A space-based system edge cloud architecture and self-organizing system and method

Abstract

The present invention discloses a space-based system edge cloud architecture, a self-organizing system and a method, which can flexibly dispatch satellite resources for tasks, complete collaborative processing, achieve rapid and immediate response to complex tasks, and support space-based tactical tasks such as regional navigation enhancement, emergency networking communication, and collaborative observation. The edge cloud of the space-based system can provide two different levels of task organization methods, "task-level collaboration" and "signal-level collaboration", according to task requirements, and can coordinate and flexibly dispatch space-based system resources as needed, so that the utilization efficiency of space-based system resources is optimized. The present invention is applied to aerospace systems, and can solve the problems of traditional satellite single working mode, low resource utilization, difficult collaboration, and untimely service response. It has broad application prospects in the field of intelligent services of aerospace systems.

Description

Technical Field

[0001] The present invention relates to the field of aerospace technology, and in particular to an edge cloud architecture, a self-organizing system and a method for a space-based system. Background Art

[0002] The development of aerospace systems has gone through the stages of independent development and interconnected sharing. Typical aerospace systems include satellite navigation, communication, remote sensing and other constellation systems, but their construction and development have long been positioned in strategic application services, making it difficult to adapt to the flexible and diverse application service needs of the future intelligent unmanned era. Informatization and future intelligent warfare will manifest as full-factor, all-day, and multi-dimensional system confrontations. There is an urgent need to build a service-oriented, combat-mission-centered intelligent space-based system to promote the expansion of space-based systems from strategic applications to tactical applications, and from passive support to autonomous services.

[0003] In recent years, in order to improve the security, rapid response capability and intelligence level of space-based systems, people in the aerospace field are constantly exploring the expansion of space-based systems from strategic applications to tactical applications. For example, the "Tactical Satellite 3" (TacSat-3) project in the field of reconnaissance satellites. However, this type of satellite is only a certain type of satellite that improves the real-time response service of this type of satellite resources by increasing the number of satellites and improving the satellite's on-orbit processing capabilities, and has limited support for tactical applications. The concept of "combat cloud" uses a method similar to cloud computing to realize the information sharing capability of air forces of various services. This is the application of cloud computing technology to the battlefield, which can realize the information sharing of weapons and equipment and the efficient use of resources, and does not involve satellites. Existing studies consider organizing satellites into edge service clusters, and multiple satellite nodes cooperate with each other to complete on-orbit detection tasks. Through on-orbit power and software optimization, the response speed and reliability of the task are improved. However, the satellite cluster in this type of research is a small satellite formation with a fixed number of satellite nodes, unchanged network topology, and it can only handle detection tasks. Some studies introduce edge computing into space-based systems to improve the efficiency of satellite resource utilization through business migration, task planning and other means. However, when applying edge computing to space-based systems, due to constraints such as the heterogeneity of satellite resources, the dynamic nature of satellite network connections, and strict limitations on satellite size and power consumption, there are still challenges such as a single task organization form, low resource utilization, and untimely task response. Summary of the invention

[0004] In view of the above-mentioned deficiencies in the prior art, the present invention provides a space-based system edge cloud architecture and a self-organizing system and method to solve the problems of traditional satellite resources being scattered and independent, difficult to collaborate, slow service response, and large delay.

[0005] To achieve the above objectives, the present invention provides a space-based system edge cloud architecture, comprising:

[0006] Edge cloud, a cloud-network integrated distributed task cluster built by dynamic networking of intelligent satellites, provides instant and efficient space-based resource services for user terminals;

[0007] Edge nodes, satellites in the edge cloud, satellites dynamically join or exit the edge cloud according to mission requirements or network topology changes. After the edge node exits the edge cloud, it can be managed locally and autonomously, and join the edge cloud service at any time on demand;

[0008] User terminals are the objects to which edge clouds provide resource services.

[0009] In one embodiment, the space-based system edge cloud architecture further includes:

[0010] The central cloud is a cluster system with strong resource service capabilities. It provides functions such as complex business management, wide-area resource scheduling, and big data analysis. The data and services of the edge cloud and the central cloud are linked to meet business needs with high complexity and service quality.

[0011] The ground station is used to assist the space-based system in operation and maintenance management and business evaluation, and to collect space-based system status information while maintaining connection with the space-based system.

[0012] In one embodiment, the central cloud and the edge cloud adopt a unified standard architecture and a unified protocol interface, and are uniformly deployed through the central cloud to reduce the cost of developing an edge cloud separately.

[0013] In one embodiment, the central cloud is a data and service center deployed on the ground, or the central cloud is a backbone satellite cluster.

[0014] In one embodiment, the organizational model of the edge cloud includes:

[0015] Mission-level collaboration: Space-based system satellites complete mission-level collaboration. Satellites in the edge cloud synchronously perform navigation, communication, remote sensing and other functions according to mission requirements, providing multi-functional cluster services.

[0016] Signal-level coordination is achieved by the satellites of the space-based system. The satellites in the edge cloud have high-precision synchronization requirements, including synchronous execution of collaborative detection and collaborative power synthesis, and provide distributed coherent signal cluster services according to mission requirements.

[0017] To achieve the above object, the present invention further provides an edge cloud system, comprising:

[0018] The system management engine is a distributed software platform built based on lightweight satellite resource virtualization technology. It is responsible for organizing and managing edge node resources in the edge cloud, ensuring that all types of resources in the edge cloud are unified into the resource pool and realizing resource sharing of edge nodes.

[0019] The resource scheduling module is the basic service software on top of the system management engine. It is used to dynamically schedule resources encapsulated in containers, with the goal of maximizing resource utilization and load balancing, to provide users with efficient space-based resource services.

[0020] In one embodiment, the system management engine includes:

[0021] The resource virtualization environment is a container-based resource virtualization platform used to achieve lightweight resource virtualization on satellites.

[0022] The network management component is used to establish and maintain the network topology of the satellite cluster and manage the dynamically changing satellite network to maintain the network connection of the edge cloud;

[0023] The node management component manages the nodes of the edge cloud, maintains the node registry in the management cluster, responds to the dynamic joining or exit of edge nodes, and eliminates node conflicts in the cluster.

[0024] In one embodiment, the resource scheduling module includes:

[0025] Resource management component, which is used to manage satellite logical resources on the basis of resource virtualization, including resource synchronization, release, and maintenance, and to update the resource attributes and capabilities of each satellite node in real time;

[0026] The service parsing component is used to receive mission requests from local satellites or other satellites, parse them into business functions, read the resource status in the edge cloud, and deploy containers;

[0027] The container management component is used to manage the entire container life cycle, including but not limited to container suspension, migration, fault recovery, and container network management.

[0028] In one of the embodiments, the edge cloud organizes and switches between the two working modes of task-level collaboration and signal-level collaboration. After completing the task resolution, the service resolution component determines the working mode and submits the resource management component for the corresponding level of resource synchronization. At the same time, the software is started through the container management component to perform the corresponding operations.

[0029] To achieve the above-mentioned objectives, the present invention provides an edge cloud self-organizing method, which adopts the above-mentioned edge cloud system, and the network management component in the satellite node that receives the task requirement or initiates the task request initiates the demand for building an edge cloud. After the edge cloud is built, dynamic negotiation is carried out to maintain the edge cloud networking operation until all tasks are completed.

[0030] The edge cloud architecture and self-organizing system and method of a space-based system provided by the present invention break the situation of excessive concentration or isolated dispersion of satellite resources in traditional space-based systems, and realize rapid and immediate response to complex tasks by aggregating satellite resources in the mission area, coordinating tasks on orbit, and completing typical space-based tactical tasks such as regional navigation enhancement, emergency networking communication, and collaborative observation. The edge cloud of the space-based system can provide two different levels of task organization methods, "task-level collaboration" and "signal-level collaboration", according to mission requirements, and can coordinate and flexibly dispatch space-based system resources on demand, so that the utilization efficiency of space-based system resources is optimized, which makes the present invention have broad application prospects in the application service field of aerospace systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying creative work.

[0032] Figure 1 This is a schematic diagram of the edge cloud architecture of a space-based system according to an embodiment of the present invention;

[0033] Figure 2 This is a schematic diagram of a working scenario of a space-based system edge cloud system according to an embodiment of the present invention;

[0034] Figure 3 A schematic diagram of implementing edge cloud self-organization according to an embodiment of the present invention;

[0035] Figure 4 Schematic diagram of the edge cloud workflow in the collaborative observation task according to an embodiment of the present invention.

[0036] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0038] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0039] In addition, in the present invention, descriptions such as "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0040] In the present invention, unless otherwise clearly specified and limited, the terms "connection", "fixation", etc. should be understood in a broad sense. For example, "fixation" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection, an electrical connection, a physical connection, or a wireless communication connection; it can be a direct connection, or an indirect connection through an intermediate medium, or it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0041] In addition, the technical solutions between the various embodiments of the present invention can be combined with each other, but it must be based on the fact that ordinary technicians in the field can implement it. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0042] In order to solve the problems of traditional satellite resources being scattered and independent, difficult to collaborate, slow service response, and large delays, this embodiment designs a new type of space-based system organization model, namely a space-based system edge cloud architecture for tactical tasks, to break the situation of excessive concentration or isolated dispersion of satellite resources in traditional space-based systems, and aggregate satellite resources nearby in the mission area, and collaboratively process tasks on orbit to achieve rapid response to complex tasks. Specifically, the edge cloud architecture of the space-based system in this embodiment includes an edge cloud, a central cloud, edge nodes, a ground station, and a user terminal. Among them, the core is the edge cloud, edge nodes, and user terminals. The central cloud and ground station are not required to be included in the architecture, and the architecture still holds true without the central cloud and ground station. Edge clouds and edge nodes are satellites that provide resource services, and user terminals are objects that enjoy resource services, without limiting the terminal type.

[0043] Among them, the edge cloud of the space-based system is a distributed satellite cluster that integrates cloud and network resources and is flexibly and instantly constructed by networking satellites in orbit when there are specific complex tasks or specific battlefield mission requirements in the constellation. It uses resource virtualization and distributed computing technologies to build a distributed edge cloud computing environment, run user software or system software, and provide user terminals with unified, on-demand space-based resource services to achieve intelligent applications. For example, for a disaster-stricken area, several satellites that are visible to the target can form a remote sensing detection edge cloud to collaboratively detect the area, which can improve the coverage area and remote sensing accuracy of the area. At the same time, when the satellite leaves, it can be transferred to other satellites entering the area through task migration to increase the coverage time of the target area.

[0044] The central cloud is a cluster system with strong resource service capabilities. It provides functions such as complex business management, wide-area resource scheduling, and big data analysis. The data and services of the edge cloud and the central cloud are linked to meet business needs with high complexity and service quality. Among them, the complexity and high service quality specifically refer to business needs with many types of tasks that are difficult to predict and demanding response time. For example, in regional operations, the user types are relatively diverse, and the required communication, navigation, and detection services change dynamically, and real-time and rapid response is required. Preferably, the central cloud and the edge cloud adopt a unified standard architecture and a unified protocol interface, and are uniformly deployed through the central cloud to reduce the cost of developing edge clouds separately. In the specific implementation process, the central cloud can be a data center deployed in a ground computer room or ground station, or it can be a backbone satellite cluster with rich computing and storage resources. This general deployment is a large satellite deployed in medium and high orbits.

[0045] Edge nodes are satellite nodes in the edge cloud. Because the orbital motion of satellites causes changes in the satellite network topology, satellites will dynamically join or exit the edge cloud according to mission requirements or due to changes in network topology. Satellite nodes that exit the edge cloud do not belong to edge nodes. Edge nodes can also perform local autonomy after exiting the edge cloud.

[0046] The ground station is used to assist the space-based system in operation and maintenance management and business evaluation, and to collect space-based system status information while maintaining connection with the space-based system.

[0047] The user terminal is the object that uses the resource services provided by the edge cloud. The user terminal can be a common handheld terminal that can access the central cloud or directly access a satellite of the edge cloud. Alternatively, the terminal can install a user program that can access the central cloud and obtain resource services of the central cloud or edge cloud through a common interface.

[0048] In this embodiment, for each satellite node in the edge cloud, the three layers (infrastructure layer, platform layer and application layer) in cloud computing can be fully coordinated to meet the needs of resource coordination, network coordination, data coordination, application coordination and service coordination. Through the coordination of these three layers, the integration of cloud resources and network resources is realized, and the constructed edge cloud of the space-based system meets the requirements of the cloud-network integration system.

[0049] During the specific implementation process, the edge cloud architecture of the space-based system will also seamlessly extend the capabilities of the central cloud to the edge satellite nodes, which can not only provide elastically scalable resource services, but also maximize the efficiency of space-based resources and improve the quality of space-based resource services through resource collaboration among the central cloud, edge cloud and other edge nodes.

[0050] In this embodiment, the schematic diagram of the edge cloud architecture of the space-based system is as follows: Figure 1 As shown. The figure includes the space-based central cloud, the edge cloud of the space-based system, edge nodes, user terminals and ground stations. The central cloud is a cloud data center relative to the edge cloud of the space-based system. It can be a large cloud data center built on the ground station, which integrates multiple servers in the computer room to build a central cloud with a large amount of computing and storage resources; it can also be a large satellite / space station that integrates multiple server nodes in space, or multiple satellite nodes that can maintain a stable network topology. From a functional point of view, the central cloud does not restrict the physical location, but needs to adopt a unified architecture with the edge cloud and have the ability to interconnect and share resources. The edge cloud can be dynamically constructed into one or more according to mission requirements, Figure 2 Two space-based system edge clouds were established.

[0051] The edge cloud adopts a decentralized self-organizing network control structure. The network management component in the satellite node that receives the mission requirements or initiates the mission request is used as the starting node to initiate the demand for building the edge cloud. After the edge cloud is built, dynamic negotiation is carried out to maintain the stability of the space-based edge cloud until all tasks are completed. The edge cloud of the space-based system can complete typical space-based tactical tasks such as regional navigation enhancement, emergency networking communication, and collaborative observation. If a user needs to request the service of the edge cloud of the space-based system, one way is to access the ground station through the ground network, and then the ground station will initiate a resource service request to the space-based edge cloud in a unified manner; another way is that the device with satellite access capability can directly initiate a mission request to the satellite node according to the mission template, and the satellite node transmits the request through the inter-satellite link and responds to the resource service request.

[0052] In the specific implementation process, the initiation of a task can be a request from a user terminal, or a task instruction sent uniformly by a ground station, or it can be a task initiated autonomously by an edge node or edge cloud through continuous remote sensing detection, image recognition, and task matching. This type of task is generally a task that the satellite can judge autonomously or requires high real-time performance, such as a storm or fire in a certain area. When an edge node detects a suspected problem, it can autonomously cooperate with nearby satellites to make further judgments and identification.

[0053] The edge cloud of the space-based system in this embodiment is a distributed autonomous system, which is constructed by a self-organizing method. The self-organizing method has lower cost and better scalability, and can effectively and quickly integrate the resources of smart satellites to achieve resource sharing. Figure 3 As shown in the figure, there are two modules on each edge node, namely the system management engine and the resource scheduling module. The system management engine is responsible for managing the node management in the edge cloud cluster. It must ensure that all resources in the same edge cloud cluster can be unified into the resource pool to achieve resource sharing among nodes. The resource scheduling module is above the system management engine and is used to manage and schedule application software that uses containers as resource encapsulation units. It schedules edge cloud resources with the goal of maximizing resource utilization and load balancing, and provides users with tactical-level space-based resource services.

[0054] The system management engine module provides the function of organizing and managing the resources of the edge cloud, and ensures that all satellite resources added to the space-based edge cloud are processed as a cluster. In this embodiment, the system management engine module is composed of three main components, namely, resource virtualization environment, network management component and node management component.

[0055] The resource virtualization environment is the foundation and core of the system management engine module. It creates and maintains a distributed resource virtualization computing platform between all satellite edge nodes involved in building the edge cloud, and provides a resource virtualization environment and distributed management for the edge cloud. The resource virtualization environment needs to complete the virtualization of satellite resources, and provide the physical resource information of satellite nodes in the form of logical resources and add them to the edge cloud. Among them, the resource information storage adopts a distributed storage management method, and each node in the edge cloud collects information about its own resources and service execution status. Furthermore, the edge cloud of the space-based system does not restrict the database technology used for distributed storage, but needs to provide access and reading interfaces for node resources to achieve resource sharing. After the resources are virtualized, the characteristics and functions of satellite resources can be encapsulated to provide a unified description, allowing the edge cloud to uniformly process heterogeneous resources and share resources between nodes.

[0056] The network management component is responsible for providing network solutions for the edge cloud of the space-based system and performing network management of the edge cloud to cope with changes in the topology of the edge cloud caused by changes in the network topology due to satellite orbital motion. Due to the limited storage and computing resources of satellite nodes, the network control structure of the edge cloud of the space-based system is not suitable for a fully distributed self-organizing network structure. In a hierarchical distributed control network, a centralized approach is prone to single point failure problems, so the self-organizing network of the edge cloud of the space-based system adopts a decentralized control structure. The network management component tracks the dynamic changes of the satellite network and corrects the network parameters of the nodes to maintain the edge cloud network in a relatively stable state.

[0057] The node management component is mainly used to manage the availability of satellite nodes. It collects monitoring information about the status of edge nodes, maintains the node registry in the management cluster, responds to the dynamic joining or exit of edge nodes, and eliminates node conflicts in the cluster. The registration of nodes is obtained by merging them into the node distributed registry. The parameters collected by each node include the following aspects: memory, CPU, storage, network bandwidth, and battery power, including the status of solar panels. At the same time, based on its own resources and status information, on the one hand, resource usage limits, flow control, power consumption limits, etc. are performed, and on the other hand, the node's own status is self-checked to maintain the basic health of the satellite's in-orbit movement.

[0058] The resource scheduling module is task-oriented and takes the maximum resource utilization and load balancing as the goals to schedule the edge cloud resources and provide users with tactical-level space-based resource services. In this embodiment, the resource scheduling module is specifically implemented as three components, namely, resource management, service management, and container management.

[0059] The resource management component is used to manage satellite logical resources on the basis of resource virtualization, mainly realizing functions such as resource update, release, positioning and synchronization. The resource management component periodically updates the capability status of satellite resources to provide the latest resource information. During the application process, the resource management component provides satellite resource attributes and capability status information by publishing resources to the self-organizing edge cloud, so that other satellite nodes can subscribe to its resources and share the resources of the node. When the resource is subscribed, the resource management component needs to provide the resource service with the function of locating satellite resources, which is achieved by retrieving the resource library. Once located, it interacts with the corresponding resource management component to implement the required resource scheduling operations on each node.

[0060] In the edge cloud of the space-based system, each edge node is responsible for a part of the entire information system. The resource management component of each node only manages part of the information about resources, the execution and monitoring information of the service components, so there is no single point of failure problem of centralized management. When the resources that need to be scheduled fail, such as the node leaving the edge cloud due to orbital motion, the resource management component will reconfigure the resources of another node.

[0061] The service management component connects to the user's task requirements and parses the task requirements into edge cloud services. The services complete resource service operations through the container management component. The task requirements parsed by the service management component come from two sources: one is the task requirements submitted by the user to the satellite according to the task template, and the second is the service request submitted by the satellite locally or by other satellites. After the task is parsed into a service, the service management component manages the satellite's services in a unified manner, monitors the running status of the service, and is responsible for performing operations for all services of the entire satellite, such as starting, stopping, resuming, and terminating. The operation of the service is triggered according to the requirements of the task. During the operation of the service, the service management component reads the resource information provided by the node management component, and adjusts the number and running location of the container entities corresponding to the service in real time through load balancing and other planning.

[0062] The container management component is used to manage the entire container life cycle, including but not limited to container suspension, migration, fault recovery, and container network management. Specifically, the container management component provides operations related to the application life cycle, such as container deployment, including container creation, deployment, suspension, and recovery. Applications are encapsulated in the form of containers, which helps to uniformly execute in the heterogeneous execution environments of various satellite nodes. The most widely used Docker container can be used, and lightweight containerization technologies such as gVisor can be used for modification, so that it can be adapted for application on satellites.

[0063] In this embodiment, the edge cloud has two working modes: task-level collaboration and signal-level collaboration. Task-level collaboration is completed by satellites in the edge cloud. Satellites in the edge cloud cluster synchronously perform navigation, communication, and remote sensing functions according to task requirements, and provide information-level synchronization services. Signal-level collaboration is completed by satellites in the edge cloud. Satellites in the edge cloud cluster provide signal-level synchronization services according to task requirements, including synchronous execution of collaborative detection and other functions with high-precision synchronization requirements. Furthermore, the organization and switching of the edge cloud between the two working modes of task-level collaboration and signal-level collaboration is that the service management component determines the working mode required by the service after task decomposition after completing task analysis, submits the resource management component for resource synchronization at the corresponding level, and starts the software through the container management component to execute the corresponding resource operation.

[0064] refer to Figure 2In order to establish the workflow of the edge cloud of two space-based systems, a natural disaster area needs high-resolution and real-time satellite remote sensing images as an example. After task analysis, it is concluded that several satellites that are visible to the target area need to be observed in a coordinated manner to obtain high-resolution satellite remote sensing images. This is a "signal-level collaboration" working mode. When the image is transmitted back, since the transmission destination is far away, the image must be transmitted back through the intersatellite link and the satellite-to-ground link. At the same time, because the image information data of multiple satellites is large, multiple satellites can be coordinated to transmit part of the image to the ground separately to improve the real-time nature of the transmission and reduce the transmission delay. Moreover, two transmission methods can be used. The first is to transmit the original image information immediately, and the second is to transmit the key information back after the image information has been processed on orbit. In any case, the coordination between satellite nodes is required. This coordination is at the information level and belongs to the "task-level collaboration" working mode.

[0065] The workflow in the edge cloud of the space-based system is as follows Figure 4 As shown. Taking the space-based edge cloud for collaborative detection as an example, the system management engine establishes a space-based edge cloud serving the region. Since the satellite node with the highest orbit has the longest visibility time for the target area, it serves as the initiator node of the collaborative detection task and negotiates with other satellites for collaborative observation. The initiator node periodically sends heartbeat monitoring information to check the connection status of other satellite nodes and determine their movement trends. If it is about to leave the edge cloud, the network management component will find an alternative node to supplement the edge cloud. If no alternative node is found, the node management component modifies the node registry, reduces the scale of the edge cloud, and uses the existing satellite resources at the current moment to provide services.

[0066] The resource management module in the resource scheduling module first refreshes its own resource status, obtains resource information of other nodes through the resource publish-subscribe mechanism, and the initiating node finally decides the satellite nodes to participate in the collaborative observation. Then each node deploys the container through the container management component and starts the collaborative observation. During the observation process, the network management component is used to synchronize the spatiotemporal information, and the resource management component is used to synchronize the resource updates.

[0067] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. All equivalent structural changes made by using the contents of the present invention specification and drawings under the inventive concept of the present invention, or directly / indirectly applied in other related technical fields are included in the patent protection scope of the present invention.

Claims

1. A space-based system edge cloud architecture, characterized in that: include: Edge cloud, a cloud-network integrated distributed task cluster built by dynamic networking of intelligent satellites, provides instant and efficient space-based resource services for user terminals; Edge nodes, satellites in the edge cloud, satellites dynamically join or exit the edge cloud according to mission requirements or network topology changes. The edge nodes are managed locally and autonomously after exiting the edge cloud, and can join the edge cloud service on demand at any time; User terminals are the objects for which edge clouds provide resource services; The organizational model of the edge cloud includes: Mission-level collaboration: Space-based system satellites complete mission-level collaboration. Satellites in the edge cloud synchronously perform navigation, communication, and remote sensing functions according to mission requirements, providing multi-functional cluster services. Signal-level coordination is achieved by the satellites of the space-based system. The satellites in the edge cloud have high-precision synchronization requirements, including synchronous execution of collaborative detection and collaborative power synthesis, and provide distributed coherent signal cluster services according to mission requirements.

2. The edge cloud architecture of the space-based system according to claim 1, characterized in that: Also includes: The central cloud is a cluster system with strong resource service capabilities. It provides complex business management, wide-area resource scheduling, big data analysis, and cloud-edge collaborative artificial intelligence training functions. The data and services of the edge cloud and the central cloud are linked to meet the needs of complex and high-quality services. The ground station is used to assist the space-based system in operation and maintenance management and business evaluation, and to collect space-based system status information while maintaining connection with the space-based system.

3. The edge cloud architecture of the space-based system according to claim 2, characterized in that: The central cloud and the edge cloud adopt a unified standard architecture and a unified protocol interface and are uniformly deployed through the central cloud to reduce the cost of developing an edge cloud separately.

4. The edge cloud architecture of the space-based system according to claim 2, characterized in that: The central cloud is a data and service center deployed on the ground, or the central cloud is a backbone satellite cluster.

5. An edge cloud system according to any one of claims 1 to 4, characterized in that: Including those deployed on edge nodes: The system management engine is a distributed software platform built based on lightweight satellite resource virtualization technology. It is responsible for organizing and managing edge node resources in the edge cloud, ensuring that all types of resources in the edge cloud are unified into the resource pool and realizing resource sharing of edge nodes. The resource scheduling module is the basic service software on top of the system management engine. It is used to dynamically schedule resources encapsulated in containers, with the goal of maximizing resource utilization and load balancing, to provide users with efficient space-based resource services. The resource scheduling module includes: Resource management component, which is used to manage satellite logical resources on the basis of resource virtualization, including resource synchronization, release, and maintenance, and to update the resource attributes and capabilities of each satellite node in real time; The service parsing component is used to receive mission requests from local satellites or other satellites, parse them into business functions, read the resource status in the edge cloud, and deploy containers; Container management components, used to manage the entire container lifecycle, including but not limited to container suspension, migration, fault recovery, and container network management; The edge cloud organizes and switches between the two working modes of task-level collaboration and signal-level collaboration. After completing the task analysis, the service analysis component determines the working mode and submits the resource management component for the corresponding level of resource synchronization. At the same time, the software is started through the container management component to perform corresponding operations.

6. The edge cloud system according to claim 5, characterized in that: The system management engine includes: The resource virtualization environment is a container-based resource virtualization platform used to achieve lightweight resource virtualization on satellites. The network management component is used to establish and maintain the network topology of the satellite cluster and manage the dynamically changing satellite network to maintain the network connection of the edge cloud; The node management component manages the nodes of the edge cloud, maintains the node registry in the management cluster, responds to the dynamic joining or exit of edge nodes, and eliminates node conflicts in the cluster.

7. An edge cloud self-organizing method according to any one of claims 1 to 4, characterized in that: By adopting the edge cloud system described in any one of claims 5 to 6, the network management component in the satellite node that receives the task requirement or initiates the task request initiates the demand for building the edge cloud, and dynamically negotiates after the edge cloud is built to maintain the edge cloud networking operation until all tasks are completed.

Images