A data processing priority scheduling method for high-speed satellite communication and related equipment

Abstract

This application provides a data processing priority scheduling method and related equipment for high-speed satellite communication, which can effectively improve the transmission performance of high-speed satellite communication systems to adapt to the differentiated needs of various communication scenarios. The application includes: acquiring cross-layer state information; invoking a policy matrix, which defines the weighting coefficients of different data types under different network states and channel qualities; calculating target priority scores for the data streams to be transmitted based on the cross-layer state information and the policy matrix; sorting the target priority scores from high to low to obtain a ranking result; scheduling the transmission queues of the data streams according to the ranking result, and allocating a buffered transmission queue for data streams with high priority scores; when the priority score of a new data stream exceeds a preset emergency threshold, inserting the new data stream into the buffered transmission queue of the transmission queue, and implementing backpressure control on other priority data streams.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a data processing priority scheduling method and related equipment for high-speed satellite communication. Background Technology

[0002] With the continuous integration of aerospace and communication technologies, high-speed satellite communication, with its advantages of wide coverage, long transmission distance, and lack of geographical limitations, has been widely applied in emergency communication, aerospace, and remote area communication. However, during operation, high-speed satellite communication systems are susceptible to the transmission characteristics of satellite-to-ground links, resulting in problems such as network congestion fluctuations and unstable channel transmission quality. Furthermore, the diverse types of transmitted data streams and significant differences in service requirements place higher demands on the real-time performance and reliability of data processing and transmission.

[0003] Most existing data processing priority scheduling methods determine scheduling priorities based on only a single data type or simple network parameters. This singular scheduling mode easily leads to delays in high-priority data transmission, low-priority data occupying critical transmission resources, and in the face of sudden high-urgency data streams, it cannot respond quickly and guarantee their transmission priority, easily causing problems such as data loss and transmission interruption, thus making it difficult to meet the communication needs of various scenarios. Summary of the Invention

[0004] To address the aforementioned technical problems, this application provides a data processing priority scheduling method and related equipment for high-speed satellite communication.

[0005] The technical solution provided in this application is described below:

[0006] The first aspect of this application provides a data processing priority scheduling method for high-speed satellite communication, the method comprising:

[0007] Obtain cross-layer status information, which includes data type attributes, network congestion status, and channel transmission quality;

[0008] Call the policy matrix, which is used to define the weighting coefficients of different data types under different network states and channel quality;

[0009] Calculate the target priority score for the data stream to be transmitted based on the cross-layer state information and the policy matrix;

[0010] The target priority scores are sorted from high to low to obtain the sorting results;

[0011] The data stream is scheduled for transmission according to the sorting result, and a buffered transmission queue is allocated for the data stream with high priority score.

[0012] When the priority score of a new data stream exceeds the preset emergency threshold, the new data stream is inserted into the buffered transmission queue of the transmission queue, and backpressure control is applied to other priority data streams.

[0013] After the new data stream transmission is completed, the backpressure control of the other priority data streams is released, and data transmission proceeds normally.

[0014] Optionally, calculating a target priority score for the data stream to be transmitted based on the cross-layer state information and the policy matrix includes:

[0015] The cross-layer state information is standardized and quantized to obtain quantized standard cross-layer state information;

[0016] Based on the cross-layer state information of the quantization standard, the corresponding data type weight coefficient, network congestion state weight coefficient and channel transmission quality weight coefficient are matched in the policy matrix.

[0017] The data type weight coefficient, the network congestion state weight coefficient, and the channel transmission quality weight coefficient are weighted and summed to obtain the basic priority score of the data stream to be transmitted.

[0018] The satellite communication scenario dynamic correction factor is invoked, and the basic priority score is adjusted to obtain the target priority score.

[0019] Optionally, the transmission queues of the data streams are scheduled for transmission according to the sorting results, and buffered transmission queues are allocated for data streams with high priority scores, including:

[0020] Based on the sorting results, the basic transmission queue of the data stream is constructed, and the transmission scheduling rules of the queue are initialized in sequence.

[0021] Extract the high-priority data stream from the basic transmission queue;

[0022] A dedicated cache transmission queue is configured for the high-priority data stream, and an independent scheduling channel is established between the basic transmission queue and the cache transmission queue.

[0023] Optionally, when the priority score of a new data stream exceeds a preset emergency threshold, the new data stream is inserted into the buffered transmission queue of the transmission queue, and backpressure control is implemented on other priority data streams, including:

[0024] The priority score of the new data streams detected is compared with the preset emergency threshold in real time to obtain the comparison results;

[0025] Based on the comparison results, determine whether the new data stream is an emergency data stream;

[0026] If so, the new data stream is directly inserted into the head position of the cached transmission queue;

[0027] Obtain the resource occupancy status of the cache transmission queue, and initiate backpressure control on other priority data streams besides the emergency data stream to restrict transmission requests and cache writes of other priority data streams.

[0028] Optionally, after determining that the new data stream transmission is complete, the backpressure control of the other priority data streams is released, and data transmission proceeds normally, including:

[0029] After the new data stream transmission is completed, determine whether there is any remaining data to be transmitted in the buffer transmission queue;

[0030] If not, then the transmission and buffering restrictions on other priority data streams are lifted, and the state of the transmission queues of other priority data streams is reset and the buffered transmission queues are restored to the reserved state.

[0031] The target priority score of the data stream to be transmitted is recalculated based on the real-time cross-layer status information, and the allocation and scheduling are carried out normally.

[0032] Optionally, extracting high-priority data streams from the underlying transmission queue includes:

[0033] Obtain historical cross-layer status information;

[0034] A high-priority judgment threshold is generated based on the historical cross-layer status information, and the high-priority judgment threshold is used to define the filtering threshold for high-priority data streams;

[0035] In the basic transmission queue, data streams with priority scores not lower than the high priority determination threshold are identified as high priority data streams.

[0036] Optionally, a high-priority judgment threshold is generated based on the historical cross-layer state information, including:

[0037] The data type attributes, network congestion status, and channel transmission quality in the historical cross-layer state information are jointly analyzed to construct a comprehensive state feature vector.

[0038] The comprehensive state feature vector is input into the strategy function for calculation to output the candidate high-priority judgment threshold;

[0039] The candidate high-priority decision threshold is calibrated according to the preset optimization objective to generate the high-priority decision threshold.

[0040] A second aspect of this application provides a data processing priority scheduling apparatus for high-speed satellite communication, the apparatus comprising:

[0041] The first acquisition unit is used to acquire cross-layer status information, which includes data type attributes, network congestion status and channel transmission quality information.

[0042] The calling unit is used to call the policy matrix, which is used to define the weighting coefficients of different data types under different network states and channel quality.

[0043] The calculation unit is used to calculate the target priority score for the data stream to be transmitted based on the cross-layer state information and the policy matrix;

[0044] The second acquisition unit is used to sort the target priority scores from high to low to obtain a sorting result.

[0045] The scheduling unit is used to schedule the transmission queue of the data stream for transmission according to the sorting result, and to allocate a buffer transmission queue for the data stream with a high priority score.

[0046] An insertion unit is used to insert the new data stream into the buffered transmission queue of the transmission queue when the priority score of the new data stream is detected to exceed a preset emergency threshold, and to implement backpressure control on other priority data streams.

[0047] The release unit is used to release the back pressure control of the other priority data streams and allow normal data transmission after determining that the new data stream transmission is complete.

[0048] A third aspect of this application provides a data processing priority scheduling apparatus for high-speed satellite communication, the apparatus comprising:

[0049] Processor, memory, input / output units, and bus;

[0050] The processor is connected to the memory, the input / output unit, and the bus;

[0051] The memory stores a program, which the processor invokes to perform the method as described in the first aspect and any one of the first aspects.

[0052] A fourth aspect of this application provides a computer-readable storage medium on which a program is stored, which, when executed on a computer, performs the methods described in the first aspect and any one of the first aspects.

[0053] As can be seen from the above technical solutions, this application has the following beneficial effects:

[0054] 1. This application achieves comprehensive priority scheduling by obtaining cross-layer status information such as data type attributes, network congestion status, and channel transmission quality, and by combining the target priority score with the policy matrix. This effectively avoids priority judgment bias caused by a single scheduling parameter, ensures priority transmission of high-demand data streams, and improves the rationality of data transmission.

[0055] 2. This application allocates a dedicated buffer transmission queue for high-priority data streams, thereby reducing transmission conflicts between high-priority and low-priority data, reducing transmission latency of high-priority data, and ensuring the real-time transmission of high-priority data.

[0056] 3. This application adopts a combination of buffer insertion and backpressure control for new data streams whose priority scores exceed the preset emergency threshold, so as to achieve rapid response to sudden emergency data streams, avoid emergency data loss or transmission interruption, and at the same time, backpressure control can prevent emergency data transmission from causing excessive interference to other data streams.

[0057] 4. In this application, releasing the back pressure control after emergency data transmission is completed can effectively restore normal transmission order, thereby effectively improving the transmission performance and anti-interference capability of the high-speed satellite communication system to adapt to the differentiated needs of various communication scenarios. Attached Figure Description

[0058] To more clearly illustrate the technical solutions in this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0059] Figure 1 This is a schematic diagram of an embodiment of the data processing priority scheduling method for high-speed satellite communication according to this application;

[0060] Figure 2 This is a schematic diagram of another embodiment of the data processing priority scheduling method for high-speed satellite communication according to this application;

[0061] Figure 3 This is a schematic diagram of another embodiment of the data processing priority scheduling method for high-speed satellite communication according to this application;

[0062] Figure 4 This is a schematic diagram of another embodiment of the data processing priority scheduling method for high-speed satellite communication according to this application;

[0063] Figure 5 This is a schematic diagram of another embodiment of the data processing priority scheduling method for high-speed satellite communication according to this application;

[0064] Figure 6 This is a schematic diagram of another embodiment of the data processing priority scheduling method for high-speed satellite communication according to this application;

[0065] Figure 7 This is a schematic diagram of an embodiment of the data processing priority scheduling device for high-speed satellite communication according to this application;

[0066] Figure 8 This is a schematic diagram of another embodiment of the data processing priority scheduling device for high-speed satellite communication according to this application;

[0067] Figure 9 This is a schematic diagram illustrating the application scenario of the data processing priority scheduling device for high-speed satellite communication according to this application. Detailed Implementation

[0068] It should be noted that the data processing priority scheduling method for high-speed satellite communication provided in this embodiment of the invention does not have a specific limitation on the executing entity, and can be flexibly configured according to the deployment requirements of the actual application scenario. Specifically, the scheduling method can be executed independently by any hardware device, software module, or hardware-software combination device in the high-speed satellite communication system that has data processing, instruction execution, and queue scheduling capabilities, or it can be executed collaboratively by multiple different functional modules.

[0069] For example, the executing entity may include, but is not limited to: the scheduling controller of the satellite communication ground station, the data processing unit in the satellite payload, the communication processing module of the user terminal, or the cloud scheduling server and edge computing node deployed in the satellite communication system; whether a single device / module independently undertakes all scheduling steps, or multiple devices / modules cooperate (such as one module being responsible for obtaining cross-layer status information, and another module being responsible for priority score calculation and queue scheduling), as long as all the steps of the scheduling method described in the embodiments of the present invention can be implemented, they all fall within the scope of protection of the present invention, and the specific form, number and deployment location of the executing entity are not limited thereto.

[0070] Most existing data processing priority scheduling methods determine scheduling priorities based on only a single data type or simple network parameters. This singular scheduling mode easily leads to delays in high-priority data transmission, low-priority data occupying critical transmission resources, and in the face of sudden high-urgency data streams, it cannot respond quickly and guarantee their transmission priority, easily causing problems such as data loss and transmission interruption, thus making it difficult to meet the communication needs of various scenarios.

[0071] Based on this, this application provides a data processing priority scheduling method and related equipment for high-speed satellite communication, which can effectively improve the transmission performance of high-speed satellite communication systems to adapt to the differentiated needs of various communication scenarios.

[0072] Please see Figure 1 This application discloses a data processing priority scheduling method for high-speed satellite communication, the method comprising:

[0073] 101. Obtain cross-layer status information, which includes data type attributes, network congestion status, and channel transmission quality;

[0074] 102. Call the policy matrix, which is used to define the weighting coefficients of different data types under different network states and channel quality.

[0075] 103. Calculate the target priority score for the data stream to be transmitted based on the cross-layer state information and the policy matrix;

[0076] 104. Sort the target priority scores from high to low to obtain the sorting results;

[0077] 105. Schedule the transmission queue of the data stream according to the sorting result, and allocate a buffer transmission queue for the data stream with high priority score;

[0078] 106. When the priority score of a new data stream exceeds the preset emergency threshold, the new data stream is inserted into the buffered transmission queue of the transmission queue, and backpressure control is applied to other priority data streams.

[0079] 107. After confirming that the new data stream transmission is complete, release the backpressure control of the other priority data streams and proceed with data transmission normally.

[0080] In this embodiment, cross-layer status information is first obtained, including data type attributes, network congestion status, and channel transmission quality. After obtaining the cross-layer status information, a policy matrix is ​​invoked. The policy matrix is ​​used to define the weight coefficients of different data types under different network states and channel qualities. Then, a target priority score is calculated for the data stream to be transmitted based on the cross-layer status information and the policy matrix. The target priority scores are then ordered from high to low to obtain a sorting result. After obtaining the sorting result, the transmission queue of the data stream is scheduled for transmission according to the sorting result, and a buffer transmission queue is allocated for the data stream with high priority score. When the priority score of a new data stream exceeds a preset emergency threshold, the new data stream is inserted into the buffer transmission queue of the transmission queue, and backpressure control is implemented for other priority data streams. Finally, after the transmission of the new data stream is completed, the backpressure control of other priority data streams is released, and data transmission proceeds normally.

[0081] Specifically, in step 101, cross-layer status information is acquired. This cross-layer status information includes data type attributes, network congestion status, and channel transmission quality. The cross-layer status information is collected through the cross-layer sensing module of the satellite communication system. The data type attributes are extracted from the data packet identifier field of the data link layer. These attributes include service type identifier, service quality level requirements, data latency sensitivity coefficient, and packet loss tolerance. Specific examples include, but are not limited to, high-definition video transmission data, IoT sensor data, and voice communication data. Different data types correspond to preset basic attribute labels. For example, telemetry and control signaling data is labeled as ultra-high latency sensitivity and zero packet loss tolerance; video data is labeled as high bandwidth requirement and medium packet loss tolerance; and sensor data is labeled as low latency requirement and high packet loss tolerance.

[0082] Network congestion status is jointly obtained from the network layer's queue buffer module and the transport layer's congestion indication field. Specifically, it collects the buffer queue occupancy rate of forwarding nodes, packet queuing time, link data forwarding rate, and congestion warning indicators. When the buffer queue occupancy rate exceeds 70% or the packet queuing time exceeds a preset threshold, it is determined to be a network congestion state; otherwise, it is considered an idle or lightly loaded network state. Channel transmission quality is obtained from the physical layer's channel detection module. Specifically, it collects the signal-to-noise ratio, bit error rate, real-time channel bandwidth, and channel fading coefficient of the satellite communication link. Through normalization of the above physical layer parameters, a quantitative index characterizing channel transmission quality is obtained; the higher the index value, the better the channel transmission quality.

[0083] In step 102, the strategy matrix is ​​invoked. This strategy matrix defines the weighting coefficients for different data types under different network states and channel qualities. Specifically, the strategy matrix is ​​a three-dimensional weighting matrix pre-constructed based on the service characteristics, channel characteristics, and network transmission patterns of a high-speed satellite communication scenario. Its dimensions correspond to the data type dimension, network state dimension, and channel transmission quality dimension, respectively. The data type dimension corresponds one-to-one with the various data type attributes extracted in step 101, and each data type is assigned an independent dimension index. The network state dimension is divided into four levels: idle, lightly congested, moderately congested, and heavily congested, matching the network congestion state quantification results obtained in step 101. The channel transmission quality dimension is divided into four levels: excellent, good, medium, and poor, corresponding to the channel transmission quality quantification indicators obtained in step 101. Each element of the strategy matrix is ​​the weighting coefficient for the corresponding data type under the specified network state and channel quality. This weighting coefficient comprehensively considers the data's service quality requirements, network resource allocation efficiency, and channel transmission reliability.

[0084] For example, in cases of severe network congestion and poor channel quality, the weighting coefficients for telemetry, tracking, and command (TT&C) signaling data are set to their maximum values, while the weighting coefficients for low-priority sensor data are set to their minimum values. It should be noted that the policy matrix is ​​stored in the local storage unit of the onboard scheduling module of the satellite communication system and supports dynamic updates, allowing adjustments to the weighting coefficients based on actual changes in satellite communication services, channel environment fluctuations, and network transmission requirements. Furthermore, after cross-layer status information collection is completed, the policy matrix is ​​immediately retrieved from the local storage unit to ensure the timeliness of subsequent priority calculations. During the retrieval process, index matching is used to quickly locate the matrix region corresponding to the current cross-layer status information, improving the efficiency of policy matrix retrieval.

[0085] In step 103, after obtaining the cross-layer state information and policy matrix, the target priority score is calculated for the data stream to be transmitted based on the cross-layer state information and policy matrix. The unique target priority score of each data stream to be transmitted is obtained through quantization calculation. The specific calculation process is as follows: First, the collected cross-layer state information is dimension matched. The data type attribute is matched to the data type dimension of the policy matrix, the network congestion state is matched to the network state dimension of the policy matrix, and the channel transmission quality is matched to the channel quality dimension of the policy matrix to determine the weight coefficient in the policy matrix corresponding to each data stream to be transmitted. Next, base scores are assigned to each quantitative indicator in the cross-layer state information, including a base score for data type, a network congestion state correction score, and a channel transmission quality correction score. The base score for data type is preset based on the data's quality of service level; data that is latency-sensitive or has low packet loss tolerance receives a higher base score. The network congestion state correction score is set according to the network congestion level; the higher the network congestion level, the higher the correction score for high-priority data and the greater the deduction for low-priority data. The channel transmission quality correction score is set according to the channel quality level; the better the channel quality, the higher the correction score for high-bandwidth, high-real-time data. Finally, using the weighting coefficients matched in the policy matrix as weighting factors, the base score for data type, the network congestion state correction score, and the channel transmission quality correction score are weighted and summed to obtain the target priority score for the data stream to be transmitted.

[0086] The calculation formula is: Target priority score = Data type base score × Data type weight coefficient + Network congestion state correction score × Network congestion state weight coefficient + Channel transmission quality correction score × Channel transmission quality weight coefficient. Each weight coefficient comes from the matrix element in the policy matrix that matches the current cross-layer state information. After the calculation is completed, the target priority score is normalized and mapped to a preset numerical range.

[0087] In step 104, the target priority scores are sorted from high to low to obtain a sorting result. Specifically, the target priority scores of all data streams to be transmitted are sorted in descending order. During the sorting process, the unique identifier of each data stream is associated with its target priority score to ensure that each data stream identifier corresponds one-to-one with its corresponding score, avoiding misalignment between data streams and scores during the sorting process. If multiple data streams to be transmitted have the same target priority score, they are sorted a second time according to their arrival time, with data streams arriving earlier being sorted first. If the scores are the same and the arrival times are the same, they are sorted a third time according to the data's packet loss tolerance, with data streams having lower packet loss tolerance being sorted first. Through multi-level sorting rules, the uniqueness and rationality of the sorting result are guaranteed. The sorting result forms a priority queue of the data streams to be transmitted. The order of the data streams in this queue is the basic order for subsequent transmission scheduling. When new cross-layer status information is updated, the sorting result will be recalculated and updated to ensure the dynamic nature of the sorting.

[0088] In step 105, the transmission queues of the data streams are scheduled for transmission according to the sorting results, and buffer transmission queues are allocated to data streams with high priority scores. Specifically, the scheduling and resource allocation of the on-board transmission queues are completed based on the sorting results. First, the queue scheduling unit of the on-board scheduling module maps the data streams to be transmitted to the main transmission queue of the satellite communication system according to the sorting results. The data stream transmission order in the main transmission queue is completely consistent with the sorting results, that is, the priority data streams in the sorting results get priority transmission resources in the main transmission queue and are sent sequentially according to the transmission rate of the satellite-to-ground link. Then, a high priority score threshold is preset, and data streams with a target priority score exceeding the threshold are judged as high priority data streams. For these high priority data streams, a dedicated buffer transmission queue is allocated separately outside the main transmission queue. This buffer transmission queue is an independent queue resource in the on-board high-speed cache module. The buffer transmission queue works in parallel with the main transmission queue, and the transmission resource priority of the buffer transmission queue is higher than that of the main transmission queue. When there is competition for transmission resources between the main transmission queue and the buffer transmission queue, the buffer transmission queue is given priority in allocating resources such as channel bandwidth and forwarding time slots.

[0089] Meanwhile, a dedicated resource reservation mechanism is set up for the buffered transmission queue to ensure that even under network congestion or poor channel quality, the buffered transmission queue can still obtain a preset proportion of transmission resources, avoiding increased transmission latency or packet loss for high-priority data streams due to insufficient resources. It should be noted that both the scheduling of the transmission queue and the allocation of the buffered transmission queue are dynamic operations. When the sorting results are updated, the data streams in the main transmission queue and the buffered transmission queue will be adjusted in real time to ensure that the transmission scheduling matches the priority of the data streams. Furthermore, the number of buffered transmission queues can be dynamically increased or decreased according to the number of high-priority data streams, improving resource utilization efficiency.

[0090] In step 106, when the priority score of a new data stream exceeds a preset emergency threshold, the new data stream is inserted into the buffer transmission queue of the transmission queue, and backpressure control is implemented on other priority data streams. This is an emergency scheduling mechanism for high-speed satellite communication scenarios, adapted to the transmission needs of sudden high-priority data streams. The preset emergency threshold is higher than the high-priority score threshold set in step 105, and is only for a very small number of extremely urgent sudden data streams, such as satellite telemetry and control emergency signaling, and satellite-to-ground emergency communication data. During this process, the newly entered data streams in the transmission queue are continuously detected, the target priority score of the new data stream is calculated in real time, and it is compared with the preset emergency threshold. When the score of a new data stream exceeds the preset emergency threshold, the new data stream is inserted into the buffer transmission queue, and backpressure control is implemented on other priority data streams. When the threshold is reached, an emergency scheduling process is immediately triggered: First, the new data stream is directly inserted into the head position of the buffer transmission queue allocated for the high-priority data stream in step 105, giving it the highest transmission priority. If a data stream is already being transmitted in the buffer transmission queue, the current transmission is paused, and the emergency new data stream is transmitted first. Then, backpressure control is implemented on other priority data streams in the main transmission queue (excluding the high-priority data stream) and other data streams in the buffer transmission queue (excluding the emergency new data stream). Specific backpressure control measures include: temporarily reducing the transmission rate of other data streams, suspending the transmission of some low-priority data streams, increasing the queuing waiting time threshold for other data streams, and restricting new low-priority data streams from entering the main transmission queue. Through the above backpressure control measures, the occupation of transmission resources by other data streams can be reduced, and sufficient channel bandwidth, forwarding time slots, and other transmission resources can be reserved for the emergency new data stream, ensuring low-latency and high-reliability transmission of the emergency new data stream.

[0091] It should be noted that the backpressure control is a soft control method that only limits and pauses the transmission of other data streams, rather than completely interrupting them, in order to avoid irreversible packet loss or interruption of other data streams due to emergency scheduling.

[0092] In step 107, after confirming the completion of the new data stream transmission, the backpressure control of other priority data streams is released, and data transmission proceeds normally. The transmission confirmation frame and data packet completion flags from the satellite-to-ground link are used to determine whether the emergency new data stream has been successfully transmitted. Once it is confirmed that all data packets of the emergency new data stream have been successfully sent to the ground receiver and transmission confirmation is complete, the backpressure control release process is immediately triggered: First, the backpressure control measures on other priority data streams are gradually cancelled, restoring their normal transmission rates, queuing time thresholds, and queue entry permissions. The transmission resource allocation mechanism of the main transmission queue and the buffer transmission queue is restored to the normal state of step 105. Then, data streams whose transmission was temporarily suspended during backpressure control are rescheduled and, according to their target priority score and arrival time, are sequentially restored to their corresponding transmission queues for continued transmission. For new data streams that entered the waiting queue during backpressure control, priority calculation, sorting, and queue scheduling are performed according to the normal process of steps 101 to 105 of this method.

[0093] Therefore, it can be seen that by timely release of back pressure control and restoration of transmission status, this application ensures priority transmission of emergency new data streams while minimizing the impact of emergency scheduling on the transmission of other data streams, thus guaranteeing the overall transmission efficiency and service quality of the satellite communication system.

[0094] Please refer to Figure 2 According to some embodiments of the present invention, in step 103, calculating the target priority score for the data stream to be transmitted based on the cross-layer state information and the policy matrix may specifically include, but is not limited to, the following:

[0095] 201. Standardize and quantize the cross-layer state information to obtain quantized standard cross-layer state information;

[0096] 202. Based on the cross-layer state information of the quantization standard, match the corresponding data type weight coefficient, network congestion state weight coefficient and channel transmission quality weight coefficient in the policy matrix;

[0097] 203. The data type weight coefficient, the network congestion state weight coefficient, and the channel transmission quality weight coefficient are weighted and summed to obtain the basic priority score of the data stream to be transmitted;

[0098] 204. Call the satellite communication scenario dynamic correction factor and adjust the basic priority score to obtain the target priority score.

[0099] In this embodiment, cross-layer state information is standardized and quantized to obtain standardized cross-layer state information. Specifically, for data type attributes, qualitative and semi-quantitative information such as service type identifier, service quality level requirements, latency sensitivity coefficient, and packet loss tolerance are converted into standardized quantized values ​​within a preset range. For example, ultra-high latency sensitivity and zero packet loss tolerance measurement and control signaling data are quantized to a value of 90-100, and low latency requirements and high packet loss tolerance sensor data are quantized to a value of 10-30, with the quantized value being positively correlated with the data's service quality requirements. For network congestion status, collected parameters such as buffer queue occupancy rate, data packet queuing time, and link forwarding rate are converted into standardized quantized values ​​of 0-1 using a normalization algorithm. The closer the quantized value is to 1, the higher the degree of network congestion. To address channel transmission quality, physical layer parameters such as signal-to-noise ratio, bit error rate, real-time channel bandwidth, and channel fading coefficient are transformed into standardized quantized values ​​of 0-1 using a standardized mapping model. The closer the quantized value is to 1, the better the channel transmission quality. All cross-layer state information standardization and quantization processing adopts lightweight algorithms adapted to high-speed onboard computing, ensuring processing accuracy while controlling computational latency to meet the transmission requirements of high-speed satellite communication.

[0100] Based on the quantized standard cross-layer state information, the corresponding data type weight coefficients, network congestion state weight coefficients, and channel transmission quality weight coefficients are matched in the policy matrix. The specific matching process is as follows: First, the quantized values ​​of the data types in the quantized standard cross-layer state information obtained in step 201 are extracted, and the numerical range to which the quantized value belongs is located in the data type dimension of the policy matrix to obtain the corresponding data type weight coefficients. Then, the standardized quantized values ​​of the network congestion state are extracted, and the range corresponding to the quantized value is matched in the network state dimension of the policy matrix to obtain the network congestion state weight coefficients. Finally, the standardized quantized values ​​of the channel transmission quality are extracted, and the range matching is completed in the channel quality dimension of the policy matrix to obtain the channel transmission quality weight coefficients.

[0101] The entire matching process achieves high-speed matching through an index positioning algorithm. The on-board scheduling module can directly map the values ​​of the cross-layer state information of the quantification standard to the corresponding positions in the policy matrix without additional complex calculations, ensuring matching efficiency. Moreover, the weight coefficients corresponding to each value interval in the policy matrix are pre-optimized based on the scenario characteristics of high-speed satellite communication, which can reflect the degree of influence of each dimension of information on the data transmission priority under different states.

[0102] Then, the data type weight coefficient, network congestion state weight coefficient, and channel transmission quality weight coefficient are weighted and summed to obtain the basic priority score of the data stream to be transmitted. Based on the three types of weight coefficients matched in step 202, the basic priority score of the data stream to be transmitted is calculated by weighted summation, realizing the initial transformation from cross-layer state information to priority score.

[0103] In the specific calculation process, the standardized quantized value corresponding to the cross-layer state information obtained in step 201 is used as the weighting base, multiplied by the corresponding weight coefficient obtained by matching, and then summed. The specific calculation formula is: Basic priority score = Data type quantized value × Data type weight coefficient + Network congestion state quantized value × Network congestion state weight coefficient + Channel transmission quality quantized value × Channel transmission quality weight coefficient. This calculation method combines the adjustment effect of the weight coefficient with the actual state of the cross-layer state information, avoiding the score calculation deviation caused by a single weight coefficient. For example, when the network congestion state quantized value is close to 1, indicating severe congestion, and the matched network congestion state weight coefficient is high, it will significantly increase the impact on the basic priority score, which meets the requirement of prioritizing the scheduling of high-priority data under congestion conditions in high-speed satellite communication.

[0104] Finally, the satellite communication scenario dynamic correction factor is invoked, and the basic priority score is adjusted to obtain the target priority score. Specifically, the satellite communication scenario dynamic correction factor is a set of correction coefficients calculated in real time by the onboard scheduling module based on the real-time scenario parameters of satellite communication. It includes orbital position correction factor, link attenuation correction factor, service burst correction factor, and onboard resource occupancy correction factor, etc. Each correction factor is calculated based on the corresponding real-time scenario parameters, with a value range of 0.8-1.2. When the satellite is in a low-Earth orbit with high dynamics and the satellite-to-ground link is severely attenuated, the corresponding correction factor will be appropriately increased to improve the priority score of latency-sensitive data. When the onboard transmission resource occupancy rate is low and the service transmission is stable, the correction factor will remain at the baseline value of 1, and the basic priority score will not be significantly adjusted.

[0105] When the dynamic correction factor is invoked, the onboard scheduling module selects correction factors that match the type of data stream to be transmitted based on the current satellite communication scenario. It then adjusts the base priority score obtained in step 203 using a weighted product method. The specific calculation formula is: Target priority score = Base priority score × Core correction factor 1 × Core correction factor 2 × … × Core correction factor n. The adjusted target priority score better reflects the real-time characteristics of satellite communication scenarios, solving the problem that the original fixed calculation method could not adapt to dynamic changes in the scenario, and making the priority scheduling results more consistent with the actual transmission needs of high-speed satellite communication.

[0106] Please refer to Figure 3According to some embodiments of the present invention, in step 105, the transmission queues of the data streams are scheduled for transmission according to the sorting result, and buffered transmission queues are allocated for data streams with high priority scores. Specifically, this may include, but is not limited to, the following:

[0107] 301. Based on the sorting results, construct the basic transmission queue of the data stream, and initialize the transmission scheduling rules of the queue in sequence;

[0108] 302. Extract the data stream with high priority score from the basic transmission queue;

[0109] 303. Configure a dedicated cache transmission queue for the high-priority data stream and establish an independent scheduling channel between the basic transmission queue and the cache transmission queue.

[0110] In this embodiment, a basic transmission queue for the data stream is built according to the sorting results, and the transmission scheduling rules of the queue are initialized in sequence. Specifically, during the building process, the order of the sorting results is followed, and the priority data streams with higher sorting are arranged in the front of the basic transmission queue, while the priority data streams with lower sorting are arranged in the back of the queue. This ensures that the order of the data streams in the queue is highly matched with their priority scores. At the same time, a unique queue identifier is assigned to each data stream to bind the data stream to the queue position, thus avoiding the problems of data stream misalignment and scheduling chaos.

[0111] After the basic transmission queue is established, transmission scheduling rules corresponding to the queue sequence are simultaneously implemented. These rules are designed based on the high bandwidth and low latency transmission requirements of high-speed satellite communication, and include key aspects such as the queue's polling scheduling cycle, data packet transmission time slot allocation, and transmission resource occupancy thresholds. Furthermore, the parameters of the scheduling rules are set in a gradient according to the priority order of data streams in the queue. Specifically, for priority data streams at the front of the basic transmission queue, shorter polling scheduling cycles, more dedicated transmission time slots, and higher transmission resource occupancy thresholds are set; for priority data streams at the back of the queue, appropriate conventional scheduling parameters are set. Simultaneously, these scheduling rules are adapted to the physical layer channel transmission parameters and network layer congestion control mechanisms of the satellite communication system, ensuring that the scheduling logic of the basic transmission queue conforms to the actual satellite communication network environment. Moreover, the established basic transmission queue is a dynamically adjustable architecture, allowing for real-time updates of queue nodes based on the addition of new data streams and the completion of existing data stream transmissions.

[0112] Next, high-priority data streams are extracted from the basic transmission queue. Specifically, high-priority data stream extraction is performed based on a preset high-priority score threshold. This threshold is pre-set based on the service quality requirements of different services in high-speed satellite communication scenarios and the capacity of onboard transmission resources, and can be dynamically adjusted according to actual network congestion and channel transmission quality. For example, when the network is heavily congested and the channel quality is poor, the threshold can be appropriately increased to reduce the number of high-priority data streams extracted, ensuring efficient utilization of onboard resources. When the network is idle and the channel quality is good, the threshold can be appropriately decreased to expand the coverage of high-priority data streams and improve overall data transmission efficiency.

[0113] During the extraction process, the queue parsing unit of the onboard scheduling module verifies the target priority score of each data stream in the basic transmission queue. Data streams with scores exceeding a preset threshold are identified as high-priority data streams, and their location and extraction are completed using the unique queue identifier of the data stream. During the extraction process, the order information of this type of data stream in the basic transmission queue is retained. At the same time, an independent temporary index table is established for the extracted high-priority data streams, recording information such as their priority score, data type attributes, and original queue position. This ensures the accuracy of high-priority data stream extraction and provides complete basic data for the subsequent configuration of dedicated cache transmission queues. Furthermore, the extraction operation adopts a non-removal method, meaning that after the high-priority data streams are extracted, they remain in the basic transmission queue and are only distinguished from ordinary data streams by index tags. This avoids the architecture of the basic transmission queue from becoming chaotic due to the extraction operation and ensures the integrity of the basic transmission queue.

[0114] Finally, a dedicated cached transmission queue is configured for high-priority data streams, and an independent scheduling channel is established between the basic transmission queue and the cached transmission queue. This queue is a dedicated transmission resource independent of the basic transmission queue. During the configuration process, the node capacity and resource allocation ratio of the dedicated cached transmission queue are dynamically adjusted according to the number of high-priority data streams extracted and the data transmission bandwidth requirements to ensure that the queue capacity can match the transmission requirements of high-priority data streams. At the same time, the temporary index table of high-priority data streams established in step 302 is bound to the dedicated cached transmission queue. According to the order information in the temporary index table, the high-priority data streams are arranged sequentially in the dedicated cached transmission queue, preserving their original priority order.

[0115] After configuring the dedicated buffered transmission queue, independent scheduling channels are simultaneously established for the basic transmission queue and the buffered transmission queue. These channels are independent data forwarding links and scheduling control channels configured for the two queues within the onboard scheduling module. There is no resource contention or data interaction between the two channels, and each is equipped with its own dedicated scheduling control unit, transmission resource allocation module, and channel access interface. The scheduling channel for the buffered transmission queue is given higher transmission resource priority, enjoying priority in onboard transmission resource allocation and channel time slot occupancy. Both independent scheduling channels support direct connection to the physical layer channel transmission module, reducing intermediate data forwarding steps and lowering transmission latency. Simultaneously, a collaborative scheduling mechanism is established for the two independent scheduling channels. After the high-priority data stream in the dedicated buffered transmission queue completes transmission, the transmission resources it occupies can be dynamically allocated to the scheduling channel of the basic transmission queue through the collaborative mechanism, achieving flexible allocation and efficient utilization of transmission resources.

[0116] Please refer to Figure 4 According to some embodiments of the present invention, in step 106, when the priority score of a new data stream is detected to exceed a preset emergency threshold, the new data stream is inserted into the buffered transmission queue of the transmission queue, and backpressure control is implemented on other priority data streams. Specifically, this may include, but is not limited to, the following:

[0117] 401. The priority score of the new data streams detected is compared with the preset emergency threshold in real time to obtain the comparison results;

[0118] 402. Determine whether the new data stream is an emergency data stream based on the comparison results;

[0119] 403. If so, the new data stream is directly inserted into the head position of the buffer transmission queue;

[0120] 404. Obtain the resource occupancy status of the cache transmission queue, and initiate backpressure control on other priority data streams except the emergency data stream, in order to restrict the transmission requests and cache writes of other priority data streams.

[0121] In this embodiment, the priority score of the detected new data stream is compared with a preset emergency threshold in real time to obtain a comparison result. The result includes only two cases: "the priority score of the new data stream is higher than the preset emergency threshold" or "the priority score of the new data stream does not exceed the preset emergency threshold". This provides a direct and clear basis for the subsequent determination of emergency data streams. The entire comparison process is seamlessly connected with the priority score calculation process of the new data stream, ensuring the real-time identification of emergency data streams and adapting to the high-speed, low-latency transmission requirements of high-speed satellite communication.

[0122] Next, based on the comparison results, it is determined whether the new data stream is an emergency data stream. Specifically, the determination rule is a fixed rule preset by the system, without any additional adjustments or determination dimensions. That is, if the comparison result is "the priority score of the new data stream is higher than the preset emergency threshold", then the new data stream is directly determined to be an emergency data stream; if the comparison result is "the priority score of the new data stream does not exceed the preset emergency threshold", then the new data stream is determined to be a normal data stream, and there is no need to enter the subsequent emergency dispatch process.

[0123] Then, queue scheduling and transmission will be carried out according to the normal steps of the overall scheduling method. After the judgment is completed, the judgment result will be generated immediately and synchronized to the queue scheduling unit and resource control unit of the on-board scheduling module to ensure the continuity of emergency data flow scheduling. The judgment result will be stored in real time as the execution certificate for subsequent emergency scheduling operations to avoid scheduling misalignment or misjudgment.

[0124] The operation is triggered when the determination result is "the new data stream is an emergency data stream". This buffered transmission queue is an independent and dedicated queue with low latency and high bandwidth transmission characteristics, and its transmission resource priority is higher than that of the main transmission queue, ensuring priority transmission of high-priority data streams. The main body performing the insertion operation in this step is the queue scheduling unit of the on-board scheduling module. The insertion method is "direct head insertion", without queue queuing or sequential waiting process. Regardless of whether there are other high-priority data streams queuing or transmitting in the buffered transmission queue, the emergency data stream is placed directly at the front of the buffered transmission queue, giving it the highest transmission priority in the entire satellite communication system's transmission queue. If there is already a data stream transmitting in the buffered transmission queue, the queue scheduling unit will immediately issue a pause command to temporarily suspend the transmission of the current data stream. After the emergency data stream is inserted at the head of the queue, its transmission process will be started first. The insertion operation will update the data stream order in the buffered transmission queue in real time to ensure that the queue order matches the priority.

[0125] Next, the resource occupancy status of the cached transmission queue is obtained, and backpressure control is initiated for all priority data streams except the emergency data stream to restrict transmission requests and cache writes of other priority data streams. Specifically, the resource occupancy status of the cached transmission queue is first obtained by retrieving the current resource data of the cached transmission queue in real time, including the queue's bandwidth utilization, time slot allocation status, cache space usage, and the identifier of the currently transmitted data stream. This provides data support for setting the strength and scope of backpressure control, ensuring that backpressure control measures match the resource status and avoiding resource waste or insufficient resources for emergency data stream transmission. Then, backpressure control is initiated. The object of backpressure control is all other priority data streams except the emergency data stream, including other high-priority data streams in the cached transmission queue and all ordinary priority data streams in the main transmission queue, ensuring no control omissions.

[0126] Backpressure control operates through two aspects: "transmission request restriction" and "buffer write restriction." Regarding transmission requests, the resource control unit temporarily reduces the transmission rate request permissions of other data streams, suspends their requests for transmission time slot allocation, and restricts them from sending transmission requests to the satellite-to-ground link. Regarding buffer writes, the resource control unit reduces the buffer write space for other data streams, increases their buffer write threshold, and restricts new ordinary data streams from writing into the buffer space of the main transmission queue and the buffer transmission queue. Simultaneously, it suspends the transmission of ordinary data streams that were written but not transmitted before backpressure control. Through these backpressure control measures, the occupation of satellite communication system transmission resources by other data streams can be minimized, reserving sufficient dedicated resources such as channel bandwidth, transmission time slots, and buffer space for emergency data streams in the buffer transmission queue, ensuring that emergency data streams can complete transmission with the lowest latency and highest reliability.

[0127] Please refer to Figure 5 According to some embodiments of the present invention, in step 107, after determining that the new data stream transmission is complete, the backpressure control of the other priority data streams is released, and data transmission proceeds normally. Specifically, this may include, but is not limited to, the following:

[0128] 501. After determining that the new data stream transmission is completed, determine whether there is any remaining data to be transmitted in the buffer transmission queue;

[0129] 502. If not, then remove the transmission and buffering restrictions on other priority data streams, reset the state of the transmission queues of other priority data streams, and restore the buffered transmission queues to the reserved state.

[0130] 503. Recalculate the target priority score of the data stream to be transmitted based on the real-time cross-layer status information, and perform normal allocation and scheduling.

[0131] In this embodiment, after the new data stream transmission is completed, it is determined whether there is any remaining data to be transmitted in the buffered transmission queue. In the aforementioned steps, after all new data streams exceeding the preset emergency threshold have been transmitted using information such as transmission confirmation frames from the satellite-to-ground link and data packet transmission completion markers, the backpressure control is not released directly. Instead, the remaining data in the dedicated buffered transmission queue is checked first. Because the emergency new data stream is allocated to the head of the buffered transmission queue, there may still be other high-priority data to be transmitted in this queue, which are only suspended during emergency scheduling.

[0132] Therefore, a full scan of the data packet storage address, data frame identifier, and transmission progress marker of the buffer transmission queue is required to identify whether there is any high-priority data to be transmitted that has not been completed. At the same time, the transmission status of each remaining data is verified to distinguish between valid data that has only been suspended and data that has not yet started transmission, and to exclude invalid data that has been completed but whose identifier is still stored. This results in the determination of the remaining data to be transmitted in the buffer transmission queue. This determination serves as the basis for subsequent backpressure control release and queue status adjustment to ensure the continuity of high-priority data transmission in the buffer transmission queue and to avoid the omission of the original high-priority data transmission after emergency scheduling.

[0133] After confirming that there is no incomplete transmission of valid high-priority data in the buffered transmission queue, the backpressure control is completely lifted first. All transmission and buffering restrictions, including transmission rate limits, transmission pauses, and queue entry restrictions, implemented on other data streams in the main transmission queue and buffered transmission queue, are lifted across all dimensions. This restores the normal transmission permissions of other priority data streams, including restoring the original transmission rate thresholds, canceling queue entry restrictions for low-priority data streams, and restoring normal packet queuing time thresholds, ensuring that the transmission resource allocation for other priority data streams returns to normal rules. Next, the transmission queues of other priority data streams are reset. The queue management unit of the onboard scheduling module resets and calibrates the queuing status, transmission progress, and resource allocation flags of each priority data stream in the main transmission queue. Temporary restriction flags added during emergency scheduling for backpressure control are cleared, and normal transmission scheduling flags are regenerated for data streams whose transmission was suspended during backpressure control. Simultaneously, parameters such as queue scheduling counts and resource allocation counts are reset to ensure that the scheduling logic of the main transmission queue returns to normal priority sorting rules, preventing temporary flags from emergency scheduling from affecting subsequent normal scheduling.

[0134] Finally, the buffered transmission queue is restored to the reserved state. Since this buffered transmission queue is a resource exclusively allocated for high-priority data streams, after there is no remaining data to be transmitted and the emergency scheduling is completed, it is switched from the "emergency transmission working state" to the "reserved state". In the reserved state, the buffered transmission queue maintains a dedicated resource configuration, reserving a preset proportion of channel bandwidth, forwarding time slots and other transmission resources. The temporary flags related to emergency transmission in the queue are cleared, and it is restored to the idle reserved state consistent with the initial allocation. This is so that when a high-priority data stream or emergency data stream is received again, the queue can be directly called for transmission without the need for resource reallocation, thereby improving the scheduling efficiency of subsequent high-priority data.

[0135] Finally, the target priority score of the data streams to be transmitted is recalculated based on the real-time cross-layer status information, and allocation and scheduling are carried out normally. Specifically, firstly, real-time acquisition and updating of cross-layer status information is performed. This is because during the entire emergency scheduling process, cross-layer status information such as network congestion status and channel transmission quality in satellite communication may have undergone dynamic changes. For example, the degree of network congestion may be alleviated, and the channel transmission quality may fluctuate due to the time-varying characteristics of the satellite link. Therefore, the onboard cross-layer sensing module acquires the latest cross-layer status information in real time, including the latest data type attributes of all data streams to be transmitted, the real-time network congestion status of the onboard relay nodes, and the real-time channel transmission quality of the satellite-to-ground link, ensuring that the acquired status information is completely consistent with the actual scenario of current satellite communication. Then, based on the updated real-time cross-layer status information, the target priority score for all data streams to be transmitted is recalculated according to the calculation rules, using the strategy matrix. This includes new data streams entering the transmission queue during backpressure control and existing data streams that were temporarily suspended during emergency scheduling. All of these are recalculated according to a unified weighting coefficient calculation rule to ensure the real-time performance and accuracy of the priority scores, adapting to the dynamic scenario of satellite communication. Finally, according to the normal scheduling rules, the recalculated target priority scores are sorted from high to low. Based on the sorting results, all data streams to be transmitted are allocated and scheduled in a normal transmission queue. Data streams with high priority scores are allocated to the buffered transmission queues that have been restored to a reserved state. The remaining data streams are mapped to the main transmission queues in order of priority. The normal resource allocation mechanism is restored, including the parallel transmission rules between the buffered transmission queues and the main transmission queues, the priority allocation rules during resource contention, and the resource reservation mechanism for high-priority data streams. This allows the entire satellite communication data processing priority scheduling process to completely return to the normal dynamic scheduling logic, achieving a seamless connection between emergency scheduling and normal scheduling.

[0136] Please refer to Figure 6 According to some embodiments of the present invention, the extraction of high-priority data streams from the basic transmission queue in step 302 may specifically include, but is not limited to, the following:

[0137] 601. Obtain historical cross-layer status information;

[0138] 602. Generate a high-priority judgment threshold based on the historical cross-layer status information, wherein the high-priority judgment threshold is used to define the filtering threshold for high-priority data streams;

[0139] 603. In the basic transmission queue, data streams with priority scores not lower than the high priority determination threshold are identified as high priority data streams.

[0140] In this embodiment, historical cross-layer status information is first acquired. This acquired historical cross-layer status information is multi-dimensional status data with the same dimension and attributes as the collected real-time cross-layer status information. Specifically, it includes the data type attributes of various data streams in the satellite communication system within a historical time period, the network congestion status of the corresponding time period, and the channel transmission quality. Furthermore, the acquisition dimensions, quantization methods, and extraction rules of the historical data are consistent with the real-time cross-layer status information, ensuring data comparability and analyzability. The acquired historical cross-layer status information is full data within a preset time window. The time window can be flexibly set according to the service transmission characteristics and channel change cycle of high-speed satellite communication. It includes data from conventional scenarios with idle networks and good channel quality, as well as extreme scenarios with heavy network congestion and poor channel quality. It also includes transitional scenario data under different time periods and service loads. The data source is the historical data storage unit of the satellite communication system's on-board scheduling module.

[0141] Then, a high-priority judgment threshold is generated based on historical cross-layer status information. This threshold defines the screening threshold for high-priority data streams. Specifically, it is a dynamic high-priority judgment threshold generated based on historical cross-layer status information, combined with the service quality requirements of high-speed satellite communication and on-board transmission resources. This threshold is a quantitative judgment standard corresponding to the target priority score and is directly used as the screening threshold for high-priority data streams. The specific generation process is as follows: First, the historical cross-layer status information is classified into scenarios. Satellite communication transmission scenarios are divided according to the combination of network congestion status and channel transmission quality, and the dimensional features of the aforementioned strategy matrix are matched. Then, for each typical scenario, the target priority score of all data streams to be transmitted in that scenario within the historical time period is extracted. Correlation analysis is performed by combining the transmission effect data of each data stream to screen out the lowest target priority score of the data stream that can guarantee high service quality transmission in that scenario. This score is used as the initial threshold for that scenario.

[0142] Next, weighting coefficients are introduced to weight and fuse the initial thresholds for each typical scenario. The weighting coefficients are set according to the frequency of occurrence and business importance of each scenario in the historical period. The higher the frequency of occurrence and the more core the corresponding business, the higher the weighting coefficient. Finally, the weighted and fused thresholds are smoothed to eliminate threshold fluctuations caused by extreme scenarios and generate a dynamic high-priority judgment threshold set adapted to different transmission scenarios. The high-priority judgment threshold set is not a single fixed value, but a dynamic threshold bound to different network congestion states and channel transmission quality. It also supports real-time updates. When the time window of historical cross-layer status information is updated or a large amount of new scenario data is added, the threshold generation process will be re-executed to update the threshold set, ensuring that the thresholds match the actual transmission scenarios in real time.

[0143] The generated high-priority judgment threshold is directly used as the basis for filtering high-priority data streams and also provides a filtering standard for the allocation of cache transmission queues, replacing the original fixed threshold and solving the problem of low filtering accuracy and poor adaptability of fixed thresholds in different scenarios.

[0144] Subsequently, in the basic transmission queue, data streams with priority scores not lower than the high-priority determination threshold are identified as high-priority data streams. The basic transmission queue in this step is the total queue of data streams to be transmitted obtained after sorting the target priority scores in descending order in step 104 above. It is the basic queue for the subsequent allocation of the main transmission queue and the cache transmission queue. This step, as the execution link for high-priority data stream filtering, connects the threshold generation result with the queue resource allocation link to realize the filtering of high-priority data streams. The specific execution process is as follows: First, the onboard scheduling module matches the high-priority judgment threshold corresponding to the current network congestion state and channel transmission quality from the generated dynamic high-priority judgment threshold set based on the currently collected cross-layer status information in real time, achieving "scenario-threshold" matching. Then, it iterates through all data streams to be transmitted in the basic transmission queue, extracts the target priority score for each data stream, and compares this real-time score with the matched current scenario high-priority judgment threshold. Finally, data streams with target priority scores greater than or equal to the judgment threshold are uniformly determined as high-priority data streams, while data streams with scores lower than the threshold are ordinary-priority data streams, completing the secondary priority division of data streams in the basic transmission queue. The filtering results are directly used as the basis for the allocation of the buffer transmission queue, that is, only the high-priority data streams selected in this filtering are allocated a dedicated buffer transmission queue, ensuring the allocation and efficient utilization of the buffer transmission queue resource, and avoiding the problem of wasted buffer transmission queue resources or missed high-priority data streams under a fixed threshold.

[0145] Please refer to Figure 7 According to some embodiments of the present invention, in step 602, a high-priority determination threshold is generated based on the historical cross-layer state information, which may specifically include, but is not limited to, the following:

[0146] 701. Jointly analyze the data type attributes, network congestion status, and channel transmission quality in the historical cross-layer state information to construct a comprehensive state feature vector;

[0147] 702. Input the comprehensive state feature vector into the strategy function for calculation to output the candidate high priority judgment threshold;

[0148] 703. The candidate high-priority decision threshold is calibrated according to the preset optimization target to generate the high-priority decision threshold.

[0149] In this embodiment, the data type attributes, network congestion status, and channel transmission quality in the cross-layer state information are jointly analyzed to construct a comprehensive state feature vector. This step is based on the cross-layer state information collected in the original step 101, and completes the feature fusion and quantitative modeling of multi-dimensional state information through joint analysis. Specifically, the data type attributes, network congestion status, and channel transmission quality in the cross-layer state information are first normalized and quantized. The data type attributes are converted into quantized feature values ​​in the 0-1 range based on core indicators such as latency sensitivity coefficient, packet loss tolerance, and bandwidth requirements. The higher the latency sensitivity and the lower the packet loss tolerance, the higher the corresponding quantized feature value. The network congestion status is divided into continuous quantized values ​​in the 0-1 range based on indicators such as buffer queue occupancy rate and data packet queuing time. The higher the congestion level, the larger the corresponding quantized value. The channel transmission quality is converted into quantized feature values ​​in the 0-1 range based on parameters such as signal-to-noise ratio, bit error rate, and channel fading coefficient. The better the channel quality, the higher the corresponding quantized value.

[0150] Then, the normalized quantized feature values ​​of the above three dimensions are jointly analyzed. Combining the correlation between the influence of each state dimension on data transmission priority determination in high-speed satellite communication scenarios, feature dimension weights are assigned to the quantized feature values ​​of each dimension. These feature dimension weights are pre-set based on the transmission patterns of satellite communication services and can be dynamically fine-tuned according to actual service changes. For example, in scenarios with a high proportion of telemetry, tracking, and command (TT&C) signaling services, the feature dimension weight of data type attributes is appropriately increased; in scenarios with frequent channel fading, the feature dimension weight of channel transmission quality is appropriately increased. Finally, the weighted quantized feature values ​​of each dimension are combined in a fixed dimensional order to construct a one-dimensional comprehensive state feature vector. The dimension of this vector is consistent with the core feature dimension of the cross-layer state information. Each element in the vector uniquely corresponds to the weighted cross-layer state feature quantized value. The construction of the comprehensive state feature vector realizes the transformation of cross-layer state information from scattered dimensions to a unified feature model, providing standardized feature input for the calculation of high-priority determination thresholds.

[0151] The comprehensive state feature vector is then input into the strategy function for calculation to output the candidate high-priority judgment threshold. Specifically, this strategy function is a threshold calculation model trained based on high-speed satellite communication scenarios, consisting of a basic calculation module and a scenario correction module. The basic calculation module uses the comprehensive state feature vector as a variable and completes the calculation of the basic threshold value through a multiple linear regression algorithm. The scenario correction module dynamically corrects the basic threshold value according to the real-time service scenario characteristics of high-speed satellite communication. The scenario correction factors include the proportion of real-time service types, the utilization rate of on-board transmission resources, and the transmission requirements of the satellite-to-ground link. For example, when the utilization rate of on-board buffer transmission queue resources is low, the scenario correction factor is appropriately increased to correct the basic threshold value upwards, expanding the judgment range of high-priority data streams; when on-board transmission resources are scarce, the scenario correction factor is appropriately decreased to correct the basic threshold value downwards, narrowing the judgment range of high-priority data streams and avoiding overload of buffer transmission queue resources. In the calculation process, after the comprehensive state feature vector is input into the strategy function according to a preset format, the basic threshold value is first obtained through the basic calculation module, and then corrected by the scenario correction module in combination with the real-time scenario correction factor, finally outputting the candidate high-priority judgment threshold. Finally, the candidate high-priority decision thresholds are calibrated according to the preset optimization objectives to generate high-priority decision thresholds.

[0152] Please see Figure 8 The second aspect of this application provides a data processing priority scheduling apparatus for high-speed satellite communication, the apparatus comprising:

[0153] The first acquisition unit 801 is used to acquire cross-layer status information, which includes data type attributes, network congestion status and channel transmission quality information.

[0154] Calling unit 802 is used to call the policy matrix, which is used to define the weight coefficients of different data types under different network states and channel quality.

[0155] The calculation unit 803 is used to calculate the target priority score for the data stream to be transmitted based on the cross-layer state information and the strategy matrix;

[0156] The second acquisition unit 804 is used to sort the target priority scores from high to low to obtain a sorting result.

[0157] The scheduling unit 805 is used to schedule the transmission queue of the data stream for transmission according to the sorting result, and to allocate a buffer transmission queue for the data stream with a high priority score.

[0158] The insertion unit 806 is used to insert the new data stream into the buffered transmission queue of the transmission queue when the priority score of the new data stream is detected to exceed the preset emergency threshold, and to implement backpressure control on other priority data streams.

[0159] Release unit 807 is used to release the back pressure control of other priority data streams and perform data transmission normally after determining that the new data stream transmission is completed.

[0160] Please see Figure 9 This application also provides a data processing priority scheduling device for high-speed satellite communication, the device comprising:

[0161] Processor 901, memory 902, input / output unit 903, bus 904;

[0162] The processor 901 is connected to the memory 902, the input / output unit 903, and the bus 904;

[0163] The memory 902 stores a program, and the processor 901 calls the program to execute any of the methods described above.

[0164] This application also relates to a computer-readable storage medium on which a program is stored, which, when run on a computer, causes the computer to perform any of the methods described above.

[0165] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0166] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, 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 coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between apparatuses or units, and may be electrical, mechanical, or other forms.

[0167] 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.

[0168] Furthermore, the functional units in the various embodiments of this application 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.

[0169] 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 this application, 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 of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A data processing priority scheduling method for high-speed satellite communication, characterized in that, The method includes: Obtain cross-layer status information, which includes data type attributes, network congestion status, and channel transmission quality; Call the policy matrix, which is used to define the weighting coefficients of different data types under different network states and channel quality; Calculate the target priority score for the data stream to be transmitted based on the cross-layer state information and the policy matrix; The target priority score is calculated according to the following formula: Target priority score = Data type base score × Data type weight coefficient + Network congestion state correction score × Network congestion state weight coefficient + Channel transmission quality correction score × Channel transmission quality weight coefficient; Among them, the data type base score is preset according to the data service quality level, the network congestion state correction score is set according to the network congestion level, and the channel transmission quality correction score is set according to the channel quality level; the data type weight coefficient, network congestion state weight coefficient, and channel transmission quality weight coefficient are weight coefficients obtained by matching the policy matrix with the current cross-layer state information. Sort the target priority scores from high to low to obtain the sorting results; The data stream is scheduled for transmission according to the sorting result, and a buffered transmission queue is allocated for the data stream with high priority score. The data stream with high priority score is the data stream whose target priority score exceeds the high priority score threshold. When a new data stream is detected to have a priority score exceeding a preset emergency threshold, the new data stream is inserted into the buffer transmission queue, and backpressure control is applied to other priority data streams. The preset emergency threshold is higher than the high priority score threshold. After the new data stream transmission is completed, the backpressure control of the other priority data streams is released, and data transmission proceeds normally.

2. The data processing priority scheduling method for high-speed satellite communication according to claim 1, characterized in that, Calculate the target priority score for the data stream to be transmitted based on the cross-layer state information and the policy matrix, including: The cross-layer state information is standardized and quantized to obtain quantized standard cross-layer state information; Based on the cross-layer state information of the quantization standard, the corresponding data type weight coefficient, network congestion state weight coefficient and channel transmission quality weight coefficient are matched in the policy matrix. The data type weight coefficient, the network congestion state weight coefficient, and the channel transmission quality weight coefficient are weighted and summed to obtain the basic priority score of the data stream to be transmitted. The satellite communication scenario dynamic correction factor is invoked, and the basic priority score is adjusted to obtain the target priority score.

3. The data processing priority scheduling method for high-speed satellite communication according to claim 1, characterized in that, The data stream is scheduled for transmission according to the sorting result, and a buffered transmission queue is allocated for data streams with high priority scores, including: Based on the sorting results, the basic transmission queue of the data stream is constructed, and the transmission scheduling rules of the queue are initialized in sequence. Extract the high-priority data stream from the basic transmission queue; A dedicated cache transmission queue is configured for the high-priority data stream, and an independent scheduling channel is established between the basic transmission queue and the cache transmission queue.

4. The data processing priority scheduling method for high-speed satellite communication according to claim 1, characterized in that, When a new data stream's priority score exceeds a preset emergency threshold, the new data stream is inserted into the buffer transmission queue, and backpressure control is applied to other priority data streams, including: The priority score of the new data streams detected is compared with the preset emergency threshold in real time to obtain the comparison results; Based on the comparison results, determine whether the new data stream is an emergency data stream; If so, the new data stream is directly inserted into the head position of the cached transmission queue; Obtain the resource occupancy status of the cache transmission queue, and initiate backpressure control on other priority data streams besides the emergency data stream to restrict transmission requests and cache writes of other priority data streams.

5. The data processing priority scheduling method for high-speed satellite communication according to claim 1, characterized in that, After confirming the completion of the new data stream transmission, release the backpressure control of the other priority data streams and proceed with normal data transmission, including: After the new data stream transmission is completed, determine whether there is any remaining data to be transmitted in the buffer transmission queue; If not, then the transmission and buffering restrictions on other priority data streams are lifted, and the state of the transmission queues of other priority data streams is reset and the buffered transmission queues are restored to the reserved state. The target priority score of the data stream to be transmitted is recalculated based on the real-time cross-layer status information, and the allocation and scheduling are carried out normally.

6. The data processing priority scheduling method for high-speed satellite communication according to claim 3, characterized in that, Extracting high-priority data streams from the underlying transmission queue includes: Obtain historical cross-layer status information; A high-priority score threshold is generated based on the historical cross-layer status information. The high-priority score threshold is used to define the filtering threshold for high-priority data streams. In the basic transmission queue, data streams whose target priority score exceeds the high priority score threshold are identified as high priority data streams.

7. The data processing priority scheduling method for high-speed satellite communication according to claim 6, characterized in that, Generate high-priority score thresholds based on the historical cross-layer state information, including: The data type attributes, network congestion status, and channel transmission quality in the historical cross-layer state information are jointly analyzed to construct a comprehensive state feature vector. The comprehensive state feature vector is input into the policy function for calculation to output the candidate high-priority score threshold; The candidate high-priority score thresholds are calibrated according to the preset optimization objective to generate the high-priority score thresholds.

8. A data processing priority scheduling device for high-speed satellite communication, characterized in that, The device includes: The first acquisition unit is used to acquire cross-layer status information, which includes data type attributes, network congestion status and channel transmission quality information. The calling unit is used to call the policy matrix, which is used to define the weighting coefficients of different data types under different network states and channel quality. The calculation unit is used to calculate the target priority score for the data stream to be transmitted based on the cross-layer state information and the policy matrix; The target priority score is calculated according to the following formula: Target priority score = Data type base score × Data type weight coefficient + Network congestion state correction score × Network congestion state weight coefficient + Channel transmission quality correction score × Channel transmission quality weight coefficient; Among them, the data type base score is preset according to the data service quality level, the network congestion state correction score is set according to the network congestion level, and the channel transmission quality correction score is set according to the channel quality level; the data type weight coefficient, network congestion state weight coefficient, and channel transmission quality weight coefficient are weight coefficients obtained by matching the policy matrix with the current cross-layer state information. The second acquisition unit is used to sort the target priority scores from high to low to obtain the sorting results; The scheduling unit is used to schedule the transmission queue of the data stream for transmission according to the sorting result, and to allocate a buffer transmission queue for the data stream with a high priority score, wherein the high priority data stream is the data stream whose target priority score exceeds the high priority score threshold; An insertion unit is used to insert the new data stream into the buffer transmission queue when the priority score of the new data stream exceeds a preset emergency threshold, and to implement backpressure control on other priority data streams. The preset emergency threshold is higher than the high priority score threshold. The release unit is used to release the back pressure control of the other priority data streams and allow normal data transmission after determining that the new data stream transmission is complete.

9. A data processing priority scheduling device for high-speed satellite communication, characterized in that, The device includes: Processor, memory, input / output units, and bus; The processor is connected to the memory, the input / output unit, and the bus; The memory stores a program, which the processor invokes to perform the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium contains a program that, when executed on a computer, performs the method as described in any one of claims 1 to 7.

Images