Satellite communication resource allocation system and method based on artificial intelligence

Abstract

The invention discloses a satellite communication resource allocation system and method based on artificial intelligence, and relates to the technical field of data analysis, and the method comprises the steps: carrying out the statistics of a scheduling interval, recognizing an abnormal behavior, and building an abnormal scheduling label set based on a satellite communication resource scheduling process; satellite channel quality, service requirements and load states are collected and quantified, and satellite real-time state characteristics are constructed; fusing state features, dynamically adjusting a scheduling period through an attention mechanism, and realizing a period compression and amplification strategy; a resource optimization model is constructed, a resource weight is minimized under a constraint condition, a scheduling trigger mechanism under a minimum period is supported, the key technical problems of poor rigidity and adaptability and response lagging of existing period setting are solved, the flexibility and timeliness of resource scheduling are improved, and energy efficiency optimization of communication resource configuration is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and specifically to a satellite communication resource allocation system and method based on artificial intelligence. Background Art

[0002] In modern satellite communication systems, the resource scheduling efficiency directly determines the overall service capacity and communication quality of the system. With the rapid deployment of low-earth orbit satellite constellations and the continuous growth of user access density, traditional fixed-cycle resource scheduling mechanisms have gradually revealed problems such as slow response and low resource utilization rate;

[0003] Existing scheduling mechanisms usually execute resource allocation decisions based on preset time intervals, lacking the ability of dynamic perception and feedback adjustment of service status and link conditions. Some systems have introduced partial event-driven or load-aware scheduling mechanisms, but have not yet formed a mature cycle adaptive optimization system. At the same time, for different types of resources, there are differences in their optimal scheduling cycles;

[0004] Therefore, there is a need for a satellite communication resource allocation system and method based on artificial intelligence to support the adaptive adjustment of the scheduling cycle, cross-resource type collaborative modeling, and intelligent algorithm-driven optimization, so as to solve the key technical problems of the existing rigid cycle setting, poor adaptability, and lagging response, improve the flexibility and timeliness of resource scheduling, and achieve energy efficiency optimization of communication resource allocation. Summary of the Invention

[0005] The purpose of the present invention is to provide a satellite communication resource allocation system and method based on artificial intelligence to solve the problems raised in the prior art.

[0006] To solve the above technical problems, the present invention provides the following technical solution: A satellite communication resource allocation method based on artificial intelligence, the method includes:

[0007] Step S100: Based on the satellite communication resource scheduling process, count the scheduling interval, identify abnormal behaviors, and establish an abnormal scheduling tag set;

[0008] Step S200: Collect and quantify satellite channel quality, service requirements, and payload status, and construct satellite real-time state features;

[0009] Step S300: Dynamically adjust the scheduling cycle through the attention mechanism by fusing state features, and implement cycle compression and amplification strategies;

[0010] Step S400: Construct a resource optimization model, minimize the resource weight under constraint conditions, and support the scheduling trigger mechanism under the minimum cycle.

[0011] Further, step S100 includes:

[0012] Step S101: In a satellite communication system, monitor the payload status, channel quality, and service requirements of the satellite. When the satellite communication resources are reallocated, generate a scheduling record.

[0013] Step S102: Obtain historical scheduling records, collect the time points corresponding to each historical scheduling record, calculate the interval duration between every two adjacent historical scheduling records, summarize all the interval durations, and calculate the average interval duration.

[0014] Step S103: Extract abnormal periodic change points, collect the scheduling behaviors corresponding to the abnormal periodic change points, and establish a historical abnormal scheduling behavior label set.

[0015] By continuously monitoring the payload status, channel quality, and service requirements of the satellite, dynamic perception and analysis of communication resources are realized, improving the accuracy of scheduling. The resource allocation strategy can be automatically adjusted according to changing environmental conditions and service priorities, reducing manual intervention and enhancing the system's adaptive capacity.

[0016] Based on the scheduling records and the results of historical data analysis, predict and prepare for resource reallocation in advance to avoid resource idleness or conflicts. By calculating the average interval duration, the scheduling frequency and trend can be grasped, thereby reasonably arranging the scheduling cycle and improving the rhythm and coordination of scheduling behaviors.

[0017] Using the periodic analysis and abnormal periodic change point extraction mechanism, potential instability factors or emergencies in the system operation can be identified in a timely manner. The abnormal scheduling behaviors are collected and marked to construct a historical abnormal scheduling behavior label set, which helps to build a knowledge graph of scheduling behaviors and provides a data basis for subsequent identification and intervention.

[0018] Based on the analysis of historical abnormal scheduling behaviors, an intelligent model can be trained to achieve abnormal scheduling early warning, perceive potential problems in advance, and build a fault-tolerant scheduling strategy for the system. When facing sudden scheduling demands or resource bottlenecks, a quick response can be made to ensure that the communication link is not interrupted.

[0019] The accumulation of historical scheduling behaviors and abnormal labels constitutes the knowledge basis for the continuous learning and optimization of the system. As the data accumulates, the system scheduling algorithm can be continuously updated and evolved, thereby gradually achieving an optimal or sub-optimal scheduling strategy, demonstrating a certain degree of "self-optimization" ability.

[0020] After the scheduling is more scientific and reasonable, the timeliness and reliability of high-priority services can be guaranteed, improving the user experience. At the same time, through the abnormal behavior recognition mechanism, the impact on communication quality caused by scheduling interruptions or resource conflicts can be avoided.

[0021] Further, step S200 includes:

[0022] Step S201: Collect the real-time channel quality of the satellite and calculate the effective channel quality according to the following formula:

[0023]

[0024] where Q represents the effective channel quality, and A a represents the signal-to-noise and interference ratio of the ath communication link, B a represents the weight of the ath communication link, and b represents the total number of communication links;

[0025] Step S202: Collect the real-time service requirements of the satellite and calculate the service score according to the following formula:

[0026]

[0027] where C t represents the service score at the t-th time point, D t represents the latency requirement at the t-th time point, F t represents the bandwidth requirement at the t-th time point, and d and f respectively represent the weights of the latency requirement and the bandwidth requirement;

[0028] Step S203: Collect the real-time payload status of the satellite and construct a real-time status matrix of the satellite;

[0029] The calculation of the effective channel quality Q fully considers the signal-to-noise and interference ratio and link weight of each communication link, and can truly and objectively reflect the communication ability between the satellite and the ground station. By integrating multi-link information in a weighted manner, it avoids the distortion phenomenon caused by relying solely on a single channel indicator, enabling the scheduling system to maintain good judgment in a complex and changing channel environment. The service score combines two key performance indicators of latency and bandwidth, and is dynamically adjusted according to the weights, accurately depicting the immediate demand of the service for communication resources, and enhancing the timeliness and priority recognition ability of scheduling;

[0030] The construction of the real-time payload status matrix realizes a systematic expression of various physical states such as the current resource occupancy, processing ability, and energy consumption level of the satellite, providing structured data support for the scheduling strategy. As an input, the status matrix can be integrated with machine learning models and scheduling rule engines to achieve state-aware decision-making, which helps to formulate a more scientific and reasonable resource scheduling plan;

[0031] In a complex space environment, the link quality fluctuates frequently. This method realizes the real-time evaluation of link performance by dynamically calculating the effective channel quality Q, thereby supporting link-level dynamic resource allocation. It can preferentially allocate communication resources to high-quality links, avoiding communication interruptions or packet losses caused by channel deterioration, and improving the overall link stability and transmission efficiency;

[0032] The service scoring mechanism can subdivide the sensitivity of different services to bandwidth and latency, provide higher-priority scheduling guarantees for critical tasks such as telemetry, remote sensing, and video backhaul, support "allocation according to demand", and flexibly adjust the resource allocation strategy according to real-time service demand changes, thereby achieving differential guarantees and dynamic optimization of service quality QoS;

[0033] The characteristic channel quality, service score, and payload status matrix, as high-dimensional inputs of the scheduling model, can be used to train scheduling optimization algorithms such as reinforcement learning and graph neural networks, improving the efficiency and generalization ability of the algorithm to learn scheduling rules, and helping the system to automatically optimize and continuously evolve in different task scenarios;

[0034] The multi-source information fusion mechanism avoids the risks brought by single-index judgment. It can still make reliable decisions in the face of network disturbances or sudden service demands. Even if some links fail temporarily, the system can still reconfigure resources according to the quality of the remaining links and service scores, demonstrating strong fault tolerance and redundant scheduling capabilities. It is an input module for advanced functions such as subsequent anomaly detection, trend prediction, and task planning, and has good potential for platformization and modular development.

[0035] Furthermore, step S300 includes:

[0036] Step S301: Concatenate the effective channel quality, service score, and real-time status matrix of the satellite and send them into the attention network to calculate the corrected period T1. Calculate the real-time scheduling period according to the following formula:

[0037] T = r × T2 + (1 - r) × T1, r ∈ [0, 1];

[0038] where T represents the real-time scheduling period, T2 represents the average interval duration, and r represents the weight of the real-time scheduling period;

[0039] Step S302: Preset the acquisition time interval, calculate the change rate of the service score for each time interval, and preset the change rate threshold. If it exceeds the change rate threshold, compress the period to T3 = p × T, where T3 represents the compressed period and p represents the preset compression coefficient;

[0040] Step S303: Collect the resource utilization rate of the satellite, preset the resource utilization rate threshold. If it does not exceed the resource utilization rate threshold for k consecutive acquisition time intervals, amplify the period to T4 = min(q × T, Tmax), where T4 represents the amplified period, q represents the preset amplification coefficient, and Tmax represents the preset maximum period;

[0041] By splicing the effective channel quality, service score, and real-time status matrix of the satellite and inputting them into the attention network, the system can calculate the corrected scheduling period in real time, ensuring that the scheduling strategy can be adjusted in a timely manner according to the changes in the satellite status. This dynamic decision-making mechanism can handle different communication requirements and channel environments, ensuring that resources are efficiently utilized while meeting the timeliness requirements of services;

[0042] By monitoring the change rate of the service score, if the change exceeds the preset threshold, the scheduling period can be compressed in real time to ensure the timely processing of burst services or tasks with higher priorities. This mechanism ensures the rapid response of resource scheduling in high-demand scenarios;

[0043] Through the mechanism of compressing and amplifying the scheduling period, the scheduling period can be flexibly adjusted according to real-time service requirements, resource utilization rate, and system load. Especially when there is insufficient resource utilization in the system, the period can be extended to reduce the scheduling frequency and system load, thereby improving the overall stability and reliability of the system. This flexible period adjustment mechanism effectively responds to changes in communication tasks. For example, when the system detects high-frequency changes in service requirements, it will compress the scheduling period to shorten the resource allocation time; when the resource utilization rate is low, the system will amplify the scheduling period, thereby reducing invalid scheduling requests and energy consumption;

[0044] By dynamically adjusting the scheduling period, the system can extend the scheduling period when the resource utilization rate is low, thus avoiding resource waste and redundant calculations caused by frequent scheduling. When the resource utilization rate is high, the system will compress the scheduling period to ensure that resources can be allocated in a timely manner under high load, avoiding task failures or packet losses caused by delayed scheduling. Due to the compression and amplification mechanism of the scheduling period, the system can effectively avoid performance degradation caused by over-scheduling or resource idleness. The scheduling system can adaptively adjust its behavior to make resource allocation and use more balanced and efficient;

[0045] Using the attention network, the system can accurately evaluate and adjust the scheduling period according to factors such as the current channel quality, service requirements, and payload status. This mechanism enables the system to automatically identify which factors are more important in a complex multi-dimensional environment, thereby accurately scheduling resources and maximizing communication efficiency;

[0046] By extending the scheduling period during low demand, the system can reduce unnecessary scheduling operations, thereby reducing energy consumption. This mechanism is particularly applicable to high-energy-consuming systems such as satellite communication, effectively reducing the energy consumption pressure of the system, avoiding over-scheduling, reducing the overloading operation of satellite equipment, extending the service life of the satellite, and improving its long-term operation stability.

[0047] Furthermore, step S400 includes:

[0048] Step S401: When the adjustment period arrives, establish a resource optimization model, where the resource optimization model is to minimize where J i represents the weight of the i-th type of resource, and L i represents the allocation amount of the i-th type of resource;

[0049] The constraint of the optimization model is that the sum of all resource allocation amounts does not exceed the preset resource upper limit, and the effective channel quality formed after each resource configuration is not lower than the target effective channel quality;

[0050] Step S403: Preset several trigger conditions. If there is a certain trigger condition, skip the originally planned scheduling period and use the preset minimum period for resource scheduling;

[0051] The construction of the resource optimization model aims at "minimizing the total weighted resource usage", fully considering the importance of different types of resources, and can achieve "on-demand allocation and trade-off optimization" of resources. The scheduling decision is upgraded from "whether to schedule" to "how to schedule optimally", realizing a leap from coarse-grained control to fine-grained optimal configuration, and greatly improving the resource management efficiency and scheduling accuracy;

[0052] The optimization model introduces constraint conditions to ensure that the total amount of all resource allocations does not exceed the resource upper limit that the system can bear, such as power, bandwidth, computing power, etc., and the effective channel quality achieved after each type of resource configuration is not lower than the established target value, avoiding the degradation of the communication link due to insufficient resource allocation. This dual constraint mechanism enhances the controllability and execution feasibility of scheduling, and ensures that the communication quality bottom line during task execution is not breached;

[0053] The trigger mechanism for skipping the original scheduling period enables the system to immediately trigger the minimum scheduling period for resource allocation when facing emergencies such as sudden task increase and sudden degradation of critical links, without waiting for the original period, improving the system's response speed to emergencies, having higher real-time performance and adaptability, and ensuring uninterrupted communication in emergency situations;

[0054] The goal of resource minimization helps to reduce satellite power consumption, reduce thermal load, and extend the payload life, which is a specific practice of the green communication concept in the satellite system. The system can achieve "energy-saving scheduling" through minimum allocation during non-critical mission periods, providing strong energy efficiency guarantee for long-cycle missions and low-power satellites.

[0055] To better implement the above method, a satellite communication resource allocation system based on artificial intelligence is also proposed. The system includes a scheduling record module, a real-time analysis module, an adjustment period module, and an optimized resource module;

[0056] Scheduling Record Module: Based on the satellite communication resource scheduling process, it calculates the scheduling interval, identifies abnormal behaviors, and establishes an abnormal scheduling tag set;

[0057] Real-time Analysis Module: It collects and quantifies the satellite channel quality, service requirements, and payload status, and constructs the satellite real-time status features;

[0058] Adjustment Period Module: It fuses the status features and dynamically adjusts the scheduling period through the attention mechanism to implement the period compression and amplification strategies;

[0059] Optimized Resource Module: It constructs a resource optimization model, minimizes the resource weight under the constraint conditions, and supports the scheduling trigger mechanism under the minimum period.

[0060] Furthermore, the scheduling record module includes an average interval duration calculation unit and a behavior tag set unit:

[0061] Average Interval Duration Calculation Unit: In the satellite communication system, it monitors the payload status, channel quality, and service requirements of the satellite. When the satellite communication resources are reallocated, it generates a scheduling record, obtains the historical scheduling records, collects the time points corresponding to each historical scheduling record, calculates the interval duration between every two adjacent historical scheduling records, summarizes all the interval durations, and calculates the average interval duration;

[0062] Behavior Tag Set Unit: It extracts the abnormal period change points, collects the scheduling behaviors corresponding to the abnormal period change points, and establishes a historical abnormal scheduling behavior tag set.

[0063] Furthermore, the real-time analysis module includes an effective channel quality calculation unit and a service score calculation unit:

[0064] Effective Channel Quality Calculation Unit: It collects the real-time channel quality of the satellite and calculates the effective channel quality;

[0065] Service Score Calculation Unit: It collects the real-time service requirements of the satellite, calculates the service score, collects the real-time payload status of the satellite, and constructs the real-time status matrix of the satellite.

[0066] Furthermore, the adjustment period module includes a real-time scheduling period calculation unit and an adjustment period determination unit:

[0067] Real-time Scheduling Period Calculation Unit: It splices the effective channel quality, service score, and real-time status matrix of the satellite and sends them into the attention network, calculates the corrected period, and calculates the real-time scheduling period;

[0068] Determine the adjustment period unit: Preset the acquisition time interval, calculate the change rate of the service score for each time interval, preset the change rate threshold. If the change rate threshold is exceeded, the compression period is T3 = p×T, and collect the resource utilization rate of the satellite. Preset the resource utilization rate threshold. If the resource utilization rate threshold is not exceeded for k consecutive acquisition time intervals, the amplification period is T4 = min(q×T, Tmax).

[0069] Furthermore, the resource optimization module includes an optimization model establishment unit and a trigger condition determination unit:

[0070] Optimization model establishment unit: When the adjustment period arrives, establish a resource optimization model. The constraints of the optimization model are that the sum of all resource allocation amounts does not exceed the preset resource upper limit, and the effective channel quality formed after each resource configuration is not lower than the target effective channel quality;

[0071] Trigger condition determination unit: Preset several trigger conditions. If there is a certain trigger condition, skip the originally planned scheduling period and use the preset minimum period for resource scheduling.

[0072] Compared with the prior art, the beneficial effects of the present invention are as follows: In the prior art, satellite resource scheduling is mostly based on preset rules or fixed strategies, with lagging response and poor adaptability; while the present invention fully introduces the attention mechanism and multi-source real-time data fusion, enabling the scheduling behavior to have intelligent capabilities such as state perception, anomaly recognition, and cycle adaptability. Based on the learning of historical scheduling behavior and the construction of a label set, it supports subsequent intelligent prediction and anomaly intervention mechanisms, demonstrating a high degree of self-learning and self-optimization capabilities;

[0073] The present invention realizes real-time correction and dynamic adjustment of the scheduling period by introducing an attention network model, and can automatically compress or amplify the scheduling period according to factors such as link quality, service score, and system load, improving the system response ability and resource utilization flexibility;

[0074] The present invention simultaneously collects and fuses link channel quality, service score, and real-time load status, constructs a system multi-dimensional state matrix, provides more comprehensive and accurate input features for the scheduling algorithm, makes the scheduling strategy more accurate and reliable, can support differential service guarantee and link dynamic adjustment, and improves the accuracy and generalization ability of the overall scheduling decision;

[0075] The present invention proposes a scheduling optimization method based on minimizing the resource weighted objective function, which can achieve strategic trade-off and fine control of resource scheduling. Especially when resources are limited or task priorities conflict, it ensures the priority of core services and improves the task completion rate and resource utilization efficiency of the system;

[0076] The current system responds with a lag when faced with sudden link degradation or high-priority task insertion. The present invention sets scheduling trigger conditions so that when certain emergency situations are met, the original planned cycle can be skipped and the minimum scheduling cycle can be quickly entered to execute tasks, thereby greatly improving the real-time performance and adaptability of the system, and effectively ensuring that key tasks are not interrupted and communication links are not failed.

[0077] This method actively extends the scheduling cycle when resource utilization is low. Under the premise of ensuring service quality, it reduces system power consumption and load pressure, improves system energy efficiency, supports energy-aware scheduling and satellite equipment life management, and is in line with the development trend of the new generation of "green satellite communications". BRIEF DESCRIPTION OF THE DRAWINGS

[0078] Figure 1 A schematic diagram of a flow chart of a satellite communication resource allocation method based on artificial intelligence according to the present invention;

[0079] Figure 2 The present invention is a schematic structural diagram of a satellite communication resource allocation system based on artificial intelligence. DETAILED DESCRIPTION

[0080] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0081] See also Figure 1 The present invention provides a technical solution: a satellite communication resource allocation method based on artificial intelligence, the method comprising:

[0082] Step S100: Based on the satellite communication resource scheduling process, counting the scheduling intervals, identifying abnormal behaviors and establishing an abnormal scheduling tag set;

[0083] Wherein, step S100 includes:

[0084] Step S101: In a satellite communication system, monitoring the satellite's load status, channel quality, and service requirements, and generating a scheduling record when satellite communication resources are reallocated;

[0085] Step S102: Obtain historical scheduling records, collect the time point corresponding to each historical scheduling record, calculate the interval duration between every two adjacent historical scheduling records, summarize all interval durations, and calculate the average interval duration;

[0086] Step S103: Extract abnormal cycle change points, collect the scheduling behaviors corresponding to the abnormal cycle change points, and establish a historical abnormal scheduling behavior tag set;

[0087] For example, there are 4 historical scheduling records, and the time points corresponding to each historical scheduling record are 12s, 20s, 35s, and 50s. The calculated adjacent scheduling intervals are 12s, 8s, 15s, and 15 seconds, and the calculated average interval duration is 12.5s.

[0088] Step S200: Collect and quantify the satellite channel quality, service requirements, and payload status, and construct the satellite real-time state characteristics;

[0089] Among them, Step S200 includes:

[0090] Step S201: Collect the real-time channel quality of the satellite and calculate the effective channel quality according to the following formula:

[0091]

[0092] Among them, Q represents the effective channel quality, and A a represents the signal-to-noise interference ratio of the a-th communication link, and B a represents the weight of the a-th communication link, and b represents the total number of communication links;

[0093] Step S202: Collect the real-time service requirements of the satellite and calculate the service score according to the following formula:

[0094]

[0095] Among them, C t represents the service score at the t-th time point, D t represents the delay requirement at the t-th time point, F t represents the bandwidth requirement at the t-th time point, and d and f respectively represent the weights of the delay requirement and the bandwidth requirement;

[0096] Step S203: Collect the real-time payload status of the satellite and construct the real-time state matrix of the satellite;

[0097] For example, collect the signal-to-noise interference ratio of the first link as 10, the weight as 0.5, the signal-to-noise interference ratio of the second link as 5, the weight as 0.3, and the signal-to-noise interference ratio of the third link as 2, the weight as 0.2, and calculate the effective channel quality as 0.94;

[0098] Collect the delay requirement as 8, the weight as 0.7, the bandwidth requirement as 5, the weight as 0.3, and calculate the service score as 0.9992.

[0099] Step S300: The fusion state features dynamically adjust the scheduling period through the attention mechanism to implement the period compression and amplification strategy;

[0100] Among them, Step S300 includes:

[0101] Step S301: Concatenate the effective channel quality, service score, and real-time status matrix of the satellite and send them into the attention network to calculate the corrected period T1, and calculate the real-time scheduling period according to the following formula:

[0102] T = r × T2 + (1 - r) × T1, r ∈ [0, 1];

[0103] Among them, T represents the real-time scheduling period, T2 represents the average interval duration, and r represents the weight of the real-time scheduling period;

[0104] Step S302: Preset the acquisition time interval, calculate the change rate of the service score for each time interval, preset the change rate threshold. If it exceeds the change rate threshold, compress the period to T3 = p × T, where T3 represents the compressed period and p represents the preset compression coefficient;

[0105] Step S303: Collect the resource utilization rate of the satellite, preset the resource utilization rate threshold. If it does not exceed the resource utilization rate threshold for k consecutive acquisition time intervals, amplify the period to T4 = min(q × T, Tmax), where T4 represents the amplified period, q represents the preset amplification coefficient, and Tmax represents the preset maximum period;

[0106] For example, input the effective channel quality of 0.94, service score of 0.9992, remaining power ratio of 0.7, and remaining channel ratio of 0.3 in the satellite real-time state in the embodiment of Step S200 into the attention network, calculate the correction coefficient to be 0.82. In the embodiment of Step S100, calculate the average interval duration to be 12.5 s, calculate the corrected period to be 10.25 seconds, the weight of the real-time scheduling period to be 0.6, and calculate the real-time scheduling period to be 11.6 seconds;

[0107] Preset the acquisition time interval to be 5 s, the change rate threshold to be 0.2, the first service score to be 0.6, the second service score to be 0.85, the change rate to be 0.05, and since it does not exceed the change rate threshold, no compression is performed;

[0108] The utilization rate at the first time point is 0.4, the utilization rate at the second time point is 0.5, the utilization rate at the third time point is 0.55, the resource utilization rate threshold is 0.6, and k is preset to be 3. Then, for the amplified period, calculate min(12.3, 20), and the amplified period is 12.3 s.

[0109] Step S400: Build a resource optimization model to minimize the resource weight under constraints, and support the scheduling trigger mechanism under the minimum cycle;

[0110] Among them, step S400 includes:

[0111] Step S401: When the adjustment cycle arrives, establish a resource optimization model, and the resource optimization model is to minimize where J i represents the weight of the i-th type of resource, and L i represents the allocation amount of the i-th type of resource;

[0112] The constraint of the optimization model is that the sum of all resource allocation amounts does not exceed the preset resource upper limit, and the effective channel quality formed after each resource configuration is not lower than the target effective channel quality;

[0113] Preset several trigger conditions. If there is a certain trigger condition, skip the original planned scheduling cycle and use the preset minimum cycle for resource scheduling.

[0114] To better implement the above method, a satellite communication resource allocation system based on artificial intelligence is also proposed. The system includes a scheduling record module, a real-time analysis module, an adjustment cycle module, and an optimized resource module;

[0115] Scheduling record module: Based on the satellite communication resource scheduling process, count the scheduling interval, identify abnormal behaviors, and establish an abnormal scheduling label set;

[0116] Among them, the scheduling record module includes an average interval duration calculation unit and a behavior label set unit:

[0117] Average interval duration calculation unit: In the satellite communication system, monitor the payload status, channel quality, and service requirements of the satellite. When the satellite communication resources are reallocated, generate a scheduling record, obtain the historical scheduling records, collect the time points corresponding to each historical scheduling record, calculate the interval duration between every two adjacent historical scheduling records, summarize all the interval durations, and calculate the average interval duration;

[0118] Behavior label set unit: Extract abnormal cycle change points, and collect the scheduling behaviors corresponding to the abnormal cycle change points to establish a historical abnormal scheduling behavior label set.

[0119] Real-time analysis module: Collect and quantify the satellite channel quality, service requirements, and payload status, and construct the satellite real-time state characteristics;

[0120] Among them, the real-time analysis module includes an effective channel quality calculation unit and a service score calculation unit:

[0121] Effective Channel Quality Calculation Unit: Collect the real-time channel quality of the satellite and calculate the effective channel quality;

[0122] Service Score Calculation Unit: Collect the real-time service requirements of the satellite, calculate the service score, collect the real-time payload status of the satellite, and construct the real-time status matrix of the satellite.

[0123] Adjustment Period Module: Dynamically adjust the scheduling period through the attention mechanism by fusing state features, and implement the period compression and amplification strategies;

[0124] Among them, the adjustment period module includes a real-time scheduling period calculation unit and an adjustment period determination unit:

[0125] Real-time Scheduling Period Calculation Unit: Concatenate the effective channel quality, service score, and real-time status matrix of the satellite and send them into the attention network, calculate the corrected period, and calculate the real-time scheduling period;

[0126] Adjustment Period Determination Unit: Preset the acquisition time interval, calculate the change rate of the service score for each time interval, preset the change rate threshold. If it exceeds the change rate threshold, compress the period to T3 = p × T. Collect the resource utilization rate of the satellite, preset the resource utilization rate threshold. If the resource utilization rate threshold is not exceeded for k consecutive acquisition time intervals, amplify the period to T4 = min(q × T, Tmax).

[0127] Resource Optimization Module: Construct a resource optimization model, minimize the resource weight under the constraint conditions, and support the scheduling trigger mechanism under the minimum period;

[0128] Among them, the resource optimization module includes an optimization model establishment unit and a trigger condition determination unit:

[0129] Optimization Model Establishment Unit: When the adjustment period arrives, establish a resource optimization model. The constraints of the optimization model are that the sum of all resource allocation amounts does not exceed the preset resource upper limit, and the effective channel quality formed after each resource configuration is not lower than the target effective channel quality;

[0130] Trigger Condition Determination Unit: Preset several trigger conditions. If there is a certain trigger condition, skip the originally planned scheduling period and use the preset minimum period for resource scheduling.

[0131] It is obvious to those skilled in the art that the present invention is not limited to the details of the above-described exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention. Therefore, in any respect, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Thus, all changes that fall within the meaning and scope of the equivalent elements of the claims are intended to be embraced within the present invention. Any reference signs in the claims should not be construed as limiting the claims involved.

Claims

1. A method for allocating satellite communication resources based on artificial intelligence, characterized in that, The method includes: Step S100: Based on the satellite communication resource scheduling process, count the scheduling intervals, identify abnormal behaviors, and establish an abnormal scheduling tag set; Step S200: Collect and quantify the satellite channel quality, service requirements, and payload status, and construct the satellite real-time status features; Step S300: Dynamically adjust the scheduling period through the attention mechanism by fusing the status features, and implement the period compression and amplification strategies; Step S400: Construct a resource optimization model, minimize the resource weight under the constraint conditions, and support the scheduling trigger mechanism under the minimum period.

2. The method for allocating satellite communication resources based on artificial intelligence according to claim 1, characterized in that The said step S100 includes the following steps: Step S101: In the satellite communication system, monitor the payload status, channel quality, and service requirements of the satellite. When the satellite communication resources are reallocated, generate a scheduling record; Step S102: Obtain the historical scheduling records, collect the time points corresponding to each historical scheduling record, calculate the interval duration between every two adjacent historical scheduling records, summarize all the interval durations, and calculate the average interval duration; Step S103: Extract the abnormal period change points, and collect the scheduling behaviors corresponding to the abnormal period change points, and establish a historical abnormal scheduling behavior tag set.

3. The satellite communication resource allocation method based on artificial intelligence according to claim 2, wherein, The said step S200 includes the following steps: Step S201: Collect the real-time channel quality of the satellite, and calculate the effective channel quality according to the following formula: where Q represents the effective channel quality, and A a represents the signal-to-noise and interference ratio of the a-th communication link, and B a represents the weight of the a-th communication link, and b represents the total number of communication links; Step S202: Collect the real-time service requirements of the satellite, and calculate the service score according to the following formula: Among them, C t represents the service score at the t-th time point, D t represents the latency requirement at the t-th time point, F t represents the bandwidth requirement at the t-th time point, and d and f represent the weights of the latency requirement and the bandwidth requirement respectively; Step S203: Collect the real-time payload status of the satellite, and construct the real-time status matrix of the satellite.

4. A satellite communication resource allocation method based on artificial intelligence according to claim 3, characterized in that, The said step S300 includes the following steps: Step S301: Concatenate the effective channel quality, service score, and real-time status matrix of the satellite and send them into the attention network, calculate the corrected period T1, and calculate the real-time scheduling period according to the following formula: T = r×T2+(1 - r)×T1, r∈[0,1]; Among them, T represents the real-time scheduling period, T2 represents the average interval duration, and r represents the weight value of the real-time scheduling period; Step S302: Preset the acquisition time interval, calculate the change rate of the service score for each time interval, preset the change rate threshold. If it exceeds the change rate threshold, compress the period to T3 = p×T, where T3 represents the compressed period, and p represents the preset compression coefficient; Step S303: Collect the resource utilization rate of the satellite, preset the resource utilization rate threshold. If it meets the condition of not exceeding the resource utilization rate threshold for consecutive k acquisition time intervals, amplify the period to T4 = min(q×T, Tmax), where T4 represents the amplified period, q represents the preset amplification coefficient, and Tmax represents the preset maximum period.

5. A method for allocating satellite communication resources based on artificial intelligence according to claim 4, characterized in that, The said step S400 includes the following steps: Step S401: When the adjustment period is reached, a resource optimization model is established, and the resource optimization model is to minimize where J i represents the weight of the i-th type of resource, and L i represents the allocation amount of the i-th type of resource; Step S402: The constraints of the optimization model are that the sum of all resource allocation amounts does not exceed the preset resource upper limit, and the effective channel quality formed after each resource configuration is not lower than the target effective channel quality; Step S403: Preset several trigger conditions. If there is a certain trigger condition, skip the original planned scheduling period and use the preset minimum period for resource scheduling.

6. A satellite communication resource allocation system based on artificial intelligence, which is used to implement the satellite communication resource allocation method based on artificial intelligence according to any one of claims 1-5, characterized in that, The system includes a scheduling record module, a real-time analysis module, an adjustment period module, and an optimized resource module; The scheduling record module: Based on the satellite communication resource scheduling process, it counts the scheduling intervals, identifies abnormal behaviors, and establishes an abnormal scheduling label set; The real-time analysis module: Collects and quantifies the satellite channel quality, service requirements, and payload status, and constructs the satellite real-time status features; The adjustment period module: Dynamically adjusts the scheduling period through an attention mechanism by fusing the status features, and implements the period compression and amplification strategies; The optimized resource module: Constructs a resource optimization model, minimizes the resource weight under the constraint conditions, and supports the scheduling trigger mechanism under the minimum period.

7. An artificial intelligence-based satellite communication resource allocation system according to claim 6, characterized in that, The scheduling record module includes an average interval duration calculation unit and a behavior label set unit: The average interval duration calculation unit: In the satellite communication system, it monitors the payload status, channel quality, and service requirements of the satellite. When the satellite communication resources are reallocated, it generates a scheduling record, obtains the historical scheduling records, collects the time points corresponding to each historical scheduling record, calculates the interval duration between every two adjacent historical scheduling records, summarizes all the interval durations, and calculates the average interval duration; The behavior label set unit: Extracts the abnormal period change points, collects the scheduling behaviors corresponding to the abnormal period change points, and establishes a historical abnormal scheduling behavior label set.

8. An artificial intelligence-based satellite communication resource allocation system according to claim 6, characterized in that, The real-time analysis module includes an effective channel quality calculation unit and a service score calculation unit: The effective channel quality calculation unit: Collects the real-time channel quality of the satellite and calculates the effective channel quality; The service score calculation unit: Collects the real-time service requirements of the satellite, calculates the service score, collects the real-time payload status of the satellite, and constructs the real-time status matrix of the satellite.

9. The satellite communication resource allocation system based on artificial intelligence according to claim 6, characterized in that, The adjustment period module includes a real-time scheduling period calculation unit and an adjustment period determination unit: The real-time scheduling period calculation unit: Concatenates the effective channel quality, service score, and real-time status matrix of the satellite and sends them into the attention network, calculates the corrected period, and calculates the real-time scheduling period; The adjustment period determination unit: Presets the acquisition time interval, calculates the change rate of the service score for each time interval, presets the change rate threshold. If the change rate threshold is exceeded, the period is compressed to T3 = p×T. It collects the resource utilization rate of the satellite, presets the resource utilization rate threshold. If the resource utilization rate threshold is not exceeded for k consecutive acquisition time intervals, the period is amplified to T4 = min(q×T, Tmax).

10. The satellite communication resource allocation system based on artificial intelligence according to claim 6, characterized in that, The optimized resource module includes an optimization model establishment unit and a trigger condition determination unit: The optimization model establishment unit: When the adjustment period arrives, it establishes a resource optimization model. The constraint of the optimization model is that the sum of all resource allocation amounts does not exceed the preset resource upper limit, and the effective channel quality formed after each resource configuration is not lower than the target effective channel quality; The trigger condition determination unit: Presets several trigger conditions. If there is a certain trigger condition, it skips the originally planned scheduling period and uses the preset minimum period for resource scheduling.

Images