharp drop in the receiver's signal-to-interference-plus-noise ratio (SNR), resulting in increased bit error rate, transmission rate fluctuations, and other problems, severely restricting the stability of satellite communication services. Furthermore, in practical applications, the environmental conditions of the coverage areas of each satellite beam objectively require matching the most suitable sub-frequency band. Therefore, it is still possible for adjacent beams to scan using beams from the same sub-frequency band. This makes it difficult to completely avoid co-channel interference, especially in the edge areas of beam coverage, where sidelobe leakage and signal superposition are more prominent, seriously affecting communication quality.

[0051] In view of this, this application provides a beam scanning scheduling method for a multi-beam satellite communication system. First, the processor collects the characteristic parameters of the ground coverage area corresponding to each satellite beam and inputs the characteristic parameters into a pre-trained neural network model to match the most suitable sub-frequency band for each beam. Then, a chromosome vector (indicating the scanning position of each beam in each time slot of the hopping beam cycle) is defined and an initial population is constructed. At the same time, a fitness function related to the degree of co-channel interference is constructed to quantify the evaluation scheme. Then, the initial population is iteratively optimized through a genetic algorithm (calculating fitness, selecting parents, crossover mutation to generate offspring, and screening to form a new population) to determine the optimal chromosome vector. Finally, the scanning position of each beam in each time slot of the hopping beam cycle is determined accordingly, so as to minimize co-channel interference while meeting the sub-frequency band adaptation requirements and improve communication quality. Therefore, this application not only ensures the adaptability of each beam sub-band to the coverage area environment and service requirements through neural networks, but also avoids coverage overlap and sidelobe leakage interference of co-frequency beams to the greatest extent from the scanning timing dimension by using a genetic algorithm combined with an interference quantization adaptation function. It simultaneously achieves the dual goals of sub-band adaptation and interference suppression, thereby solving the technical problems in the prior art that it is difficult to suppress interference caused by co-frequency configuration of adjacent beams while meeting the sub-band adaptation requirements, as well as the signal-to-interference-plus-noise ratio reduction caused by high spectrum reuse and beam physical characteristics superposition.

[0052] Optionally, the operation of acquiring parameter characteristics of multiple coverage areas of the satellite includes acquiring the following parameter characteristics: average rainfall rate of the coverage area; user density of the coverage area; service traffic demand of the coverage area; beam elevation angle of the corresponding beam of the coverage area; and atmospheric water vapor density of the coverage area.

[0053] Specifically, obtain each coverage area S1~S m Parameter characteristics F1~F related to satellite communication m For example, in an embodiment of the present invention, the values ​​of each coverage area S1~S2 are obtained respectively. m The parameter characteristics include the following parameters and their corresponding physical meanings:

[0054] 1. Average rainfall rate (unit: mm / h) has the physical significance of directly determining the degree of rainfall attenuation of Ka-band satellite signals. Different frequency bands have different sensitivities to rainfall. For example, the sensitivity of 38GHz band signals to rainfall is about 3 times that of 28GHz band signals. This parameter is a key environmental indicator for evaluating the transmission loss of high-frequency band signals.

[0055] 2. User density (unit: users / km) 2 Its physical meaning lies in representing the density of communication users within the coverage area. Areas with higher user density have a greater volume of concurrent communication services, which usually requires larger transmission bandwidth or more robust frequency bands (such as the 28GHz band) to meet the needs of multiple users communicating simultaneously.

[0056] 3. Business traffic requirements (unit: Mbps / km) 2 Its physical meaning lies in: quantitatively reflecting the data transmission demand of communication services per unit area within the coverage area. The higher the demand for service traffic, the greater the demand for transmission bandwidth. In this case, higher frequency bands (such as the 38GHz band) are more suitable to obtain wider available spectrum resources.

[0057] 4. Beam elevation angle (unit: degrees), its physical meaning is that the beam elevation angle is directly related to the signal propagation path length. The lower the elevation angle, the longer the signal propagation path, and the more significant the attenuation caused by rainfall and atmospheric loss. Moreover, this effect is more prominent in high-frequency signals (such as 38GHz), and it is an important spatial parameter for assessing signal propagation loss.

[0058] 5. Atmospheric water vapor density (unit: g / m³) 3 Its physical significance lies in the fact that, compared to relative humidity, this parameter can more directly and accurately reflect the absorption and attenuation effect of atmospheric water vapor content on high-frequency (frequency > 30 GHz) satellite signals, and is one of the core environmental parameters for assessing atmospheric transmission loss of high-frequency signals.

[0059] It should be noted that for the feature parameters F1~F m Any parameter feature F in i All of them have: ;in, For coverage area S i The average rainfall rate; For coverage area S i User density; For coverage area S i The business traffic requirements; For coverage area S i Corresponding beam B i The beam elevation angle; and Corresponding to coverage area S i Atmospheric water vapor density.

[0060] By collecting parameter characteristics through the above methods, we can comprehensively reflect the geographical environment, service load, and signal propagation conditions of each coverage area, providing multi-dimensional data support for the formulation of subsequent sub-band adaptation and beam scheduling strategies.

[0061] Optionally, the operation of inputting parameter features into a pre-trained neural network model and determining the sub-bands adapted to multiple beams through the neural network model includes: inputting parameter features corresponding to the coverage area into the neural network model and then outputting corresponding classification information through a classifier, wherein the classification information includes the probability value of each sub-band being used by the beam corresponding to the coverage area; and selecting the sub-band with the highest probability value as the sub-band being used by the beam corresponding to the coverage area.

[0062] Specifically, the parameter features F1~F corresponding to each coverage area are... m Input the pre-trained neural network model into each beam B1~B1 to determine the relationship with each beam. m Adapted sub-band. (Reference) Figure 4 As shown, with coverage area S i Corresponding parameter feature F i After being input into the neural network, the softmax classifier outputs the corresponding classification information H. i :

[0063]

[0064] in, Represented as beam B i The probability of assigning the j-th sub-band is determined. The sub-band with the highest probability value is selected as the one corresponding to beam B. i The corresponding sub-band.

[0065] This allows us to determine the specific characteristics of each beam B1~B. mThe allocated sub-bands N1~N4 are shown in the table below:

[0066] Table 1

[0067]

[0068] It should be noted that "Y" indicates that the sub-band is compatible with the beam, and "N" indicates that the sub-band is not compatible with the coverage area (this application uniquely assigns the most suitable sub-band to each beam).

[0069] In an embodiment of the present invention, the neural network model used to determine the beam-adaptive sub-bands is trained as follows: First, a training sample set is constructed, including "input feature groups (average rainfall rate, user density, service traffic demand, beam elevation angle, and atmospheric water vapor density of the coverage area)" and "labels (sub-bands that optimize communication quality in the area)". A classification network structure is designed, consisting of an input layer (matching 5 feature dimensions), hidden layers (1-3 layers with ReLU activation function), and an output layer (matching the number of sub-bands with Softmax activation function). Then, the sample features are standardized and divided into training, validation, and test sets. The model is iteratively trained using cross-entropy loss function and gradient descent optimization algorithm (such as Adam). Hyperparameters are tuned using the validation set to avoid overfitting. After the validation set performance reaches a preset threshold, the model's generalization ability is verified using the test set. Finally, the model that meets the requirements is solidified and deployed for subsequent sub-band adaptation determination.

[0070] Through the above methods, and by using probabilistic output and optimal selection mechanisms, sub-band allocation is based on both the deep learning results of neural network models on parameter characteristics and sub-band adaptation rules, and the ability to intuitively determine the optimal solution. This ensures that the sub-band of each beam is accurately matched with the environmental characteristics, service requirements, and propagation conditions of the coverage area, avoiding the bias of subjective experience allocation. It provides an adaptability basis for interference suppression in subsequent beam scanning scheduling, and improves the scientificity and effectiveness of sub-band resource allocation.

[0071] Optionally, the operation of initializing chromosome vectors and constructing an initial population includes: defining chromosome vectors and corresponding each gene of the chromosome vectors with the wave positions scanned by each beam in different hopping beam slots of the hopping beam period; generating multiple chromosome vectors that conform to the definition; and randomly encoding the genes in each chromosome vector according to preset constraints to construct an initial population, wherein the constraints stipulate that multiple beams scan all their corresponding wave positions within the hopping beam period.

[0072] Specifically, beams B1 to B are determined using a genetic algorithm. m The scanning scheduling strategy for each beam position in each hop beam time slot within a hop beam cycle. (Reference) Figure 5As shown, in an embodiment of the present invention, each coverage area S i This corresponds to a bandgap cluster consisting of 7 bandgap positions (denoted as bandgap 1 to bandgap 7). Because within each hopping beam slot, beam B... i Only one positron can be scanned within this positron cluster, thus a hopping beam cycle must include at least 7 hopping beam slots to allow beam B to... i It can traverse and scan all positions of its corresponding position cluster. For the sake of simplicity, the following explanation will use a hop beam cycle consisting of 7 hop beam slots as an example.

[0073] First, define a chromosome vector X=[x1, x2, ..., x] to characterize the beam scanning scheduling scheme. 7m ] T Where m represents the total number of satellite beams (i.e., beams B1~B1). m Quantity); x L (L ranges from 1 to 7m) represents the Lth element in the chromosome vector X (i.e., the gene in the chromosome vector), with values ​​ranging from integers 1 to 7. Each value uniquely corresponds to the scanning position of a specific beam within a specific time slot (e.g., x). L =1 represents the corresponding beam scanning position 1, x L =2 represents the corresponding beam scanning wave position 2, and so on up to x. L =7 represents the corresponding beam scanning position 7). For example:

[0074] x1~x m Used to indicate the first hop beam time slot, each beam B1~B m The scanned wave position;

[0075] Where x m+1 ~x 2m Used to indicate the second hop beam time slot, each beam B1~B m The scanned wave position; ......;

[0077] And so on, x 6m+1 ~x 7m Used to indicate the 7th hop beam time slot, each beam B1~B m The wave position being scanned.

[0078] Secondly, to construct the initial population required for the genetic algorithm iteration, pre-defined constraints are needed, namely, that within one hopping beam cycle, each beam must at least traverse and scan all positions of its corresponding position cluster (i.e., beam B). i (At least one scan of wave positions 1 through 7 is required within each of the 7 hopping beam time slots), and n chromosome vectors should be randomly generated according to this constraint to form the initial population. The expression for the k-th chromosome vector in the initial population (where k ranges from 1 to n, and n is the initial population size) is:

[0079] X k= [x k,1 , x k,2 , x k,3 , ..., x k,7m ] T

[0080] in, Used to represent the l-th element in the k-th chromosome vector, its value range is still 1~7 (corresponding to wave position 1~wave position 7), and it needs to meet the constraint conditions;

[0081] Used to represent the second element in the k-th chromosome vector, its value range is still 1~7 (corresponding to wave position 1~wave position 7), and it needs to meet the constraint conditions;

[0082] And so on, This is used to represent the 7m-th element in the k-th chromosome vector. Its value range is still 1~7 (corresponding to wave position 1~wave position 7), and it needs to meet the constraint conditions.

[0083] In other words, for beam B j (j takes values ​​from 1 to m), in The seven elements related to this beam must include all values ​​corresponding to wave positions 1 through 7 to ensure no wave positions are missed; thus, in generating each chromosome vector X1 through X... n During the process, the genes in each chromosome vector need to be randomly encoded and simultaneously checked to see if they meet the above constraints. If a chromosome vector has a beam scan missed position, it is removed and regenerated. Finally, n chromosome vectors that all meet the constraints are obtained, and the initial population initialization is completed.

[0084] The above methods can be used to construct the initial population required for the genetic algorithm. On the one hand, chromosome vectors (candidate scheduling schemes) are defined to provide a clear scheme representation for subsequent optimization. On the other hand, according to the constraints, it is ensured that all candidate scheduling schemes meet the basic communication service requirements (no missed wavelet scans) during the initial population generation stage, avoiding invalid schemes from entering the iteration process. This not only ensures the effectiveness of the initial population, but also lays a reliable foundation for the subsequent selection of the optimal scheduling scheme with low interference and high adaptability based on the fitness function.

[0085] Optionally, the operation of constructing the fitness function includes constructing a fitness function S(X) as follows:

[0086]

[0087] Where I1(X) represents the time slots of each beam B1~B according to the chromosome vector X in each beam hopping time slot. m In the case of beam assignment, the number of overlapping regions formed by two beams of the same frequency band appearing in the entire beam-hopping period; and I2(X) represents the number of beams B1~B1 in each beam-hopping time slot according to the chromosome vector X. m In the case of assigned beam positions, the number of overlapping regions formed by the overlap of three beams in the same frequency band that occur throughout the entire hopping beam period.

[0088] Specifically, the fitness function S(X) reflects the severity of co-channel interference within the satellite's coverage area. Figure 6 This is a schematic diagram of the overlapping region formed by two beams from the same frequency band. (Refer to...) Figure 6 As shown, the coverage areas of beams B1 and B2 overlap. Therefore, when beams B1 and B2 use the same sub-frequency band, two types of co-channel interference will occur in the overlapping area SD1: beam B2 will interfere with users establishing communication through beam B1; and beam B1 will interfere with users establishing communication through beam B2.

[0089] Therefore, in this case, take Reflecting the chromosome vector X in each hopping beam time slot as beams B1~B m The severity of co-channel interference caused by the overlapping area of ​​two co-channel beams when the wavelength is allocated.

[0090] also, Figure 7 This is a schematic diagram of the overlapping region formed by three beams of the same frequency band. (Refer to...) Figure 7 As shown, the areas covered by beams B1 to B3 overlap. Therefore, when beams B1 to B3 use the same sub-frequency band, six types of co-channel interference will occur in the overlapping area SD2: beams B2 and B3 will interfere with users establishing communication via beam B1; beams B1 and B3 will interfere with users establishing communication via beam B2; and beams B1 and B2 will interfere with users establishing communication via beam B3.

[0091] Therefore, in this case, take Reflecting the chromosome vector X in each hopping beam time slot as beams B1~B m Given a beam assignment, S(X) represents the severity of co-channel interference caused by the overlapping area of ​​three beams in the same frequency band. Therefore, S(X) as a whole reflects the severity of co-channel interference within the satellite's coverage area.

[0092] By using the above methods, an adaptive function that takes chromosome vector X as input and can quantitatively evaluate the interference level of beam scanning scheduling schemes is constructed, providing a scientific and accurate quantitative basis for subsequent genetic algorithm iteration to select the optimal scheduling scheme.

[0093] Optionally, the iterative optimization of the initial population using a genetic algorithm includes: using the initial population as the parent population, performing crossover and mutation operations on multiple chromosome vectors in the parent population to generate multiple chromosome vectors as the child population; calculating the fitness value of each chromosome vector in the parent and child populations using a fitness function; sorting the chromosome vectors of the parent and child populations together according to their fitness values, and selecting a predetermined number of chromosome vectors with the lowest fitness values ​​as the parent population for the next iteration.

[0094] Specifically, the iterative optimization process of the genetic algorithm uses the initialized chromosome vectors... Based on the initial parent population and the fitness function S(X), the optimal chromosome vector X is determined through multiple rounds of iterative calculation. best Since a lower value of the fitness function S(X) in the embodiments of the present invention represents a lighter co-frequency interference of the corresponding scheduling scheme, in each iteration of the genetic algorithm, the chromosome vectors X1~X1 of the parent population can be targeted first. n Perform crossover and mutation operations to generate n new chromosome vectors X. n+1 ~X 2n As the subpopulation; then the 2n chromosome vectors of the parent population and the subpopulation are merged, and the fitness value of each chromosome vector is calculated one by one using the fitness function S(X); then, the n chromosome vectors with the lowest fitness value (i.e. the best performance) are selected from these 2n chromosome vectors as the parent population in the next round of iteration (i.e., selection operation).

[0095] Finally, determine if the current iteration meets the termination condition (e.g., the iteration result converges or the preset number of iterations is reached). If the termination condition is not met, a new round of iteration is performed using the updated parent population. If the termination condition is met, the chromosome vector with the lowest fitness value in the current population is determined as the optimal chromosome vector X. best .

[0096] Through the above methods, on the one hand, new scheduling schemes (subpopulations) are continuously generated by crossover and mutation operations, ensuring population diversity and preventing the algorithm from getting trapped in local optima; on the other hand, the n scheduling schemes with the lowest fitness values ​​(least interference from co-current events) are always retained as the parent population for the next round, ensuring that each iteration approaches a better scheduling scheme; at the same time, through explicit termination condition judgment, both insufficient optimization due to insufficient iteration and resource waste caused by excessive iteration are avoided, ultimately efficiently converging to the optimal chromosome vector X.best This provides precise support for the operation of the wave positions scanned by each beam in each hop beam time slot of the hop beam cycle.

[0097] Optionally, the operation of determining the wave positions scanned by each beam in each hop beam time slot of the hop beam period based on the optimal chromosome vector includes: determining the wave positions scanned by each beam in each hop beam time slot of the hop beam period based on the coding values ​​of each gene in the optimal chromosome vector.

[0098] Specifically, based on the optimal chromosome vector X best Determine the position of each beam B1~B in each hop beam time slot of the hop beam period. m The specific wave position scanned. That is, based on X... best In the middle and each beam B1~B in each hopping beam time slot m The corresponding gene coding values ​​are determined in relation to each beam B1~B m The corresponding wave position.

[0099] By using the above methods, we can meet the communication needs of each coverage area while avoiding co-channel interference between beams.

[0100] In addition, refer to Figure 1 As shown, according to a second aspect of this embodiment, a storage medium is provided. The storage medium includes a stored program, wherein, when the program is executed, a processor performs any of the methods described above.

[0101] Therefore, according to this embodiment, this application not only ensures the adaptability of each beam sub-band to the coverage area environment and service requirements through neural networks, but also avoids coverage overlap and sidelobe leakage interference of co-frequency beams to the greatest extent from the scanning timing dimension by using a genetic algorithm combined with an interference quantization adaptation function. This simultaneously achieves the dual goals of sub-band adaptation and interference suppression, thereby solving the technical problems in the prior art that make it difficult to suppress interference caused by co-frequency configuration of adjacent beams while meeting the sub-band adaptation requirements, as well as the signal-to-interference-plus-noise ratio reduction caused by high spectrum reuse and beam physical characteristics superposition.

[0102] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the present invention is not limited to the described order of actions, because according to the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0103] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0104] Example 2

[0105] Figure 8 A satellite beam scanning scheduling apparatus according to the first aspect of this embodiment is shown, which corresponds to the method described according to Embodiment 1. Reference Figure 8 As shown, the device includes: an acquisition module 810 for acquiring parameter features of the coverage area of ​​multiple beams of a satellite, wherein the parameter features are used to characterize the communication link characteristics between the satellite and the coverage area; an input module 820 for inputting the parameter features into a pre-trained neural network model, and determining the sub-frequency bands adapted to the multiple beams through the neural network model; an initialization module 830 for initializing chromosome vectors and constructing an initial population, wherein the chromosome vectors are used to indicate the positions scanned by each beam of the satellite in each hop beam time slot of the hop beam period; a construction module 840 for constructing an fitness function, wherein the function value of the fitness function is related to the severity of co-channel interference in the satellite coverage area; an iteration module 850 for iteratively optimizing the initial population according to a genetic algorithm to determine the optimal chromosome vector; and a determination module 860 for determining the positions scanned by each beam in each hop beam time slot of the hop beam period based on the optimal chromosome vector.

[0106] Optionally, the operation of acquiring parameter characteristics of multiple coverage areas of the satellite includes acquiring the following parameter characteristics: average rainfall rate of the coverage area; user density of the coverage area; service traffic demand of the coverage area; beam elevation angle of the corresponding beam of the coverage area; and atmospheric water vapor density of the coverage area.

[0107] Optionally, the operation of inputting parameter features into a pre-trained neural network model and determining the sub-bands adapted to multiple beams through the neural network model includes: inputting parameter features corresponding to the coverage area into the neural network model and then outputting corresponding classification information through a classifier, wherein the classification information includes the probability value of each sub-band being used by the beam corresponding to the coverage area; and selecting the sub-band with the highest probability value as the sub-band being used by the beam corresponding to the coverage area.

[0108] Optionally, the operation of initializing chromosome vectors and constructing an initial population includes: defining chromosome vectors and corresponding each gene of the chromosome vectors with the wave positions scanned by each beam in different hopping beam slots of the hopping beam period; generating multiple chromosome vectors that conform to the definition; and randomly encoding the genes in each chromosome vector according to preset constraints to construct an initial population, wherein the constraints stipulate that multiple beams scan all their corresponding wave positions within the hopping beam period.

[0109] Optionally, the operation of constructing the fitness function includes constructing a fitness function S(X) as follows:

[0110]

[0111] Where I1(X) represents the time slots of each beam B1~B according to the chromosome vector X in each beam hopping time slot. m In the case of beam assignment, the number of overlapping regions formed by two beams of the same frequency band appearing in the entire beam-hopping period; and I2(X) represents the number of beams B1~B1 in each beam-hopping time slot according to the chromosome vector X. m In the case of assigned beam positions, the number of overlapping regions formed by the overlap of three beams in the same frequency band that occur throughout the entire hopping beam period.

[0112] Optionally, the iterative optimization of the initial population using a genetic algorithm includes: using the initial population as the parent population, performing crossover and mutation operations on multiple chromosome vectors in the parent population to generate multiple chromosome vectors as the child population; calculating the fitness value of each chromosome vector in the parent and child populations using a fitness function; sorting the chromosome vectors of the parent and child populations together according to their fitness values, and selecting a predetermined number of chromosome vectors with the lowest fitness values ​​as the parent population for the next iteration.

[0113] Optionally, the operation of determining the wave positions scanned by each beam in each hop beam time slot of the hop beam period based on the optimal chromosome vector includes: determining the wave positions scanned by each beam in each hop beam time slot of the hop beam period based on the coding values ​​of each gene in the optimal chromosome vector.

[0114] Therefore, according to this embodiment, this application not only ensures the adaptability of each beam sub-band to the coverage area environment and service requirements through neural networks, but also avoids coverage overlap and sidelobe leakage interference of co-frequency beams to the greatest extent from the scanning timing dimension by using a genetic algorithm combined with an interference quantization adaptation function. This simultaneously achieves the dual goals of sub-band adaptation and interference suppression, thereby solving the technical problems in the prior art that make it difficult to suppress interference caused by co-frequency configuration of adjacent beams while meeting the sub-band adaptation requirements, as well as the signal-to-interference-plus-noise ratio reduction caused by high spectrum reuse and beam physical characteristics superposition.

[0115] Example 3

[0116] Figure 9 A satellite beam scanning scheduling apparatus according to this embodiment is shown, which corresponds to the method described according to Embodiment 1. (Reference) Figure 9 As shown, the device includes: a processor 910; and a memory 920 connected to the processor 910, for providing the processor 910 with instructions to process the following steps: acquiring parameter characteristics of the coverage area of ​​multiple beams of a satellite, wherein the parameter characteristics are used to characterize the communication link characteristics between the satellite and the coverage area; inputting the parameter characteristics into a pre-trained neural network model, and determining the sub-frequency bands adapted to the multiple beams through the neural network model; initializing chromosome vectors and constructing an initial population, wherein the chromosome vectors are used to indicate the positions scanned by each beam of the satellite in each hop beam time slot of the hop beam period; constructing an fitness function, wherein the function value of the fitness function is related to the severity of co-channel interference in the satellite coverage area; iteratively optimizing the initial population according to a genetic algorithm to determine the optimal chromosome vector; and determining the positions scanned by each beam in each hop beam time slot of the hop beam period according to the optimal chromosome vector.

[0117] Optionally, the operation of acquiring parameter characteristics of multiple coverage areas of the satellite includes acquiring the following parameter characteristics: average rainfall rate of the coverage area; user density of the coverage area; service traffic demand of the coverage area; beam elevation angle of the corresponding beam of the coverage area; and atmospheric water vapor density of the coverage area.

[0118] Optionally, the operation of inputting parameter features into a pre-trained neural network model and determining the sub-bands adapted to multiple beams through the neural network model includes: inputting parameter features corresponding to the coverage area into the neural network model and then outputting corresponding classification information through a classifier, wherein the classification information includes the probability value of each sub-band being used by the beam corresponding to the coverage area; and selecting the sub-band with the highest probability value as the sub-band being used by the beam corresponding to the coverage area.

[0119] Optionally, the operation of initializing chromosome vectors and constructing an initial population includes: defining chromosome vectors and corresponding each gene of the chromosome vectors with the wave positions scanned by each beam in different hopping beam slots of the hopping beam period; generating multiple chromosome vectors that conform to the definition; and randomly encoding the genes in each chromosome vector according to preset constraints to construct an initial population, wherein the constraints stipulate that multiple beams scan all their corresponding wave positions within the hopping beam period.

[0120] Optionally, the operation of constructing the fitness function includes constructing a fitness function S(X) as follows:

[0121]

[0122] Where I1(X) represents the time slots of each beam B1~B according to the chromosome vector X in each beam hopping time slot. m In the case of beam assignment, the number of overlapping regions formed by two beams of the same frequency band appearing in the entire beam-hopping period; and I2(X) represents the number of beams B1~B1 in each beam-hopping time slot according to the chromosome vector X. m In the case of assigned beam positions, the number of overlapping regions formed by the overlap of three beams in the same frequency band that occur throughout the entire hopping beam period.

[0123] Optionally, the iterative optimization of the initial population using a genetic algorithm includes: using the initial population as the parent population, performing crossover and mutation operations on multiple chromosome vectors in the parent population to generate multiple chromosome vectors as the child population; calculating the fitness value of each chromosome vector in the parent and child populations using a fitness function; sorting the chromosome vectors of the parent and child populations together according to their fitness values, and selecting a predetermined number of chromosome vectors with the lowest fitness values ​​as the parent population for the next iteration.

[0124] Optionally, the operation of determining the wave positions scanned by each beam in each hop beam time slot of the hop beam period based on the optimal chromosome vector includes: determining the wave positions scanned by each beam in each hop beam time slot of the hop beam period based on the coding values ​​of each gene in the optimal chromosome vector.

[0125] Therefore, according to this embodiment, this application not only ensures the adaptability of each beam sub-band to the coverage area environment and service requirements through neural networks, but also avoids coverage overlap and sidelobe leakage interference of co-frequency beams to the greatest extent from the scanning timing dimension by using a genetic algorithm combined with an interference quantization adaptation function. This simultaneously achieves the dual goals of sub-band adaptation and interference suppression, thereby solving the technical problems in the prior art that make it difficult to suppress interference caused by co-frequency configuration of adjacent beams while meeting the sub-band adaptation requirements, as well as the signal-to-interference-plus-noise ratio reduction caused by high spectrum reuse and beam physical characteristics superposition.

[0126] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0127] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0128] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0129] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0130] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0131] If the integrated unit is implemented as 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 technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0132] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A satellite beam scanning scheduling method, characterized in that, include: The parameter characteristics of the coverage area of ​​multiple beams of a satellite are obtained, wherein the parameter characteristics are used to characterize the communication link characteristics between the satellite and the coverage area; The parameter features are input into a pre-trained neural network model, and the sub-bands adapted to the multiple beams are determined by the neural network model. Initialize the chromosome vector and construct an initial population, wherein the chromosome vector is used to indicate the wave positions scanned by each beam of the satellite in each hop beam time slot of the hop beam period; Construct an adaptation function, wherein the function value of the adaptation function is related to the severity of co-channel interference within the satellite coverage area; The initial population is iteratively optimized using a genetic algorithm to determine the optimal chromosome vector; and Based on the optimal chromosome vector, determine the wave positions scanned by each beam in each hop beam time slot of the hop beam period; The operation of inputting the parameter features into a pre-trained neural network model and determining the sub-frequency bands adapted to the multiple beams through the neural network model includes: After the parameter features corresponding to the coverage area are input into the neural network model, the classifier outputs corresponding classification information, wherein the classification information includes the probability values ​​of the beam corresponding to the coverage area using each sub-frequency band; and The sub-frequency band with the highest probability value is used as the sub-frequency band for the beam corresponding to the coverage area; The operation of determining the wave positions scanned by each beam in each hop beam slot of the hop beam period based on the optimal chromosome vector includes: Based on the coding values ​​of each gene in the optimal chromosome vector, the wave positions scanned by each beam in each hop beam time slot of the hop beam period are determined.

2. The method according to claim 1, characterized in that, The operation of obtaining parameter characteristics of multiple coverage areas of a satellite includes obtaining the following parameter characteristics: The average rainfall rate of the covered area; User density in the coverage area; The service traffic requirements of the coverage area; The beam elevation angle of the beam corresponding to the coverage area; and The atmospheric water vapor density of the covered area.

3. The method according to claim 1, characterized in that, The operations for initializing chromosome vectors and constructing the initial population include: Define a chromosome vector and associate each gene in the chromosome vector with the wave position scanned by each beam in different hop beam time slots of the hop beam period; Generate multiple chromosome vectors that conform to the definition; and The genes in each chromosome vector are randomly encoded according to preset constraints to construct the initial population, wherein the constraints stipulate that the multiple beams scan all their corresponding positions within the beam-hopping period.

4. The method according to claim 1, characterized in that, The operation of constructing the fitness function includes constructing the fitness function S(X) as described below: Wherein, I1(X) represents the time slots of each beam B1~B according to the chromosome vector X in each beam hopping time slot. m In the case of beam assignment, the number of overlapping regions caused by two beams of the same frequency band appearing throughout the entire beam-hopping period; and I2(X) represents the time slots of each beam hopping beam according to the chromosome vector X, which are each beam B1~B. m In the case of assigned beam positions, the number of overlapping regions formed by the overlap of three beams in the same frequency band that occur throughout the entire hopping beam period.

5. The method according to claim 1, characterized in that, The operation of iteratively optimizing the initial population according to the genetic algorithm includes: Using the initial population as the parent population, perform crossover and mutation operations on multiple chromosome vectors in the parent population to generate multiple chromosome vectors as the child population. The fitness value of each chromosome vector in the parent population and the child population is calculated using the fitness function; The chromosome vectors of the parent population and the child population are sorted together according to their fitness values, and a predetermined number of chromosome vectors with the lowest fitness values ​​are selected as the parent population for the next round of iteration.

6. A storage medium, characterized in that, The storage medium includes a stored program, wherein, when the program is executed, the method described in any one of claims 1 to 5 is performed by a processor.

7. A satellite beam scanning and scheduling device, characterized in that, include: An acquisition module is used to acquire parameter characteristics of the coverage area of ​​multiple beams of a satellite, wherein the parameter characteristics are used to characterize the communication link characteristics between the satellite and the coverage area; An input module is used to input the parameter features into a pre-trained neural network model, and to determine the sub-frequency bands that are adapted to the multiple beams through the neural network model; An initialization module is used to initialize chromosome vectors and construct an initial population, wherein the chromosome vectors are used to indicate the wave positions scanned by each beam of the satellite in each hop beam time slot of the hop beam period; A construction module is used to construct an adaptation function, wherein the function value of the adaptation function is related to the severity of co-channel interference within the satellite coverage area; An iterative module is used to iteratively optimize the initial population using a genetic algorithm to determine the optimal chromosome vector; and The determination module is used to determine the wave positions scanned by each beam in each hop beam time slot of the hop beam period based on the optimal chromosome vector. The operation of inputting the parameter features into a pre-trained neural network model and determining the sub-frequency bands adapted to the multiple beams through the neural network model includes: After the parameter features corresponding to the coverage area are input into the neural network model, the classifier outputs corresponding classification information, wherein the classification information includes the probability values ​​of the beam corresponding to the coverage area using each sub-frequency band; and The sub-frequency band with the highest probability value is used as the sub-frequency band for the beam corresponding to the coverage area; The operation of determining the wave positions scanned by each beam in each hop beam slot of the hop beam period based on the optimal chromosome vector includes: Based on the coding values ​​of each gene in the optimal chromosome vector, the wave positions scanned by each beam in each hop beam time slot of the hop beam period are determined.

8. A satellite beam scanning and scheduling device, characterized in that, include: processor; as well as A memory, connected to the processor, for providing the processor with instructions to perform the following processing steps: The parameter characteristics of the coverage area of ​​multiple beams of a satellite are obtained, wherein the parameter characteristics are used to characterize the communication link characteristics between the satellite and the coverage area; The parameter features are input into a pre-trained neural network model, and the sub-bands adapted to the multiple beams are determined by the neural network model. Initialize the chromosome vector and construct an initial population, wherein the chromosome vector is used to indicate the wave positions scanned by each beam of the satellite in each hop beam time slot of the hop beam period; Construct an adaptation function, wherein the function value of the adaptation function is related to the severity of co-channel interference within the satellite coverage area; The initial population is iteratively optimized using a genetic algorithm to determine the optimal chromosome vector; and Based on the optimal chromosome vector, determine the wave positions scanned by each beam in each hop beam time slot of the hop beam period; The operation of inputting the parameter features into a pre-trained neural network model and determining the sub-frequency bands adapted to the multiple beams through the neural network model includes: After the parameter features corresponding to the coverage area are input into the neural network model, the classifier outputs corresponding classification information, wherein the classification information includes the probability values ​​of the beam corresponding to the coverage area using each sub-frequency band; and The sub-frequency band with the highest probability value is used as the sub-frequency band for the beam corresponding to the coverage area; The operation of determining the wave positions scanned by each beam in each hop beam slot of the hop beam period based on the optimal chromosome vector includes: Based on the coding values ​​of each gene in the optimal chromosome vector, the wave positions scanned by each beam in each hop beam time slot of the hop beam period are determined.

Images