An AI-rule fusion decision-based low-orbit satellite communication AMC optimization method

Abstract

The application relates to the technical field of wireless communication, and discloses an AMC optimization method for low-orbit satellite communication based on AI-rule fusion decision, which comprises the following steps: obtaining the measurement value of a low-orbit satellite load scheduling parameter; constructing a low-orbit satellite communication adaptive modulation and coding optimization model, and predicting an initial modulation and coding scheduling result according to the measurement value of the low-orbit satellite load scheduling parameter; generating a modulation and coding scheduling optimization result by adopting a rule-based adaptive modulation and coding optimization method; calculating a correction coefficient according to the initial modulation and coding scheduling result and the modulation and coding scheduling optimization result; and correcting the initial modulation and coding scheduling result by using the correction coefficient to obtain a final modulation and coding scheduling result. The application can dynamically and adaptively select the most suitable modulation and coding mode, and can realize the maximum system throughput as much as possible under the condition that the bit error rate is controlled in a lower range.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of wireless communication, and particularly relates to a low-orbit satellite communication AMC optimization method based on AI-rule fusion decision. BACKGROUND

[0002] Low-orbit satellite communication (LEO, Low Earth Orbit) refers to using a satellite constellation with an orbital height of 500-2000 km to provide global coverage communication services. In recent years, with the rapid development of commercial space technology (such as SpaceX Starlink, OneWeb, Telesat, etc.), low-orbit satellite communication has become an important part of 5G / 6G networks. Compared with traditional satellite communication (such as GEO / MEO) and ground communication networks, the respective characteristics are as shown in Table 1:

[0003] Table 1 Comparison of various communication technologies

[0004] Characteristics Low Earth Orbit (LEO) Geostationary Orbit (GEO) Terrestrial 5G / Fiber Latency 20-50 ms 250 ms 5-10 ms (fiber) Coverage Global (including remote areas) Wide-area fixed coverage Urban / densely populated areas Deployment cost Medium (large constellation required) High (single satellite expensive) High (base stations / fiber rollout) Vulnerability Very high (distributed constellation) Medium (single point of failure risk) Low (dependent on terrestrial infrastructure) Typical applications Global internet, emergency communications Broadcast TV, maritime communications Urban high-speed communications

[0005] Low-orbit satellite communication is expected to realize "space-air-ground-sea integration" communication through the advantages of low delay, global coverage, high spectral efficiency, etc. At present, low-orbit satellite communication is reshaping the global communication architecture by virtue of its unique orbital characteristics and technical design. In China, low-orbit satellite communication technology has been highly valued. In recent years, China has accelerated the layout in the field of low-orbit satellite communication, and gradually built a satellite Internet system that is self-controllable through policy support, the rise of commercial space and technological innovation.

[0006] Low-orbit satellite communication technology also faces many challenges in the process of development, and a suitable adaptive modulation and coding (AMC) scheme is one of them.

[0007] AMC is a core technology in wireless communication systems, which dynamically adjusts the modulation mode and coding rate to optimize the transmission performance according to the real-time channel conditions, that is, to achieve the maximum flow transmission while ensuring a low bit error rate. The core principle is simply summarized as follows: when the channel quality is good, high-order modulation and high code rate are used to achieve the purpose of maximizing throughput, and when the channel quality is poor, low-order modulation and low code rate are used to ensure transmission reliability.

[0008] A good AMC scheme can balance spectral efficiency and transmission reliability to achieve better system throughput, otherwise, a poor AMC scheme will result in a high bit error rate during information transmission or a serious reduction in spectral efficiency, ultimately making the system throughput at a very low level.

[0009] Compared with ground base stations, the channel of low-orbit satellite communication has problems such as high dynamic channel environment, long propagation delay, large-scale fading and occlusion of satellite-ground link, large Doppler frequency shift and phase noise, etc. Under the influence of these problems, the performance of the traditional AMC method for low-orbit satellite communication will be greatly reduced. The main reason is that although the transmission delay of low-orbit satellites is lower than that of stationary orbit satellites, it is still much higher than that of the ground, and the high-speed movement of the satellite will cause the channel state between the user terminal and the satellite to change rapidly. The traditional AMC relies on periodic CSI (Channel State Information) feedback and error rate-based processing. In the low-orbit satellite communication scenario, the channel quality reported by the UE arrives at the satellite payload after a large transmission delay, and the satellite channel changes faster than the feedback period, so this channel quality may have become outdated and invalid. Similarly, the historical error statistics obtained under this condition also have the problem of being outdated, and the AMC performed at the current time cannot provide accurate reference value, so that the satellite payload cannot select the MCS to adapt to the actual situation, thereby seriously affecting the throughput of the system. SUMMARY

[0010] In view of the above problems in the prior art, the present application provides an AMC optimization method for low-orbit satellite communication based on AI-rule fusion decision, so as to dynamically and adaptively select the most suitable modulation and coding mode for the low-orbit satellite payload during scheduling, and to realize the maximum system throughput as much as possible while controlling the error rate in a lower range.

[0011] In order to achieve the above-mentioned application purposes, the technical scheme adopted by the present application is as follows:

[0012] An AMC optimization method for low-orbit satellite communication based on AI-rule fusion decision, comprising the following steps:

[0013] Obtaining the measurement value of the low-orbit satellite payload scheduling parameter;

[0014] Constructing a low-orbit satellite communication adaptive modulation and coding optimization model, and predicting an initial modulation and coding scheduling result according to the measurement value of the low-orbit satellite payload scheduling parameter;

[0015] Generating a modulation and coding scheduling optimization result by using a rule-based adaptive modulation and coding optimization method, calculating a correction coefficient according to the initial modulation and coding scheduling result and the modulation and coding scheduling optimization result, and correcting the initial modulation and coding scheduling result by using the correction coefficient to obtain a final modulation and coding scheduling result.

[0016] Further, the low-orbit satellite payload scheduling parameter includes signal-to-interference noise ratio, received signal strength indication, time advance and scheduling check result.

[0017] Further, the rule-based adaptive modulation and coding optimization method is used to generate a modulation and coding scheduling optimization result, comprising:

[0018] According to the scheduling check result of the uplink and downlink in the scheduling process, it is determined whether to adjust the scheduling index parameter; if the scheduling check result is passed, the scheduling index parameter is increased according to the set step; if the scheduling check result is not passed, the scheduling index parameter is decreased according to the set target error rate.

[0019] Further, the adjustment amount calculation method of the scheduling index parameter decreased according to the set target error rate is:

[0020]

[0021] wherein, is the adjustment amount of the scheduling index parameter decreased, is the set step, is the set target error rate.

[0022] Further, when receiving a first transmission hybrid automatic repeat request feedback valid for the current modulation and coding update, adaptive modulation and coding optimization is performed.

[0023] The first transmission hybrid automatic repeat request feedback valid for the current modulation and coding update satisfies:

[0024] When the hybrid automatic repeat request feedback is incorrect, the current modulation and coding should be less than or equal to the modulation and coding currently used by the base station;

[0025] When the hybrid automatic repeat request feedback is correct, the current modulation and coding should be greater than or equal to the modulation and coding currently used by the base station;

[0026] When the current modulation and coding is equal to the modulation and coding currently used by the base station minus 1 and the current scheduling index parameter is between the index upper boundary and the index lower boundary, the hybrid automatic repeat request feedback is valid regardless of whether it is correct or not.

[0027] Further, the index upper boundary is the sum of one-half of the scheduling index parameter corresponding to the modulation and coding currently used by the base station and the scheduling index parameter corresponding to the modulation and coding currently used by the base station minus 1, and the index lower boundary is the scheduling index parameter corresponding to the modulation and coding currently used by the base station.

[0028] Further, the probability of the hybrid automatic repeat request check passing corresponding to each modulation and coding within the set scheduling times is dynamically counted, and the probability of the hybrid automatic repeat request check passing corresponding to the modulation and coding currently used by the base station and the probability of the hybrid automatic repeat request check passing corresponding to the modulation and coding currently used by the base station minus 1 are used to determine the modulation and coding ratio used when scheduling the uplink and downlink.

[0029] Further, the modulation and coding ratio calculation method used in scheduling uplink and downlink is:

[0030]

[0031] Wherein, is the scheduling ratio, is the target bit error rate set, is the modulation and coding corresponding to the scheduling index parameter used by the current base station, is the modulation and coding corresponding to the scheduling index parameter used by the current base station minus 1.

[0032] Further, the low-orbit satellite communication adaptive modulation and coding optimization model adopts a number of stacked Transformer encoder layer structures, and is mapped to different modulation and coding through a fully connected layer.

[0033] Further, the low-orbit satellite communication adaptive modulation and coding optimization model sets a time period and a data collection period during model training, performs modulation and coding scheduling within the time period, collects training data from the start time of the time period to the data collection period, and performs model training from the data collection period to the end time of the time period.

[0034] The present application has the following beneficial effects:

[0035] The present application can estimate the probability of passing the MCS scheduling check result according to the measurement quantity by establishing an AI-rule fusion decision based low-orbit satellite communication adaptive modulation and coding optimization, and at the same time establishes a rule-based MCS scheduling method, and uses the rule-based scheduling result to correct the output of AI. The model considers both the bit error rate and the spectral efficiency, and can dynamically and adaptively select the most appropriate modulation and coding mode, and in the case of controlling the bit error rate in a lower range, the maximum system throughput is realized as much as possible. BRIEF DESCRIPTION OF DRAWINGS

[0036] Figure 1 It is a low-orbit satellite communication AMC optimization method process schematic diagram based on AI-rule fusion decision;

[0037] Figure 2 It is a neural network schematic diagram;

[0038] Figure 3 It is a network update schematic diagram. DETAILED DESCRIPTION

[0039] The specific embodiments of the present application are described below to facilitate the understanding of the present application for those skilled in the art, but it should be clear that the present application is not limited to the scope of the specific embodiments, and for those skilled in the art, it is obvious that various changes are within the spirit and scope of the present application defined and determined by the appended claims, and all the inventions utilizing the concept of the present application are within the scope of protection.

[0040] As shown in Figure 1 , the low-orbit satellite communication AMC optimization method based on AI-rule fusion decision provided by the embodiment of the present application comprises the following steps S1 to S3:

[0041] S1, obtaining the measurement value of the low-orbit satellite payload scheduling parameter;

[0042] In an optional embodiment of the present application, the measurement value of the low-orbit satellite payload scheduling parameter obtained in step S1 includes the signal-to-interference-and-noise ratio, the received signal strength indication, the time advance and the scheduling verification result.

[0043] S2, constructing a low-orbit satellite communication adaptive modulation and coding optimization model, and predicting an initial modulation and coding scheduling result according to the measurement value of the low-orbit satellite payload scheduling parameter;

[0044] In an optional embodiment of the present application, the low-orbit satellite communication adaptive modulation and coding optimization model is constructed by using a neural network, the neural network adopts a number of stacked Transformer encoder layer structures, and is mapped to different modulation and coding through a full connection layer.

[0045] The neural network adopts an online training method to update the parameters. Specifically, a time period TP and a data collection time period TC (TC<TP) are set. In the first TP, a traditional MCS scheduling method is used for scheduling. At the same time, in the (0, TC) time period, training data is collected. The training data includes and the corresponding MCS scheduling verification result at different moments. In the (TC, TP) time period, the neural network is trained using the gradient descent algorithm. At this time, the initial weight of the neural network is the randomly initialized weight . After the training is completed, the weight of the neural network is . In the (TP, 2TP) time period, the MCS selection method in S1 is used for scheduling, and at the same time, in the (TP, TP+TC) time period, the training data is re-collected, and in the (TP+TC, 2TP) time period, the neural network is re-trained. At this time, the initial weight of the neural network is . In the subsequent time period, the operation of (TP, 2TP) is repeated.

[0046] The label generation method when collecting data is: in the (0, TC) time period, the MCS selected according to the traditional method index0 If the CRC check result is passed, the MCS less than or equal to MCS index0 corresponds to label 1, and the MCS greater than MCS index0 corresponds to label 0. If the CRC check result is not passed, the MCS less than MCS index0 corresponds to label 1, and the MCS greater than or equal to MCS index0 corresponds to label 0.

[0047] In the (TP, TP+TC) time period, the neural network outputs the probability of each MCS passing the CRC, and then the optimal MCS is selected according to the MCS selection method in S1 index1 , and the corresponding neural network output probability is p1. If the CRC check result is passed, the MCS in the interval [max(0.1, p1- ), 1] corresponds to label 1, and the MCS in the interval (0, max(0.1, p1- )) corresponds to label 0. If the CRC check result is not passed, the MCS in the interval [min(0.9, p1+ ), 1] corresponds to label 1, and the MCS in the interval (0, min(0.9, p1+ )) corresponds to label 0. Wherein, and are pre-set parameters.

[0048] In this embodiment, TP is set to 20 minutes, and TC is set to 10 minutes. In the first TP, the traditional MCS scheduling method is used for scheduling. At the same time, in the (0, TC) time period, training data is collected. The training data contains and the check results of different MCS scheduling at the corresponding time. In this embodiment, k is set to 5. The label generation method when collecting data is: in the (0, TC) time period, the MCS selected according to the traditional method index0 If the CRC check result is passed, the MCS less than or equal to MCS index0 corresponds to label 1, and the MCS greater than MCS index0 corresponds to label 0. If the CRC check result is not passed, the MCS less than MCS index0 corresponds to label 1, and the MCS greater than or equal to MCS index0 corresponds to label 0.

[0049] The construction is as follows Figure 2The neural network shown has M set to 2. The network's initial weights are initialized using a random method, and the gradient descent algorithm is used to update the network weights.

[0050] like Figure 3 As shown, this embodiment uses a neural network for scheduling while simultaneously collecting new training data: MCS scheduling is performed using a trained neural network and an optimized model, while new training data is collected. In the new training data, the labels are generated as follows: within the time period (TP, TP+TC), the neural network outputs the probability of each MCS passing the CRC check, and then selects the optimal MCS_index1 according to the MCS selection method, with the corresponding neural network output probability p1. If the CRC check passes, the probability is within the range [max(0.1, p1-...]. ), 1) If the label corresponding to the MCS in the interval is 1, then the probability is in the range (0, max(0.1, p1- The label corresponding to the MCS within the interval is 0. If the CRC check fails, the probability is in the range [min(0.9, p1+ ] ]. ), 1) The label corresponding to the MCS in the interval is 1, in (0, min(0.9, p1+ The label corresponding to the MCS within the interval is 0. In this embodiment, and Set it to 0.2.

[0051] S3. A rule-based adaptive modulation and coding optimization method is used to generate modulation and coding scheduling optimization results. Correction coefficients are calculated based on the initial modulation and coding scheduling results and the optimization results. The initial modulation and coding scheduling results are corrected using the correction coefficients to obtain the final modulation and coding scheduling results.

[0052] In an optional embodiment of the present invention, step S3, which uses a rule-based adaptive modulation and coding optimization method to generate modulation and coding scheduling optimization results, includes:

[0053] The scheduling index parameters are adjusted based on the scheduling verification results of uplink and downlink during the scheduling process. If the scheduling verification result passes, the scheduling index parameters are increased according to the set step size. If the scheduling verification result fails, the scheduling index parameters are decreased according to the set target bit error rate.

[0054] The calculation method for adjusting the scheduling index parameters based on the set target bit error rate is as follows:

[0055]

[0056] in, To reduce the adjustment amount of the scheduling index parameters, To set the step size, The target bit error rate is set.

[0057] This embodiment establishes a rule-based MCS scheduling process, specifically including setting the intermediate parameter cqi. state During the scheduling process, the scheduling verification results of uplink and downlink are used as a basis. Adjust cqi_state. Validation passed, cqi state Upgrade; verification failed, cqi state Adjust downwards. The values ​​for both upward and downward adjustments are based on the set target bit error rate (target). bler Settings. cqi state The adjustment step size should be less than or equal to mapcqi mcs In the table, cqi state Half of the minimum value of adjacent intervals.

[0058] In this embodiment, cqi state The adjustment step size is set to 0.15, with an upward adjustment of 0.15 and a downward adjustment of 0.15*(1-target). bler ) / target bler .

[0059] Finally, through CQI state Mapping table mapcqi with MCS mcs The table retrieves the MCS value to be used in the next scheduling iteration. mcs cqi state Mapping table mapcqi with MCS mcs The table is shown in Table 2.

[0060] Table 2cqi state Mapping table with MCS

[0061] cqi state ]]> MCS index 1 0 2 0 2.5 1 3 2 3.5 3 4 4 4.5 5 4 6 5.5 7 6 8 6.5 9 7 10 7.5 11 8 12 8.5 13 9 14 9.5 15 10 16 10.5 17 11 18 11.5 19 12 20 12.5 21 13 22 13.5 23 14 24 14.3 25 14.7 26 15 27

[0062] In an optional embodiment of the present invention, when step S3 receives a feedback of an initial hybrid automatic repeat request that is valid for the current modulation and coding update, adaptive modulation and coding optimization is performed.

[0063] The current modulation and coding scheme update is valid. The initial hybrid automatic repeat request feedback is satisfied:

[0064] When the Hybrid Automatic Repeat Request returns an error, the current modulation and coding scheme must be less than or equal to the modulation and coding scheme currently being used by the base station.

[0065] When the hybrid automatic repeat request feedback is correct, the current modulation and coding must be greater than or equal to the modulation and coding currently being used by the base station.

[0066] When the current modulation coding equals to the modulation coding currently used by the base station minus 1 and the current scheduling index parameter is between the index upper boundary and the index lower boundary, the hybrid automatic repeat request feedback is valid regardless of whether it is correct or not.

[0067] Wherein the index upper boundary is the sum of the scheduling index parameter corresponding to the modulation coding currently used by the base station and half of the scheduling index parameter corresponding to the modulation coding currently used by the base station minus 1, and the index lower boundary is the scheduling index parameter corresponding to the modulation coding currently used by the base station.

[0068] The embodiment establishes the updating mechanism of MCS scheduling. When the initial transmission hybrid automatic repeat request feedback valid for updating the current MCS is received, the CQI adjustment and the MCS updating are performed. state

[0069] The definition of the hybrid automatic repeat request feedback valid for updating the current MCS is as follows:

[0070] When the hybrid automatic repeat request feedback is incorrect, the following condition needs to be met: mcs sched mcs curr mcs ;

[0071] When the hybrid automatic repeat request feedback is correct, the following condition needs to be met: mcs sched mcs curr mcs ;

[0072] When sched mcs equals to curr mcs-1 and the current CQI state is between (mapcqi mcs table[curr mcs ] +mapcqi mcs table[curr mcs-1 ] / 2) and mapcqi mcs table[curr mcs ], the hybrid automatic repeat request feedback is valid regardless of whether it is correct or not. sched mcs is the MCS corresponding to the current hybrid automatic repeat request feedback, and curr mcs represents the MCS currently used by the base station.

[0073] In an optional embodiment of the present application, step S3 dynamically calculates the probability of passing the hybrid automatic repeat request check using each modulation coding within a set number of scheduling times, and determines the proportion of the modulation coding used in scheduling the uplink and the downlink according to the probability of passing the hybrid automatic repeat request check corresponding to the modulation coding currently used by the base station and the probability of passing the hybrid automatic repeat request check corresponding to the modulation coding currently used by the base station minus 1.

[0074] The embodiment establishes a MCS scheduling balance mechanism to prevent high error code when using certain MCS and persisting for multiple slots. The ACK rate of the harq corresponding to the last 100 times of scheduling using each MCS is dynamically counted. The proportion of the MCS used when scheduling uplink and downlink is determined according to the ACK rate of the curr mcs ACK rate and the ACK rate of the curr mcs -1 ACK rate. a is the proportion of using the current MCS.

[0075] The scheduling proportion calculation method of mcs and mcs-1 is as follows:

[0076]

[0077] Wherein, is the scheduling proportion, is the set target error code rate, is the scheduling index parameter corresponding to the modulation and coding currently used by the base station, is the scheduling index parameter corresponding to the modulation and coding-1 currently used by the base station.

[0078] In an optional embodiment of the application, step S3 finally establishes an AI-rule fusion MCS scheduling optimization model, which is expressed as:

[0079]

[0080] Wherein, represents the optimized MCS value. SINR (Signal-to-Interference-plus-Noise Ratio) represents the signal-to-interference-plus-noise ratio, RSSI (Received Signal Strength Indicator) represents the received signal strength indicator, and TA (Timing Advance) represents the timing advance, represents the scheduling check result (CRC for uplink and HARQ ACK for downlink). represents the measurement value of each parameter in the interval from t-k time to t time, represents the probability of passing the scheduling check result based on the current measurement. represents the spectrum efficiency corresponding to different MCS.

[0081] Wherein The calculation method of is as follows:

[0082]

[0083] Wherein, represents a sigmoid function, which is used to map the output of function f into the interval (0, 1) as a probability output.

[0084] represents a correction coefficient, which is used to correct the result output by AI, and the calculation formula is:

[0085]

[0086] wherein MCS represents different MCS values that can be scheduled, represents a rule-based MCS scheduling value determined through S1-S3. is a regulation factor, which is used to regulate the influence weight of AI and rules on the final result. In the embodiment, takes the value of 0.5.

[0087] The values are shown in Table 3:

[0088] Table 3 Value reference table

[0089]

[0090] The present application is described with reference to flowcharts and / or block diagrams of the method, device (system), and computer program product according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate a device that implements the flow Figure 1 one or more flows and / or blocks Figure 1 means for performing the function specified by one or more blocks.

[0091] These computer program instructions can also be stored in a computer-readable memory that can direct the computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including instruction means, which implements the flow Figure 1 one or more flows and / or blocks Figure 1 means for performing the function specified by one or more blocks.

[0092] These computer program instructions can also be loaded into a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 These computer program instructions can also be loaded into a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 These computer program instructions can also be loaded into a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks.

[0093] The principles and implementations of the present application are illustrated in the embodiments. The above description is only used to help understand the method and the core idea of the present application. For those skilled in the art, according to the idea of the present application, the specific implementation and application range can be changed. The above description should not be understood as a limitation of the present application.

[0094] Those skilled in the art will realize that the embodiments described herein are for the purpose of understanding the principles of the present application and should not be construed as limiting the scope of the present application. Those skilled in the art can make various other specific modifications and combinations according to the technical inspiration of the present application without departing from the spirit of the present application, and these modifications and combinations are still within the scope of the present application.

Claims

1. An AI-rule fusion decision-based low-orbit satellite communication AMC optimization method, characterized in that, The method comprises the following steps: Obtaining a measurement value of a low-orbit satellite payload scheduling parameter; Building a low-orbit satellite communication adaptive modulation and coding optimization model, and predicting an initial modulation and coding scheduling result according to the measurement value of the low-orbit satellite payload scheduling parameter; Generating a modulation and coding scheduling optimization result by using a rule-based adaptive modulation and coding optimization method, calculating a correction coefficient according to the initial modulation and coding scheduling result and the modulation and coding scheduling optimization result, and correcting the initial modulation and coding scheduling result by using the correction coefficient to obtain a final modulation and coding scheduling result; The rule-based adaptive modulation and coding optimization method for generating the modulation and coding scheduling optimization result comprises: Judging whether to adjust the scheduling index parameter according to the scheduling check result of the uplink and downlink in the scheduling process; if the scheduling check result is passed, increasing the scheduling index parameter according to a set step; if the scheduling check result is not passed, decreasing the scheduling index parameter according to a set target bit error rate, and the adjustment amount is calculated in the following manner: wherein, is an adjustment amount for down-adjusting the scheduling index parameter, is a set step size, is a set target bit error rate.

2. The AMC optimization method for low-orbit satellite communication based on AI-rule fusion decision according to claim 1, characterized in that, The low-orbit satellite payload scheduling parameter comprises a signal-to-interference-and-noise ratio, a received signal strength indication, a time advance and a scheduling check result.

3. The AMC optimization method for low-orbit satellite communication based on AI-rule fusion decision according to claim 1, characterized in that, When a first transmission hybrid automatic repeat request feedback valid for the current modulation and coding update is received, adaptive modulation and coding optimization is performed; The first transmission hybrid automatic repeat request feedback valid for the current modulation and coding update satisfies the following conditions: When the hybrid automatic repeat request feedback is incorrect, the current modulation and coding needs to be less than or equal to the modulation and coding currently used by the base station; When the hybrid automatic repeat request feedback is correct, the current modulation and coding needs to be greater than or equal to the modulation and coding currently used by the base station; When the current modulation and coding is equal to the modulation and coding currently used by the base station minus 1 and the current scheduling index parameter is between the index upper boundary and the index lower boundary, the hybrid automatic repeat request feedback is valid regardless of whether it is correct or not.

4. The AMC optimization method for low-orbit satellite communication based on AI-rule fusion decision according to claim 3, characterized in that, The index upper boundary is the sum of one-half of the scheduling index parameter corresponding to the modulation and coding currently used by the base station and the scheduling index parameter corresponding to the modulation and coding currently used by the base station minus 1, and the index lower boundary is the scheduling index parameter corresponding to the modulation and coding currently used by the base station.

5. The low-orbit satellite communication AMC optimization method based on AI-rule fusion decision according to claim 1, characterized in that, The probability of the hybrid automatic repeat request check passing for each modulation and coding within a set scheduling number of times is dynamically counted, and the probability of the hybrid automatic repeat request check passing for the modulation and coding currently used by the base station and the probability of the hybrid automatic repeat request check passing for the modulation and coding currently used by the base station minus 1 are used to determine the modulation and coding ratio used when scheduling the uplink and downlink.

6. The AMC optimization method for low-orbit satellite communication based on AI-rule fusion decision according to claim 5, characterized in that, The modulation and coding ratio used when scheduling the uplink and downlink is calculated in the following manner: wherein, is a scheduling ratio, is a set target bit error rate, is a scheduling index parameter corresponding to a modulation and coding pair currently used by the base station, is a scheduling index parameter corresponding to a modulation and coding pair currently used by the base station minus 1.

7. The AMC optimization method for low-orbit satellite communication based on AI-rule fusion decision according to claim 1, characterized in that, The low-orbit satellite communication adaptive modulation and coding optimization model adopts a plurality of stacked Transformer encoder layer structures, and is mapped to different modulation and coding through a fully connected layer.

8. The AMC optimization method for low-orbit satellite communication based on AI-rule fusion decision according to claim 1, characterized in that, The low-orbit satellite communication adaptive modulation and coding optimization model sets a time period and a data collection time period during model training, performs modulation and coding scheduling within the time period, collects training data from the start time of the time period to the data collection time period, and trains the model from the data collection time period to the end time of the time period.

Images