Planning Method, Device, Electronic Equipment and Medium for Constellation Measurement and Control and Data Transmission Tasks

Abstract

The present application provides a method, device, electronic device and medium for planning TT&C and data transmission tasks of a giant constellation, which relates to the technical field of multi-satellite mission planning. The present application aims at the integrated TT&C and data transmission mission scheduling strategy for ultra-large-scale constellations, and lies in fully combining the complex constraints of TT&C and data transmission tasks in the giant constellation. Through the powerful learning and decision-making capabilities of the deep reinforcement learning algorithm, ground station resources are efficiently and reasonably allocated for the giant constellation, and the task execution plan is optimized, so as to take into account the execution effects of both task types, significantly improve the task satisfaction rate of the system, and enhance the utilization rate of time resources; In summary, through multi-dimensional resource collaborative optimization and dynamic task planning, the bottlenecks of traditional scheduling strategies in terms of task capacity, response timeliness, etc. are broken through, so as to ensure the highly reliable on-orbit operation of the constellation system and the data transmission capacity of massive data.

Description

Technical Field

[0001] This application relates to the technical field of multi-satellite mission planning. Specifically, it relates to a method, device, electronic device, and medium for planning TT&C and data transmission tasks of a mega-constellation. Background Art

[0002] With the revolutionary breakthrough of space technology and the deep expansion of space information application scenarios, the networking deployment and collaborative application of large-scale constellation systems have become the strategic high points competing for development in the global space field. As the core technical system to support the stable in-orbit operation of the constellation system, the coordination and scheduling efficiency of the TT&C link maintenance and data transmission service is directly related to the mission execution efficiency of the mega-constellation. The traditional ground station system generally adopts a split scheduling mode for TT&C and data transmission tasks, which has problems such as low utilization rate of equipment resources and is difficult to meet the normal requirements of high-density constellation clusters. With the characteristics of integration of TT&C and data transmission emerging in satellite ground stations, ground station equipment has begun to support the synchronous execution of TT&C tasks and data transmission tasks for the same satellite. Figure 1 The architecture of the mega-constellation system with integrated TT&C and data transmission is presented. The TT&C center and the application center send task requirements to the task management center. After task planning, the mega-constellation communicates with the ground station through the TT&C link and the data transmission link, and then transmits the data back to the ground. Task planning optimizes resource allocation and task execution processes in the system and plays a key role.

[0003] Currently, the methods are still concentrated in medium and small-scale scenarios, and there is no systematic solution for the task scheduling of mega-constellations, and the equipment characteristics of integration of TT&C and data transmission are not considered. Therefore, when facing the huge number of satellites and complex task requirements of mega-constellations, problems gradually emerge, such as poor exploration ability and inability to meet complex constraint conditions. At the same time, it is difficult to achieve the collaborative optimization between TT&C and data transmission tasks, which seriously affects the overall execution efficiency of mega-constellation tasks. Summary of the Invention

[0004] The purpose of the embodiments of this application is to provide a method, device, electronic device, and medium for planning TT&C and data transmission tasks of a mega-constellation, which solves the above problems existing in the prior art and can ensure the high-reliability in-orbit operation of the constellation system and the transmission capacity of massive data.

[0005] In a first aspect, a method for planning TT&C and data transmission tasks of a mega-constellation is provided, and the method may include:

[0006] Obtain the set of equipment disabled times, the set of visibility prediction information, and the total task set of the mega-constellation of the ground station; the set of equipment disabled times includes the disabled periods of each ground station equipment, the set of visibility prediction information includes multiple visibility prediction information, and the total task set includes multiple tasks of each satellite and corresponding task parameters;

[0007] For any task of any satellite, using the configured task planning constraint model, process the task parameters of the task, the disabled periods of each ground station device, and multiple visibility prediction information to determine multiple target visibility prediction information;

[0008] Based on the multiple target visibility prediction information, determine the task planning scheme for the satellite corresponding to the task.

[0009] In a possible implementation, the target visibility prediction information includes: satellite codes corresponding to multiple satellites performing corresponding tasks and cycle visibility prediction information corresponding to multiple total cycles;

[0010] The cycle visibility prediction information includes: total cycle, total number of passes, ascending / descending orbit status, and multiple optional arcs corresponding to the total cycle;

[0011] The optional arc includes: approach pitch angle, approach time, maximum elevation pitch angle, maximum elevation time, departure pitch angle, departure time, and the set of available ground station devices corresponding to the optional arc;

[0012] The set of ground station devices includes: multiple available ground station devices.

[0013] In a possible implementation, the task planning scheme includes: target ground station device, target time window, and target cycle;

[0014] Based on the multiple target visibility prediction information, determining the task planning scheme for the satellite corresponding to the task includes:

[0015] Based on the multiple target visibility prediction information, determine multiple optional cycles for the corresponding task;

[0016] Use the deep Q-network algorithm to process the optional cycle information corresponding to each optional cycle to obtain the target cycle;

[0017] Based on the target cycle and the greedy strategy, determine the target time window;

[0018] Based on the target time window and the load balancing algorithm, determine the target ground station device.

[0019] In a possible implementation, using the deep Q-network algorithm to process multiple optional cycles to obtain the target cycle includes:

[0020] Use the deep Q-network algorithm to process the optional cycle information corresponding to multiple optional cycles to obtain multiple Q values;

[0021] Use the ε-greedy strategy to determine the maximum Q value among the multiple Q values;

[0022] Determine the optional lap number corresponding to the maximum Q value as the target lap number.

[0023] In a possible implementation, determining a target time window based on the target lap number and a greedy strategy includes:

[0024] Based on the correspondence between different total lap numbers and multiple optional arc segments, determine multiple target optional arc segments corresponding to the target lap number;

[0025] Based on the corresponding inbound time and outbound time in the multiple optional arc segments, determine multiple time windows for executing tasks corresponding to the configured time step;

[0026] Calculate the lengths of the multiple time windows to obtain the lengths of each time window;

[0027] Adopt a greedy strategy to screen the multiple lengths, determine the minimum length, and determine the time window corresponding to the minimum length as the target time window.

[0028] In a possible implementation, determining a target ground station device based on the target time window and a load balancing algorithm includes:

[0029] Based on the correspondence between different optional arc segments and the set of available ground station devices, determine the set of target available ground station devices for the optional arc segments corresponding to the target time window;

[0030] For any available ground station device, calculate the average disabled duration of each disabled duration of the available ground station device to obtain the average disabled duration;

[0031] Based on the average disabled duration and the boundary values of the target time window, determine the time non-disabled factor;

[0032] Determine the available ground station device corresponding to the minimum value among the multiple time non-disabled factors as the set of target available ground station devices.

[0033] In a possible implementation, after completing the tasks of the satellite corresponding to any time step based on the task planning scheme, the method further includes:

[0034] Determine the target success rate of each task planning scheme within this time step;

[0035] Based on the correspondence between different success rates and different reward values, determine the target reward value of the target success rate;

[0036] Based on the target success rate, target reward value, optional lap number information of this time step, and optional lap number information of the next time step of this time step, determine an experience tuple;

[0037] After multiple time steps are completed, multiple experience tuples are obtained;

[0038] Calculate the parameters in the multiple experience tuples to obtain a target value;

[0039] Calculate the target value to obtain the target network parameters of the deep Q-network algorithm.

[0040] In a second aspect, a planning device for the measurement and control and data transmission tasks of a giant constellation is provided. The device may include:

[0041] An acquisition unit, configured to acquire a set of device disable times of a ground station, a set of visible prediction information, and a set of total tasks of the giant constellation; the set of device disable times includes the disable periods of each ground station device, the set of visible prediction information includes multiple pieces of visible prediction information, and the set of total tasks includes multiple tasks of each satellite and corresponding task parameters;

[0042] A determination unit, configured to, for any task of any satellite, process the task parameters of the task, the disable periods of each ground station device, and multiple pieces of visible prediction information by using a configured task planning constraint model to determine multiple target visible prediction information;

[0043] And, based on the multiple target visible prediction information, determine a task planning scheme for the satellite corresponding to the task.

[0044] In a third aspect, an electronic device is provided. The electronic device includes a processor, a communication interface, a memory, and a communication bus. Among them, the processor, the communication interface, and the memory complete communication with each other through the communication bus;

[0045] The memory is used to store a computer program;

[0046] The processor, when executing the program stored on the memory, implements any of the method steps described in the first aspect above.

[0047] In a fourth aspect, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements any of the method steps described in the first aspect above.

[0048] The task scheduling strategy for integrated TT&C and data transmission facing ultra-large-scale constellations in this application lies in fully combining the complex constraints of TT&C and data transmission tasks in the mega constellation. Through the powerful learning and decision-making capabilities of the deep reinforcement learning algorithm, it efficiently and reasonably allocates ground station resources for the mega constellation, optimizes the task execution plan, so as to balance the execution effects of the two task types, significantly improve the task satisfaction rate of the system, and enhance the utilization rate of time resources. In summary, through multi-dimensional resource collaborative optimization and dynamic task planning, it breaks through the bottlenecks of traditional scheduling strategies in terms of task capacity, response timeliness, etc., so as to ensure the highly reliable on-orbit operation of the constellation system and the transmission capacity of massive data. Brief Description of the Drawings

[0049] To more clearly illustrate the technical solutions of the embodiments of this application, the following will briefly introduce the drawings required to be used in the embodiments of this application. It should be understood that the following drawings only show some embodiments of this application, so they should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other relevant drawings can also be obtained based on these drawings.

[0050] Figure 1 It is an architecture diagram of a mega constellation system for integrated TT&C and data transmission provided by an embodiment of this application;

[0051] Figure 2 It is a flow schematic diagram of a planning method for mega constellation TT&C and data transmission tasks provided by an embodiment of this application;

[0052] Figure 3 It is a schematic diagram of a time window provided by an embodiment of this application;

[0053] Figure 4 It is a comparison schematic diagram of the task satisfaction rates of different solutions for processing multi-satellite tasks provided by an embodiment of this application;

[0054] Figure 5 It is a comparison schematic diagram of the proportion of unused whole-block idle resources between the single-stage DQN algorithm and this solution provided by an embodiment of this application;

[0055] Figure 6 It is a structural schematic diagram of a planning device for mega constellation TT&C and data transmission tasks provided by an embodiment of this application;

[0056] Figure 7 It is a structural schematic diagram of an electronic device provided by an embodiment of this application. Detailed Embodiments

[0057] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0058] With the revolutionary breakthrough of space technology and the deep expansion of space information application scenarios, the networking deployment and collaborative application of large-scale constellation systems have become the strategic high points for global space development. As the core technical system to support the stable operation of constellation systems in orbit, the collaborative scheduling efficiency of the TT&C link maintenance and data transmission service directly affects the mission execution efficiency of giant constellations. The traditional ground station system generally adopts a split scheduling mode for TT&C and data transmission tasks, with problems such as low utilization rate of equipment resources, and it is difficult to meet the normal requirements of high-density constellation clusters. With the emergence of the integrated TT&C and data transmission feature in satellite ground stations, ground station equipment has begun to support the synchronous execution of TT&C tasks and data transmission tasks for the same satellite. Figure 1 The architecture of a giant constellation system with integrated TT&C and data transmission is presented. The TT&C center and the application center send task requirements to the mission management center. After mission planning, the giant constellation communicates with the ground station through the TT&C link and the data transmission link, and then transmits the data back to the ground. Mission planning optimizes resource allocation and task execution processes in the system and plays a key role.

[0059] Currently, mission planning methods mainly include mathematical programming methods, graph model search algorithms, heuristic algorithms, and meta-heuristic algorithms. Among mathematical programming methods, integer linear programming and mixed integer programming are more common. Although there are studies on constructing corresponding problem models and using iterative algorithms, Lagrangian relaxation, and linear search techniques for solution, due to high time complexity, they are only applicable to small-scale scenarios. The graph model search algorithm transforms mission planning into a graph search problem by establishing a vertex set and an edge set, such as modeling using graph coloring theory and solving with tabu search algorithms and ant colony optimization algorithms. The heuristic algorithm is an effective means to solve NP-hard combinatorial optimization problems. Its core lies in achieving the efficient solution of approximate optimal solutions through intelligent search strategies and domain knowledge guidance based on experience and domain knowledge, such as genetic algorithms and artificial bee colony algorithms, which are widely used in practical problems.

[0060] However, the current methods still focus on medium- and small-scale scenarios, and there is no systematic solution for the mission scheduling of giant constellations, nor do they consider the equipment characteristics of integrated TT&C and data transmission. Therefore, when facing the large number of satellites and complex task requirements of giant constellations, problems gradually emerge, such as poor exploration ability and inability to meet complex constraint conditions. At the same time, it is difficult to achieve collaborative optimization between TT&C and data transmission tasks, seriously affecting the overall execution efficiency of giant constellation missions.

[0061] Therefore, the present application provides a method for planning the measurement and control and data transmission tasks of a giant constellation to solve the above problems existing in the prior art, and can ensure the highly reliable on-orbit operation of the constellation system and the data transmission capacity of a large amount of data.

[0062] The preferred embodiments of the present application will be described below in conjunction with the accompanying drawings of the specification. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application, and are not used to limit the present application. And without conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

[0063] Figure 2 It is a schematic flow chart of a method for planning the measurement and control and data transmission tasks of a giant constellation provided by an embodiment of the present application. As Figure 2 shown, the method may include:

[0064] Step S210, obtain the set of equipment disabling times, the set of visible prediction information, and the total task set of the giant constellation of the ground station.

[0065] Among them, the set of equipment disabling times includes the disabling periods of each ground station equipment, the set of visible prediction information includes multiple visible prediction information, and the visible prediction information is the satellite and its operation parameters expected to be observed by the ground station; the total task set includes multiple tasks and corresponding task parameters of each satellite.

[0066] Specifically, the measurement and control and data transmission task planning is to fully consider the measurement and control and data transmission integration characteristics of the ground station resources, determine the time to execute the satellite tasks, and allocate the ground station resources for the satellite tasks, so as to meet the task requirements of the giant constellation as much as possible.

[0067] The set of ground station equipment for measurement and control and data transmission integration is D = {d1, d2,..., d S}; d i represents the information of the i-th ground station equipment, wherein, d i represents the number of the ground station, represents the function supported by the ground station equipment. Similar to typ i Among them, represents that the ground station equipment can only perform measurement and control tasks; represents that the ground station equipment can only perform data transmission tasks; represents that the ground station equipment can perform both measurement and control and data transmission tasks, but cannot perform two types of tasks simultaneously; represents that the ground station equipment can perform the measurement and control tasks and data transmission tasks of a satellite simultaneously.

[0068] A. The overall task set can be expressed as: J = {j1, j2,..., j​N};

[0069] The i-th task where s i represents the satellite code, and typ i represents the task type, and typ i ∈ {1, 2}, and typ i = 1 indicates that the task is a TT&C task, and typ i = 2 indicates that the task is a data transmission task. pre i represents the link establishment time, and dis i represents the link disconnection time, represents the minimum value of the tracking maximum elevation angle, and con i represents the constraint definition method (known quantity), represents the offset under the allowable range, represents the most desired time / circle number, represents the offset above the allowable range;

[0070] It can be understood that the above-mentioned task parameters are: s i , typ i , pre i , dis i , con i , D.

[0071] B. The visible prediction information set is the set of foreseeable information expected to be observed by the ground station; the visible prediction information set can be expressed as: F = {f1, f2,..., f L};

[0072] For the i-th visible prediction information where s i represents the satellite code, and d i represents the equipment code, represents the total number of circles, represents the total number of circles during transit (the number of consecutive circles visible within this territory), and rf i represents the ascending / descending orbit state, represents the approach pitch angle, represents the approach time, represents the maximum elevation pitch angle, represents the maximum elevation time, represents the departure pitch angle, represents the departure time.

[0073] C. The equipment disable time set is the set composed of the disable time information of each equipment at the ground station; the equipment disable time set can be expressed as: DT = {dt1, dt2,..., dtS}; the i-th disabling time information and is the boundary value (start and end time points) of the K-th disabling period in the i-th disabling time information.

[0074] It should be noted that, as shown in Figure 3 , when the forecast information for a certain task is selected, assuming satellite s i has a visible forecast start and end time of Considering the link establishment duration and link disconnection duration of the corresponding satellite s i , expand the tracking start time by pre i seconds and extend the tracking end time by dis j seconds, and use them as the start time ms i and end time me i of this forecast time window respectively, that is, [ms i , me i .

[0075] Specifically, the calculation methods of the start time and end time are as follows:

[0076]

[0077] Step S220, for any task of any satellite, use the configured task planning constraint model to process the task parameters of this task, the disabling periods of each ground station device, and multiple visible forecast information, and determine multiple target visible forecast information.

[0078] The task planning constraint model can be expressed as:

[0079]

[0080] C4: me j ≥ms i and me i ≥ms j , i≠j

[0081] C5: rev i ≠rev j , if typ i =typ j , i≠j

[0082] Among them, C1 represents the maximum elevation angle constraint, and it can be seen that the maximum elevation angle is greater than the minimum value of the maximum elevation angle; C2 represents the rotation position constraint, C3 represents the disabled time constraint, and there is no overlap between the device execution task time window and the corresponding disabled time interval; C4 represents the time window constraint, and the time intervals occupied by different satellites on the same ground station device do not overlap. When the ground station device supports simultaneous TT&C and data transmission, except for the case where the same satellite performs TT&C and data transmission tasks simultaneously. C5 represents the satellite orbit constraint, and two tasks of the same type (TT&C or data transmission) are not arranged in the same orbit of the same satellite. The task planning scheme P = {P1, P2, …, P i , …, P N}, where the scheme P i of the i-th task = {x i , s i , d i , rev i , ms i , me i}. x i indicates whether the task is successfully executed, s i is the satellite number, d i is the device number of the target ground station device, rev i represents the target orbit, and ms i and me i represent the boundary values of the target time window.

[0083] Among them, the rotation position constraint is as follows:

[0084] (1) When con i = 0, the current window constraint is invalid.

[0085] (2) The constraint means that when con i = 1,

[0086] (3) The constraint is that when con i = 2 and , The constraint is that when con i = 2 and ,

[0087] (4) The constraint is that when con i = 3 and , the selected visible forecast ascending / descending orbit state must be the ascending orbit arc segment and must satisfy The constraint is that when con i = 3 and When, the selected visible forecast ascending / descending orbit state must be the ascending orbit arc segment and must satisfy

[0088] (5), Constraint is when con i = 4 and When, the selected visible forecast ascending / descending orbit state must be the descending orbit arc segment and must satisfy Constraint is when con i = 4 and When, the selected visible forecast ascending / descending orbit state must be the descending orbit arc segment and must satisfy and must satisfy Among them, T represents the time of one day, the unit is seconds, and s0 represents the offset coefficient.

[0089] This task planning constraint model models the task planning problem to be solved as a constrained optimization problem to clarify the task objectives and make the constraint conditions transparent, ensure finding the optimal solution, and thus enhance the credibility of the solution.

[0090] Specifically, first, process the specific parameters in the multiple visible forecast information of the satellites corresponding to all tasks according to the number of orbits, time windows, and available ground station equipment to obtain the initial visible forecast set F ′ = {f1′, f2′,…, f N ′}; This initial visible forecast set contains multiple initial visible forecast information f i ′ ; The initial visible forecast information f i ′ corresponding to the i-th task, the total number of all orbits it contains is L1, that is Among them, REV i represents the orbit rev t i otal A series of orbit visible forecast information with the same; L2 represents the total number of time windows. Among them, ARC i represents the i-th optional arc segment ARC in the orbit i = {ang0, t0, ang1, t1, ang2, t2, D i}, in this optional arc segment set, D i represents the set of available ground station equipment that can be occupied within the time window of the arc segment ARC i , that is:

[0091] In this method, the data corresponding to any task of any satellite is classified and processed to obtain several time windows included in the same orbit, and there are several available ground station equipment within the same time window.

[0092] After that, a mission planning constraint model is used to process the mission parameters of the currently processed mission, the disabled periods of each ground station device, and the initial visibility prediction set, and multiple target visibility prediction information that meets the preset constraint conditions is obtained. Among them, the order in which the mission planning constraint model processes each mission is carried out according to the arrangement order of each mission in the total mission set;

[0093] That is to say, the target visibility prediction information includes: the satellite codes corresponding to the satellites that execute the corresponding missions and the cycle visibility prediction information corresponding to multiple total cycles;

[0094] The cycle visibility prediction information includes: the total cycle, the total number of transit cycles, the ascending / descending orbit state, and multiple optional arcs corresponding to the total cycle; that is, the corresponding relationship between different total cycles and multiple optional arcs is determined;

[0095] The optional arc includes: the inbound pitch angle, the inbound time, the highest elevation pitch angle, the highest elevation time, the outbound pitch angle, the outbound time, and the set of available ground station devices corresponding to the optional arc; that is, the corresponding relationship between different optional arcs and the set of available ground station devices is determined;

[0096] The set of ground station devices includes: multiple available ground station devices.

[0097] This method is to screen the initial visibility prediction information in the classified initial visibility prediction set through the preset constraint conditions and the obtained known data by the mission planning constraint model, and obtain the target visibility prediction information that meets the preset constraint conditions in the currently processed mission. It can be understood that the structure of the initial visibility prediction set is the same as that of the target visibility prediction information.

[0098] Step S230: Based on multiple target visibility prediction information, determine the mission planning plan for the satellite corresponding to the mission.

[0099] Specifically, step 23-1: Based on multiple target visibility prediction information, determine multiple optional cycles for the corresponding mission; convert the mission decision into a Markov decision process, and use the deep Q-network algorithm to process the optional cycle information corresponding to each optional cycle to obtain the target cycle;

[0100] Among them, build the algorithm framework of the Deep Q–Network (DQN) and initialize it. Use the fully connected network as the function approximator, and generate the Q-value function Q(s t ,a t; θ), i.e., the Q network, where θ is the DNN parameter. Initialize the Q network and the target network of the agent with random parameters. Set parameters such as the number of cycles, the time step length, the batch size, the experience pool capacity, the discount factor, and the learning rate. One cycle is the entire plan of the total task. Among them, within each time step, one task is planned, and the agent interacts with the task planning environment.

[0101] Specifically, for any configured time step t, the optional round information s of the corresponding task t ={typ t , rev t , REV t} is determined as the current state; where rev t is a set of m rounds that meet the preset constraint conditions, and REV t contains all the time window information corresponding to each of the m rounds that meet the preset constraint conditions in the visible forecast of the current task represents the kth time window in the ith round, that is i The agent generates the current state into a state vector and inputs the state vector into the Q network to obtain the Q value; if the task cannot be executed, the target round a t =0.

[0102] If the task is executed, the action of the agent will determine the round selected in the visible forecast, that is, the target round a t num =rev num .

[0103] After that, adopt the ε-greedy strategy to randomly select multiple optional rounds based on the first probability ε of the configuration; based on the second probability 1 - ε of the configuration, select the action corresponding to the maximum Q value among multiple Q values; that is, determine the optional round corresponding to the maximum Q value as the target round.

[0104] Step 23-2: Determine the target time window based on the target round and the greedy strategy;

[0105] Specifically, based on the corresponding relationship between different total rounds and multiple optional arc segments, determine multiple target optional arc segments corresponding to the target round;

[0106] Based on the corresponding inbound time and outbound time among multiple optional arc segments, determine multiple time windows for executing the task corresponding to the configured time step;

[0107] Calculate the lengths of multiple time windows to obtain the lengths of each time window;

[0108] Adopt a greedy strategy to screen multiple lengths, determine the minimum length, and determine the time window corresponding to the minimum length as the target time window.

[0109] This method can be understood as that at time step t, there are several time windows within the lap selected by the agent, which are where, T i =[ms i , me i . Calculate the length d of all time windows i , that is, d i =me i -ms i . Adopt a greedy strategy to select the time window with the minimum length, that is:

[0110] Step 23-3: Determine the target ground station equipment based on the target time window and the load balancing algorithm.

[0111] Specifically, based on the corresponding relationship between different optional arcs and the set of available ground station equipment, determine the set of target available ground station equipment for the optional arc corresponding to the target time window;

[0112] For any available ground station equipment, calculate the average disabled duration of each disabled duration of this available ground station equipment to obtain the average disabled duration;

[0113] Based on the average disabled duration and the boundary values of the target time window, determine the time non-disabled factor;

[0114] Determine the available ground station equipment corresponding to the minimum value among multiple time non-disabled factors as the set of target available ground station equipment.

[0115] This method can be understood as: after determining the time window [s, e], use the load balancing algorithm based on time fine-grained analysis to make a decision on ground station selection. For the set of available ground station equipment within the same time window Define the time non-disabled factor to measure the proportion occupied by each available ground station equipment during the non-disabled time. If the disabled times of the selected available ground station equipment are arranged in ascending order as dt t ={st1, et1, st2, et2,..., st m , et m}, the time non-disabled factor of the i-th optional equipment is:

[0116]

[0117] where, T abd represents the average disabled duration, that is According to the time non-disabled factor of each device, select the device with the minimum time non-disabled factor, that is:

[0118] In summary, a task planning scheme for the currently processed task is obtained, and then the following steps are returned: Using the task planning constraint model, process the task parameters of the next task, the disabled time periods of each ground station device, and the initial visibility prediction set to obtain multiple target visibility prediction information that meets the preset constraint conditions. Among them, the next task is the next task of the currently processed task in the total task set.

[0119] When the d i , rev i , ms i and me i in the task planning schemes of all tasks corresponding to the satellite within this time step are determined, i , rev i , ms i and me i are used to execute the task, and the execution result x i is counted.

[0120] After all tasks corresponding to any time step are completed, the method may further include:

[0121] Determine the target success rate of each task planning scheme within this time step;

[0122] Based on the corresponding relationship between different success rates and different reward values, determine the target reward value r t of the target success rate;

[0123]

[0124] Among them, tr t represents the target success rate of the TT&C task in the current time step, and dr t represents the target success rate of the data transmission task in the current time step.

[0125] After that, the environment will enter a new state s t+1 , and based on the target success rate, target reward value, optional loop times information of this time step, and the optional loop times information of the next time step of this time step, determine the experience tuple (s t , a t , r t , s t+1 );

[0126] When multiple time steps are completed, multiple experience tuples are obtained;

[0127] Calculate the parameters in the multiple experience tuples to obtain the target value;

[0128] This method uses a memory replay scheme to train the Q-network, that is, the agent extracts previous samples from the experience pool to alleviate the non-stationary experience distribution. In the DQN structure, the agent has a target network with the same structure as the Q-network. The target network can be expressed as where represents the target network parameters of the agent. During training, each agent samples n experience tuples from the experience pool, that is, (s j , a j , r j , s j+1 ), j = 1, 2, …, n, and calculates the target value, that is:[[]]

[0129]

[0130] where γ is the discount factor. Then calculate the mean squared error loss and use the adaptive moment estimation method to train the Q-network.[[]] Finally, update the network parameters θ, and copy the weights θ of the updated Q-network to the target network parameters every C time steps

[0131] After completing one cycle of training, calculate the total reward value, reset the task planning environment, and start a new cycle of training. After multiple cycles of training, the DQN-greedy policy-time load balancing task planning algorithm constructed in this application will converge to obtain the optimal planning scheme.[[]]

[0132] This application fully considers complex constraint conditions such as the support relationship between different types of devices in the measurement and control and data transmission integration scenario, adopts a phased decision-making mode to decompose the solution space layer by layer, the agent determines the number of task circles executed by the satellite, and then the greedy algorithm for the time window length and the load balancing algorithm based on time granularity analysis respectively make decisions on the time window and ground station devices, cooperate with the DQN to optimize the overall planning scheme, generate global rewards according to the task satisfaction situation and feedback them to the agent, so as to effectively improve the satisfaction rates of measurement and control and data transmission tasks and the proportion of idle resources in the whole block.[[]]

[0133] In a specific example, the scheme is applied under the constellation system architecture of measurement and control and data transmission integration as shown in Figure 1 . The total number of satellites is 400, the total number of tasks is 19,840, of which the number of measurement and control tasks is 12,800, the number of data transmission tasks is 7,040, the number of ground stations is 52, of which the number of measurement and control ground stations is 31, the number of data transmission ground stations is 5, and the number of ground stations that support both measurement and control and data transmission is 16. During the simulation process, the scheme of this application is used for task planning, and the satisfaction rates of measurement and control and data transmission tasks are calculated respectively.[[]]

[0134] Under the above simulation conditions, in this example, simulations are carried out point by point at intervals of 10 in the range of 320 to 400 satellites, and the task satisfaction rates of TT&C (Tracking, Telemetry and Command) and data transmission are obtained for different numbers of satellites. Then, the performance of this solution is compared with the task planning solutions of existing genetic algorithms, artificial bee colony algorithms, and single-stage DQN (Deep Q-Network) algorithms. The comparison results are as Figure 4 shown. The red dots and triangular curves are the TT&C and data transmission simulation results of this application respectively. It can be seen that this solution can significantly improve the task satisfaction rates of TT&C and data transmission. Calculate the proportion of unused whole-block idle resources in this solution, that is, the proportion of non-occupied time longer than 600s in all non-disabled time, and compare it with the solution of the single-stage DQN algorithm. The results are as Figure 5 shown. When the task satisfaction rate of the proposed solution has an obvious advantage, the proportion of unused whole-block idle resources in it is also better than that of the single-stage DQN algorithm, indicating that the proposed solution can optimize the utilization of time resources.

[0135] The TT&C and data transmission integrated task scheduling strategy of this application for ultra-large-scale constellations lies in fully combining the complex constraints of TT&C and data transmission tasks in the mega constellation, and through the powerful learning and decision-making capabilities of the deep reinforcement learning algorithm, efficiently and reasonably allocating ground station resources for the mega constellation, optimizing the task execution plan, so as to take into account the execution effects of both task types, significantly improve the task satisfaction rate of the system, and enhance the utilization rate of time resources; In summary, through multi-dimensional resource collaborative optimization and dynamic task planning, break through the bottlenecks of traditional scheduling strategies in terms of task capacity, response timeliness, etc., so as to ensure the highly reliable on-orbit operation of the constellation system and the transmission capacity of massive data.

[0136] Corresponding to the above method, the embodiment of this application also provides a planning device for TT&C and data transmission tasks of a mega constellation, as Figure 6 shown. The device includes:

[0137] An acquisition unit 610, configured to acquire the device disabled time set of the ground station, the visible prediction information set, and the total task set of the mega constellation; the device disabled time set includes the disabled periods of each ground station device, the visible prediction information set includes multiple visible prediction information, and the total task set includes multiple tasks of each satellite and corresponding task parameters;

[0138] A determination unit 620, configured to, for any task of any satellite, process the task parameters of the task, the disabled periods of each ground station device, and multiple visible prediction information by using the configured task planning constraint model to determine multiple target visible prediction information;

[0139] And, based on multiple target visible prediction information, determine the task planning solution for the satellite corresponding to the task.

[0140] The functions of the functional units of a planning device for a giant constellation TT&C and data transmission task provided in the above embodiments of the present application can be implemented by the above method steps. Therefore, the specific working processes and beneficial effects of each unit in a planning device for a giant constellation TT&C and data transmission task provided in the embodiments of the present application will not be repeated here.

[0141] The embodiments of the present application also provide an electronic device, as Figure 7 shown, including a processor 710, a communication interface 720, a memory 730, and a communication bus 740. Among them, the processor 710, the communication interface 720, and the memory 730 communicate with each other through the communication bus 740.

[0142] The memory 730 is used to store a computer program;

[0143] When the processor 710 is used to execute the program stored on the memory 730, the following steps are implemented:

[0144] Obtain the device disable time set, visible prediction information set of the ground station, and the total task set of the giant constellation; the device disable time set includes the disable periods of each ground station device, the visible prediction information set includes multiple visible prediction information, and the total task set includes multiple tasks of each satellite and corresponding task parameters;

[0145] For any task of any satellite, using the configured task planning constraint model, process the task parameters of the task, the disable periods of each ground station device, and multiple visible prediction information to determine multiple target visible prediction information;

[0146] Based on the multiple target visible prediction information, determine the task planning scheme of the satellite corresponding to the task.

[0147] The above-mentioned communication bus may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of simplicity, only a thick line is shown in the figure, but it does not mean that there is only one bus or one type of bus.

[0148] The communication interface is used for communication between the above electronic device and other devices.

[0149] The memory may include a Random Access Memory (RAM), or may also include a Non-Volatile Memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0150] The aforementioned processor may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0151] Since the implementation manners and beneficial effects of the various components of the electronic device in the above embodiments can be seen from Figure 2 the steps in the illustrated embodiments, the specific working process and beneficial effects of the electronic device provided in the embodiments of the present application will not be elaborated herein.

[0152] In another embodiment provided by the present application, there is also provided a computer-readable storage medium storing instructions, which when running on a computer, cause the computer to execute the planning method for a giant constellation TT&C and data transmission task described in any one of the above embodiments.

[0153] In another embodiment provided by the present application, there is also provided a computer program product containing instructions, which when running on a computer, cause the computer to execute the planning method for a giant constellation TT&C and data transmission task described in any one of the above embodiments.

[0154] Those skilled in the art should understand that the embodiments in the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the embodiments in the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments in the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program codes.

[0155] Embodiments of the present application are described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or means for implementing the functions specified in multiple blocks.

[0156] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or means for implementing the functions specified in multiple blocks.

[0157] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or means for implementing the functions specified in multiple blocks.

[0158] Unless otherwise defined, the technical terms or scientific terms used in the present application should have the ordinary meanings understood by those of ordinary skill in the field to which the present invention belongs. The terms "first", "second", and similar terms used in the present application do not denote any order, quantity, or importance, but are only used to distinguish different components. Words such as "including" or "comprising" mean that the elements or objects appearing before the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Words such as "connected", "coupled", or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "up", "down", "left", and "right" are only used to indicate relative positional relationships, and when the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0159] Although the preferred embodiments in the embodiments of the present application have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concept. Therefore, the embodiments of the present application are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present application.

[0160] Obviously, those skilled in the art can make various changes and modifications to the embodiments in the embodiments of the present application without departing from the spirit and scope of the embodiments in the embodiments of the present application. Thus, if these modifications and variations of the embodiments in the embodiments of the present application fall within the scope of the embodiments of the present application and their equivalent technologies, the embodiments of the present application are also intended to include these changes and modifications.

Claims

1. A planning method for the measurement and control and data transmission tasks of a giant constellation, characterized in that, The method includes: Obtaining a set of equipment disabling times, a set of visible prediction information, and a total task set of a giant constellation of a ground station; the set of equipment disabling times includes the disabling periods of each ground station equipment, the set of visible prediction information includes multiple visible prediction information, and the total task set includes multiple tasks of each satellite and corresponding task parameters; For any task of any satellite, using the configured task planning constraint model to process the task parameters of the task, the disabling periods of each ground station equipment, and multiple visible prediction information to determine multiple target visible prediction information; Based on the multiple target visible prediction information, determining a task planning scheme for the satellite corresponding to the task; Wherein, the task planning scheme includes: target ground station equipment, target time window, and target orbit number; Based on the multiple target visible prediction information, determining a task planning scheme for the satellite corresponding to the task, including: Based on the multiple target visible prediction information, determining multiple optional orbit numbers corresponding to the corresponding task; Using the deep Q-network algorithm to process the optional orbit number information corresponding to the multiple optional orbit numbers to obtain multiple Q values; Using the ε-greedy strategy to determine the maximum Q value among the multiple Q values; Determining the optional orbit number corresponding to the maximum Q value as the target orbit number; Based on the corresponding relationship between different total orbit numbers and multiple optional arc segments, determining multiple target optional arc segments corresponding to the target orbit number; Based on the corresponding inbound time and outbound time in the multiple optional arc segments, determining multiple time windows for executing the task corresponding to the configured time step; Calculating the lengths of the multiple time windows to obtain the lengths of each time window; Using the greedy strategy to screen the multiple lengths, determining the minimum length, and determining the time window corresponding to the minimum length as the target time window; Based on the corresponding relationship between different optional arc segments and the set of available ground station equipment, determining the set of target available ground station equipment for the optional arc segment corresponding to the target time window; For any available ground station equipment, calculating the disabling durations of the available ground station equipment to obtain the average disabling duration; Based on the average disabling duration and the boundary values of the target time window, determining the time non-disabling factor; Determining the available ground station equipment corresponding to the minimum value among the multiple time non-disabling factors as the set of target available ground station equipment.

2. The method according to claim 1, wherein The target visible prediction information includes: satellite codes corresponding to multiple satellites for executing the corresponding task and orbit visible prediction information corresponding to multiple total orbit numbers; The orbit visible prediction information includes: total orbit number, total number of passes, ascending / descending orbit status, and multiple optional arc segments corresponding to the total orbit number; The optional arc segment includes: inbound pitch angle, inbound time, highest elevation pitch angle, highest elevation time, outbound pitch angle, outbound time, and the set of available ground station equipment corresponding to the optional arc segment; The set of ground station equipment includes: multiple available ground station equipment.

3. The method according to claim 1, characterized in that, After completing the task of the satellite corresponding to any time step based on the task planning scheme, the method further includes: Determining the target success rate of each task planning scheme within the time step; Determine the target reward value of the target success rate based on the corresponding relationship between different success rates and different reward values; Determine an experience tuple based on the target success rate, target reward value, optional loop count information of this time step, and the optional loop count information of the next time step of this time step; When multiple time steps are completed, multiple experience tuples are obtained; Calculate the parameters in multiple experience tuples to obtain a target value; Calculate the target value to obtain the target network parameters of the deep Q-network algorithm.

4. A planning device for the measurement and control and data transmission tasks of a giant constellation, characterized in that, The device includes: An acquisition unit, configured to acquire a device disable time set of a ground station, a visible prediction information set, and a total task set of a mega constellation; the device disable time set includes the disable periods of each ground station device, the visible prediction information set includes multiple visible prediction information, and the total task set includes multiple tasks of each satellite and corresponding task parameters; A determination unit, configured to, for any task of any satellite, process the task parameters, the disable periods of each ground station device, and multiple visible prediction information by using a configured task planning constraint model to determine multiple target visible prediction information; And determine a task planning scheme for the satellite corresponding to the task based on the multiple target visible prediction information; Wherein, the task planning scheme includes: a target ground station device, a target time window, and a target loop count; Determine a task planning scheme for the satellite corresponding to the task based on multiple target visible prediction information, including: Determine multiple optional loop counts corresponding to the corresponding task based on the multiple target visible prediction information; Use the deep Q-network algorithm to process the optional loop count information corresponding to the multiple optional loop counts to obtain multiple Q values; Use the ε-greedy strategy to determine the maximum Q value among the multiple Q values; Determine the optional loop count corresponding to the maximum Q value as the target loop count; Determine multiple target optional arc segments corresponding to the target loop count based on the corresponding relationship between different total loop counts and multiple optional arc segments; Determine multiple time windows for executing tasks corresponding to the configured time step based on the corresponding inbound time and outbound time in the multiple optional arc segments; Calculate the lengths of the multiple time windows to obtain the lengths of each time window; Use the greedy strategy to screen the multiple lengths, determine the minimum length, and determine the time window corresponding to the minimum length as the target time window; Determine the target available ground station device set of the optional arc segment corresponding to the target time window based on the corresponding relationship between different optional arc segments and the available ground station device set; For any available ground station device, calculate the disable durations of the available ground station device to obtain an average disable duration; Determine a time non-disable factor based on the average disable duration and the boundary values of the target time window; Determine the available ground station device corresponding to the minimum value among the multiple time non-disable factors as the target available ground station device set.

5. An electronic device, characterized in that, The electronic device includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; The memory is used for storing a computer program; A processor, when executing a program stored in a memory, implements the method steps described in any one of claims 1-3.

6. A computer-readable storage medium, characterized in that, A computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the method steps described in any one of claims 1-3 are implemented.

Images