A Multi-Agent Cooperative Scheduling and Control Method, Device, Equipment and Computer Readable Storage Medium for Satellite Ground System

Abstract

The present invention relates to the technical field of collaborative scheduling control, and discloses a multi-agent collaborative scheduling control method, device, equipment and computer-readable storage medium for a satellite ground system. Remote sensing data, task requirements, etc. are respectively input into the main agent and the backup agent to obtain the tasks and job execution results output by the main agent and the tasks and job execution results output by the backup agent. It is judged whether the tasks and job execution results output by the main agent reach the preset results. If so, the tasks and job execution results output by the main agent are input into the remote sensing data service system. If not, the tasks and job execution results output by the backup agent are input into the remote sensing data service system. When the main agent fails to reach the preset results in terms of tasks and job execution results, the backup agent can quickly take over the tasks to ensure the continuous and stable operation of the satellite ground system.

Description

Technical Field

[0001] The present invention relates to the technical field of collaborative scheduling control, and particularly to a multi-agent collaborative scheduling control method, device, equipment and computer-readable storage medium for a satellite ground system. Background Art

[0002] Currently, with the development of satellite technology, there are more and more satellites in the sky above the earth capturing remote sensing data related to the earth. These remote sensing data contain rich geographical information. Therefore, the analysis and utilization of remote sensing data have been increasingly emphasized.

[0003] However, with the increasing complexity of the observation systems on satellites and the processing requirements of remote sensing data, after the ground station receives the remote sensing data transmitted by the satellite, the ground system has difficulty meeting the increasingly complex processing requirements, cannot achieve reliable and efficient job scheduling control, cannot ensure the reliable and efficient execution of jobs, and cannot realize the intelligence of the scheduling decision-making process.

[0004] Therefore, the present invention provides a multi-agent collaborative scheduling control method for a satellite ground system. Summary of the Invention

[0005] The present invention provides a multi-agent collaborative scheduling control method, device, equipment and computer-readable storage medium for a satellite ground system to partially solve the above problems existing in the prior art.

[0006] The present invention adopts the following technical solutions:

[0007] The present invention provides a multi-agent collaborative scheduling control method for a satellite ground system, including:

[0008] Obtaining the remote sensing data transmitted by the satellite and the task requirements corresponding to the remote sensing data;

[0009] Inputting the remote sensing data and the task requirements into a primary intelligent agent and a backup intelligent agent respectively to obtain the tasks and job execution results output by the primary intelligent agent and the tasks and job execution results output by the backup intelligent agent;

[0010] Judging whether the tasks and job execution results output by the primary intelligent agent reach a preset result;

[0011] If so, inputting the tasks and job execution results output by the primary intelligent agent into a remote sensing data service system so that the remote sensing data service system processes the remote sensing data according to the tasks and job execution results output by the primary intelligent agent;

[0012] If not, input the tasks and job execution results output by the standby intelligent agent into the remote sensing data service system, so that the remote sensing data service system processes the remote sensing data according to the tasks and job execution results output by the standby intelligent agent.

[0013] Optionally, the main intelligent agent includes a positioning and registration system, a calibration processing system, and a product generation system;

[0014] Inputting the remote sensing data and the task requirements into the main intelligent agent to obtain the tasks and job execution results output by the main intelligent agent specifically includes:

[0015] Input the remote sensing data and the task requirements into the positioning and registration system in the main intelligent agent to obtain the first task scheduling data;

[0016] Input the first task scheduling data into the calibration processing system to obtain the second task scheduling data;

[0017] Input the second task scheduling data into the product generation system to obtain the tasks and job execution results.

[0018] Optionally, determining whether the tasks and job execution results output by the main intelligent agent reach the preset results specifically includes:

[0019] Determine the state vector arrays of the remote sensing data, the first task scheduling data, the second task scheduling data, and the tasks and job execution results;

[0020] Determine the reinforcement value of the main intelligent agent according to the state vector arrays and the action information of the main intelligent agent;

[0021] Determine the maximum expected value of the main intelligent agent according to the reinforcement value of the main intelligent agent, the state vector arrays, and the preset strategy;

[0022] Judge whether the maximum expected value reaches the preset expected result.

[0023] Optionally, the representation form of the state vector arrays is:

[0024] ;

[0025] Among them, L0 represents the remote sensing data, L1A represents the first task scheduling data, L1 represents the second task scheduling data, L2 represents the tasks and job execution results, represents the L0 data integrity flag, represents the L0 data timeliness flag, represents the L1A data quality inspection result, represents the L1A data timeliness flag, Indicates the L1 data quality inspection result, Indicates the L1 data timeliness identifier, Indicates the L2 data quality inspection result, Indicates the data timeliness identifier.

[0026] Optionally, the calculation formula for the reinforcement value of the main agent is:

[0027] ;

[0028] Wherein, Indicates the i-th agent, Indicates the current state of the agent, Indicates the current action of the agent, Is a preset learning rate, r is a preset reward value, γ is a preset discount factor, Indicates the next state of the agent, Indicates the next action of the agent.

[0029] Optionally, the calculation formula for the maximum expected value of the main agent is:

[0030] ;

[0031] Wherein, A is the joint action space, Is the probability of taking the joint action a in the state s.

[0032] Optionally, the constraint formula for the maximum expected value of the main agent is:

[0033] .

[0034] The present invention provides a multi-agent collaborative scheduling and control device for a satellite ground system, including:

[0035] An acquisition module, configured to acquire remote sensing data transmitted by a satellite and task requirements corresponding to the remote sensing data;

[0036] An output module, configured to input the remote sensing data and the task requirements into a main agent and a standby agent respectively, and obtain tasks, job execution results output by the main agent, and tasks, job execution results output by the standby agent;

[0037] A judgment module is used to judge whether the task and operation execution result output by the main intelligent agent reach a preset result; if so, the task and operation execution result output by the main intelligent agent are input into the remote sensing data service system, so that the remote sensing data service system processes the remote sensing data according to the task and operation execution result output by the main intelligent agent; if not, the task and operation execution result output by the backup intelligent agent are input into the remote sensing data service system, so that the remote sensing data service system processes the remote sensing data according to the task and operation execution result output by the backup intelligent agent.

[0038] The present invention provides a computer-readable storage medium storing a computer program, which when executed by a processor implements the above-mentioned multi-agent collaborative scheduling control method for a satellite ground system.

[0039] The present invention provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the program, it implements the multi-agent collaborative scheduling control method for a satellite ground system.

[0040] The above at least one technical solution adopted by the present invention can achieve the following beneficial effects:

[0041] The multi-agent collaborative scheduling control method for a satellite ground system provided by the present invention first obtains remote sensing data transmitted by a satellite and the task requirements corresponding to the remote sensing data. The remote sensing data and the task requirements are respectively input into the main intelligent agent and the backup intelligent agent to obtain the task and operation execution results output by the main intelligent agent and the task and operation execution results output by the backup intelligent agent. It is judged whether the task and operation execution results output by the main intelligent agent reach a preset result. If so, the task scheduling result output by the main intelligent agent is input into the remote sensing data service system, so that the remote sensing data service system performs the operation execution of remote sensing data processing according to the task output by the main intelligent agent. If not, the task and operation execution results output by the backup intelligent agent are input into the remote sensing data service system, so that the remote sensing data service system performs the operation execution of remote sensing data processing according to the task output by the backup intelligent agent.

[0042] The multi-agent collaborative scheduling control method designed by the present invention can effectively improve the reliability of the satellite ground system. When the main intelligent agent has an abnormality, a performance decline, or the task scheduling result fails to reach the preset result, the backup intelligent agent can quickly take over the task to ensure the continuous and stable operation of the satellite ground system. Through the global control strategy and the efficient information transmission mechanism, the system can quickly respond to complex business changes and make optimal decisions autonomously, thereby enhancing the adaptability and robustness of the system. In addition, through the working mode of combining local control and global coordination, the system can dynamically adjust resource allocation to ensure the maximum utilization of resources and greatly improve the system operation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The drawings described herein are provided to further understand the present specification and form a part of the present specification. The schematic embodiments of the present specification and their descriptions are used to explain the present specification and do not constitute an improper limitation to the present specification. In the drawings:

[0044] Figure 1 is a schematic flow chart of a multi-agent collaborative scheduling control method for a satellite ground system provided by an embodiment of the present invention;

[0045] Figure 2 is a schematic diagram of the primary and standby collaborative work of a ground system provided by the present invention;

[0046] Figure 3 is a business flow chart of multi-agent collaborative scheduling control provided by the present invention;

[0047] Figure 4 is a schematic diagram of a multi-agent collaborative scheduling control device for a satellite ground system provided by the present invention;

[0048] Figure 5 is provided by the present invention corresponding to Figure 1 a schematic diagram of the structure of an electronic device. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0049] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below in conjunction with the specific embodiments of the present specification and the corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present specification, rather than all of the embodiments. Based on the embodiments in the present specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of this application.

[0050] The technical solutions provided by each embodiment of the present specification will be described in detail below in conjunction with the drawings.

[0051] Figure 1 is a schematic flow chart of a multi-agent collaborative scheduling control method for a satellite ground system provided by an embodiment of the present specification, including the following steps:

[0052] S100: Obtain the remote sensing data transmitted by the satellite and the task requirements corresponding to the remote sensing data.

[0053] In the process of multi-agent collaborative scheduling and control of the satellite ground system in this specification, in the embodiments of this specification, the server may execute the process of multi-agent collaborative scheduling and control of the satellite ground system. Of course, this specification does not limit which device executes the process of multi-agent collaborative scheduling and control of the satellite ground system, and devices such as personal computers and mobile terminals may also be used to execute the process of multi-agent collaborative scheduling and control of the satellite ground system. For the convenience of description, the control server is used as the execution subject for explanation below.

[0054] In one or more embodiments of this specification, after the satellite acquires remote sensing data, the remote sensing data can be transmitted to the ground station, and the ground station transmits the remote sensing data to the control server. After the server receives the remote sensing data, it is necessary to process the remote sensing data according to the task plan. For some tasks with high real-time requirements, the server needs to process them in real time. For some non-real-time tasks, the server schedules resources according to the task requirements to execute these tasks with low real-time requirements.

[0055] Therefore, after the server obtains the remote sensing data transmitted by the satellite, it can also obtain the task requirements set for these remote sensing data, so as to distinguish which data in the remote sensing data need to be processed in real time and which data need to be processed non-real-time, so that the server can allocate resources to process the remote sensing data as needed.

[0056] In one or more embodiments of this specification, the server can control the satellite ground system. The ground system may include several systems that perform different functions, such as an operation control system, a data reception and command control system, a calibration processing system, a positioning and registration system, an observation simulation system, a product generation system, a quality assessment system, etc. This specification does not limit how many systems that perform different functions the server-controlled ground system may include, and it can be set according to the actual situation. Among them, the server can formulate a unified task plan through the operation control system in the ground system. The satellite and the ground system are driven by the task schedule allocated in the task plan for automated intelligent operation, and the integrated and hierarchical combination method can be adopted to perform fusion scheduling and control on each system in the ground system. Integrated scheduling is adopted for business systems and operations with high timeliness requirements, and hierarchical scheduling is performed on business systems and operations with low real-time requirements. Integrated real-time scheduling control is adopted for the data reception and command control system, the positioning and registration system, the calibration processing system, and the product generation system (key products) with high real-time requirements. Hierarchical scheduling control is adopted for the product generation system (secondary products), the observation simulation system, the quality assessment system, etc. with low real-time requirements. Integrated scheduling and centralized management are conducive to system performance optimization and facilitate unified management of the entire process. Hierarchical scheduling does not affect each other and has the ability of reprocessing scheduling control. According to the system operation requirements, the scheduling method can also be appropriately adjusted to achieve intelligent and refined scheduling and management.

[0057] S102: Input the remote sensing data and the task requirements into the primary intelligent agent and the backup intelligent agent respectively, and obtain the tasks output by the primary intelligent agent, the job execution results, the tasks output by the backup intelligent agent, and the job execution results.

[0058] In one or more embodiments of this specification, the server may input the acquired remote sensing data and task requirements into the primary intelligent agent to obtain the tasks output by the primary intelligent agent, and the job execution results obtained by executing the tasks as jobs. The server inputs the acquired remote sensing data and task requirements into the backup intelligent agent to obtain the tasks output by the backup intelligent agent, and the job execution results obtained by executing the tasks as jobs.

[0059] Specifically, the server may input the remote sensing data and task requirements into the positioning and registration system in the primary intelligent agent to obtain the first task scheduling data. Input the first task scheduling data into the calibration processing system to obtain the second task scheduling data. Input the second task scheduling data into the product generation system to obtain the tasks and job execution results. Similarly, the process of obtaining the tasks and job execution results output by the backup intelligent agent may also refer to the above process.

[0060] It should be noted that whether in the primary intelligent agent or the standby intelligent agent, after the server inputs remote sensing data, the integrated scheduling control management in the above-mentioned ground system can be triggered. Taking the primary intelligent agent as an example, in the primary intelligent agent, the integrated scheduling control management mainly realizes the integrated scheduling control management of real-time operations and the policy configuration of the resources required for the operation of the business system to meet the efficient operation of the operations and resources. The job scheduling strategies in the task scheduling results include immediate execution, one-time execution, periodic execution, the parallelism of the job flow, and the priority of the job flow can be dynamically adjusted. According to the definition of the system external interface, integrated real-time scheduling control is adopted for the positioning and registration system, the calibration processing system, and the product generation system. Among them, the integrated scheduling control management completes the task planning according to the task requirements and generates a load task schedule regularly every day. Each system participating in the integrated scheduling provides job information, job parameters, required resources, input data that needs to be monitored for arrival, output products, provides a job process topology diagram, scheduling strategy information, completes the job integration configuration, and forms an input configuration, a product configuration, and a flow template configuration. The timed scheduling starts the plan generation process regularly every day according to the job integration configuration information to generate an input plan, a product plan, and a scheduling plan. The real-time scheduling is divided into positioning and registration scheduling, calibration processing scheduling, and product generation scheduling according to the systems participating in the integrated scheduling. According to the scheduling plan, the input plan, and the product plan, the business processing processes of each system are scheduled to complete, the jobs of each system are submitted to the system for resource scheduling, and at the same time, the job operation results returned by the system are collected and recorded. The internal line distribution pushes the products at all levels generated by each system in the integrated scheduling to the atmospheric remote sensing data service system. The execution situation of the business processes of each system in the integrated scheduling is collected, and the status of the product distribution results is collected to realize the monitoring of the business processes of the entire system.

[0061] For hierarchical scheduling control management, hierarchical scheduling control mainly realizes the hierarchical scheduling control and management of jobs with low real-time requirements. For jobs with low real-time requirements, there are primary scheduling and secondary scheduling. For example, task schedules, dispatching orders, public configuration parameters, etc. are for primary scheduling. The operation control system completes the generation, sending, and execution status monitoring of dispatching orders and has the function of dispatching order management on the main console. According to the definition of the system external interface, hierarchical scheduling control is adopted for the data reception and instruction control system, payload antenna dynamic measurement and calibration system, observation simulation system, quality assessment system, data archiving and management system, data archiving and management system, etc. Hierarchical scheduling control completes task planning according to task requirements, generates payload task schedules, observation schedules, and broadcast schedules at a fixed time every day, sends various schedules to relevant technical systems, and issues a dispatching order for the daily task schedule to be issued. The secondary monitoring of each technical system analyzes the task schedule, confirms normal reception, and reports the response to the dispatching order. The secondary monitoring of each technical system generates the job plan of its own system according to the attribute description of the tasks in the task schedule, and schedules the automatic operation of the jobs in its own system according to the job plan to complete their respective business functions. The secondary monitoring of each technical system promptly reports the task execution status and monitors the entire process of each payload observation task. For the task schedule being executed, due to changes in business requirements and user requirements, the arrangement order of tasks needs to change, or tasks that have been arranged need to be added or reduced in the task schedule being executed. In this case, the task schedule needs to be modified manually. After completion, the updated task schedule is sent to relevant technical systems, and a dispatching order for task schedule update is issued to notify each system to update the new task schedule at the specified time. Each technical system reports the fault information during operation and monitors and alarms the operation status of the entire business process.

[0062] S104: Determine whether the task and job execution results output by the main agent reach the preset results. If so, execute step S106; if not, execute step S108.

[0063] In one or more embodiments of this specification, the server can determine whether the task and job execution results output by the main agent reach the preset results. If so, execute step S106; if not, execute step S108.

[0064] For the integrated scheduling part of the ground system, a primary-backup collaborative scheduling control method is adopted, such as Figure 2 Schematic diagram of the primary-backup collaborative work of the ground system and Figure 3Multi-agent collaborative scheduling control business process diagram. The primary agent and the backup agent work simultaneously. Only the host outputs the status synchronization of the standby machine externally, that is, the primary agent mainly processes the business, and the backup agent works as an auxiliary. When the host of a certain ground system has an abnormal operation or interrupts the service, the backup agent takes over the primary agent to undertake the business service. Without manual intervention, the two work collaboratively to automatically ensure that the system can continuously provide services. For multi-agent collaborative scheduling control, specifically, the server can input remote sensing data (L0) and task requirements into the positioning and registration system in the primary agent to obtain the first task scheduling data (L1A). Input the first task scheduling data into the calibration processing system to obtain the second task scheduling data (L1). Input the second task scheduling data into the product generation system to obtain the task and job execution results (L2). Similarly, the server can also input remote sensing data (L0) and task requirements into the positioning and registration system in the backup agent to obtain the first task scheduling data (L1A). Input the first task scheduling data into the calibration processing system to obtain the second task scheduling data (L1). Input the second task scheduling data into the product generation system to obtain the task and job execution results (L2).

[0065] After that, taking the primary agent as an example for illustration, the server can determine the state vector arrays of the remote sensing data (L0), the first task scheduling data (L1A), the second task scheduling data (L1), and the task and job execution results (L2).

[0066] The representation form of the state vector array is as follows:

[0067] ;

[0068] Among them, L0 represents the remote sensing data, L1A represents the first task scheduling data, L1 represents the second task scheduling data, L2 represents the task and job execution results, represents the data integrity flag of L0, represents the data timeliness flag of L0, represents the quality inspection result of L1A data, represents the data timeliness flag of L1A, represents the quality inspection result of L1 data, represents the data timeliness flag of L1, represents the quality inspection result of L2 data, represents the data timeliness flag.

[0069] The server then determines the reinforcement value of the primary agent according to the state vector array and the action information of the primary agent. According to the reinforcement value of the primary agent, the state vector array, and the preset strategy, the maximum expected value of the primary agent is determined. Finally, it can be judged whether the maximum expected value reaches the preset expected result.

[0070] The calculation formula for the reinforcement value of the main agent is as follows:

[0071]

[0072] Wherein, represents the i-th agent, represents the current state of the agent, represents the current action of the agent, is the preset learning rate, r is the preset reward value, and γ is the preset discount factor. represents the next state of the agent, represents the next action of the agent.

[0073] The calculation formula for the maximum expected value of the main agent is as follows:

[0074]

[0075] Wherein, A is the joint action space, is the probability of taking the joint action α in the state s.

[0076] The constraint formula for the maximum expected value of the main agent is as follows:

[0077]

[0078] It should be noted that in this multi-agent framework, each state transition is the result of the joint actions of all agents. The reward return of each agent depends not only on its own policy selection but also on the joint actions of other agents. Therefore, the returns obtained by different agents may vary, and each agent has its own state value function. Specifically, given a specific policy, the value function Vi of agent i in state s is defined as

[0079]

[0080] Wherein, a = (a1, a2,..., aN) is the joint action, π is the policy followed by the agent, indicating that the action of each agent is a decision made based on its own policy and the environmental state. The magnitude of the discount factor γ reflects the importance of future rewards and current rewards. When γ is 0, it means that the agent only considers the current reward, and when γ is 1, it means that the rewards at each future moment are equally important as the current reward. What is finally obtained is the present value of the total expected return that can be achieved starting from the initial condition s according to the above rules.

[0081] S106: Input the tasks and job execution results output by the primary agent into the remote sensing data service system, so that the remote sensing data service system processes the remote sensing data according to the tasks and job execution results output by the primary agent.

[0082] In one or more embodiments of this specification, if the tasks and job execution results output by the primary agent reach the preset results, the server inputs the tasks and job execution results output by the primary agent into the atmospheric remote sensing data service system, so that the atmospheric remote sensing data service system performs task scheduling for remote sensing data processing according to the tasks and job execution results output by the primary agent. At the same time, the atmospheric remote sensing data service system also transmits the tasks and job execution results to the data archiving and management system for archiving.

[0083] S108: Input the tasks and job execution results output by the standby agent into the remote sensing data service system, so that the remote sensing data service system processes the remote sensing data according to the tasks and job execution results output by the standby agent.

[0084] In one or more embodiments of this specification, if the tasks and job execution results output by the primary agent do not reach the preset results, the server inputs the tasks and job execution results output by the standby agent into the atmospheric remote sensing data service system, so that the atmospheric remote sensing data service system performs task scheduling for remote sensing data processing according to the tasks and job execution results output by the standby agent.

[0085] It should be noted that if the tasks and job execution results output by the primary agent do not reach the preset results and it is necessary to enable the tasks and job execution results output by the standby agent, the big data multi-modal adaptive health management subsystem of the operation control system evaluates the L1A, L1, and L2 data quality of the primary agent and the standby agent and outputs the results. The primary and standby L1A / L1 / L2 data service decision subsystem makes decisions on the operation quality and data quality inspection results of the big data multi-modal adaptive health management subsystem. Transmit the L1A / L1 / L2 data of the decision-making primary agent or standby agent to the atmospheric remote sensing data service system, and the atmospheric remote sensing data service system transmits each data (L1A / L1 / L2) to the data archiving and management system for archiving.

[0086] The above is a multi-agent collaborative scheduling control method for a satellite ground system provided by one or more embodiments of this specification. Based on the same idea, this specification also provides a corresponding multi-agent collaborative scheduling control device for a satellite ground system, as Figure 4 shown.

[0087] An acquisition module 400, configured to acquire the remote sensing data transmitted by the satellite and the task requirements corresponding to the remote sensing data;

[0088] An output module 402 for inputting the remote sensing data and the task requirements into a primary intelligent agent and a backup intelligent agent respectively, to obtain the tasks and job execution results output by the primary intelligent agent and the tasks and job execution results output by the backup intelligent agent;

[0089] A judgment module 404 for judging whether the tasks and job execution results output by the primary intelligent agent reach a preset result; if so, inputting the tasks and job execution results output by the primary intelligent agent into a remote sensing data service system, so that the remote sensing data service system processes the remote sensing data according to the tasks and job execution results output by the primary intelligent agent; if not, inputting the tasks and job execution results output by the backup intelligent agent into the remote sensing data service system, so that the remote sensing data service system processes the remote sensing data according to the tasks and job execution results output by the backup intelligent agent.

[0090] Optionally, the primary intelligent agent includes a positioning and registration system, a calibration processing system, and a product generation system;

[0091] The output module 402 is configured to input the remote sensing data and the task requirements into the positioning and registration system in the primary intelligent agent to obtain first task scheduling data, input the first task scheduling data into the calibration processing system to obtain second task scheduling data, and input the second task scheduling data into the product generation system to obtain tasks and job execution results.

[0092] Optionally, the output module 402 is configured to determine a state vector array of the remote sensing data, the first task scheduling data, the second task scheduling data, and the tasks and job execution results, determine a reinforcement value of the primary intelligent agent according to the state vector array and the action information of the primary intelligent agent, determine a maximum expected value of the primary intelligent agent according to the reinforcement value of the primary intelligent agent, the state vector array, and a preset policy, and judge whether the maximum expected value reaches a preset expected result.

[0093] Optionally, the representation form of the state vector array in the output module 402 is:

[0094]

[0095] wherein, L0 represents the remote sensing data, L1A represents the first task scheduling data, L1 represents the second task scheduling data, L2 represents the tasks and job execution results, represents the data integrity flag of L0, represents the data timeliness flag of L0, represents the data quality inspection result of L1A, represents the data timeliness flag of L1A, Indicates the L1 data quality inspection result, Indicates the L1 data timeliness identifier, Indicates the L2 data quality inspection result, Indicates the data timeliness identifier.

[0096] Optionally, the calculation formula for the reinforcement value of the main agent in the output module 402 is:

[0097]

[0098] Wherein, Indicates the i-th agent, Indicates the current state of the agent, Indicates the current action of the agent, Is a preset learning rate, r is a preset reward value, γ is a preset discount factor, Indicates the next state of the agent, Indicates the next action of the agent.

[0099] Optionally, the calculation formula for the maximum expected value of the main agent in the output module 402 is:

[0100]

[0101] Wherein, A is the joint action space, Is the probability of taking the joint action α in the state s.

[0102] Optionally, the constraint formula for the maximum expected value of the main agent in the output module 402 is:

[0103]

[0104] This specification also provides a computer-readable storage medium, which stores a computer program that can be used to execute the above Figure 1 Provided a multi-agent collaborative scheduling control method for a satellite ground system.

[0105] This specification also provides Figure 5 The schematic structural diagram of the electronic device shown. As Figure 5 Shown, at the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory. Of course, it may also include other hardware required for other services. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to implement the above Figure 1 Described multi-agent collaborative scheduling control method for a satellite ground system.

[0106] Of course, in addition to the software implementation, this specification does not exclude other implementation methods, such as logical devices or a combination of software and hardware, etc. That is to say, the execution subject of the following processing flow is not limited to each logical unit, and can also be hardware or logical devices.

[0107] In the 1990s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to circuit structures such as diodes, transistors, switches, etc.) or software improvements (improvements to method flows). However, with the development of technology, many method flow improvements today can be regarded as direct improvements to hardware circuit structures. Almost all designers obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement to a method flow cannot be implemented using a hardware entity module. For example, a programmable logic device (PLD) (e.g., a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by a user's programming of the device. Designers can program themselves to "integrate" a digital system onto a single PLD, without having to ask a chip manufacturer to design and fabricate a dedicated integrated circuit chip. Moreover, nowadays, instead of manually fabricating integrated circuit chips, this programming is mostly implemented using "logic compiler" software, which is similar to the software compilers used in program development and writing. The original code before compilation also has to be written in a specific programming language, which is called a hardware description language (HDL). There is not just one type of HDL, but many types, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones currently are VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also be aware that by simply performing a little logical programming on the method flow using the above-mentioned several hardware description languages and programming it into an integrated circuit, it is easy to obtain the hardware circuit that implements the logical method flow.

[0108] The controller can be implemented in any suitable manner. For example, the controller can take the form of, for example, a microprocessor or a processor and a computer-readable medium storing computer-readable program code (such as software or firmware) executable by the (micro)processor, logic gates, switches, an application specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of the controller include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that, in addition to implementing the controller in the form of pure computer-readable program code, it is entirely possible to make the controller implement the same function in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, such a controller can be considered a hardware component, and the devices included therein for implementing various functions can also be regarded as the structures within the hardware component. Or even, the devices for implementing various functions can be regarded as either software modules for implementing the method or the structures within the hardware component.

[0109] The systems, devices, modules, or units illustrated in the above embodiments can be specifically implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0110] For the convenience of description, when describing the above devices, they are described separately as various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0111] Those skilled in the art should understand that the embodiments of this specification can be provided as a method, a system, or a computer program product. Therefore, this specification can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, this specification 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 code.

[0112] This specification is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the specification. It should be understood that each flow and / or block in the flowchart and / or block diagram, and combinations 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, special-purpose computer, embedded processor, or other programmable data processing device to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing device produce means for implementing the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 means for implementing the functions specified in one or more of the blocks.

[0113] 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 operate in a specific manner, such that the instructions stored in the computer-readable memory produce a manufacture including instruction means that implement the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 means for implementing the functions specified in one or more of the blocks.

[0114] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operational steps are performed 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 or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 means for implementing the functions specified in one or more of the blocks.

[0115] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0116] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of computer-readable media.

[0117] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0118] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0119] It should be understood by those skilled in the art that the embodiments of this specification may be provided as methods, systems or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, this specification may take the 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.

[0120] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0121] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other, and the key point of each embodiment is to illustrate the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for the relevant parts, reference can be made to the partial description of the method embodiment.

[0122] The above description is only for the embodiments of this specification and is not intended to limit this specification. For those skilled in the art, various modifications and changes can be made to this specification. Any modification, equivalent replacement, improvement, etc. made within the technical scope and principle of this specification shall be included within the scope of the claims of this specification.

Claims

1. A multi-agent collaborative scheduling and control method for a satellite ground system, characterized in that, Including: Obtain the remote sensing data transmitted by the satellite and the task requirements corresponding to the remote sensing data; Input the remote sensing data and the task requirements into the main intelligent agent and the backup intelligent agent respectively, and obtain the tasks, job execution results output by the main intelligent agent and the tasks, job execution results output by the backup intelligent agent; Judge whether the tasks and job execution results output by the main intelligent agent reach the preset results; If so, input the tasks and job execution results output by the main intelligent agent into the remote sensing data service system, so that the remote sensing data service system processes the remote sensing data according to the tasks and job execution results output by the main intelligent agent; If not, input the tasks and job execution results output by the backup intelligent agent into the remote sensing data service system, so that the remote sensing data service system processes the remote sensing data according to the tasks and job execution results output by the backup intelligent agent; The main intelligent agent includes a positioning and registration system, a calibration processing system, and a product generation system; Inputting the remote sensing data and the task requirements into the main intelligent agent to obtain the tasks and job execution results output by the main intelligent agent specifically includes: Input the remote sensing data and the task requirements into the positioning and registration system in the main intelligent agent to obtain the first task scheduling data; Input the first task scheduling data into the calibration processing system to obtain the second task scheduling data; Input the second task scheduling data into the product generation system to obtain the tasks and job execution results; Judging whether the tasks and job execution results output by the main intelligent agent reach the preset results specifically includes: Determine the state vector arrays of the remote sensing data, the first task scheduling data, the second task scheduling data, and the tasks and job execution results; Determine the reinforcement value of the main intelligent agent according to the state vector array and the action information of the main intelligent agent; Determine the maximum expected value of the main intelligent agent according to the reinforcement value of the main intelligent agent, the state vector array, and the preset strategy; Judge whether the maximum expected value reaches the preset expected result; The representation form of the state vector array is: ； Among them, L0 represents remote sensing data, L1A represents the first task scheduling data, L1 represents the second task scheduling data, and L2 represents the task and job execution results. represents the L0 data integrity flag. represents the L0 data timeliness flag. represents the L1A data quality inspection result. represents the L1A data timeliness flag. represents the L1 data quality inspection result. represents the L1 data timeliness flag. represents the L2 data quality inspection result. represents the data timeliness flag; The calculation formula for the reinforcement value of the main intelligent agent is: ； Among them, represents the i-th agent, represents the current state of the agent, represents the current action of the agent, is the preset learning rate, r is the preset reward value, and γ is the preset discount factor, represents the next state of the agent, represents the next action of the agent.

2. The multi-agent collaborative scheduling and control method for a satellite ground system according to claim 1, wherein The calculation formula for the maximum expected value of the main intelligent agent is: ； where \(A\) is the joint action space, is the probability of taking the joint action \(\alpha\) in state \(s\).

3. The multi-agent collaborative scheduling and control method for satellite ground systems according to claim 2, wherein, The constraint formula for the maximum expected value of the main intelligent agent is: 。 4. A multi-agent collaborative scheduling and control device for a satellite ground system, characterized in that, Implement the multi-intelligent agent collaborative scheduling control method for the satellite ground system described in any one of claims 1 to 3, including: An acquisition module, configured to acquire the remote sensing data transmitted by the satellite and the task requirements corresponding to the remote sensing data; An output module, configured to input the remote sensing data and the task requirements into the main intelligent agent and the backup intelligent agent respectively, and obtain the tasks, job execution results output by the main intelligent agent and the tasks, job execution results output by the backup intelligent agent; A judgment module, configured to judge whether the task and operation execution result output by the main intelligent agent reach a preset result; if so, input the task and operation execution result output by the main intelligent agent into the remote sensing data service system, so that the remote sensing data service system processes the remote sensing data according to the task and operation execution result output by the main intelligent agent; if not, input the task and operation execution result output by the backup intelligent agent into the remote sensing data service system, so that the remote sensing data service system processes the remote sensing data according to the task and operation execution result output by the backup intelligent agent.

5. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of claims 1 to 3 above is implemented.

6. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, the method described in any one of claims 1 to 3 above is implemented.

Images