Satellite measurement and control subsystem full-digital simulation platform

Abstract

The invention discloses an all-digital simulation platform for a satellite measurement and control subsystem, which relates to the technical field of satellite measurement, operation and control planning and is characterized in that orbit dynamic simulation and a deep learning model are utilized to predict an orbit coverage range, evaluate a resource state of a ground station and generate a coverage window and resource availability data; an optimized task scheduling scheme is generated through task priority ranking and a load balancing model, and ground station resources are balanced while task execution efficiency is improved; a digital twin model is adopted to simulate a task execution path and link performance, and a scheduling scheme is dynamically adjusted according to simulation feedback, so that a plan better meets actual task requirements; in addition, by means of orbit dynamics modeling and deep learning technologies, the accuracy of orbit coverage prediction is improved; efficient task scheduling is carried out through an intelligent optimization algorithm; the link performance evaluation reliability is guaranteed by adopting a digital twin technology; compared with a traditional method, manual intervention and repeated adjustment time are reduced, and the resource utilization rate of the ground measurement and control station is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of satellite measurement, operation and control planning, and particularly to an all-digital simulation platform for a satellite measurement and control subsystem. Background Art

[0002] Digital simulation is a key tool in satellite mission planning and is widely used in mission verification, resource scheduling, and link performance analysis. In actual operation, the satellite measurement, operation and control plan calculates the time period when the satellite passes by the ground station based on the distribution of each satellite orbit and ground stations, and makes an overall plan according to the daily measurement, operation and control requirements. The measurement, operation and control plan is generally divided into a daily plan and a weekly plan. The daily plan is usually formulated one day in advance and is relatively accurate and will not be adjusted except in special circumstances. In case of special circumstances, it can be adjusted within a few hours before the mission execution. The weekly plan is more focused on generality, understanding the tracking capabilities of each station in advance, and the specific mission execution is based on the daily plan.

[0003] It can be seen that this method relies on manual experience and multiple adjustments. With the increase in the number of tasks, the efficiency problem becomes more and more serious. The planning cycle of the traditional solution is relatively long, and it is difficult to respond to dynamic changes in a timely manner. At the same time, the optimization ability of resource scheduling is insufficient, and the utilization rate of ground station resources cannot be maximized. Some measurement and control stations are in a high-load state for a long time, while other stations are not fully utilized, resulting in unbalanced resource allocation.

[0004] In response to these problems, some traditional methods refine the design of the simulation module and separate functions such as orbit prediction, link calculation, and task allocation. Some other solutions optimize the resource scheduling process through preset rules and manual intervention to reduce the dependence on complex algorithms. However, these improvements can only alleviate the problems to a certain extent and do not fundamentally solve the problems of long time consumption and low resource utilization efficiency. In the face of dynamic adjustment and large-scale task collaboration requirements, traditional methods are still difficult to meet the actual needs. Therefore, there is an urgent need for an all-digital simulation solution for the satellite measurement and control subsystem to solve such problems. Summary of the Invention

[0005] In view of the above existing problems, the present invention is proposed.

[0006] The present invention provides an all-digital simulation platform for a satellite measurement and control subsystem to solve the problems that the formulation of traditional measurement and control management plans requires a large amount of manpower and time, and the resources of the measurement and control stations cannot be maximally utilized.

[0007] To solve the above technical problems, the present invention provides the following technical solutions:

[0008] An embodiment of the present invention provides an all-digital simulation platform for a satellite measurement and control subsystem, which includes,

[0009] An initialization module, which is used to obtain measurement, operation and control data, including satellite orbit data, ground measurement and control station resource load information and mission requirements, and preprocess the measurement, operation and control data to convert it into standardized data;

[0010] A resource analysis module, which is used to receive the standardized data of the initialization module, predict the satellite orbit coverage range through orbital dynamics simulation combined with a deep learning model, and evaluate the resource load status of the ground measurement and control station at the same time to generate analysis data, including coverage window time and resource availability;

[0011] A task allocation and scheduling module, which uses the analysis data of the resource analysis module and combines the satellite mission importance, resource availability and coverage window time to dynamically generate a task scheduling plan;

[0012] A simulation verification module, which receives the scheduling plan generated by the task allocation and scheduling module, and uses a digital twin model to perform link performance simulation and adjustment on the plan to generate an adjusted verification result;

[0013] A plan output module, which receives the verification result of the simulation verification module and generates a complete plan report.

[0014] As a preferred solution of the all-digital simulation platform for a satellite measurement and control subsystem described in the present invention, wherein: the method for generating the task scheduling plan includes:

[0015] Construct a task priority table, and sort it according to the mission importance and coverage window time,

[0016] Establish a load balancing model, and adjust the task allocation of the ground measurement and control station based on resource availability.

[0017] As a preferred solution of the all-digital simulation platform for a satellite measurement and control subsystem described in the present invention, wherein: the simulation verification module generates an adjusted verification result by simulating the task execution path and adjusting the resource configuration according to the simulation feedback;

[0018] The plan report includes a final task allocation table and a backup adjustment plan designed for possible sudden tasks or resource conflicts.

[0019] As a preferred solution of the all-digital simulation platform for a satellite measurement and control subsystem described in the present invention, wherein: the simulation steps of the all-digital simulation platform for the satellite measurement and control subsystem include,

[0020] Step S1, extract and standardize satellite orbit data, ground measurement and control station resource load information and mission requirements to form basic data input;

[0021] Step S2, based on the input of basic data, predict the satellite orbit coverage range through orbital dynamics simulation and deep learning models, evaluate the resource status of ground TT&C stations, and generate analysis data, including coverage window time and resource availability;

[0022] Step S3, construct a task priority table, sort it according to task importance and coverage window time, and adjust the task allocation of ground TT&C stations based on resource availability through a load balancing model, and output a task scheduling plan;

[0023] Step S4, use a digital twin model to perform link performance simulation on the task scheduling plan, simulate the task execution path, and dynamically adjust the plan according to the feedback to generate an adjusted verification result;

[0024] Step S5, generate a plan report based on the verification result, and the report content includes a task allocation table and an alternative adjustment plan.

[0025] As a preferred solution of the all-digital simulation platform for a satellite TT&C subsystem described in the present invention, wherein: the step of predicting the satellite orbit coverage range through orbital dynamics simulation and deep learning models and evaluating the resource status of ground TT&C stations is as follows,

[0026] Conduct dynamic modeling of the orbit, and the model formula is:

[0027]

[0028] where r(t) represents the satellite position vector at time t, r 0 is the initial position vector, v(t) is the satellite velocity vector at time t, v 0 is the initial velocity vector, a total (τ) represents the total acceleration, including gravitational force and other external disturbances, and τ is the time integration variable;

[0029] Calculate the visibility between the ground station and the satellite, and the calculation formula is:

[0030]

[0031] When θ ≤ θ max , the ground station s is visible,

[0032] where θ represents the angle between the satellite and the ground station, g s is the position vector of the ground station s, |r(t)| represents the modulus of the satellite position vector, |g s | represents the modulus of the ground station position vector, and θ max is the visibility angle threshold;

[0033] Perform time discretization processing, and the discretization formula is:

[0034] If θ ≤ θ max , then C s,t = 1, otherwise C s,t = 0,

[0035] where C s,t represents the coverage status of ground station s at time step t, t is the discretized time step, and θ max is the visible angle threshold;

[0036] Perform deep learning model fusion, and the fusion formula is:

[0037] y t = σ(W 2 ·ReLU(W 1 ·X t + b 1 ) + b 2 ),

[0038] where y t is the output result of the deep learning model at time step t, including the coverage time period and the load status, X t represents the input features at time step t, including orbital parameters and the location of the ground station, W 1 , W 2 are the weight matrices of the first and second layers respectively, b 1 , b 2 are the bias vectors of the first and second layers respectively, ReLU(·) is the activation function, with a value of max(0, x), and σ(·) is the Sigmoid activation function;

[0039] Evaluate the resource status, and the evaluation formula is:

[0040]

[0041] where R s represents the average load rate of ground station s, T is the total number of time steps, U s is the resource usage per unit time of ground station s, and C s,t is the coverage status of ground station s at time step t,

[0042] Output the analysis data D analysis :

[0043] D analysis = {(t start , t end , R s ) | s = 1, 2, …, S},

[0044] where D analysis is the analysis data set, t start and t endrespectively represent the start time and end time of the coverage window, R s represents the resource load rate of ground station s, and S is the total number of ground stations.

[0045] As a preferred solution of the all-digital simulation platform for a satellite TT&C subsystem described in the present invention, wherein: the step of constructing the task priority table and sorting according to task importance and coverage window time is as follows

[0046] Calculate the task priority, and the calculation formula is:

[0047]

[0048] where P j represents the priority of task j, w 1 , w 2 , w 3 are the weight coefficients of task importance, time window, and resource requirement respectively, satisfying w 1 + w 2 + w 3 = 1, I j is the importance score of task j, T j is the length of the coverage time window of task j, T max is the maximum time window of all tasks, R j is the resource requirement of task j, and arrange the task list in descending order of priority;

[0049] Construct a load balancing model, and the model formula is:

[0050]

[0051] where S is the total number of ground stations, M is the total number of tasks, A j,s is a binary variable indicating whether task j is assigned to ground station s, 1 means assigned, 0 means not assigned, C s is the total resource of ground station s.

[0052] As a preferred solution of the all-digital simulation platform for a satellite TT&C subsystem described in the present invention, wherein: the step of adjusting the task assignment of ground TT&C stations based on resource availability and outputting a task scheduling scheme is as follows

[0053] Define the task assignment adjustment rule as, if:

[0054] then A j,s = 1, otherwise A j,s = 0,

[0055] where A j,sIndicates the status of the adjusted task j assigned to the ground station s. The threshold is the load balancing threshold, representing the upper limit of the resource utilization rate of the ground station;

[0056] Output the task scheduling scheme S schedule :

[0057] S schedule ={(j, s)|j = 1, 2, …, M; s = 1, 2, …, S},

[0058] where S schedule is the final task scheduling scheme, j is the task number, and s is the ground station number.

[0059] As an optimal scheme of a full digital simulation platform for a satellite TT&C subsystem according to the present invention, wherein: the step of using the digital twin model to perform link performance simulation on the task scheduling scheme and simulating the task execution path is as follows:

[0060] Model the link performance indicators and define the link performance score. The model formula is:

[0061]

[0062] where L s represents the link performance score of the ground station s, SNR s is the signal-to-noise ratio of the ground station s, SNR threshold is the minimum signal-to-noise ratio requirement, B s is the link load of the ground station s,

[0063] Combined with the task scheduling scheme, use the digital twin model to perform dynamic simulation on the task execution. The model formula is:

[0064] F s = simulate(S schedule , L s , R s ),

[0065] where F s is the simulation feedback data of the ground station s, S schedule is the task scheduling scheme, defining the allocation relationship between the task and the ground station, L s is the link performance score of the ground station s, R s is the resource load rate of the ground station s, and simulate(·) represents the simulation function, simulating the execution of the task in the link, and the output includes link delay, task completion rate, and resource usage status;

[0066] Analyze the task execution path step by step and extract the key performance indicators:

[0067]

[0068] Among them, T delay represents the average delay time of the link task, t represents the discrete time step, T is the total number of time steps, and BW t,s is the bandwidth of the ground station s at time step t, and Load t,s is the link load of the ground station s at time step t.

[0069] As a preferred solution of the all-digital simulation platform for a satellite TT&C subsystem according to the present invention, wherein: the step of generating an adjusted verification result according to the feedback dynamic adjustment scheme is

[0070] Generate a simulation feedback result, and synthesize the simulation feedback data of each ground station to form a task execution performance matrix M performance :

[0071] M performance = {(L s , T delay , R s ) | s = 1, 2,..., S},

[0072] Among them, M performance represents the performance matrix, S is the total number of ground stations, L s is the link performance score of the ground station s, T delay is the average delay time of the ground station S, and R s is the resource load rate of the ground station S;

[0073] Adjust the task scheduling scheme according to the simulation feedback, and the adjustment formula is:

[0074] S adjusted = S schedule + ΔS(M performance ),

[0075] Among them, S adjusted is the adjusted task scheduling scheme, and ΔS(M performance ) is the adjustment and optimization amount feedback according to the performance matrix.

[0076] As a preferred solution of the all-digital simulation platform for a satellite TT&C subsystem according to the present invention, wherein: the step of generating a planned report based on the verification result is

[0077] Summarize the adjusted task scheduling scheme and the backup scheme to form the final verification result R final :

[0078] R final = {S adjusted , S backup},

[0079] Among them, R final is the set of final verification results, S adjusted is the adjusted final task scheduling plan, and S backup is the backup task scheduling plan;

[0080] Prepare a plan report based on the verification results, including: task allocation table, link performance data, and backup adjustment plan.

[0081] The beneficial effects of the present invention are as follows:

[0082] In the present invention, by using orbital dynamics simulation and deep learning models, the orbital coverage is predicted and the resource status of ground stations is evaluated to generate coverage windows and resource availability data. Through task priority sorting and load balancing models, an optimized task scheduling plan is generated, which improves the task execution efficiency while balancing the resources of ground stations and avoiding overload and resource waste. A digital twin model is used to simulate the task execution path and link performance, and the scheduling plan is dynamically adjusted according to the simulation feedback to make the plan more in line with the actual task requirements and improve the robustness and execution effect of the plan.

[0083] The present invention relies on orbital dynamics modeling and deep learning technology to improve the accuracy of orbital coverage prediction; performs efficient task scheduling through intelligent optimization algorithms; uses digital twin technology to ensure the reliability of link performance evaluation; compared with traditional methods, it not only reduces the time of manual intervention and repeated adjustment, but also significantly improves the overall utilization rate of the resources of ground measurement and control stations, providing a more efficient and robust solution for satellite measurement and control in multi-task complex scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0084] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings without creative efforts based on these drawings.

[0085] Figure 1 It is a schematic diagram of the framework of the all-digital simulation platform for the satellite measurement and control subsystem of the present invention.

[0086] Figure 2 It is a flowchart of the simulation method of the all-digital simulation platform for the satellite measurement and control subsystem of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0087] In order to make the above objects, features, and advantages of the present invention more obvious and understandable, the following detailed description of the specific embodiments of the present invention will be made in conjunction with the drawings of the specification.

[0088] In the following description, numerous specific details are set forth to provide a thorough understanding of the present invention. However, the present invention may be practiced in other ways different from those described herein. Persons skilled in the art can make similar extensions without departing from the spirit of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0089] Secondly, as used herein, an "embodiment" or "embodiments" refers to specific features, structures, or characteristics that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it an isolated or alternative embodiment mutually exclusive of other embodiments.

[0090] Embodiment 1, referring to Figure 1 and Figure 2 , this embodiment provides a full digital simulation platform for a satellite TT&C subsystem, including:

[0091] An initialization module, configured to obtain TT&C operation data, including satellite orbit data, ground TT&C station resource load information, and mission requirements, and preprocess the TT&C operation data to convert it into standardized data;

[0092] A resource analysis module, configured to receive the standardized data from the initialization module, predict the satellite orbit coverage range through orbital dynamics simulation in combination with a deep learning model, and simultaneously evaluate the resource load status of the ground TT&C stations to generate analysis data, including coverage window time and resource availability;

[0093] A task allocation and scheduling module, which uses the analysis data of the resource analysis module and combines the importance of satellite tasks, resource availability, and coverage window time to dynamically generate a task scheduling plan;

[0094] The method for generating a task scheduling plan includes:

[0095] Construct a task priority table, and sort it according to the importance of the task and the coverage window time.

[0096] Establish a load balancing model, and adjust the task allocation of the ground TT&C stations based on resource availability;

[0097] A simulation verification module, which receives the scheduling plan generated by the task allocation and scheduling module, and uses a digital twin model to perform link performance simulation and adjustment on the plan to generate an adjusted verification result;

[0098] The simulation verification module adjusts the resource configuration according to the simulation feedback by simulating the task execution path to generate an adjusted verification result;

[0099] A plan output module, which receives the verification result of the simulation verification module and generates a complete plan report;

[0100] The plan report includes the final task assignment table and an alternative adjustment plan designed for possible unexpected tasks or resource conflicts.

[0101] This embodiment also provides a simulation method for the all-digital simulation platform of the satellite TT&C subsystem, including:

[0102] Step S1, extract and standardize satellite orbit data, ground TT&C station resource load information, and task requirements to form basic data input;

[0103] Step S2, based on the basic data input, predict the satellite orbit coverage range through orbital dynamics simulation and deep learning models, evaluate the resource status of ground TT&C stations, and generate analysis data, including coverage window time and resource availability;

[0104] The steps of predicting the satellite orbit coverage range and evaluating the resource status of ground TT&C stations through orbital dynamics simulation and deep learning models are as follows:

[0105] Conduct dynamic modeling of the orbit, and the model formula is:

[0106]

[0107] where r(t) represents the satellite position vector at time t, r 0 is the initial position vector, v(t) is the satellite velocity vector at time t, v 0 is the initial velocity vector, a total (τ) represents the total acceleration, including gravitational force and other external perturbations, and τ is the time integration variable;

[0108] Calculate the visibility between the ground station and the satellite, and the calculation formula is:

[0109]

[0110] When θ ≤ θ max , the ground station s is visible,

[0111] where θ represents the angle between the satellite and the ground station, g s is the position vector of the ground station s, |r(t)| represents the modulus of the satellite position vector, |g s | represents the modulus of the ground station position vector, and θ max is the visibility angle threshold;

[0112] Conduct time discretization processing, and the discretization formula is:

[0113] If θ ≤ θ max , then C s,t = 1, otherwise C s,t = 0,

[0114] Among them, C s,t represents the coverage status of the ground station s at time step t, where t is the discretized time step, and θ max is the visible angle threshold;

[0115] Perform deep learning model fusion, and the fusion formula is:

[0116] y t = σ(W 2 ·ReLU(W 1 ·X t + b 1 ) + b 2 ),

[0117] Among them, y t is the output result of the deep learning model at time step t, including the coverage time period and the load status, X t represents the input features at time step t, including the orbital parameters and the ground station location, W 1 , W 2 are the weight matrices of the first layer and the second layer respectively, b 1 , b 2 are the bias vectors of the first layer and the second layer respectively, ReLU(·) is the activation function, with a value of max(0, x), and σ(·) is the Sigmoid activation function;

[0118] Evaluate the resource status, and the evaluation formula is:

[0119]

[0120] Among them, R s represents the average load rate of the ground station s, T is the total number of time steps, U s is the resource usage per unit time of the ground station s, C s,t is the coverage status of the ground station s at time step t,

[0121] Output the analysis data D analysis :

[0122] D analysis = {(T start , t end , R s ) | s = 1, 2, …, S},

[0123] Among them, D analysis is the analysis data set, t start and t end respectively represent the start time and the end time of the coverage window, R s represents the resource load rate of the ground station s, and S is the total number of ground stations;

[0124] Specifically, through orbital dynamics modeling and time discretization processing, the visibility relationship between the satellite orbit and the ground station is calculated, the coverage prediction result is optimized by combining with the deep learning model, and the resource status is analyzed through load rate evaluation to generate comprehensive coverage time windows and resource availability data.

[0125] Step S3: Construct a task priority table, sort it according to task importance and coverage window time, and adjust the task allocation of ground measurement and control stations based on resource availability through a load balancing model, and output a task scheduling plan;

[0126] The steps of constructing a task priority table and sorting it according to task importance and coverage window time are as follows:

[0127] Calculate the task priority, and the calculation formula is:

[0128]

[0129] Among them, P j represents the priority of task j, w 1 , w 2 , w 3 are the weight coefficients of task importance, time window, and resource requirement respectively, satisfying w 1 + w 2 + w 3 = 1, I j is the importance score of task j, T j is the length of the coverage time window of task j, T max is the maximum time window of all tasks, R j is the resource requirement of task j, and the task list is arranged from high to low according to priority;

[0130] Construct a load balancing model, and the model formula is:

[0131]

[0132] Among them, S is the total number of ground stations, M is the total number of tasks, A j,s is a binary variable indicating whether task j is assigned to ground station s, 1 means assigned, 0 means not assigned, C s is the total resource of ground station s;

[0133] The steps of adjusting the task allocation of ground measurement and control stations based on resource availability and outputting a task scheduling plan are as follows:

[0134] Define the task allocation adjustment rule as: if:

[0135] Then A j,s = 1, otherwise A j,s = 0.

[0136] Among them, A j,s represents the state where the adjusted task j is assigned to the ground station s, and threshold is the load balancing threshold, representing the upper limit of the resource utilization rate of the ground station;

[0137] Output the task scheduling scheme S schedule :

[0138] S schedule = {(j, s)|j = 1, 2, …, M; s = 1, 2, …, S},

[0139] Among them, S schedule is the final task scheduling scheme, j is the task number, and s is the ground station number;

[0140] Specifically, through priority sorting and load balancing model optimization, an even distribution is carried out between tasks and ground stations to ensure the execution of high-priority tasks while balancing the resource utilization rate.

[0141] Step S4, use the digital twin model to perform link performance simulation on the task scheduling scheme, simulate the task execution path, and dynamically adjust the scheme according to the feedback to generate the adjusted verification result;

[0142] The steps of using the digital twin model to perform link performance simulation on the task scheduling scheme and simulate the task execution path are as follows:

[0143] Model the link performance indicators, define the link performance score, and the model formula is:

[0144]

[0145] Among them, L s represents the link performance score of the ground station s, SNR s is the signal-to-noise ratio of the ground station s, SNR threshold is the minimum signal-to-noise ratio requirement, B s is the link load of the ground station s,

[0146] Combined with the task scheduling scheme, use the digital twin model to perform dynamic simulation on the task execution, and the model formula is:

[0147] F s = simulate(S schedule , L s , R s ),

[0148] Among them, F s is the simulation feedback data of the ground station s, S schedule is the task scheduling scheme, defining the allocation relationship between tasks and ground stations, L sThe link performance score for ground station s, R s The resource load rate of ground station s, simulate(·) represents the simulation function, simulating the execution of tasks in the link, and the output includes link delay, task completion rate, and resource usage status;

[0149] Analyze the task execution path step by step and extract key performance indicators:

[0150]

[0151] Among them, T delay represents the average delay time of link tasks, t represents discrete time steps, T is the total number of time steps, BW t,s is the bandwidth of ground station s at time step t, Load t,s is the link load of ground station s at time step t;

[0152] The steps to dynamically adjust the scheme according to the feedback and generate the adjusted verification result are as follows:

[0153] Generate simulation feedback results, integrate the simulation feedback data of each ground station, and form the task execution performance matrix M performance :

[0154] M performance ={(L s ,T delay ,R s )|s = 1, 2, …, S},

[0155] Among them, M performance represents the performance matrix, S is the total number of ground stations, L s is the link performance score of ground station s, T delay is the average delay time of ground station s, R s is the resource load rate of ground station s;

[0156] Adjust the task scheduling scheme according to the simulation feedback, and the adjustment formula is:

[0157] S adjusted = S schedule + ΔS(M performance ),

[0158] Among them, S adjusted is the adjusted task scheduling scheme, and ΔS(M performance ) is the adjustment and optimization amount according to the feedback of the performance matrix;

[0159] Specifically, evaluate the link performance and resource status during task execution through the digital twin model, and adopt a feedback adjustment mechanism to ensure the reliability of link performance and the rationality of resource allocation, so that the scheduling scheme meets the actual task requirements.

[0160] Step S5, generate a plan report based on the verification result, and the report content includes a task allocation table and an alternative adjustment plan;

[0161] The steps for generating a plan report based on the verification result are as follows:

[0162] Summarize the adjusted task scheduling plan and the alternative plan to form the final verification result R final :

[0163] R final ={S adjusted , S backup},

[0164] wherein, R final is the set of final verification results, S adjusted is the adjusted final task scheduling plan, and S backup is the alternative task scheduling plan;

[0165] Prepare a plan report based on the verification result, including: a task allocation table, link performance data, and an alternative adjustment plan;

[0166] Specifically, the final plan report integrates the verification result and the simulation feedback, provides a primary and backup implementation plan for task execution, and designs a coping strategy for emergencies while ensuring the completion of core tasks.

[0167] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. A satellite measurement and control subsystem full digital simulation platform, characterized by: include, The initialization module is used to obtain measurement, operation and control data, including satellite orbit data, ground measurement and control station resource load information and mission requirements, and pre-process the measurement, operation and control data to convert them into standardized data; The resource analysis module receives the standardized data from the initialization module, predicts the satellite orbit coverage through orbital dynamics simulation combined with deep learning models, and evaluates the resource load status of the ground tracking and control station to generate analysis data, including coverage window time and resource availability; The task allocation and scheduling module uses the analysis data of the resource analysis module and combines the importance of satellite missions, resource availability and coverage window time to dynamically generate task scheduling plans; The simulation verification module receives the scheduling plan generated by the task allocation scheduling module, and uses the digital twin model to simulate and adjust the link performance of the plan to generate an adjusted verification result; The plan output module receives the verification results of the simulation verification module and generates a complete plan report.

2. A satellite measurement and control subsystem full digital simulation platform as claimed in claim 1, characterized in that: The method for generating a task scheduling scheme comprises: Build a task priority table and sort the tasks according to their importance and coverage window time. A load balancing model is established to adjust the task allocation of ground tracking and control stations based on resource availability.

3. A satellite measurement and control subsystem full digital simulation platform as claimed in claim 2, characterized in that: The simulation verification module simulates the task execution path, adjusts the resource configuration according to the simulation feedback, and generates the adjusted verification result; The planning report includes the final task allocation table and alternative adjustment plans designed for possible unexpected tasks or resource conflicts.

4. A satellite measurement and control subsystem full digital simulation platform as claimed in claim 3, characterized in that: The simulation steps of the satellite measurement and control subsystem all-digital simulation platform include: Step S1, extracting and standardizing satellite orbit data, ground tracking and control station resource load information and mission requirements to form basic data input; Step S2, based on the basic data input, through orbital dynamics simulation and deep learning model, predict the satellite orbit coverage, evaluate the resource status of the ground tracking and control station, and generate analysis data, including coverage window time and resource availability; Step S3, constructing a task priority table, sorting tasks according to their importance and coverage window time, and adjusting the ground control station task allocation based on resource availability through a load balancing model, and outputting a task scheduling plan; Step S4, using the digital twin model to simulate the link performance of the task scheduling plan, simulate the task execution path, and dynamically adjust the plan according to the feedback to generate the adjusted verification results; Step S5, generating a plan report based on the verification result, the report content including a task allocation table and backup adjustment plans.

5. A satellite measurement and control subsystem full digital simulation platform as claimed in claim 4, characterized in that: The steps of predicting satellite orbit coverage and evaluating ground tracking and control station resource status through orbital dynamics simulation and deep learning model are as follows: The dynamic modeling of the track is carried out, and the model formula is: Among them, r(t) represents the satellite position vector at time t, r0 is the initial position vector, v(t) is the satellite velocity vector at time t, v0 is the initial velocity vector, and a total (τ) represents the total acceleration, including gravity and other external disturbances, and τ is the time-integrated variable; Calculate the visibility between the ground station and the satellite, the calculation formula is: When θ≤θ max When , the ground station s is visible, Among them, θ represents the angle between the satellite and the ground station, g s is the position vector of the ground station s, |r(t)| represents the modulus of the satellite position vector, |g s | represents the modulus of the ground station position vector, θ max is the visible angle threshold; Perform time discretization processing, the discretization formula is: If θ≤θ max , then C s，t =1, otherwise C s，t =0, Among them, C s，t represents the coverage status of ground station s at time step t, t is the discretized time step, θ max is the visible angle threshold; Perform deep learning model fusion, the fusion formula is: y t =σ(W2·ReLU(W1·X t +b1)+b2), Among them, y is the output result of the deep learning model at time step t, including the coverage time period and load status, and X t represents the input features of time step t, including orbital parameters and ground station positions, W1 and W2 are the weight matrices of the first and second layers respectively, b1 and b2 are the bias vectors of the first and second layers respectively, ReLU(·) is the activation function, and its value is max(0, x), and σ(·) is the Sigmoid activation function; Evaluate resource status. The evaluation formula is: Among them, R s represents the average load rate of ground station s, T is the total number of time steps, U s is the unit time resource usage of ground station s, C s，t is the coverage status of ground station s at time step t, Output analysis data D analysis : D analysis ={(t start ,t end ,R s )|s=1,2,...,S}, Among them, D analysis To analyze the data set, t start and t end Respectively represent the start time and end time of the coverage window, R s It represents the resource load rate of ground station s, and S is the total number of ground stations.

6. A satellite measurement and control subsystem full digital simulation platform as claimed in claim 5, characterized in that: The steps of constructing the task priority table and sorting the tasks according to their importance and coverage window time are as follows: Calculate the task priority using the following formula: Among them, P j Indicates the task j priority, w1, w2, w3 are the weight coefficients of task importance, time window and resource requirements, satisfying w1+w2+w3=1, I j Score the importance of task j, T j is the coverage time window length of task j, T max is the maximum time window of all tasks, R j is the resource requirement of task j, and arranges the task list from high to low priority; Construct a load balancing model, the model formula is: Among them, S is the total number of ground stations, M is the total number of missions, and A j，s is a binary variable indicating whether task j is assigned to ground station s, 1 indicates assigned, 0 indicates not assigned, C s is the total resources of ground station s.

7. A satellite measurement and control subsystem full digital simulation platform as claimed in claim 6, characterized in that: The step of adjusting the task allocation of the ground control station based on resource availability and outputting the task scheduling plan is as follows: Define the task allocation adjustment rules as follows: Then A j，s =1, otherwise A j，s =0, Among them, A j，s It indicates the state of the adjusted task j assigned to the ground station s, and threshold is the load balancing threshold, which indicates the upper limit of the resource utilization of the ground station; Output task scheduling scheme S schedule : S schedule ={(j,s)|j=1,2,...,M;s=1,2,...,S}, Among them, S schedule is the final task scheduling plan, j is the task number, and s is the ground station number.

8. A satellite measurement and control subsystem full digital simulation platform as claimed in claim 7, characterized in that: The steps of using the digital twin model to simulate the link performance of the task scheduling scheme and simulating the task execution path are as follows: Model the link performance indicators and define the link performance score. The model formula is: Among them, L s represents the link performance score of ground station s, SNR s is the signal-to-noise ratio of ground station s, SNR threshold is the minimum signal-to-noise ratio requirement, B s is the link load of ground station s, Combined with the task scheduling scheme, the digital twin model is used to dynamically simulate task execution. The model formula is: F s =simulate(S schedule ,L s ,R s ), Among them, F s is the simulation feedback data of ground station s, S schedule For the task scheduling scheme, define the allocation relationship between tasks and ground stations, L s is the link performance score of ground station s, R s is the resource load rate of ground station s, simulate(·) represents the simulation function, which simulates the execution of the task in the link, and the output includes link delay, task completion rate and resource usage status; Analyze the task execution path step by step and extract key performance indicators: Among them, T delay represents the average delay time of the link task, t represents the discrete time step, T is the total number of time steps, BW t，s is the bandwidth of ground station s at time step t, Load t，s is the link load of ground station s at time step t.

9. A satellite measurement and control subsystem full digital simulation platform as claimed in claim 8, characterized in that: The step of generating the adjusted verification result according to the feedback dynamic adjustment scheme is: Generate simulation feedback results, integrate the simulation feedback data of each ground station, and form the task execution performance matrix M performance : M performance ={(L s ,T delay ,R s )|s=1,2,...,S}, Among them, M performance represents the performance matrix, S is the total number of ground stations, L s is the link performance score of ground station s, T delay is the average delay time of ground station s, R s is the resource load rate of ground station s; Adjust the task scheduling plan according to the simulation feedback, and the adjustment formula is: S adjusted =S schedule +ΔS(M performance ), Among them, S adjusted is the adjusted task scheduling scheme, ΔS(M performance ) is the adjustment optimization amount based on the performance matrix feedback.

10. A satellite measurement and control subsystem full digital simulation platform as claimed in claim 9, characterized in that: The steps of generating a plan report based on the verification results are: Summarize the adjusted task scheduling plan and backup plan to form the final verification result R final : R final ={S adjusted ,S backup }, Among them, R final is the final verification result set, S adiusted is the final task scheduling solution after adjustment, S backup Scheduling solutions for backup tasks; Prepare a plan report based on the verification results, including: task allocation table, link performance data and alternative adjustment plans.

Images