Planning method and device of giant satellite base measurement and control data transmission task, electronic equipment and medium

Abstract

The invention provides a giant satellite base measurement and control data transmission task planning method and device, electronic equipment and a medium, and relates to the technical field of multi-satellite task planning. A measurement and control data transmission integrated task scheduling strategy for a super-large-scale constellation aims at fully combining complex constraints of measurement and control and data transmission tasks in a giant satellite base; ground station resources are efficiently and reasonably allocated for the giant satellite base and a task execution scheme is optimized through the powerful learning and decision-making capability of a deep reinforcement learning algorithm, so that the execution effects of two task types are considered, the task satisfaction rate of the system is remarkably improved, and the utilization rate of time resources is improved; in conclusion, through multi-dimensional resource collaborative optimization and dynamic task planning, the bottlenecks of a traditional scheduling strategy in the aspects of task capacity, response timeliness and the like are broken through, and therefore the high-reliability in-orbit operation and mass data transmission capacity of a constellation system are ensured.

Description

Technical Field

[0001] The present application relates to the technical field of multi-satellite mission planning, and in particular to a planning method, device, electronic equipment and medium for a superstar constellation measurement, control and data transmission mission. Background Art

[0002] With the revolutionary breakthroughs in aerospace technology and the in-depth expansion of space information application scenarios, the networking deployment and collaborative application of large-scale constellation systems have become a strategic commanding height for the global aerospace industry. As the core technical system supporting the stable operation of the constellation system in orbit, the collaborative scheduling efficiency of measurement and control link maintenance and data transmission service assurance is directly related to the task execution efficiency of giant constellations. Traditional ground station systems generally adopt a scheduling mode that separates measurement and control from data transmission tasks. There are problems such as low equipment resource utilization, which makes it difficult to meet the normalization needs of high-density constellation clusters. As satellite ground stations show the characteristics of integrated measurement, control and data transmission, ground station equipment has begun to support the simultaneous execution of measurement and control tasks and data transmission tasks of the same satellite. Figure 1 The system architecture of the Giant Star constellation with integrated measurement, control and data transmission is presented. The measurement and control center and the application center send the mission requirements to the mission management center. After the mission planning, the Giant Star constellation communicates with the ground station through the measurement and control link and the data transmission link, and then transmits the data back to the ground. Mission planning plays a key role in optimizing resource allocation and mission execution process in the system.

[0003] At present, the methods are still focused on small and medium-scale scenarios. There is no systematic solution for the task scheduling of the giant star constellation, and the equipment characteristics of integrated measurement, control and data transmission are not considered. Therefore, when faced with the huge number of satellites and complex mission requirements of the giant star constellation, problems gradually emerge, such as poor exploration capabilities and inability to meet complex constraints. At the same time, it is difficult to achieve coordinated optimization between measurement, control and data transmission tasks, which seriously affects the overall execution efficiency of the giant star constellation mission. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a planning method, device, electronic equipment and medium for the measurement, control and data transmission mission of the giant star constellation, so as to solve the above-mentioned problems existing in the prior art and ensure the high-reliability on-orbit operation of the constellation system and the transmission capability of massive data.

[0005] In a first aspect, a planning method for a giant star constellation measurement and control data transmission task is provided, and the method may include:

[0006] Acquire a device disabled time set, a visible forecast information set, and a total task set of the giant star constellation of the ground station; the device disabled time set includes a disabled period of each ground station device, the visible forecast information set includes a plurality of visible forecast information, and the total task set includes a plurality of tasks and corresponding task parameters of each satellite;

[0007] For any mission of any satellite, the configured mission planning constraint model is used to process the mission parameters, the disabled time period of each ground station equipment and multiple visible forecast information of the mission, and determine the visible forecast information of multiple targets;

[0008] Based on the visible forecast information of multiple targets, the mission planning scheme of the satellite corresponding to the mission is determined.

[0009] In a possible implementation, the target visibility forecast information includes: satellite codes corresponding to a plurality of satellites performing corresponding tasks and circle visibility forecast information corresponding to a plurality of total circles;

[0010] The circle visible forecast information includes: total circles, total number of mirror passes, ascending and descending orbit states and multiple optional arcs corresponding to the total circles;

[0011] The optional arc segment includes: the approaching pitch angle, the approaching time, the highest elevation pitch angle, the highest elevation time, the departure pitch angle, the departure time and the available ground station equipment set corresponding to the optional arc segment;

[0012] The ground station device set includes: a plurality of available ground station devices.

[0013] In a possible implementation, the mission planning scheme includes: target ground station equipment, target time window and target number of turns;

[0014] Based on the visible forecast information of multiple targets, the mission planning scheme for the satellite corresponding to the mission is determined, including:

[0015] Based on the visible forecast information of multiple targets, multiple optional laps of the corresponding task are determined;

[0016] The deep Q network algorithm is used to process the optional circle information corresponding to each optional circle to obtain the target circle;

[0017] Based on the target number of laps and the greedy strategy, determining a target time window;

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

[0019] In a possible implementation, a deep Q network algorithm is used to process multiple optional rounds to obtain a target round, including:

[0020] A deep Q network algorithm is used to process the optional circle information corresponding to multiple optional circles to obtain multiple Q values;

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

[0022] The optional round number corresponding to the maximum Q value is determined as the target round number.

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

[0024] Based on the correspondence between different total laps and multiple optional arcs, determine multiple target optional arcs corresponding to the target laps;

[0025] Based on the corresponding entry and exit times in the multiple optional arcs, determine multiple time windows for executing the task corresponding to the configured time steps;

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

[0027] A greedy strategy is adopted to screen 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] Determine a target available ground station device set for the optional arc segment corresponding to the target time window based on the correspondence between different optional arc segments and available ground station device sets;

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

[0031] Determine a time non-banning factor based on the ban duration average value and a boundary value of the target time window;

[0032] The available ground station device corresponding to the minimum value of the multiple time non-disabled factors is determined as the target available ground station device set.

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

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

[0035] Determining a target reward value for the target success rate based on a correspondence between different success rates and different reward values;

[0036] Determine an experience tuple based on the target success rate, target reward value, optional lap information of the time step, and optional lap information of the next time step of the time step;

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

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

[0039] The target value is calculated to obtain the target network parameters of the deep Q network algorithm.

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

[0041] an acquisition unit, configured to acquire a device disabled time set, a visible forecast information set, and a total task set of a giant star constellation of a ground station; the device disabled time set includes a disabled period of each ground station device, the visible forecast information set includes a plurality of visible forecast information, and the total task set includes a plurality of tasks and corresponding task parameters of each satellite;

[0042] A determination unit is used for processing the mission parameters, the disabled time period of each ground station equipment and the multiple visible forecast information of the mission for any mission of any satellite by using the configured mission planning constraint model, and determining the multiple target visible forecast information;

[0043] And, based on the visible forecast information of multiple targets, determine the mission planning plan of the satellite corresponding to the mission.

[0044] In a third aspect, an electronic device is provided, the electronic device comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

[0045] Memory, used to store computer programs;

[0046] The processor is used to implement any method step described in the first aspect when executing the program stored in the memory.

[0047] In a fourth aspect, a computer-readable storage medium is provided, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, any method step described in the first aspect is implemented.

[0048] The integrated measurement, control and data transmission task scheduling strategy for ultra-large-scale constellations in this application is to fully combine the complex constraints of measurement, control and data transmission tasks in the giant star constellation, and through the powerful learning and decision-making capabilities of the deep reinforcement learning algorithm, efficiently and reasonably allocate ground station resources for the giant star constellation, optimize the task execution plan, thereby taking into account the execution effects of the two types of tasks, significantly improving the system's task satisfaction rate, and improving 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 and response timeliness, thereby ensuring the high reliability of the constellation system on-orbit and the transmission capacity of massive data. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0050] Figure 1 A diagram of the architecture of a giant star system with integrated measurement, control, and data transmission provided in an embodiment of the present application;

[0051] Figure 2 A flowchart of a method for planning a giant star constellation measurement and control data transmission task provided in an embodiment of the present application;

[0052] Figure 3 A schematic diagram of a time window provided in an embodiment of the present application;

[0053] Figure 4 A schematic diagram comparing the task satisfaction rates of different solutions for processing multi-satellite tasks provided in the embodiments of the present application;

[0054] Figure 5 A schematic diagram comparing the proportion of undisabled whole-block idle resources of the single-stage DQN algorithm provided in the embodiment of the present application and the present solution;

[0055] Figure 6 A schematic diagram of the structure of a planning device for a giant star constellation measurement and control data transmission task provided in an embodiment of the present application;

[0056] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0057] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0058] With the revolutionary breakthroughs in aerospace technology and the in-depth expansion of space information application scenarios, the networking deployment and collaborative application of large-scale constellation systems have become a strategic commanding height for the global aerospace industry. As the core technical system supporting the stable operation of the constellation system in orbit, the collaborative scheduling efficiency of measurement and control link maintenance and data transmission service assurance is directly related to the task execution efficiency of giant constellations. Traditional ground station systems generally adopt a scheduling mode that separates measurement and control from data transmission tasks. There are problems such as low equipment resource utilization, which makes it difficult to meet the normalization needs of high-density constellation clusters. As satellite ground stations show the characteristics of integrated measurement, control and data transmission, ground station equipment has begun to support the simultaneous execution of measurement and control tasks and data transmission tasks of the same satellite. Figure 1 The system architecture of the Giant Star constellation with integrated measurement, control and data transmission is presented. The measurement and control center and the application center send the mission requirements to the mission management center. After the mission planning, the Giant Star constellation communicates with the ground station through the measurement and control link and the data transmission link, and then transmits the data back to the ground. Mission planning plays a key role in optimizing resource allocation and mission execution process in the system.

[0059] At present, task planning methods mainly include mathematical programming methods, graphical model search algorithms, heuristic algorithms and metaheuristic algorithms. Among mathematical programming methods, integer linear programming and mixed integer programming are more common. Although some studies have solved them by constructing corresponding problem models and using iterative algorithms, Lagrangian relaxation and linear search techniques, they are only applicable to small-scale scenarios due to their high time complexity. The graphical model search algorithm transforms task planning into a graph search problem by establishing vertex sets and edge sets, such as using graph coloring theory to model and solving it with the help of taboo search algorithms and ant colony optimization algorithms. Heuristic algorithms are an effective means to solve NP-hard combinatorial optimization problems. The core of heuristic algorithms is to achieve efficient solutions to approximate optimal solutions based on experience and domain knowledge through intelligent search strategies and domain knowledge guidance, such as genetic algorithms and artificial bee colony algorithms, which are widely used in practical problems.

[0060] However, current methods are still focused on small and medium-scale scenarios. There is no systematic solution for the task scheduling of the Giant Star Constellation, and the equipment characteristics of integrated measurement, control and data transmission are not considered. Therefore, when faced with the huge number of satellites and complex mission requirements of the Giant Star Constellation, problems gradually emerged, including poor exploration capabilities and inability to meet complex constraints. At the same time, it is difficult to achieve coordinated optimization between measurement, control and data transmission tasks, which seriously affects the overall execution efficiency of the Giant Star Constellation mission.

[0061] Therefore, the present application provides a planning method for the measurement, control and data transmission tasks of the Giant Star Constellation, which is used to solve the above-mentioned problems existing in the prior art and can ensure the high-reliability on-orbit operation of the constellation system and the transmission capability of massive data.

[0062] The preferred embodiments of the present application are described below in conjunction with the drawings in 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. In addition, the embodiments and features in the embodiments of the present application may be combined with each other if there is no conflict.

[0063] Figure 2 The following is a flow chart of a method for planning a giant star constellation measurement and control data transmission task provided in an embodiment of the present application. Figure 2 As shown, the method may include:

[0064] Step S210, obtaining the equipment disabled time set, the visible forecast information set and the total task set of the giant star constellation of the ground station.

[0065] Among them, the equipment disabled time set includes the disabled time period of each ground station equipment, the visible forecast information set includes multiple visible forecast information, which are the satellites and their operating parameters expected to be observed by the ground station; the total task set includes multiple tasks of each satellite and corresponding task parameters.

[0066] Specifically, the planning of the measurement, control and data transmission mission is to fully consider the integrated characteristics of the measurement, control and data transmission of the ground station resources, determine the time to execute the satellite mission, and allocate ground station resources to the satellite mission to meet the mission requirements of the Superstar constellation as much as possible.

[0067] The ground station equipment set of integrated measurement, control and data transmission is D = {d 1 ,d 2 ,…,d S};d i Indicates the equipment information of the i-th ground station, Among them, d i Indicates the number of the ground station. Indicates the functions supported by the ground station device. i similar, in, It means that the ground station equipment can only perform measurement and control tasks; It means that the ground station equipment can only perform data transmission tasks; It means that the ground station equipment can perform both measurement and control and data transmission tasks, but not both tasks at the same time; It means that the ground station equipment can perform the measurement and control tasks and data transmission tasks of a satellite at the same time.

[0068] A. The overall task set can be expressed as: J = {j 1 ,j 2 ,…,j N};

[0069] The i-th task Among them, s i Indicates satellite code, typ i Indicates the task type, typ i ∈{1,2},typ i =1 means the task is a measurement and control task, typ i =2 means the task is a data transmission task. i Indicates the link establishment time, dis i Indicates the chain removal time. Indicates the minimum value of the highest elevation angle to be tracked, con i Indicates the constraint definition method (known quantity), Indicates the lower offset of the allowed range. Indicate the most desired time / lap, Indicates the upper offset of the allowed range;

[0070] It is understandable that the task parameters mentioned above are: i , type i , pre i ,dis i , con i , D.

[0071] B. The visible forecast information set is the set of foreseeable information expected to be observed by the ground station; the visible forecast information set can be expressed as: F = {f 1 ,f 2 ,…,f L};

[0072] For the i-th visible forecast information Among them, s i represents the satellite code, d i Indicates the device code. Indicates the total number of laps, Indicates the total number of transit circles (the number of consecutive circles visible in this territory), rf i Indicates the state of the lifting rail. Indicates the approach pitch angle, Indicates the time of entering the station. Indicates the highest elevation pitch angle, Indicates the moment of highest elevation angle, Indicates the outbound pitch angle, Indicates the departure time.

[0073] C. The device disabled time set is a set of disabled time information of each device in the ground station. The device disabled time set can be expressed as: DT = {dt 1 ,dt 2 ,…,dt S}; The i-th disabled time information and It is the boundary value (start and end time points) of the Kth prohibited period in the i-th prohibited time information.

[0074] It should be noted that, combined with Figure 3 As shown in the figure, when the forecast information for a certain task is selected, assuming that the satellite s i The visible forecast start and end time is Consider the corresponding satellite s i The length of the chain establishment and chain removal is extended to the start time of tracking i seconds, delay dis after tracking end time j seconds, respectively, as the start time of the forecast time window ms i and the end moment me i , that is, [ms i ,me i ].

[0075] Specifically, the start time and end time are calculated as follows:

[0076]

[0077] Step S220: For any mission of any satellite, the configured mission planning constraint model is used to process the mission parameters of the mission, the disabled time period of each ground station equipment and multiple visible forecast information, and determine the visible forecast information of multiple targets.

[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 type i =type j ,i≠j

[0082] Among them, C1 represents the maximum elevation angle constraint, which shows 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 the time window for the equipment to execute the task does not overlap with the corresponding disabled time interval; C4 represents the time window constraint, and the time intervals occupied by different satellites on the same ground station equipment do not overlap, except when the ground station equipment supports simultaneous measurement, control and data transmission, and the same satellite simultaneously executes measurement, control and data transmission tasks. C5 represents the satellite circle constraint, and the same satellite in the same circle will not arrange two circles of the same type (measurement, control or data transmission) tasks. Task planning scheme P = {P 1 ,P 2 ,…,P i ,…,P N}, where the solution P for the i-th task i ={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 Indicates the target number of laps, ms i and me i Indicates the boundary value of the target time window.

[0083] Among them, the rotation position constraint The details are as follows:

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

[0085] (2) Constraints It means when con i =1,

[0086] (3) Constraints For the i =2 and hour, constraint For the i =2 and hour,

[0087] (4) Constraints For the i =3 and When the visible forecast ascending and descending orbit state is selected, it must be an ascending orbit arc segment and must satisfy constraint For thei =3 and When the visible forecast ascending and descending orbit state is selected, it must be an ascending orbit arc segment and must satisfy

[0088] (5) Constraints For the i =4 and When the selected visible forecast ascending and descending orbit state must be a descending orbit arc segment and must satisfy constraint For the i =4 and When the selected visible forecast ascending and descending orbit state must be a descending orbit arc segment and must satisfy Where T represents the time of a day in seconds, s 0 Indicates the offset factor.

[0089] The task planning constraint model models the task planning problem to be solved as a constrained optimization problem to clarify the task objectives, make the constraints transparent, and ensure that the optimal solution is found, thereby enhancing the credibility of the solution.

[0090] Specifically, firstly, the specific parameters in the multiple visible forecast information of all missions corresponding satellites are processed according to the orbit, time window and available ground station equipment to obtain the initial visible forecast set F ′ ={f 1 ′,f 2 ′,…,f N ′}; The initial visible forecast set contains multiple initial visible forecast information f i ′ ; The initial visible forecast information f corresponding to the i-th task i ′, the total number of all the cycles is L 1 ,Right now Among them, REV i Indicates rev of laps t i otal The same series of circles visible forecast information; L 2 Indicates the total number of time windows. i Indicates the number of laps The i-th optional arc ARC in i ={ang 0 ,t 0 ,ang 1 ,t 1 ,ang 2 ,t 2 ,D i}, in this optional arc segment set, D iRepresents arc segment ARC i The set of available ground station equipment that can be occupied within the time window is:

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

[0092] Afterwards, the task planning constraint model is used to process the task parameters of the currently processed task, the disabled time period of each ground station equipment, and the initial visible forecast set to obtain multiple target visible forecast information that meets the preset constraint conditions. Among them, the order in which the task planning constraint model processes each task is based on the order in which each task is arranged in the total task set;

[0093] That is to say, the target visibility forecast information includes: satellite codes corresponding to the satellites performing the corresponding tasks and circle visibility forecast information corresponding to a plurality of total circles;

[0094] The visible prediction information of the circle number includes: total circle number, total number of transit circles, ascending and descending orbit status and multiple optional arc segments corresponding to the total circle number; that is, the corresponding relationship between different total circle numbers and multiple optional arc segments is determined;

[0095] The optional arc segment includes: the approaching pitch angle, the approaching time, the highest elevation pitch angle, the highest elevation time, the departure pitch angle, the departure time and the available ground station equipment set corresponding to the optional arc segment; that is, the corresponding relationship between different optional arc segments and the available ground station equipment set is determined;

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

[0097] This method is to filter the initial visible forecast information in the classified initial visible forecast set through the preset constraints and the acquired known data through the task planning constraint model, and obtain the target visible forecast information that meets the preset constraints in the current task. It can be understood that the structure of the initial visible forecast set is the same as that of the target visible forecast information.

[0098] Step S230: Determine a mission planning scheme for the satellite corresponding to the mission based on the visible forecast information of multiple targets.

[0099] Specifically, step 23-1: based on the visible forecast information of multiple targets, determine multiple optional turns corresponding to the task; transform the task decision into a Markov decision process, use a deep Q network algorithm to process the optional turn information corresponding to each optional turn, and obtain the target turn;

[0100] Among them, the Deep Q-Network (DQN) algorithm framework is built and initialized, and a fully connected network is used as a function approximator to generate a Q-value function Q(s) corresponding to the state and action through a deep neural network (DNN). t ,a t ; θ), i.e., the Q network, where θ is the DNN parameter. Initialize the agent's Q network and target network with random parameters. Set parameters such as the number of cycles, time step length, batch size, experience pool capacity, discount factor, and learning rate. One cycle is the entire planning of the total task, where one task is planned in each time step, and the agent interacts with the task planning environment.

[0101] The specific process can be as follows: for any configured time step t, the optional lap information s of the corresponding task t ={typ t ,rev t ,REV t} is determined as the current state; among them, rev t is a set of m cycles that meet the preset constraints, REV t Contains all the time window information corresponding to the m rounds in the current task visible forecast that meet the preset constraints Indicates the kth time in the i-th cycle i time window, i.e. The agent generates the current state as a state vector and inputs the state vector into the Q network to obtain the Q value; if the task cannot be performed, the target round a t =0.

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

[0103] Afterwards, the ε-greedy strategy is adopted to randomly select multiple optional rounds based on the configured first probability ε; based on the configured second probability 1-ε, the action corresponding to the maximum Q value is selected from multiple Q values; that is, the optional round corresponding to the maximum Q value is determined as the target round.

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

[0105] Specifically, based on the correspondence between different total laps and multiple optional arcs, multiple target optional arcs corresponding to the target laps are determined;

[0106] Based on the corresponding entry and exit times in the multiple optional arcs, multiple time windows for executing the task corresponding to the configured time steps are determined;

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

[0108] A greedy strategy is adopted 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 assuming that at the time step t, there are several time windows in the round selected by the agent. Among them, T i =[ms i ,me i ] Calculate the length d of all time windows i , that is, d i =me i -ms i . A greedy strategy is used to select the time window with the shortest length, namely:

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

[0111] Specifically, based on the correspondence between different optional arcs and available ground station equipment sets, a target available ground station equipment set of the optional arc corresponding to the target time window is determined;

[0112] For any available ground station device, calculate each disabled time of the available ground station device to obtain an average disabled time;

[0113] Determine the time non-ban factor based on the average ban duration and the boundary value of the target time window;

[0114] The available ground station device corresponding to the minimum value of multiple time non-disabled factors is determined as the target available ground station device set.

[0115] This method can be understood as follows: after determining the time window [s, e], a load balancing algorithm based on time fine-grained analysis is used to make decisions on ground station selection. Define the time non-disable factor to measure the proportion of each available ground station device occupied during the non-disabled time. If the selected available ground station devices are arranged in ascending order of disabled time as dt t ={st 1 ,et 1 ,st 2 ,et 2 ,…,st m ,etm}, the time non-disabling factor of the i-th optional device is:

[0116]

[0117] Among them, T abd Indicates the average disabled duration, i.e. According to the time non-disabling factor of each device, select the device with the smallest time non-disabling factor, that is:

[0118] In summary, the task planning scheme for the currently processed task is obtained, and then the steps are returned to: the task planning constraint model is used to process the task parameters of the next task, the disabled period of each ground station equipment, and the initial visible forecast set, and the visible forecast information of multiple targets that meet the preset constraints is obtained. Among them, the next task is the next task of the currently processed task in the total task set.

[0119] When the d in the mission planning scheme for all missions corresponding to the satellite within the time step is determined i ,rev i ,ms i and me i Afterwards, based on d i ,rev i ,ms i and me i Execute the task and count the execution results x i .

[0120] After completing the tasks of all satellites corresponding to any time step, the method may further include:

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

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

[0123]

[0124] Among them, tr t represents the target success rate of the measurement and control task at the current time step, dr t Represents the target success rate of the data transmission task at the current time step.

[0125] Afterwards, the environment will enter a new state s t+1 , based on the target success rate, target reward value, optional lap information of this time step and the optional lap 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 multiple experience tuples to obtain the target value;

[0128] This method uses a memory playback 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 in, represents the target network parameters of the agent. During training, each agent samples n experience tuples from the experience pool, i.e. (s j ,a j ,r j ,s j+1 ),j=1,2,…,n, calculate the target value, that is:

[0129]

[0130] Where γ is the discount factor. Then the mean square error loss is calculated and the Q network is trained using the adaptive moment estimation method. Finally, the network parameters θ are updated, and the updated weights θ of the Q network are copied to the target network parameters every C time steps

[0131] After completing a cycle of training, the total reward value is calculated, the task planning environment is reset, and a new round of cycle training begins. After multiple cycles of training, the DQN-greedy strategy-time load balancing task planning algorithm constructed in this application will converge to obtain the optimal planning solution.

[0132] This application fully considers the complex constraints such as the support relationship between different types of equipment in the integrated measurement, control and data transmission scenario, and adopts a phased decision-making model to disassemble the solution space layer by layer. The intelligent agent determines the number of satellite mission execution circles, and then the greedy algorithm for the length of the time window and the load balancing algorithm based on time fine-grained analysis make decisions on the time window and ground station equipment respectively, and collaborates with DQN to optimize the overall planning plan, and generates global rewards based on the task satisfaction to feedback to the intelligent agent, thereby effectively improving the measurement, control and data transmission task satisfaction rate and the proportion of idle resources as a whole.

[0133] In a specific example, the scheme is applied in Figure 1In the illustrated system architecture of the integrated measurement, control and data transmission of the Giant Star constellation, the total number of satellites is 400, the total number of tasks is 19840, of which the number of measurement and control tasks is 12800, the number of data transmission tasks is 7040, 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 supporting measurement, control and data transmission is 16. During the simulation process, the solution of the present application is used for task planning, and the task satisfaction rates of measurement, control and data transmission are calculated respectively.

[0134] Under the above simulation conditions, this example simulates the number of satellites from 320 to 400, with an interval of 10, point by point, and obtains the task satisfaction rate of measurement and control and data transmission under different numbers of satellites. The performance of this scheme is compared with the existing genetic algorithm, artificial bee colony algorithm and single-stage DQN algorithm task planning scheme. The comparison results are shown in Figure 2. Figure 4 As shown in the figure, the red dots and triangular curves are the simulation results of the measurement and control and data transmission of this application. It can be seen that this solution can significantly improve the task satisfaction rate of measurement and control and data transmission. The proportion of undisabled whole blocks of idle resources in this solution is calculated, that is, the proportion of non-occupied time longer than 600s to all non-disabled time, and compared with the solution of the single-stage DQN algorithm. The results are as follows Figure 5 As shown in the figure, while the proposed scheme has an obvious advantage in task satisfaction rate, its percentage of idle resources that are not disabled is also better than that of the single-stage DQN algorithm, indicating that the proposed scheme can optimize the utilization of time resources.

[0135] The integrated measurement, control and data transmission task scheduling strategy for ultra-large-scale constellations in this application is to fully combine the complex constraints of measurement, control and data transmission tasks in the giant star constellation, and through the powerful learning and decision-making capabilities of the deep reinforcement learning algorithm, efficiently and reasonably allocate ground station resources for the giant star constellation, optimize the task execution plan, thereby taking into account the execution effects of the two types of tasks, significantly improving the system's task satisfaction rate, and improving 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 and response timeliness, thereby ensuring the high reliability of the constellation system on-orbit and the transmission capacity of massive data.

[0136] Corresponding to the above method, the embodiment of the present application also provides a planning device for the measurement and control data transmission task of the giant star constellation, such as Figure 6 As shown, the device comprises:

[0137] An acquisition unit 610 is used to acquire a device disabled time set, a visible forecast information set, and a total task set of a giant star constellation of a ground station; the device disabled time set includes a disabled period of each ground station device, the visible forecast information set includes a plurality of visible forecast information, and the total task set includes a plurality of tasks and corresponding task parameters of each satellite;

[0138] The determination unit 620 is used to process the mission parameters, the disabled time period of each ground station equipment and the multiple visible forecast information of any mission of any satellite using the configured mission planning constraint model to determine the multiple target visible forecast information;

[0139] And, based on the visible forecast information of multiple targets, determine the mission planning plan of the satellite corresponding to the mission.

[0140] The functions of the various functional units of the planning device for the giant star constellation measurement, control and digital transmission tasks provided in the above-mentioned embodiment of the present application can be realized through the above-mentioned method steps. Therefore, the specific working process and beneficial effects of each unit in the planning device for the giant star constellation measurement, control and digital transmission tasks provided in the embodiment of the present application will not be repeated here.

[0141] The present application also provides an electronic device, such as Figure 7 As shown, it includes a processor 710 , a communication interface 720 , a memory 730 and a communication bus 740 , wherein the processor 710 , the communication interface 720 , and the memory 730 communicate with each other via the communication bus 740 .

[0142] Memory 730, for storing computer programs;

[0143] The processor 710 is used to execute the program stored in the memory 730 to implement the following steps:

[0144] Acquire a device disabled time set, a visible forecast information set, and a total task set of the giant star constellation of the ground station; the device disabled time set includes a disabled period of each ground station device, the visible forecast information set includes a plurality of visible forecast information, and the total task set includes a plurality of tasks and corresponding task parameters of each satellite;

[0145] For any mission of any satellite, the configured mission planning constraint model is used to process the mission parameters, the disabled time period of each ground station equipment and multiple visible forecast information of the mission, and determine the visible forecast information of multiple targets;

[0146] Based on the visible forecast information of multiple targets, the mission planning scheme of the satellite corresponding to the mission is determined.

[0147] The communication bus mentioned above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used 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 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 above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can 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] The implementation methods and beneficial effects of the components of the electronic device in the above embodiments to solve the problems can be seen in Figure 2 The various steps in the illustrated embodiment are implemented, therefore, the specific working process and beneficial effects of the electronic device provided by the embodiment of the present application are not repeated here.

[0152] In another embodiment provided in the present application, a computer-readable storage medium is also provided, in which instructions are stored. When the computer-readable storage medium is executed on a computer, the computer executes a planning method for a giant star constellation measurement and control data transmission task as described in any of the above embodiments.

[0153] In another embodiment provided in the present application, a computer program product including instructions is also provided, which, when executed on a computer, enables the computer to execute a planning method for a giant star constellation measurement and control data transmission task as described in any one of the above embodiments.

[0154] Those skilled in the art will appreciate that the embodiments in the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt a complete hardware embodiment, a complete software embodiment, or a form of an embodiment combining software and hardware. Moreover, the present application may adopt a form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0155] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0156] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0157] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0158] Unless otherwise defined, the technical terms or scientific terms used in this application should be understood by people with ordinary skills in the field to which the present invention belongs. "First", "second" and similar words used in this application do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words 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. "Connect", "couple" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

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

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

Claims

1. A planning method for the measurement and control data transmission task of the giant star constellation, characterized in that: The method comprises: Acquire a device disabled time set, a visible forecast information set, and a total task set of the giant star constellation of the ground station; the device disabled time set includes a disabled period of each ground station device, the visible forecast information set includes a plurality of visible forecast information, and the total task set includes a plurality of tasks and corresponding task parameters of each satellite; For any mission of any satellite, the configured mission planning constraint model is used to process the mission parameters, the disabled time period of each ground station equipment and multiple visible forecast information of the mission, and determine the visible forecast information of multiple targets; Based on the visible forecast information of multiple targets, the mission planning scheme of the satellite corresponding to the mission is determined.

2. The method according to claim 1, characterized in that The target visible forecast information includes: satellite codes corresponding to multiple satellites performing corresponding tasks and circle visible forecast information corresponding to multiple total circles; The circle visible forecast information includes: total circles, total number of mirror passes, ascending and descending orbit states and multiple optional arcs corresponding to the total circles; The optional arc segment includes: the approaching pitch angle, the approaching time, the highest elevation pitch angle, the highest elevation time, the departure pitch angle, the departure time and the available ground station equipment set corresponding to the optional arc segment; The ground station device set includes: a plurality of available ground station devices.

3. The method according to claim 1, characterized in that The mission planning scheme includes: target ground station equipment, target time window and target number of laps; Based on the visible forecast information of multiple targets, the mission planning scheme for the satellite corresponding to the mission is determined, including: Based on the visible forecast information of multiple targets, multiple optional laps of the corresponding task are determined; The deep Q network algorithm is used to process the optional circle information corresponding to each optional circle to obtain the target circle; Based on the target number of laps and the greedy strategy, determining a target time window; Based on the target time window and the load balancing algorithm, a target ground station device is determined.

4. The method according to claim 3, characterized in that The deep Q network algorithm is used to process multiple optional rounds to obtain the target rounds, including: A deep Q network algorithm is used to process the optional circle information corresponding to multiple optional circles to obtain multiple Q values; Adopt ε-greedy strategy to determine the maximum Q value among multiple Q values; The optional round number corresponding to the maximum Q value is determined as the target round number.

5. The method according to claim 3, characterized in that Based on the target number of laps and the greedy strategy, a target time window is determined, including: Based on the correspondence between different total laps and multiple optional arcs, determine multiple target optional arcs corresponding to the target laps; Based on the corresponding entry and exit times in the multiple optional arcs, determine multiple time windows for executing the task corresponding to the configured time steps; Calculating the lengths of the multiple time windows to obtain the length of each time window; A greedy strategy is adopted to screen multiple lengths, determine the minimum length, and determine the time window corresponding to the minimum length as the target time window.

6. The method according to claim 3, characterized in that Based on the target time window and the load balancing algorithm, determining the target ground station device includes: Determine a target available ground station device set for the optional arc segment corresponding to the target time window based on the correspondence between different optional arc segments and available ground station device sets; For any available ground station device, calculate each disabled time of the available ground station device to obtain an average disabled time; Determine a time non-banning factor based on the ban duration average value and a boundary value of the target time window; The available ground station device corresponding to the minimum value of the multiple time non-disabled factors is determined as the target available ground station device set.

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

8. A planning device for the measurement, control and data transmission task of a giant star constellation, characterized in that: The device comprises: an acquisition unit, configured to acquire a device disabled time set, a visible forecast information set, and a total task set of a giant star constellation of a ground station; the device disabled time set includes a disabled period of each ground station device, the visible forecast information set includes a plurality of visible forecast information, and the total task set includes a plurality of tasks and corresponding task parameters of each satellite; A determination unit is used for processing the mission parameters, the disabled time period of each ground station equipment and the multiple visible forecast information of the mission for any mission of any satellite by using the configured mission planning constraint model, and determining the multiple target visible forecast information; And, based on the visible forecast information of multiple targets, determine the mission planning plan of the satellite corresponding to the mission.

9. An electronic device, characterized in that: The electronic device comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; Memory, used to store computer programs; A processor, for implementing the method steps described in any one of claims 1 to 7 when executing a program stored in a memory.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method steps described in any one of claims 1 to 7 are implemented.

Images