Inter-satellite multipoint transmission and link dynamic optimization method based on Bayesian situation awareness

Abstract

The invention relates to the technical field of link transmission optimization, in particular to an inter-satellite multipoint transmission and link dynamic optimization method based on Bayesian situation awareness. Comprising the following steps: accessing an interstellar communication network interface, collecting real-time link data including power, frequency and signal-to-noise ratio, recording the data transmission rate and delay of each link and the data packet loss rate, and generating real-time link state information. According to the method, the link state is monitored in real time, performance prediction is carried out through Bayesian statistics, potential delay and abnormity are effectively predicted, the transmission path is optimized through the Di jkstra algorithm, the method adapts to the constantly changing environment of interstellar communication, the transmission efficiency of data under the extreme condition is ensured, and the method has the advantages of being high in practicability and the like. The dynamic routing adjustment strategy is updated according to the real-time network load, the maximum efficiency of data transmission is ensured, the automatic network topology reconstruction further strengthens the self-healing capability of the system, and the shutdown time and potential performance degradation of the system are reduced through quick response.

Description

Technical Field

[0001] The present invention relates to the technical field of link transmission optimization, and in particular to an inter-satellite multi-point transmission and link dynamic optimization method based on Bayesian situational awareness. Background Art

[0002] The field of link transmission optimization technology involves improving and enhancing the transmission efficiency and reliability of data packets in data communication networks. The core goal is to reduce latency, improve bandwidth utilization, and ensure stable and secure data transmission in the network through the optimization of algorithms and strategies. Link optimization strategies may include dynamic routing algorithms, load balancing technology, error correction mechanisms, and real-time monitoring and adaptive adjustment of link status. They are widely used in wired and wireless communication networks, especially in high-demand environments such as satellite communications and interplanetary networks, where link transmission optimization is particularly critical.

[0003] Among them, intersatellite multi-point transmission and link dynamic optimization method is a technical topic specifically for link optimization in interstellar or satellite communication systems. Its main purpose is to achieve efficient and reliable data transmission in an interstellar environment. By dynamically adjusting link parameters and routing strategies to adapt to the high variability and extreme conditions in interstellar communications, it can greatly improve the data transmission capacity of the interstellar network, optimize resource allocation, reduce signal attenuation, and enhance the performance and stability of the entire communication system. In addition, it also helps to support data communications between the earth and other celestial bodies, providing key technical support for deep space exploration missions.

[0004] The shortcomings of existing technologies are mainly reflected in their poor adaptability to dynamic environments, especially in high-demand and rapidly changing scenarios such as interstellar communications. Static routing strategies and fixed link parameters often lead to poor connection stability and low data transmission efficiency when faced with extreme conditions. In addition, existing error correction and load balancing technologies perform poorly in complex environments, fail to effectively handle link failures or network congestion, and often lead to signal attenuation and data loss. For example, in the absence of a dynamic adaptation mechanism, signal attenuation and delay problems in satellite communications may lead to increased packet loss rates, directly affecting the accuracy of data reception, and further affecting the execution of deep space exploration missions and the quality of data analysis, resulting in an inability to effectively respond to rapidly changing external conditions and internal load changes. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings existing in the prior art and to propose an inter-satellite multi-point transmission and link dynamic optimization method based on Bayesian situational awareness.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] The method for dynamic optimization of inter-satellite multi-point transmission and links based on Bayesian situational awareness includes the following steps:

[0008] S1: Access the interstellar communication network interface, collect real-time link data, including power, frequency, and signal-to-noise ratio. At the same time, record the data transmission rate, latency, and packet loss rate of each link, and generate real-time link status information.

[0009] S2: Based on the real-time link status information, perform Bayesian statistical analysis processing, evaluate the link performance, calculate the potential latency within a future period of time, compare it with the benchmark data, identify anomalies, and predict the link performance to obtain the link performance prediction result.

[0010] S3: Based on the link performance prediction result, perform path calculation, search for the transmission path with the lowest cost in the network diagram, adjust the path weights according to the current network load, select the optimal transmission line, and update the Bayesian model parameters to generate a Bayesian model with optimized parameters.

[0011] S4: Based on the Bayesian model with optimized parameters, perform dynamic routing adjustment, allocate data to the optimal transmission line, update the routing table, and monitor the transmission effect in real time to confirm that the data is transmitted according to the optimal transmission line to obtain the dynamic adjustment result of data flow.

[0012] S5: According to the dynamic adjustment result of data flow, re-collect the link performance data, compare the performance differences before and after the adjustment, use the Bayesian model with optimized parameters to re-evaluate the link status, detect the effectiveness of the adjustment operation, and obtain the re-evaluation result of link performance.

[0013] S6: According to the re-evaluation result of link performance, detect any potential link failures and performance degradations, automatically trigger network topology reconstruction, avoid problem areas by activating backup links and reconfiguring the network, and synchronously update the network status monitoring information to generate the self-healing network architecture adjustment result.

[0014] Optionally, the real-time link status information includes link power metrics, signal frequency data, and signal-to-noise ratio levels; the link performance prediction result includes the estimated latency record and performance anomaly indication; the Bayesian model with optimized parameters includes the updated model parameters and the calculated optimal transmission line; the dynamic adjustment result of data flow includes the updated routing configuration, the amount of data allocated to the optimal path, and the monitored transmission efficiency; the re-evaluation result of link performance includes the performance comparison record before and after the adjustment, the adjustment effect verification result, and the re-evaluated performance metrics; the self-healing network architecture adjustment result includes the activated backup links, the reconfigured network structure, and the updated monitoring status record.

[0015] Optionally, access the interstellar communication network interface to collect real-time link data, including power, frequency, and signal-to-noise ratio, while recording the data transmission rate, latency, and packet loss rate of each link, and the specific steps for generating real-time link status information are as follows:

[0016] S101: Access the interstellar communication network interface, capture the data streams of power, frequency, and signal-to-noise ratio in real time, parse the signal parameters, and generate real-time link monitoring data;

[0017] S102: Based on the real-time link monitoring data, calculate the data transmission rate of each link, monitor the data latency situation, and count the packet loss events to obtain link performance evaluation data;

[0018] S103: Based on the link performance evaluation data, integrate the status data of all links, reveal the dynamic changes in the transmission rate, latency, and packet loss rate, and generate real-time link status information.

[0019] Optionally, based on the real-time link status information, perform Bayesian statistical analysis processing, evaluate the link performance, calculate the potential latency time within a future period, compare it with the benchmark data, identify anomalies, and predict the link performance. The specific steps for obtaining the link performance prediction result are as follows:

[0020] S201: Based on the real-time link status information, collect the data of the transmission rate, latency, and packet loss rate of the current link, organize the data, calculate the average value and standard deviation, and generate link performance baseline data;

[0021] S202: Based on the link performance baseline data, perform trend analysis, predict the future latency time, compare the current data with the benchmark performance data, and determine the increasing or decreasing trend of the latency to obtain the future latency prediction analysis result;

[0022] S203: Use the future latency prediction analysis result to identify the link performance that does not match the prediction model, mark the potential performance degradation and anomalies, and predict the future performance of the link to generate the link performance prediction result.

[0023] Optionally, based on the link performance prediction result, perform path calculation, search for the transmission path with the lowest cost in the network diagram, adjust the path weight according to the current network load, select the optimal transmission line, and update the Bayesian model parameters to generate the Bayesian model with optimized parameters. The specific steps are as follows:

[0024] S301: Based on the link performance prediction result, analyze the prediction data of all links in the network diagram, monitor the latency and packet loss rate of the links in real time, and dynamically calculate the adjusted path weight to generate path weight data;

[0025] S302: Using the path weight data, identify the transmission path with the lowest cost in the network diagram. Meanwhile, in combination with the changes in the real-time network load, determine the optimal path that matches the current network state to obtain the optimal transmission line selection result;

[0026] S303: According to the optimal transmission line selection result, update the Bayesian model parameters. Based on the latest link performance data and path selection result, adjust the model prediction algorithm to generate a Bayesian model with optimized parameters.

[0027] Optionally, the adjusted path weight is calculated according to the formula:

[0028]

[0029] where W new represents the new weight, W old represents the original path weight, which affects the current transmission efficiency of the network; d represents the average delay time of the link, which is a direct indicator reflecting the network transmission efficiency; p represents the packet loss rate of the link, which directly reflects the reliability of the network; W avg represents the average weight of all links, which is used to compare the deviation between the weights of each link and the network average level.

[0030] Optionally, based on the Bayesian model with optimized parameters, perform dynamic routing adjustment, allocate data to the optimal transmission line, and update the routing table. The specific steps for real-time monitoring of the transmission effect and confirming that the data is transmitted according to the optimal transmission line to obtain the dynamic adjustment result of the data flow are as follows:

[0031] S401: Based on the Bayesian model with optimized parameters, allocate data according to the optimal transmission line, adjust the data flow to match the new line configuration, and synchronously check the balance of the data flow to generate a data allocation strategy;

[0032] S402: Adopt the data allocation strategy to implement data flow redirection, update the routing table to match the optimal transmission line, and ensure that all data packets are transmitted according to the optimal transmission line to obtain the updated routing table information;

[0033] S403: Through the updated routing table information, continuously monitor the transmission status of the data on the optimal transmission line, verify the efficiency and correctness of the data according to the predetermined path, and generate the dynamic adjustment result of the data flow.

[0034] Optionally, according to the dynamic adjustment result of the data flow, re-collect the link performance data, compare the performance differences before and after the adjustment, use the Bayesian model with optimized parameters to re-evaluate the link state, and detect the effectiveness of the adjustment operation. The specific steps for obtaining the re-evaluation result of the link performance are as follows:

[0035] S501: According to the result of dynamically adjusting the data flow, re-collect the current transmission rate, delay time, and packet loss rate data of all links, record and organize the performance metrics, and generate a snapshot of the link performance data;

[0036] S502: Utilize the snapshot of the link performance data to analyze the link performance differences before and after the adjustment measures. By comparing the new and old data sets, calculate the performance deviation value, determine the actual areas of performance improvement and decline, and obtain the performance comparison and analysis result;

[0037] S503: Based on the performance comparison and analysis result, use the Bayesian model with optimized parameters to deeply evaluate the link status, check the performance performance of each link after adjustment, confirm the effectiveness of the adjustment operation, and obtain the link performance re-evaluation result.

[0038] Optionally, the performance deviation value is calculated according to the formula:

[0039]

[0040] where ΔP represents the performance deviation value, y i represents the actual performance value of the i-th data point, represents the predicted performance value of the i-th data point, N represents the total number of data points, and d i represents the link delay of the i-th data point.

[0041] Optionally, according to the link performance re-evaluation result, detect any potential link failures and performance degradations, automatically trigger network topology reconstruction, avoid problem areas by activating backup links and reconfiguring the network, and synchronously update the status monitoring information of the network. The specific steps for generating the self-healing network architecture adjustment result are as follows:

[0042] S601: Based on the link performance re-evaluation result, analyze each link in the network one by one, identify the links showing performance degradation and fault signs, record the actual performance metrics and fault types of the relevant links, and generate a list of faulty links;

[0043] S602: Utilize the list of faulty links to activate the pre-set backup links in the network, adjust the network configuration, and avoid the identified problem areas to obtain a network topology reconstruction plan;

[0044] S603: According to the network topology reconstruction plan, synchronously update the status monitoring information of the network, check all monitoring nodes, correctly reflect the new network structure and traffic paths, and generate the self-healing network architecture adjustment result.

[0045] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0046] In the present invention, by monitoring the link status in real time and using Bayesian statistics for performance prediction, potential delays and anomalies are effectively predicted. By applying the Dijkstra algorithm to optimize the transmission path, it adapts to the ever-changing environment of interstellar communication, ensuring the transmission efficiency of data under extreme conditions. The dynamic routing adjustment strategy is updated according to the real-time network load to ensure the maximum efficiency of data transmission. The automated network topology reconstruction further enhances the self-healing ability of the system, reducing the system downtime and potential performance degradation through rapid response. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a schematic diagram of the step flow of the present invention;

[0048] Figure 2 It is a flowchart of step S1 of the present invention;

[0049] Figure 3 It is a flowchart of step S2 of the present invention;

[0050] Figure 4 It is a flowchart of step S3 of the present invention;

[0051] Figure 5 It is a flowchart of step S4 of the present invention;

[0052] Figure 6 It is a flowchart of step S5 of the present invention;

[0053] Figure 7 It is a flowchart of step S6 of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0054] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0055] In the description of the present invention, it should be understood that the orientation or positional relationships indicated by the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. are based on the orientation or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as limiting the present invention. In addition, in the description of the present invention, "a plurality of" means two or more unless otherwise specifically defined.

[0056] Please refer to Figure 1As shown in the figure, an inter-satellite multi-point transmission and link dynamic optimization method based on Bayesian situation awareness provided by an embodiment of the present invention includes the following steps:

[0057] S1: Access the interstellar communication network interface, collect real-time link data, including power, frequency, and signal-to-noise ratio, and at the same time record the data transmission rate, delay, and packet loss rate of each link to generate real-time link status information;

[0058] S2: Based on the real-time link status information, perform Bayesian statistical analysis and processing, evaluate the performance of the link, calculate the potential delay time within a future period of time, compare it with the reference data, identify anomalies and predict the link performance to obtain the link performance prediction result;

[0059] S3: Based on the link performance prediction result, perform path calculation, search for the transmission path with the lowest cost in the network diagram, adjust the path weight according to the current network load, select the optimal transmission line, and update the Bayesian model parameters to generate a Bayesian model with optimized parameters;

[0060] S4: Based on the Bayesian model with optimized parameters, perform dynamic routing adjustment, allocate data to the optimal transmission line, update the routing table, and monitor the transmission effect in real time to confirm that the data is transmitted according to the optimal transmission line to obtain the data flow dynamic adjustment result;

[0061] S5: According to the data flow dynamic adjustment result, re-collect the link performance data, compare the performance differences before and after the adjustment, use the Bayesian model with optimized parameters to re-evaluate the link status, detect the effectiveness of the adjustment operation, and obtain the link performance re-evaluation result;

[0062] S6: According to the link performance re-evaluation result, detect any potential link failures and performance degradations, automatically trigger network topology reconstruction, avoid problem areas by activating backup links and reconfiguring the network, and synchronously update the network status monitoring information to generate a self-healing network architecture adjustment result.

[0063] The real-time link status information includes link power indicators, signal frequency data, and signal-to-noise ratio levels; the link performance prediction result includes the estimated delay time record and performance anomaly indication; the Bayesian model with optimized parameters includes the updated model parameters and the calculated optimal transmission line; the data flow dynamic adjustment result includes the updated routing configuration, the amount of data allocated to the optimal path, and the monitored transmission efficiency; the link performance re-evaluation result includes the performance comparison record before and after the adjustment, the adjustment effect verification result, and the re-evaluated performance indicators; the self-healing network architecture adjustment result includes the activated backup link, the reconfigured network structure, and the updated monitoring status record.

[0064] Please refer to Figure 2As shown, the specific steps of S1 are as follows:

[0065] S101: Access the interstellar communication network interface, capture the data streams of power, frequency, and signal-to-noise ratio in real time, analyze the signal parameters, and generate real-time link monitoring data;

[0066] In the interstellar communication network interface, capturing the data streams of power, frequency, and signal-to-noise ratio in real time involves multiple technical details. First, the capture of power and frequency depends on precisely calibrated sensors. The sensors are installed on the communication device and can continuously monitor and record the intensity and periodic changes of the incoming electrical signals. The output data of the sensors is sent to a data processing unit, which includes a preprocessing stage where the signals are preliminarily amplified and filtered to remove environmental noise and non-signal interference. Next, the enhanced signals are sent to a signal decoder. The decoder analyzes the format and structure of the signals according to the preset communication protocol, extracts the specific values of power, frequency, and signal-to-noise ratio, and thus generates real-time link monitoring data, providing a basis for the comprehensive evaluation and management of the network status.

[0067] S102: Based on the real-time link monitoring data, calculate the data transmission rate of each link, monitor the data delay situation, and count the data packet loss events to obtain the link performance evaluation data;

[0068] In the above content, based on the real-time link monitoring data, according to the formula:

[0069]

[0070] Calculate the data transmission rate of each link. In the formula, R represents the data transmission rate, V represents the data volume, M represents the data packet loss rate, and T represents the transmission time. Considering that the data transmission rate R is calculated based on the link monitoring data obtained through real-time monitoring, where the data volume V can be statistically counted in real time by the monitoring system, and the data packet loss rate M is also calculated from the real-time data. Suppose a certain link transmits 100 MB of data within a certain period of time, the data packet loss rate is 5%, that is, 0.05, and the transmission time is 10 seconds. Then the calculation process of the data transmission rate is as follows:

[0071]

[0072] The calculation results show the transmission efficiency and quality of the link under the current conditions.

[0073] S103: Based on the link performance evaluation data, integrate the status data of all links, reveal the dynamic changes of the transmission rate, delay, and data packet loss rate, and generate real-time link status information;

[0074] When integrating all link states using link performance evaluation data, the process involves multiple key steps. First is data integration, where performance data from each link, such as metrics like transmission rate, latency, and packet loss rate, are collected into the central processing unit. The data is obtained through advanced data collection techniques, involving data synchronization and timestamp alignment to ensure data consistency. After that, statistical analysis is performed on the collected data to reveal the dynamic change trends. Based on this, data visualization tools, such as dynamic charts and real-time updated dashboards, are used to visually display the changes to network administrators, enabling them to intuitively understand the health status and performance fluctuations of each link in the network, and comprehensively form real-time link state information, providing a scientific basis for adjusting and optimizing network configurations.

[0075] Please refer to Figure 3 as shown, the specific steps of SS2 are as follows:

[0076] S201: Based on the real-time link state information, collect the transmission rate, latency, and packet loss rate data of the current link, organize the data, calculate the average value and standard deviation, and generate link performance baseline data;

[0077] During the real-time link state monitoring process, first collect real-time data on the transmission rate, latency, and packet loss rate of the link through network monitoring, capture the transmission data of the link every second, and record this data for subsequent processing. Next, organize and analyze the collected data. The specific operations include calculating the values of each data point, such as the transmission rate and latency, and statistically calculating the average value and standard deviation of these data points. The generation of the performance baseline is formed by comparing the average latency and standard deviation of several consecutive time windows, aiming to provide a reference to quickly identify data that does not conform to the normal performance pattern in future monitoring.

[0078] S202: Based on the link performance baseline data, conduct trend analysis, predict the future latency time, compare the current data with the baseline performance data, determine the increasing or decreasing trend of latency, and obtain the future latency prediction analysis result;

[0079] Based on the baseline data of link performance, perform trend analysis of the latency time. First, conduct historical trend analysis on the collected latency data, including using methods such as moving average and exponential smoothing to smooth the historical data to eliminate the influence of short-term fluctuations. Through processing, the smoothed data is obtained, providing a basis for predicting future latency. After that, compare these data with the previously established baseline performance data, and use regression analysis to determine the increasing or decreasing trend of latency. The analysis result will help predict the possible latency performance of the link in the future for a period of time, so that network managers can make preparations in advance.

[0080] S203: Use the future latency prediction analysis results to identify link performances that do not match the prediction model, identify potential performance degradation and anomalies, and predict the future performance of the link to generate link performance prediction results;

[0081] Use the future latency prediction analysis results to identify and mark link performance that does not match the prediction model. The process first requires in-depth analysis of the prediction results to identify which latency metrics exceed the normal prediction range. This is achieved by setting thresholds. For example, when the actual latency exceeds 10% of the predicted latency, the system will automatically mark this performance as abnormal. Then, analyze the possible reasons behind these abnormal data, such as network congestion or hardware failures, and their potential impact on future link performance. Finally, integrate the analysis into a link performance prediction report, which includes not only the current performance status but also predicts the possible future performance trends, providing decision-making support for network operation and maintenance.

[0082] Please refer to Figure 4 as shown, the specific steps of S S3 are as follows:

[0083] S301: Based on the link performance prediction results, analyze the prediction data of all links in the network diagram, monitor the latency and packet loss rate of the links in real time, dynamically calculate the adjusted path weights, and generate path weight data;

[0084] The adjusted path weights are calculated according to the formula:

[0085]

[0086] is calculated, where W new represents the new weight, W old represents the original path weight, which affects the current transmission efficiency of the network; d represents the average latency time of the link, which is a direct indicator reflecting the network transmission efficiency; p represents the packet loss rate of the link, which directly reflects the reliability of the network; W avg represents the average weight of all links, which is used to compare the deviation of each link weight from the network average level.

[0087] W old represents the weight of the original path, assumed to be obtained by averaging network historical data, such as the average value of the link weight over a period of time.

[0088] d is the average latency of the link, which can be measured in real time through the network monitoring system, such as the average latency in the past hour.

[0089] p is the packet loss rate of the link. Similarly, this is also measured in real time through the network monitoring system, such as the packet loss rate in the past hour.

[0090] W avgis the average weight of all links, calculated as the average of the weights of all links in the network.

[0091] Obtain the following data: W old = 5, d = 0.3 seconds, p = 0.02 (i.e., 2% packet loss rate), W avg = 4.

[0092] Substitute the values into the formula to calculate W new :

[0093] Calculate

[0094] First, calculate:

[0095]

[0096] Then, calculate:

[0097]

[0098] Obtain:

[0099] e -0.159 ≈0.853

[0100] Calculate the product:

[0101]

[0102] Calculate the denominator:

[0103] 1 + |W old - W avg | = 1 + |5 - 4| = 2

[0104] Finally, calculate:

[0105]

[0106] The results show that the newly calculated link weight is 2.1325, which is significantly lower than the previous weight of 5, reflecting the actual change in link performance, especially considering the latency and packet loss rate. The decrease in weight means that the performance of this link has declined, and it is necessary to consider avoiding or reducing the use of this path to optimize network performance.

[0107] S302: Use the path weight data to identify the lowest-cost transmission path in the network diagram, and at the same time, in combination with the changes in real-time network load, determine the optimal path that matches the current network state to obtain the optimal transmission line selection result;

[0108] Using the newly generated path weight data, identify the transmission path with the lowest cost in the network diagram. The process is achieved through a series of complex algorithm calculations. First, according to the weight data collected from each link, use the shortest path algorithm in graph theory, such as Dijkstra's algorithm, to analyze and compare the total weights of different paths to determine the cost-effectiveness of each path. Next, combine the changes in real-time network load for path selection. This step includes monitoring the traffic distribution and change trends in the network to ensure that the selected path can still maintain optimal performance under high-load conditions. Through comprehensive analysis, finally determine the optimal path that best matches the current network state, not only improving the efficiency of data transmission and reducing the risk of network congestion and latency.

[0109] S303: According to the optimal transmission line selection result, update the Bayesian model parameters. According to the latest link performance data and path selection result, adjust the model prediction algorithm to generate a Bayesian model with optimized parameters;

[0110] According to the result of the optimal transmission line selection, update the Bayesian model parameters for network performance prediction. The update process first involves collecting the latest link performance data and path selection result, and then using the data to adjust the parameters of the Bayesian model. In this process, statistical methods are used to estimate the probability distribution of each parameter, such as the average delay and packet loss rate of the link, and then the estimated values are applied to the Bayesian model to optimize the prediction accuracy of the model. Not only consider historical data, but also add new performance data to ensure that the model can more accurately predict the future performance of the network. The optimized Bayesian model is more sensitive and accurate, used to dynamically adjust network policies and improve the overall performance of the network.

[0111] Please refer to Figure 5 as shown, the specific steps of SS4 are as follows:

[0112] S401: Based on the Bayesian model with optimized parameters, perform data allocation according to the optimal transmission line, adjust the data flow to match the new line configuration, and synchronously check the balance of data traffic to generate a data allocation strategy;

[0113] When using the Bayesian model with optimized parameters for data allocation, first evaluate the optimal transmission line predicted by the model, and adjust the data flow according to the prediction to adapt to the new line configuration. The process specifically includes real-time capturing of the operating data of each link, such as transmission rate and delay conditions, and inputting the data into the updated model. The model analyzes the data and provides suggestions for data traffic allocation for each link. According to the suggestions, dynamically adjust the routing and allocate the packet flow direction to ensure that at any given time, all data flows are transmitted along the path with the highest efficiency and the lowest delay. At the same time, implement the balance check to ensure that the data flow is evenly distributed in the network and avoid performance bottlenecks caused by overloading of certain links.

[0114] S402: Adopt a data distribution strategy to implement data flow redirection, update the routing table to match the optimal transmission path, ensure that all data packets are transmitted along the optimal transmission path, and obtain the updated routing table information;

[0115] During the implementation of data flow redirection, update the routing table according to the newly generated data distribution strategy to match the optimal transmission path. This includes detailed routing configuration and programming the router to ensure that data packets are transmitted along the new optimized path. Allow administrators to visualize the performance metrics of each link and select the most suitable route according to the data distribution strategy. Whenever the routing table is updated, automatically push the changes to each router in the network to ensure that the routing information on all devices is up-to-date, and data packets can flow along the predetermined optimal path. In addition, a series of network tests will be carried out to ensure that the new routing configuration does not introduce any connection errors or data transmission delays.

[0116] S403: Through the updated routing table information, continuously monitor the transmission status of data on the optimal transmission path, verify the efficiency and correctness of data along the predetermined path, and generate the dynamic adjustment result of data flow;

[0117] Through the updated routing table, continuously monitor the transmission status of data on the optimal transmission path. The monitoring work is completed by sensors deployed at key nodes in the network. The sensors can record the detailed metrics of data transmission in real time, such as traffic, rate, delay, and packet loss. At the same time, summarize the real-time data and compare it with the predetermined optimal path performance to verify whether the data flow is flowing correctly and without error along the specified path. Any deviation from the predetermined path or performance metrics will be immediately identified and reported to the network operation center. The technical team will analyze it, identify the root cause of the problem, and take corresponding measures for adjustment. The continuous monitoring and real-time feedback mechanism ensure the efficient operation of the network and the best performance of data transmission, and also provide valuable data support for possible future network optimization.

[0118] Please refer to Figure 6 as shown, the specific steps of S5 are as follows:

[0119] S501: According to the dynamic adjustment result of data flow, re-collect the current transmission rate, delay time, and packet loss rate data of all links, record and organize the performance metrics, and generate a snapshot of link performance data;

[0120] According to the dynamic adjustment results of the data stream, re-collect the current transmission rate, latency, and packet loss rate data of all links, and capture the performance data of the links in real time. The collected data is first subjected to preliminary cleaning and verification to remove any inaccurate data caused by sensor errors or abnormal data transmission. After that, the data is recorded in the performance database, and each performance metric of each link is detailedly recorded, including the rate, latency, and packet loss at each time point. During the collation of these records, a time-stamped snapshot of the performance data is generated, capturing a complete view of the link performance at a specific moment and providing the basic data for subsequent performance analysis.

[0121] S502: Utilize the snapshot of the link performance data to analyze the differences in link performance before and after the adjustment measures. By comparing the new and old data sets, calculate the performance deviation value, determine the actual areas of performance improvement and decline, and obtain the performance comparison analysis results;

[0122] The performance deviation value is calculated according to the formula:

[0123]

[0124] is calculated, where ΔP represents the performance deviation value, y i represents the actual performance value of the i-th data point, represents the predicted performance value of the i-th data point, N represents the total number of data points, and d i represents the link latency of the i-th data point.

[0125] y i : The actual performance value of the i-th data point is obtained through the real-time monitoring system of the link performance, such as the transmission speed or bandwidth utilization rate of a link.

[0126] The predicted performance value of the i-th data point is predicted based on the historical performance data.

[0127] d i : The link latency of the i-th data point is obtained from the real-time monitoring data in the network management system.

[0128] N: The total number of data points represents the total number of link data points considered during the analysis.

[0129] Suppose the performance and latency data of 3 data points are as follows:

[0130] y = [100, 150, 200] Mbps (actual performance value)

[0131] (predicted performance value)

[0132] d = [20, 30, 15] ms (latency)

[0133] Calculate the absolute performance difference for each data point:

[0134]

[0135] Sum up to get the total sum of the absolute differences:

[0136]

[0137] Calculate the total sum of the square roots of the delays:

[0138]

[0139] Substitute into the main formula:

[0140]

[0141] The results show that the standardized performance deviation value is 3.72, representing the average deviation of performance before and after the adjustment measures. This value can be used to evaluate the effectiveness of the link adjustment measures. The lower the value, the closer the adjusted performance is to the expectation, and the higher the value, the greater the deviation between the actual performance and the expectation.

[0142] S503: Based on the results of the performance comparison analysis, use the Bayesian model with optimized parameters to deeply evaluate the link status, check the performance of each link after adjustment, confirm the effectiveness of the adjustment operation, and obtain the re-evaluation results of the link performance;

[0143] Based on the performance comparison analysis, use the Bayesian model with optimized parameters to conduct a more in-depth evaluation of the status of each link. In this step, the model predicts and analyzes the performance of each link according to the latest performance data. The model evaluation includes comparing the actually observed performance data with the expected values predicted by the model to check whether each link has reached the expected performance standard after adjustment. In addition, the evaluation process also includes re-optimizing the model parameters to ensure that the model can accurately reflect the current status and potential problems of the link. In this way, the network management team can confirm the effectiveness of each adjustment operation, ensure the continuous optimization of network performance, and at the same time, the generated re-evaluation results of the link performance provide guidance for future network improvement measures.

[0144] Please refer to Figure 7 As shown, the specific steps of S S6 are as follows:

[0145] S601: Based on the re-evaluation results of the link performance, analyze each link in the network one by one, identify the links showing performance degradation and fault signs, record the actual performance indicators and fault types of the relevant links, and generate a list of faulty links;

[0146] After re-evaluating the link performance, each link in the network is analyzed one by one to identify those links showing signs of performance degradation and faults. The process is carried out through a detailed review of performance logs and fault diagnosis, deeply mining the performance data to look for any abnormal patterns or sudden changes in metrics. Once potential performance problems or fault signs are identified, such as persistent high latency or frequent packet loss events, the detailed information of the link will be recorded. The recorded content includes the actual performance metrics of the link and possible fault types. It is summarized into a list of faulty links, which lists all the links that need attention and provides a basis for further network maintenance and fault repair.

[0147] S602: Using the list of faulty links, activate the pre-set backup links in the network, adjust the network configuration, avoid the identified problem areas, and obtain a network topology reconstruction plan;

[0148] Using the generated list of faulty links, the network management team activates the pre-set backup links in the network. The steps involve precise adjustment of the network configuration to avoid the identified problem areas. Through network management, the data flow is re-routed to the backup links to ensure that data transmission is not affected. In addition, the adjustment of the network configuration also includes optimizing the routing protocol and updating the configuration settings of the switching devices to ensure that the backup links can effectively undertake the data transmission tasks of the main links. Throughout the process, closely monitor the performance changes of the network to ensure that the adjustment measures do not introduce new problems and complete a comprehensive network topology reconstruction plan.

[0149] S603: According to the network topology reconstruction plan, synchronously update the network status monitoring information, check all monitoring nodes to correctly reflect the new network structure and traffic paths, and generate the self-healing network architecture adjustment result;

[0150] According to the network topology reconstruction plan, synchronously update the network status monitoring information. This includes checking all monitoring nodes to ensure that they correctly reflect the new network structure and traffic paths. Through network monitoring, update the monitoring configuration of the nodes, including the monitoring frequency, monitored performance metrics, and alarm thresholds. At the same time, the real-time visualization interface of the network status will also be updated to display the new traffic paths and network topology, ensuring that the network monitoring system can provide accurate feedback information, promptly discover and respond to any problems caused by the structural adjustment. The generated self-healing network architecture adjustment result helps the network operation team maintain an efficient and stable network environment.

[0151] The above are only the preferred embodiments of the present invention, and do not limit the present invention in other forms. Any person skilled in the relevant art may use the technical content disclosed above to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical solution content of the present invention, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. A method for dynamic optimization of intersatellite multipoint transmission and links based on Bayesian situational awareness, characterized in that: The following steps are involved: Access the interstellar communication network interface to collect real-time link data, including power, frequency, and signal-to-noise ratio, while recording the data transmission rate and delay of each link, as well as the packet loss rate, to generate real-time link status information; Based on the real-time link status information, Bayesian statistical analysis is performed to evaluate the performance of the link, calculate the potential delay time in the future, compare it with the benchmark data, identify anomalies and predict link performance, and obtain link performance prediction results; Based on the link performance prediction results, path calculation is performed to search for the transmission path with the lowest cost in the network graph, the path weight is adjusted according to the current load of the network, the optimal transmission line is selected, and the Bayesian model parameters are updated to generate a Bayesian model with optimized parameters; Based on the Bayesian model after parameter optimization, dynamic routing adjustment is performed to distribute data to the optimal transmission line, and the routing table is updated to monitor the transmission effect in real time to confirm that the data is transmitted according to the optimal transmission line, and obtain the dynamic adjustment result of the data flow; According to the dynamic adjustment result of the data flow, re-collect link performance data, compare the performance difference before and after the adjustment, use the Bayesian model after the parameter optimization to re-evaluate the link status, detect the effectiveness of the adjustment operation, and obtain the link performance re-evaluation result; According to the link performance re-evaluation results, any potential link failures and performance degradations are detected, and network topology reconstruction is automatically triggered. Problem areas are avoided by activating backup links and reconfiguring the network, and the network status monitoring information is synchronously updated to generate self-healing network architecture adjustment results.

2. The method for inter-satellite multipoint transmission and link dynamic optimization based on Bayesian situational awareness according to claim 1, characterized in that: The real-time link status information includes link power indicators, signal frequency data and signal-to-noise ratio levels; the link performance prediction results include delay time estimation records and performance anomaly indications; the parameter-optimized Bayesian model includes updated model parameters and calculated optimal transmission lines; the data flow dynamic adjustment results include updated routing configurations, the amount of data allocated to the optimal path and the monitored transmission efficiency; the link performance re-evaluation results include performance comparison records before and after adjustment, adjustment effect verification results and re-evaluated performance indicators; the self-healing network architecture adjustment results include activated backup links, reconfigured network structures and updated monitoring status records.

3. The method for inter-satellite multipoint transmission and link dynamic optimization based on Bayesian situational awareness according to claim 1, characterized in that: Access the interstellar communication network interface and collect real-time link data, including power, frequency, and signal-to-noise ratio. Meanwhile, record the data transmission rate and delay of each link, as well as the packet loss rate. The specific steps to generate real-time link status information are as follows: Access the interstellar communication network interface to capture the data stream of power, frequency and signal-to-noise ratio in real time, analyze the signal parameters, and generate real-time link monitoring data; Based on the real-time link monitoring data, the data transmission rate of each link is calculated, the data delay is monitored, and the packet loss events are counted to obtain link performance evaluation data; Based on the link performance evaluation data, the status data of all links are integrated to reveal the dynamic changes of transmission rate, delay and packet loss rate, and generate real-time link status information.

4. The method for inter-satellite multipoint transmission and link dynamic optimization based on Bayesian situational awareness according to claim 1, characterized in that: Based on the real-time link status information, Bayesian statistical analysis is performed to evaluate the performance of the link, calculate the potential delay time in the future, compare it with the benchmark data, identify anomalies and predict link performance, and obtain the link performance prediction results in the following specific steps: Based on the real-time link status information, collect the transmission rate, delay and packet loss rate data of the current link, organize the data, calculate the average value and standard deviation, and generate link performance baseline data; Based on the link performance baseline data, trend analysis is performed to predict future delay time, current data is compared with the baseline performance data, the increase or decrease trend of delay is determined, and future delay prediction analysis results are obtained; The future delay prediction analysis results are used to identify link performance that does not match the prediction model, mark potential performance degradation and anomalies, and predict the future performance of the link to generate a link performance prediction result.

5. The method for inter-satellite multipoint transmission and link dynamic optimization based on Bayesian situational awareness according to claim 1, characterized in that: Based on the link performance prediction results, path calculation is performed to search for the transmission path with the lowest cost in the network graph, the path weight is adjusted according to the current network load, the optimal transmission line is selected, and the Bayesian model parameters are updated. The specific steps of generating the Bayesian model after parameter optimization are as follows: Based on the link performance prediction results, the prediction data of all links in the network diagram are analyzed, the delay and packet loss rate of the links are monitored in real time, the adjusted path weights are dynamically calculated, and the path weight data is generated; Using the path weight data, identifying the transmission path with the lowest cost in the network diagram, and combining the changes in real-time network load to determine the optimal path that matches the current network state, to obtain the optimal transmission line selection result; According to the optimal transmission line selection result, the Bayesian model parameters are updated, and according to the latest link performance data and path selection results, the model prediction algorithm is adjusted to generate a Bayesian model with optimized parameters.

6. The method for inter-satellite multipoint transmission and link dynamic optimization based on Bayesian situational awareness according to claim 5, characterized in that: The adjusted path weight is according to the formula: Calculate, where W new Represents the new weight, W old represents the original path weight, d represents the average delay time of the link, p represents the packet loss rate of the link, and W avg Represents the average weight of all links.

7. The inter-satellite multi-point transmission and link dynamic optimization method based on Bayesian situational awareness according to claim 1 is characterized in that: Based on the Bayesian model after parameter optimization, dynamic routing adjustment is performed to distribute data to the optimal transmission line, and the routing table is updated to monitor the transmission effect in real time to confirm that the data is transmitted according to the optimal transmission line. The specific steps for obtaining the dynamic adjustment result of the data flow are as follows: Based on the Bayesian model after the parameter optimization, data is allocated according to the optimal transmission line, the data flow is adjusted to match the new line configuration, the balance of the data flow is simultaneously checked, and a data allocation strategy is generated; Adopt the data distribution strategy, implement data flow redirection, update the routing table to match the optimal transmission line, ensure that all data packets are transmitted according to the optimal transmission line, and obtain updated routing table information; The updated routing table information is used to continuously monitor the transmission status of data on the optimal transmission line, verify the efficiency and correctness of the data along the predetermined path, and generate a dynamic adjustment result of the data flow.

8. The method for inter-satellite multipoint transmission and link dynamic optimization based on Bayesian situational awareness according to claim 1, characterized in that: According to the dynamic adjustment result of the data flow, link performance data is collected again, the performance difference before and after the adjustment is compared, the link status is re-evaluated using the Bayesian model after the parameter optimization, and the effectiveness of the adjustment operation is detected. The specific steps of obtaining the link performance re-evaluation result are: According to the dynamic adjustment result of the data flow, re-collect the current transmission rate, delay time and packet loss rate data of all links, record and organize the performance indicators, and generate a link performance data snapshot; Utilizing the link performance data snapshot, analyzing the link performance difference before and after the adjustment measures, calculating the performance deviation value by comparing the new and old data sets, determining the actual areas of performance improvement and degradation, and obtaining the performance comparison analysis results; Based on the performance comparison and analysis results, the Bayesian model after parameter optimization is used to conduct an in-depth evaluation of the link status, check the performance of each link after adjustment, confirm the effectiveness of the adjustment operation, and obtain the link performance re-evaluation results.

9. The method for inter-satellite multipoint transmission and link dynamic optimization based on Bayesian situational awareness according to claim 8, characterized in that: The performance deviation value is according to the formula: Calculate, where ΔP represents the performance deviation value, y i represents the actual performance value of the ith data point, represents the prediction performance value of the i-th data point, N represents the total number of data points, and d i Represents the link delay of the i-th data point.

10. The method for inter-satellite multipoint transmission and link dynamic optimization based on Bayesian situational awareness according to claim 1, characterized in that: According to the link performance re-evaluation results, any potential link failures and performance degradation are detected, network topology reconstruction is automatically triggered, problem areas are avoided by activating backup links and reconfiguring the network, and the network status monitoring information is synchronously updated. The specific steps for generating the self-healing network architecture adjustment results are: Based on the link performance reassessment results, analyze each link in the network one by one, identify links showing performance degradation and failure signs, record actual performance indicators and failure types of the relevant links, and generate a list of failed links; Using the fault link list, activating the backup links pre-set in the network, adjusting the network configuration, avoiding the identified problem areas, and obtaining a network topology reconstruction plan; According to the network topology reconstruction plan, the network status monitoring information is synchronously updated, all monitoring nodes are checked, the new network structure and traffic path are correctly reflected, and the self-healing network architecture adjustment result is generated.

Images