Satellite-based routing decision making method and apparatus, and storage medium

Abstract

The application discloses a satellite-based routing decision-making method and device and a storage medium, comprising the following steps: determining a plurality of reference curves in each first sampling period; determining a first distribution curve in a current period, and broadcasting the reference curve in the current period, the first distribution curve and the channel capacity of each region in the current period to each satellite; determining a reference curve in a next period, calculating the deformation relationship between the reference curve in the second sampling period and the reference curve in the third sampling period, deforming the first distribution curve to obtain a plurality of second distribution curves in the next period; predicting the satellite congestion degree of each region in the next period based on the channel capacity of each region in the current period according to the plurality of second distribution curves; and constructing a plurality of corresponding routing paths based on each region, and determining an optimal routing path in the plurality of routing paths by using a genetic algorithm. Thus, the technical effect of reliably transmitting data is achieved.

Description

Technical Field

[0001] This application relates to the field of satellite communication technology, and in particular to a satellite-based routing decision-making method, apparatus, and storage medium. Background Technology

[0002] Because satellite network topology changes rapidly and onboard resources (including bandwidth, buffers, and power) are strictly limited, satellite congestion can occur when the amount of data transmitted per second is high enough to approach or exceed channel capacity. Furthermore, to ensure better data transmission, satellite transmission routing strategies are typically implemented. This involves selecting the optimal route from multiple available options to achieve optimal network performance and balanced resource utilization. Therefore, if the specified routing strategy includes satellites with high congestion levels, traffic can easily accumulate at "critical nodes" (i.e., satellites with high congestion levels), causing localized congestion that quickly spreads and leads to a precipitous drop in overall network performance.

[0003] Furthermore, regarding routing decisions for the current time period, since the satellite congestion level can be calculated within the current timeframe, a suitable routing strategy can be formulated based on this congestion level. However, for routing strategies for the next time period, current technology typically cannot predict the satellite congestion level in the next period. Therefore, the formulated routing strategy for the next period is not based on the satellite congestion level of the next period; that is, the routing strategy for the next period is usually a continuation of the routing strategy for the current period. Consequently, during data transmission based on the original routing strategy, there is a high possibility that excessive satellite congestion will lead to data transmission delays and packet loss, resulting in unreliable data transmission.

[0004] The publication number is CN117614882A, and the title is "A Method and Apparatus for Routing Decisions in Low-Earth Orbit Satellite Networks Based on Multi-Agent Systems." The method includes: acquiring a data packet to be sent and the target satellite address; determining a target transmission path corresponding to the current satellite address and the target satellite address based on the target satellite address and a pre-established transmission routing strategy; wherein the pre-established transmission routing strategy is determined based on the state information of the source satellite node, the destination satellite node, the network status, and adjacent satellite nodes; and sending the data packet to the satellite corresponding to the target satellite address according to the target transmission path.

[0005] The publication number is CN105933227A, entitled "A Method for Routing Decision and Flow Table Consistency Optimization in Software-Defined Satellite Networks." The flow table consistency optimization method of this invention first uses network awareness to monitor the global state of the satellite network in real time, maintain the topology map of the satellite network at different times, and update the network topology state and events in a timely manner. Then, it combines routing decisions based on delivery delay and routing decisions based on path similarity, requiring relatively small delivery and write delays, thereby reducing the total latency of the flow table update process. Finally, by adjusting the delivery order of the switches, the impact of the switch-to-controller latency on flow table inconsistency is reduced. By classifying and processing old and new flow tables, the number of delivered flow table entries is reduced, thereby reducing the write time of flow table entries and thus reducing the total latency of flow table updates.

[0006] There is currently no effective solution to the technical problem in the existing technology that the inability to predict the degree of satellite congestion means that, in the process of continuing the original routing strategy for data transmission, the high degree of satellite congestion may lead to data transmission delays and packet loss, resulting in unreliable data transmission. Summary of the Invention

[0007] The embodiments of this disclosure provide a satellite-based routing decision-making method, apparatus, and storage medium to at least solve the technical problem in the prior art where, due to the inability to predict the degree of satellite congestion, data transmission delays and packet loss are highly likely to occur during the data transmission process while continuing the original routing strategy, thus leading to unreliable data transmission.

[0008] According to one aspect of the present disclosure, a satellite-based routing decision-making method is provided, comprising: determining multiple reference curves representing satellite congestion levels under each first sampling period in a sampling phase, wherein the reference curves correspond to the data traffic of satellites in corresponding areas under the first sampling period; determining a first distribution curve representing satellite congestion levels under the current period, and broadcasting the reference curve of a second sampling period corresponding to the current period, the first distribution curve, and the channel capacity of each area under the current period to each satellite, wherein the first distribution curve corresponds to the data traffic of satellites in corresponding areas under the current period; determining a reference curve for a third sampling period corresponding to the next period, calculating the deformation relationship between the reference curve of the second sampling period and the reference curve of the third sampling period, and performing deformation processing on the first distribution curve of the current period based on the deformation relationship to obtain multiple second distribution curves for the next period; predicting the satellite congestion level of each area under the next period based on the multiple second distribution curves and according to the channel capacity of each area under the current period; and constructing multiple corresponding routing paths based on each area, and using a genetic algorithm to determine the optimal routing path among the multiple routing paths, wherein the optimal routing path represents the routing path with the minimum satellite congestion level.

[0009] 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.

[0010] According to another aspect of the present disclosure, a satellite-based routing decision-making apparatus is also provided, comprising: a reference curve determination module, configured to determine multiple reference curves representing satellite congestion levels under each first sampling period in a sampling phase, wherein the reference curves correspond to the data traffic of satellites in corresponding areas under the first sampling period; and an information broadcasting module, configured to determine a first distribution curve representing satellite congestion levels under the current period, and broadcast the reference curves of a second sampling period corresponding to the current period, the first distribution curves, and the channel capacity of each area under the current period to each satellite, wherein the first distribution curves correspond to the data traffic of satellites in corresponding areas under the current period; the distribution curve determination module; and the information broadcasting module. The system is used to determine the reference curve for the third sampling period corresponding to the next time period, calculate the deformation relationship between the reference curves for the second and third sampling periods, and deform the first distribution curve for the current time period based on the deformation relationship to obtain multiple second distribution curves for the next time period; the congestion prediction module is used to predict the satellite congestion level of each region in the next time period based on multiple second distribution curves and the channel capacity of each region in the current time period; and the routing decision determination module is used to construct multiple corresponding routing paths based on each region, and use a genetic algorithm to determine the optimal routing path among the multiple routing paths, where the optimal routing path represents the routing path with the minimum satellite congestion level.

[0011] According to another aspect of the present disclosure, a satellite-based routing decision-making 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: determining a plurality of reference curves representing satellite congestion levels under each first sampling period in a sampling phase, wherein the reference curves correspond to the data traffic of satellites in corresponding areas under the first sampling period; determining a first distribution curve representing satellite congestion levels under the current period, and broadcasting the reference curve, the first distribution curve, and the channel capacity of each area under the current period to each satellite under a second sampling period corresponding to the current period, wherein the first distribution curve corresponds to the data traffic of satellites in corresponding areas under the first sampling period. The system identifies the data traffic of satellites in the corresponding regions under each segment; determines the reference curve for the third sampling period corresponding to the next time segment; calculates the deformation relationship between the reference curves for the second and third sampling periods; and deforms the first distribution curve for the current time segment based on this deformation relationship to obtain multiple second distribution curves for the next time segment. Based on these multiple second distribution curves and the channel capacity of each region under the current time segment, the system predicts the satellite congestion level for each region in the next time segment. Furthermore, based on each region, the system constructs multiple corresponding routing paths and uses a genetic algorithm to determine the optimal routing path among these paths, where the optimal routing path represents the routing path with the lowest satellite congestion level.

[0012] This application provides a satellite-based routing decision-making method. First, a gateway station determines multiple reference curves representing satellite congestion levels for each first sampling period during the sampling phase. Then, the gateway station determines a first distribution curve representing satellite congestion levels for the current period and broadcasts the reference curve for the second sampling period corresponding to the current period, the first distribution curve, and the channel capacity for each region in the current period to each satellite. Further, the gateway station determines a reference curve for the third sampling period corresponding to the next period, calculates the deformation relationship between the reference curves for the second and third sampling periods, and deforms the first distribution curve for the current period based on this deformation relationship to obtain multiple second distribution curves for the next period. Then, based on the multiple second distribution curves and the channel capacity for each region in the current period, the gateway station predicts the satellite congestion level for each region in the next period. Finally, the gateway station constructs multiple routing paths for each region and uses a genetic algorithm to determine the optimal routing path among these paths.

[0013] As described above, this application discloses the determination of a reference curve and a first distribution curve corresponding to the current time period, and broadcasts the reference curve, the first distribution curve, and the channel capacity of each region under the current time period to each satellite. Thus, when the satellite determines the region it will move to in the next time period, it can further determine the reference curve corresponding to that region in the next time period based on the broadcast information. In other words, the satellite can determine deformation information based on the reference curve of the current time period and the reference curve of the next time period, and obtain multiple second distribution curves for the next time period based on the deformation information and the first distribution curve. This enables the prediction of the congestion level of each satellite in each region for the next time period.

[0014] Furthermore, since this application predicts the congestion level of the satellite in each region before determining the optimal route path, the optimal route path determined by the genetic algorithm has a lower congestion level, which can ensure reliable data transmission.

[0015] This solves the technical problem in existing technologies where the inability to predict satellite congestion levels leads to data transmission delays and packet loss during the transmission process using the original routing strategy, resulting in unreliable data transmission. Attached Figure Description

[0016] 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:

[0017] Figure 1 This is a schematic diagram illustrating the communication connection relationship between multiple satellites and gateway stations during the current time period, as described in Embodiment 1 of this application.

[0018] Figure 2A This is a schematic diagram of the hardware architecture of the satellite according to Embodiment 1 of this application;

[0019] Figure 2B This is a schematic diagram of the hardware architecture of the gateway station according to Embodiment 1 of this application;

[0020] Figure 3 This is a schematic diagram of the satellite-based routing decision-making method according to Embodiment 1 of this application;

[0021] Figure 4 According to Embodiment 1 of this application, the current time period and region A schematic diagram of the corresponding first distribution curve and reference curve;

[0022] Figure 5 This is a schematic diagram of the satellite-based routing decision-making device according to Embodiment 2 of this application;

[0023] Figure 6 This is a schematic diagram of a satellite-based routing decision-making device according to Embodiment 3 of this application. 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-based route decision determination 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 illustrating the communication connection relationship between multiple satellites 101-103 and gateway station 20 during the current time period, according to an embodiment of this application. (Reference) Figure 1 As shown, in the current time period Below, multiple satellites 101 to 103 correspond to regions 301 to 303. Thus, satellite 101 can, for example, establish a communication connection with a terminal device in region 301, satellite 102 can, for example, establish a communication connection with a terminal device in region 302, and satellite 103 can, for example, establish a communication connection with a terminal device in region 303.

[0029] Furthermore, when satellites 101-103 receive data information transmitted from terminal devices in corresponding areas 301-303, they can transmit the corresponding data information to the gateway station 20 with communication connection, so that the gateway station 20 can perform subsequent processing on the data information.

[0030] In addition, refer to Figure 1 As shown, since satellites 101-103 are constantly moving, in the next time period, satellite 101 may, for example, move to the location corresponding to area 302 and establish a communication connection with the terminal equipment in area 302. Satellite 102 may, for example, move to the location corresponding to area 303 and establish a communication connection with the terminal equipment in area 303.

[0031] And it is worth noting that the above Figure 1The examples used are satellites 101-103; the actual situation is not limited to these.

[0032] Figure 2A Further shown Figure 1 A schematic diagram of the hardware architecture of the satellite. (Reference) Figure 2A As shown, the satellite 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, and read 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. Furthermore, the processor also communicates with devices such as cameras, star sensors, telemetry and command transponders, and data transmission equipment via the communication interface. Those skilled in the art will understand that… Figure 2A 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 2A The more or fewer components shown, or having the same Figure 2A The different configurations shown.

[0033] Figure 2B Further shown Figure 1 A schematic diagram of the hardware architecture of CITIC's gateway. (Reference) Figure 2B As shown, a gateway station may include one or more processors (processors may include, but are not limited to, microprocessors such as MCUs or programmable logic devices such as FPGAs), a memory for storing data, a transmission device for communication functions, and an input / output interface. The memory, transmission device, and input / output interface are connected to the processor via a bus. In addition, it may also include a display, keyboard, and cursor control device connected to the input / output interface. Those skilled in the art will understand that... Figure 2B The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, the ground system may also include... Figure 2B The more or fewer components shown, or having the same Figure 2B The different configurations shown.

[0034] It should be noted that, Figure 2A and Figure 2BOne 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).

[0035] Figure 2A and Figure 2B The memory shown can be used to store software programs and modules of application software, such as the program instruction / data storage device corresponding to the satellite congestion prediction-based routing decision determination method in this embodiment of the present disclosure. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby implementing the satellite congestion prediction-based routing decision determination method of the aforementioned application. 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.

[0036] It should be noted here that, in some optional embodiments, the above... Figure 2A and Figure 2B 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 2A and Figure 2B This 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.

[0037] Under the aforementioned operating environment, according to the first aspect of this embodiment, a satellite-based routing decision determination method is provided, which consists of... Figure 1 The gateway station shown is implemented. Figure 3 A flowchart illustrating the method is shown below. (Refer to...) Figure 3 As shown, the method includes:

[0038] S302: Determine multiple reference curves for representing the degree of satellite congestion during each first sampling period in the sampling phase, wherein the reference curves correspond to the traffic required for the satellite to forward data in the corresponding area during the first sampling period;

[0039] S304: Determine the first distribution curve for representing the satellite congestion level in the current time period, and broadcast the reference curve of the second sampling time period corresponding to the current time period, the first distribution curve, and the channel capacity of each region in the current time period to each satellite, wherein the first distribution curve corresponds to the traffic required for the satellite to forward the data of the corresponding region in the current time period;

[0040] S306: Determine the reference curve for the third sampling period corresponding to the next time period, calculate the deformation relationship between the reference curve for the second sampling period and the reference curve for the third sampling period, and perform deformation processing on the first distribution curve of the current time period based on the deformation relationship to obtain multiple second distribution curves for the next time period.

[0041] S308: Based on multiple second distribution curves and according to the channel capacity of each region in the current time period, predict the satellite congestion level of each region in the next time period; and

[0042] S310: Based on each region, construct multiple corresponding routing paths, and use a genetic algorithm to determine the optimal routing path among the multiple routing paths, where the optimal routing path represents the routing path with the least satellite congestion.

[0043] Specifically, first, the gateway 20 determines the multiple sampling periods included in the sampling phase. For example, the sampling phase includes sampling periods. Sampling period Sampling period Sampling period And the above sampling periods ~ All include multiple initial sampling periods. For example, the sampling period. Including the first sampling period ~ Sampling period Including the first sampling period ~ Sampling period Including the first sampling period ~ Sampling period Including the first sampling period ~ .

[0044] Therefore, gateway station 20 collects the data traffic required by each satellite to forward data information to the corresponding area during each sampling period of each sampling cycle. Table 1 shows the data traffic required by each satellite to forward data information to the corresponding area during each sampling period. The bandwidth required for each satellite to relay data information to its corresponding region.

[0045] Table 1

[0046]

[0047] Referring to Table 1, during the first sampling period , and region The corresponding satellite relay data traffic is During the first sampling period , and region The corresponding satellite relay data traffic is ..., during the first sampling period , and region The corresponding satellite relay data traffic is .

[0048] First sampling period , and region The corresponding satellite relay data traffic is During the first sampling period , and region The corresponding satellite relay data traffic is ..., during the first sampling period , and region The corresponding satellite relay data traffic is .

[0049] First sampling period , and region The corresponding satellite relay data traffic is During the first sampling period , and region The corresponding satellite relay data traffic is ..., during the first sampling period , and region The corresponding satellite relay data traffic is .

[0050] And so on.

[0051] First sampling period , and region The corresponding satellite relay data traffic is During the first sampling period , and region The corresponding satellite relay data traffic is ..., during the first sampling period , and region The corresponding satellite relay data traffic is .

[0052] Table 2 shows the sampling period The bandwidth required for each satellite to relay data information to its corresponding region.

[0053] Table 2

[0054]

[0055] Referring to Table 2, during the first sampling period , and region The bandwidth required for the corresponding satellite data relay is During the first sampling period , and region The bandwidth required for the corresponding satellite data relay is ..., during the first sampling period , and region The bandwidth required for the corresponding satellite data relay is .

[0056] First sampling period , and region The bandwidth required for the corresponding satellite data relay is During the first sampling period , and region The bandwidth required for the corresponding satellite data relay is ..., during the first sampling period , and region The bandwidth required for the corresponding satellite data relay is .

[0057] First sampling period , and region The bandwidth required for the corresponding satellite data relay is During the first sampling period , and region The bandwidth required for the corresponding satellite data relay is ..., during the first sampling period , and region The bandwidth required for the corresponding satellite data relay is .

[0058] And so on.

[0059] First sampling period , and region The bandwidth required for the corresponding satellite data relay is During the first sampling period , and region The bandwidth required for the corresponding satellite data relay is ..., during the first sampling period , and region The bandwidth required for the corresponding satellite data relay is .

[0060] Similarly, it can be concluded that...

[0061] Table 3 shows the sampling period The data traffic required for each satellite to relay data information to its corresponding region.

[0062] Table 3

[0063]

[0064] Referring to Table 3, during the first sampling period , and region The bandwidth required for the corresponding satellite data relay is During the first sampling period , and region The bandwidth required for the corresponding satellite data relay is ..., during the first sampling period , and region The bandwidth required for the corresponding satellite data relay is .

[0065] First sampling period , and region The corresponding satellite relay data traffic is During the first sampling period , and region The bandwidth required for the corresponding satellite data relay is ..., during the first sampling period , and region The bandwidth required for the corresponding satellite data relay is .

[0066] First sampling period , and region The bandwidth required for the corresponding satellite data relay is During the first sampling period , and region The bandwidth required for the corresponding satellite data relay is ..., during the first sampling period , and region The bandwidth required for the corresponding satellite data relay is .

[0067] And so on.

[0068] First sampling period , and region The bandwidth required for the corresponding satellite data relay is During the first sampling period , and region The bandwidth required for the corresponding satellite data relay is ..., during the first sampling period , and region The bandwidth required for the corresponding satellite data relay is .

[0069] Then, gateway station 20 generates table 4 based on tables 1-3 above. Table 4 shows the sampling period. ~ Within, and in each first sampling period ~ and various regions ~ The corresponding second dataset.

[0070] Table 4

[0071]

[0072] in, Indicates the first sampling period The area below The second dataset. And among them, = . Indicates the first sampling period The area below The second dataset. And among them, = And so on. Indicates the first sampling period The area below The second dataset. And among them, = .

[0073] Similarly, it can be determined that in other first sampling periods, the characteristics of each region can be determined. ~ The corresponding second dataset will not be discussed further here.

[0074] Finally, gateway station 20 performs logarithmic fitting on each of the aforementioned second datasets and determines multiple reference curves to represent the degree of satellite congestion. Among them, the reference curve generated after fitting. The curve is a normal distribution, and i = 1 ~ a, j = 1 ~ n.

[0075] Then, gateway 20 determines the current time period. and the current time period Divided into various sub-time periods The system collects the bandwidth required for satellites to relay data to the corresponding areas within each sub-time period. Table 5 shows the bandwidth required for each sub-time period. The bandwidth required for satellites to relay data to various regions.

[0076] Table 5

[0077]

[0078] Refer to Table 5. Indicates the time period Below, satellite relay area Required traffic Indicates the time period Below, satellite relay area Required traffic, ... Indicates the time period Below, satellite relay area The required traffic.

[0079] Table 6 shows the sub-time periods The bandwidth required for satellites to relay data to various regions.

[0080] Table 6

[0081]

[0082] Refer to Table 6. Indicates the time period Below, satellite relay area The data traffic required Indicates the time period Below, satellite relay area The data traffic required, ... Indicates the time period Below, satellite relay area The data traffic required.

[0083] And so on.

[0084] Table 7 shows the sub-time period The bandwidth required for satellites to relay data to various regions.

[0085] Table 7

[0086]

[0087] Refer to Table 7. Indicates the time period Below, satellite relay area The data traffic required Indicates the time period Below, satellite relay area The data traffic required, ... Indicates the time period Below, satellite relay area The data traffic required.

[0088] Therefore, the gateway station 20 can obtain the current time period based on the data listed in Tables 5 to 7 above. Below, with various regions ~ The corresponding first dataset. Table 8 shows the dataset for the current time period. Below, with various regions ~ The corresponding first dataset.

[0089] Table 8

[0090]

[0091] Thus, the gateway station 20 supports the aforementioned first datasets. ~ Perform logarithmic fitting and determine the first distribution curve representing the satellite congestion level for the current time period. Among them, the first distribution curve after fitting. The curve is a normal distribution, and i = 1 ~ a.

[0092] Afterwards, the gateway station 20 determined the current time period. The corresponding second sampling period is then determined, and a reference curve corresponding to the current period is further identified. For example, the current period... Compared with the first sampling period Correspondingly, it can be determined that the first sampling period Corresponding reference curve ~ .

[0093] Figure 4 According to the embodiments of this application, the current time period and region A schematic diagram of the corresponding first distribution curve and reference curve. (Reference) Figure 4 As shown, the current time period and region There is an overlap between the corresponding first distribution curve and the reference curve corresponding to the current time period, and the horizontal axis of this coordinate system represents the satellite relay area. The required flow of data is shown on the y-axis, which represents the probability density.

[0094] Furthermore, gateway station 20 will display the first distribution curve representing the congestion level of each satellite during the current time period. The reference curve for the second sampling period corresponding to the current period, and the pre-determined channel capacity for each region under the current period, are broadcast to each satellite. The channel capacity for each region under the current period can, for example, be determined based on Shannon's formula. The specific formula is as follows:

[0095]

[0096] in, This indicates the satellite and its corresponding region during the current time period. Channel capacity between This indicates the satellite and its corresponding region during the current time period. The channel bandwidth between them, S is the signal power, and N is the noise power. Furthermore, within each region during the current time period... The channel bandwidth, signal power, and noise power can be predetermined by the gateway station 20, for example, and are not limited here.

[0097] Furthermore, the gateway station 20 determined the next time period. The corresponding third sampling period, and determine the next sampling period. The corresponding reference curve. For example, the second sampling period corresponding to the current time period is... In the next period The corresponding third sampling period is And with the next time period. The corresponding reference curve is ~ .

[0098] Therefore, the gateway station 20 calculates the deformation relationship between the reference curve corresponding to the current time period and the reference curve for the next time period, and obtains the deformation information corresponding to the reference curve for the next time period. The reference curves are all normally distributed curves. That is, the gateway station 20 performs translation and scaling on the reference curve corresponding to the current time period to make the shape of the reference curve for the current time period the same as the shape of the reference curve for the next time period, thereby obtaining the deformation information. The calculation steps for the deformation information include: First, since the reference curve for the current time period is a normally distributed curve, the gateway station 20 can calculate the first mean and the first standard deviation corresponding to the reference curve for the current time period. Similarly, since the reference curve for the next time period is a normally distributed curve, the gateway station 20 can calculate the second mean and the second standard deviation corresponding to the reference curve for the next time period.

[0099] Furthermore, the gateway station 20 determines the scaling parameter between the two corresponding reference distribution curves based on the first standard deviation and the second standard deviation. The gateway station also determines the translation parameter between the two corresponding reference distribution curves based on the first mean and the second mean.

[0100] Therefore, given the scaling and translation parameters, the gateway station 20 can further deform the first distribution curve corresponding to the current time period based on the scaling and translation parameters to obtain the second distribution curve corresponding to the next time period.

[0101] Then, the gateway station 20 performs deformation processing on each of the first distribution curves in the current time period according to the deformation information, and obtains multiple second distribution curves for the next time period.

[0102] Furthermore, the gateway station 20 predicts the satellite congestion level of each region in the next time period based on multiple second distribution curves and the channel capacity of each region in the current time period. The above will be described in detail later, and therefore will not be repeated here.

[0103] Finally, gateway station 20 constructs multiple routing paths between adjacent regions, using two adjacent regions as the standard, and uses a genetic algorithm to determine the optimal routing path among these paths. Specifically, first, gateway station 20 initializes chromosome vectors and constructs an initial population. Then, gateway station 20 constructs a fitness function. Further, based on the fitness function, gateway station 20 performs crossover, mutation, and iterative updates on the initialized population to determine the chromosome with the highest fitness. Finally, the gateway station determines the optimal routing path based on the chromosome with the highest fitness. The above will be described in detail later, so it will not be repeated here.

[0104] As described in the background section, for routing decision-making methods in the current time period, the satellite congestion level can be calculated, allowing for the formulation of a suitable routing strategy based on this level. However, for routing strategies in the next time period, existing technologies typically cannot predict the satellite congestion level. Therefore, the formulated routing strategy is not based on the congestion level of the next time period; rather, it usually continues the routing strategy of the current time period. Consequently, during data transmission based on the existing routing strategy, excessive satellite congestion can lead to data transmission delays and packet loss, resulting in unreliable data transmission.

[0105] In view of this, this application provides a routing decision determination method based on satellite congestion prediction. As described above, this application discloses determining a reference curve and a first distribution curve corresponding to the current time period, and broadcasting the reference curve, the first distribution curve, and the channel capacity of each region under the current time period to each satellite. Thus, the satellite can determine the region to be moved to in the next time period, and, given the determined region, the satellite can determine the reference curve corresponding to that region under the next time period based on the broadcast information. In other words, the satellite can determine deformation information based on the reference curve of the current time period and the reference curve of the next time period, and obtain multiple second distribution curves for the next time period based on the deformation information and the first distribution curve. This enables the prediction of the congestion level of each satellite in each region for the next time period.

[0106] Furthermore, since this application predicts the congestion level of the satellite in each region before determining the optimal route path, the optimal route path determined by the genetic algorithm has a lower congestion level, which can ensure reliable data transmission.

[0107] This solves the technical problem in existing technologies where the inability to predict satellite congestion levels leads to data transmission delays and packet loss during the transmission process using the original routing strategy, resulting in unreliable data transmission.

[0108] Optionally, the operation of constructing multiple routing paths between regions based on two adjacent paths and using a genetic algorithm to determine the optimal routing path among the multiple routing paths includes: initializing chromosome vectors and constructing an initial population, where the chromosome vectors represent routing paths composed of various regions; constructing a fitness function, where the value of the fitness function is related to the degree of satellite congestion within the routing path; performing crossover, mutation, and iterative updates on the initial population according to the fitness function to determine the chromosome with the highest fitness; and determining the optimal routing path based on the chromosome with the highest fitness.

[0109] Specifically, first, a chromosome vector is defined to characterize the degree of satellite congestion corresponding to each routing path. This chromosome represents a routing path composed of various regions. The individual genes on this chromosome... With the i-th region Correspondingly, i = 1 ~ a.

[0110] in, And among them, when When =0, it indicates the corresponding region in the next time period. The satellites are experiencing high levels of congestion; when When =1, it indicates the corresponding region in the next time period. The satellites have a relatively low level of congestion.

[0111] Then, gateway station 20 constructs the fitness function. :

[0112]

[0113] in, This represents the vector of the h-th chromosome. This represents the satellite congestion level of the routing path corresponding to the h-th chromosome vector. Where h = 1 ~ H.

[0114] Subsequently, the gateway station randomly initialized the population and obtained the initialized population. ~ ,in ~ This represents the initial chromosome. Further, the initial chromosome... ~ Substitute each value into the fitness function and determine the corresponding fitness value. ~ The selection probability of each initial chromosome is calculated based on its fitness value. Then, the first number of initial chromosomes with the highest selection probability are selected as the first chromosome, thus generating the first population. Chromosomes with higher fitness have a greater probability of being selected, and the selection probability can be calculated using a method such as roulette wheel selection.

[0115] Then, based on a pre-set crossover rate, a second number of chromosomes are determined from the first population, and crossover is performed on these chromosomes to generate new chromosomes (i.e., the second chromosome), thereby forming the second population from the second chromosomes.

[0116] Then, based on a pre-set mutation rate, a third number of chromosomes are determined from the second population, and these chromosomes are mutated to produce new chromosomes (i.e., the third chromosome), thereby forming the third population from the third chromosomes.

[0117] This completes the first iteration of the genetic algorithm.

[0118] For the second iteration, the third chromosome from the third population is input into the fitness function to determine the fitness of each third chromosome. Then, according to the steps in the first iteration, the third chromosome is subjected to selection, crossover, and mutation operations in sequence to generate a new population.

[0119] This completes the second iteration of the genetic algorithm.

[0120] This process involves multiple rounds of iterative calculations following the steps outlined above, until a predetermined number of iterations is reached, and the chromosome with the highest fitness is determined. Among them, the chromosome with the highest fitness... Indicates from the region ~ The route with the least congestion among multiple routing paths for satellites.

[0121] In other words, given the routing path corresponding to the chromosome with the highest fitness, using satellites corresponding to each region along that routing path for data transmission in the next time period can increase data transmission efficiency and improve data transmission reliability.

[0122] Optionally, the operation of predicting the satellite congestion level of each region in the next time period based on multiple second distribution curves and according to the channel capacity of each region in the current time period includes: randomly sampling on the second distribution curves and determining prediction points, wherein the prediction points include the traffic required for satellites to forward data in the corresponding region in the next time period and the corresponding probability density; and predicting the satellite congestion level of the corresponding region in the next time period based on the traffic required for satellites to forward data in the corresponding region in the next time period and the channel capacity of the corresponding region in the current time period.

[0123] Specifically, given that the gateway station 20 has determined multiple second distribution curves, random sampling is performed on each second distribution curve, and a prediction point P is selected. Among them, the predicted point P In Indicates the satellite's position in the corresponding area during the next time period. The traffic required to forward data Representation and flow The corresponding probability density. And for example, gateway station 20 can utilize 3... Based on the principle, the above prediction point P is randomly selected within the corresponding confidence interval. This will not be elaborated upon here.

[0124] Then, gateway station 20 predicts the satellite congestion level in the corresponding area for the next time period based on the data transmission traffic required by the satellite in the corresponding area during the next time period and the channel capacity of the corresponding area in the current time period. The specific calculation formula is as follows:

[0125]

[0126] in, Indicates the area corresponding to the next time period The satellite congestion level, measured in bps. Indicates the satellite's position in the corresponding area during the next time period. The bandwidth required to forward data is measured in bps. Indicates the area corresponding to the current time period. Channel capacity, measured in bps.

[0127] For example, the gateway station 20 is determined to be related to the region. The corresponding second distribution curve is obtained, and a random sample is taken from the second distribution curve to select a prediction point P. Then, gateway station 20 determines the bandwidth required for the satellite to relay data in the corresponding area during the next time period. and the channel capacity of the corresponding region in the current time period. Determine the corresponding area for the next time period. satellite congestion .

[0128] In this way, the gateway station 20 can determine the congestion level of the satellites corresponding to each region.

[0129] Optionally, the operation of determining the first distribution curve representing the satellite congestion level in the current time period includes: dividing the current time period into multiple sub-time periods and determining the traffic required for satellites to forward data in the corresponding area in each sub-time period; constructing multiple first datasets corresponding to each area in the current time period based on the traffic required for satellites to forward data in the corresponding area in each sub-time period; fitting each first dataset to generate the first distribution curve corresponding to each area in the current time period.

[0130] Specifically, firstly, the gateway station 20 will... Divided into multiple sub-time periods And collect data for each sub-time period. The bandwidth required for internal satellites to relay data to the corresponding region. Tables 5-7 above show the bandwidth required for sub-time periods. The corresponding data traffic required for satellites to relay data from various regions. Therefore, gateway station 2 can obtain the data required for the current time period based on the data listed in Tables 5-7 above. Below, with various regions ~ The corresponding first dataset. And the gateway station 20 corresponds to each of the first datasets in Table 8. ~ A fitting process is performed to determine the first distribution curve representing the degree of satellite congestion in the current time period. . Among them, i=1~a.

[0131] Optionally, the operation of determining multiple reference curves representing satellite congestion levels under each first sampling period in the sampling phase includes: determining multiple sampling periods in the sampling phase, and collecting the traffic required for satellites to forward data to the corresponding region within each first sampling period of the multiple sampling periods, wherein the sampling period includes multiple first sampling periods; constructing multiple second datasets corresponding to each region and each first sampling period based on the data traffic under each first sampling period in the multiple sampling periods corresponding to the region; and fitting each second dataset to generate reference curves for each region corresponding to each first sampling period.

[0132] Specifically, firstly, the gateway 20 determines multiple sampling periods during the sampling phase. For example, the sampling phase includes sampling periods. Sampling period Sampling period Sampling period And the above sampling periods ~ All include multiple initial sampling periods. For example, the sampling period. Including the first sampling period ~ Sampling period Including the first sampling period ~ Sampling period Including the first sampling period ~ Sampling period Including the first sampling period ~ .

[0133] Therefore, the gateway station 20 collects the traffic required for each satellite to forward data information to the corresponding area during each sampling period of each sampling cycle, as shown in Tables 1 to 3 above. Furthermore, the gateway station 20 can obtain the data shown in Table 4 based on the data listed in Tables 1 to 3. Table 4 shows the data for each first sampling period. ~ Inside, with various regions ~ The corresponding second dataset. For example, Indicates the first sampling period The area below The second dataset. And among them, = . Indicates the first sampling period The area below The second dataset. And among them, = And so on. Indicates the first sampling period The area below The second dataset. And among them, = .

[0134] Similarly, it can be determined that in other first sampling periods, the characteristics of each region can be determined. ~ The corresponding second dataset This will not be elaborated upon here.

[0135] Finally, the gateway station 20 compared the aforementioned second datasets. Logarithmic fitting was performed, and multiple reference curves were determined to represent the degree of satellite congestion. Where i = 1 ~ a, j = 1 ~ n. And each reference curve... The curve is a normal distribution curve. The horizontal axis of this reference curve represents the flow rate required for the satellite to forward data to the corresponding area during each first sampling period, and the vertical axis represents the probability density corresponding to the flow rate.

[0136] Thus, according to the first aspect of this embodiment, the technical effect of ensuring reliable data transmission is achieved.

[0137] 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.

[0138] Thus, according to this embodiment, the technical effect of ensuring reliable data transmission is achieved.

[0139] 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.

[0140] 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.

[0141] Example 2

[0142] Figure 5 A satellite-based routing decision-making apparatus according to this embodiment is shown, which corresponds to the method described according to Embodiment 1. (Reference) Figure 5 As shown, the device includes: a reference curve determination module 510, used to determine multiple reference curves representing the satellite congestion level under each first sampling period in the sampling phase, wherein the reference curves correspond to the data traffic of the satellite in the corresponding area under the first sampling period; an information broadcasting module 520, used to determine a first distribution curve representing the satellite congestion level under the current period, and broadcast the reference curve of the second sampling period corresponding to the current period, the first distribution curve, and the channel capacity of each area under the current period to each satellite, wherein the first distribution curve corresponds to the data traffic of the satellite in the corresponding area under the current period; and a distribution curve determination module 530, used to determine the third distribution curve corresponding to the next period. The system includes a reference curve for the sampling period, a deformation relationship between the reference curves for the second and third sampling periods, and deformation processing of each first distribution curve for the current period based on the deformation relationship to obtain multiple second distribution curves for the next period; a congestion prediction module 540, which predicts the satellite congestion level of each region in the next period based on multiple second distribution curves and the channel capacity of each region in the current period; and a routing decision determination module 550, which constructs multiple corresponding routing paths based on each region and uses a genetic algorithm to determine the optimal routing path among the multiple routing paths, where the optimal routing path represents the routing path with the minimum satellite congestion level.

[0143] Optionally, the route decision determination module 550 includes: an initialization population module for initializing chromosome vectors and constructing an initialization population, wherein the chromosome vectors represent routing paths composed of various regions; a fitness function construction module for constructing a fitness function, wherein the function value of the fitness function is related to the satellite congestion level within each routing path; a fitness function determination module for performing crossover, mutation, and iterative updates on the initialization population according to the fitness function to determine the chromosome with the highest fitness; and an optimal routing path determination module for determining the optimal routing path based on the chromosome.

[0144] Optionally, the congestion prediction module 540 includes: a prediction point determination module, used to randomly sample on the second distribution curve and determine prediction points, wherein the prediction points include the data traffic of the satellite in the corresponding area in the next time period and the corresponding probability density; and a satellite congestion prediction module, used to predict the satellite congestion level in the corresponding area in the next time period based on the data traffic of the satellite in the corresponding area in the next time period and the channel capacity of the corresponding area in the current time period.

[0145] Optionally, the information broadcasting module 520 includes: a first traffic acquisition module, used to divide the current time period into multiple sub-time periods and determine the traffic required for satellites to forward data in the corresponding area within each sub-time period; a first dataset construction module, used to construct multiple first datasets corresponding to each area in the current time period based on the traffic required for satellites to forward data in the corresponding area within each sub-time period; and a first data fitting module, used to fit each first dataset and generate a first distribution curve corresponding to each area in the current time period.

[0146] Optionally, the reference curve determination module 510 includes: a second traffic acquisition module, used to determine multiple sampling periods during the sampling phase and acquire the traffic required for satellite to forward data to the corresponding area within each first sampling period of the multiple sampling periods, wherein the sampling period includes multiple first sampling periods; a second dataset construction module, used to construct multiple second datasets corresponding to each area and each first sampling period based on the traffic under each first sampling period in the multiple sampling periods corresponding to the area; and a second data fitting module, used to fit each second dataset and generate reference curves for each area corresponding to each first sampling period.

[0147] Thus, according to this embodiment, the technical effect of ensuring reliable data transmission is achieved.

[0148] Example 3

[0149] Figure 6A satellite-based routing decision-making apparatus according to this embodiment is shown, which corresponds to the method described according to Embodiment 1. (Reference) Figure 6 As shown, the device includes: a processor 610; and a memory 620 connected to the processor 610, for providing the processor 610 with instructions to process the following steps: determining multiple reference curves representing satellite congestion levels during each first sampling period in the sampling phase, wherein the reference curves correspond to the data traffic of the satellite in the corresponding area during the first sampling period; determining a first distribution curve representing satellite congestion levels during the current period, and broadcasting the reference curve, the first distribution curve, and the channel capacity of each area during the current period to each satellite for a second sampling period corresponding to the current period, wherein the first distribution curve corresponds to the data traffic of the satellite in the corresponding area during the current period. The data traffic corresponds to the domain; the reference curve for the third sampling period corresponding to the next time period is determined, the deformation relationship between the reference curve for the second sampling period and the reference curve for the third sampling period is calculated, and the first distribution curve for the current time period is deformed based on the deformation relationship to obtain multiple second distribution curves for the next time period; based on multiple second distribution curves and according to the channel capacity of each region in the current time period, the satellite congestion level of each region in the next time period is predicted; and based on each region, multiple corresponding routing paths are constructed, and the optimal routing path among the multiple routing paths is determined using a genetic algorithm, where the optimal routing path represents the routing path with the minimum satellite congestion level.

[0150] Thus, according to this embodiment, the technical effect of ensuring reliable data transmission is achieved.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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-based routing decision-making method, characterized in that, include: Multiple reference curves are determined for each first sampling period in the sampling phase to represent the degree of satellite congestion, wherein the reference curves correspond to the traffic required for the satellite to forward data to the corresponding area during the first sampling period; A first distribution curve representing the satellite congestion level is determined for the current time period, and a reference curve for a second sampling period corresponding to the current time period, the first distribution curve, and the channel capacity of each region under the current time period are broadcast to each satellite. The first distribution curve corresponds to the traffic required for the satellite to forward data to the corresponding region under the current time period, and the second sampling period is the first sampling period corresponding to the current time period among the various first sampling periods. Determine the reference curve for the third sampling period corresponding to the next time period, calculate the deformation relationship between the reference curve of the second sampling period and the reference curve of the third sampling period, and perform deformation processing on each of the first distribution curves of the current time period based on the deformation relationship to obtain multiple second distribution curves for the next time period, wherein the third sampling period refers to the first sampling period corresponding to the next time period among the various first sampling periods; Based on the multiple second distribution curves and according to the channel capacity of each region in the current time period, the satellite congestion level of each region in the next time period is predicted; as well as Based on each region, multiple corresponding routing paths are constructed, and a genetic algorithm is used to determine the optimal routing path among the multiple routing paths, wherein the optimal routing path represents the routing path with the least satellite congestion.

2. The method according to claim 1, characterized in that, Based on each region, the operation of constructing multiple corresponding routing paths and using a genetic algorithm to determine the optimal routing path among these multiple routing paths includes: Initialize chromosome vectors and construct an initial population, wherein the chromosome vectors represent routing paths composed of the respective regions; Construct a fitness function, wherein the function value of the fitness function is related to the satellite congestion level of each routing path; Based on the fitness function, the initial population is subjected to crossover, mutation, and iterative updates to determine the chromosome with the highest fitness; and The optimal routing path is determined based on the chromosome with the highest fitness.

3. The method according to claim 1, characterized in that, The operation of predicting the satellite congestion level of each region in the next time period based on the multiple second distribution curves and the channel capacity of each region in the current time period includes: Random sampling is performed on the second distribution curve to determine prediction points, wherein the prediction points include the data transmission rate required by the satellite to relay data in the corresponding area during the next time period, and the corresponding probability density; and Based on the data transmission capacity required by the satellite in the corresponding area during the next time period and the channel capacity of the corresponding area during the current time period, the satellite congestion level in the corresponding area during the next time period is predicted.

4. The method according to claim 1, characterized in that, The operations for determining the first distribution curve representing the degree of satellite congestion in the current time period include: The current time period is divided into multiple sub-time periods, and the traffic required for the satellite to forward data in the corresponding area within each sub-time period is determined; Based on the traffic required by the satellite to forward data in the corresponding area during each sub-time period, multiple first datasets corresponding to each area in the current time period are constructed. Each of the first datasets is fitted separately, and a first distribution curve corresponding to each region in the current time period is generated.

5. The method according to claim 1, characterized in that, The operation of determining multiple reference curves representing the degree of satellite congestion during each first sampling period in the sampling phase includes: In the sampling phase, multiple sampling periods are determined, and the traffic required for the satellite to forward data to the corresponding area is collected within each first sampling period in the multiple sampling periods, wherein the sampling period includes multiple first sampling periods; Based on the traffic flow during each first sampling time period within the multiple sampling periods corresponding to the region, multiple second datasets corresponding to each region and each first sampling time period are constructed; and Each second dataset is fitted separately, and reference curves for each region corresponding to each of the first sampling periods are generated.

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-based routing decision-making device, characterized in that, include: The reference curve determination module is used to determine multiple reference curves representing the degree of satellite congestion during each first sampling period in the sampling phase, wherein the reference curves correspond to the data traffic of the satellite in the corresponding area during the first sampling period; The information broadcasting module is used to determine a first distribution curve representing the satellite congestion level in the current time period, and broadcast a reference curve of a second sampling period corresponding to the current time period, the first distribution curve, and the channel capacity of each region in the current time period to each satellite. The first distribution curve corresponds to the data traffic of the satellite in the corresponding region in the current time period, and the second sampling period is the first sampling period corresponding to the current time period in each of the first sampling periods. The distribution curve determination module is used to determine the reference curve of the third sampling period corresponding to the next time period, calculate the deformation relationship between the reference curve of the second sampling period and the reference curve of the third sampling period, and perform deformation processing on each of the first distribution curves of the current time period based on the deformation relationship to obtain multiple second distribution curves of the next time period, wherein the third sampling period refers to the first sampling period corresponding to the next time period among the various first sampling periods; The congestion prediction module is used to predict the satellite congestion level of each region in the next time period based on the multiple second distribution curves and the channel capacity of each region in the current time period. as well as The routing decision determination module is used to construct multiple corresponding routing paths based on each region, and use a genetic algorithm to determine the optimal routing path among the multiple routing paths, wherein the optimal routing path represents the routing path with the least satellite congestion.

8. The apparatus according to claim 7, characterized in that, The routing decision determination module includes: An initial population module is used to initialize chromosome vectors and construct an initial population, wherein the chromosome vectors represent routing paths composed of the various regions; The fitness function construction module is used to construct fitness functions, wherein the function value of the fitness function is related to the degree of satellite congestion in each routing path; A fitness function determination module is used to perform crossover, mutation, and iterative updates on the initial population based on the fitness function to determine the chromosome with the highest fitness; and The optimal route path determination module is used to determine the optimal route path based on the chromosome.

9. The apparatus according to claim 7, characterized in that, The congestion prediction module includes: A prediction point determination module is used to randomly sample from the second distribution curve and determine prediction points, wherein the prediction points include the data traffic of the satellite in the corresponding area during the next time period, and the corresponding probability density; and The satellite congestion prediction module is used to predict the satellite congestion level in the corresponding area in the next time period based on the data traffic of the satellite in the corresponding area in the next time period and the channel capacity of the corresponding area in the current time period.

10. A satellite-based routing decision-making 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: Multiple reference curves are determined for each first sampling period in the sampling phase to represent the degree of satellite congestion, wherein the reference curves correspond to the traffic required for the satellite to forward data to the corresponding area during the first sampling period; A first distribution curve representing the satellite congestion level is determined for the current time period, and a reference curve for a second sampling period corresponding to the current time period, the first distribution curve, and the channel capacity of each region under the current time period are broadcast to each satellite. The first distribution curve corresponds to the traffic required for the satellite to forward data to the corresponding region under the current time period, and the second sampling period is the first sampling period corresponding to the current time period among the various first sampling periods. Determine the reference curve for the third sampling period corresponding to the next time period, calculate the deformation relationship between the reference curve of the second sampling period and the reference curve of the third sampling period, and perform deformation processing on each of the first distribution curves of the current time period based on the deformation relationship to obtain multiple second distribution curves for the next time period, wherein the third sampling period refers to the first sampling period corresponding to the next time period among the various first sampling periods; Based on the multiple second distribution curves and according to the channel capacity of each region in the current time period, the satellite congestion level of each region in the next time period is predicted; and based on each region, multiple corresponding routing paths are constructed, and a genetic algorithm is used to determine the optimal routing path among the multiple routing paths, wherein the optimal routing path represents the routing path with the minimum satellite congestion level.

Images