CN114531197A - On-orbit distributed information resource application service system - Google Patents

Abstract

The present invention provides an on-orbit distributed information resource application service system, comprising: a service platform layer for integrating, encapsulating and managing the computing resources, storage resources, communication resources, data resources and plug-in resources of the distributed on-orbit satellites, so as to Provide mission planning services, data processing services and information extraction services to the on-orbit satellites; a hardware environment layer is used to support the operation of the software programs required by the service platform layer for mission planning services, data processing services and information extraction services; The application plug-in layer is used for developing, integrating and running the plug-in resources required by the task planning service, data processing service and information extraction service under the support of the service platform layer.

Description

On-orbit Distributed Information Resource Application Service System

technical field

The invention relates to the technical field of on-board real-time processing of remote sensing satellite data, in particular to an on-orbit distributed information resource application service system.

Background technique

At present, the space-based information processing and service methods still follow the traditional mode of ground planning, command annotation, space-based observation, data download, ground processing, and product distribution. Simple processing such as detection and positioning cannot meet the new space-based information service requirements of rapid data acquisition and multi-source and multi-scale information fusion. In addition, the current on-board processing system design is mainly for single-satellite and single-load data processing applications, and is customized according to the characteristics of satellites and payloads. It is not versatile and cannot adapt to diverse information including mission planning, data processing, and information extraction. Service requirements, and can not meet the application requirements of networked collaborative information services under the conditions of multi-satellite networking in the future.

SUMMARY OF THE INVENTION

In view of this, the present invention provides an on-orbit distributed information resource application service system, including: a service platform layer for integrating, encapsulating and managing the computing resources, storage resources, communication resources, data resources and Plug-in resources to provide mission planning services, data processing services and information extraction services to orbiting satellites; the hardware environment layer is used to support the service platform layer and upper-layer applications to perform mission planning services, data processing services and information extraction services required software programs The application plug-in layer is used to develop, integrate and run the plug-in resources required by the task planning service, data processing service and information extraction service under the support of the service platform layer.

Optionally, the service platform layer includes: a platform resource management module for managing and maintaining the status information of the satellites in orbit and the status information of the loads corresponding to the satellites in orbit, so as to provide mission planning services and data processing services; a processing engine module , which is used to realize the aggregation, scheduling and execution of task processes from computing resources, plug-in resources to task planning services, data processing services and information extraction services respectively; the data organization management module is used to store and update data resources in a unified manner , transmission, retrieval and access; among them, data resources include original observation data, mission planning services provided by orbiting satellites and payloads, processing data and basic support data generated by data processing services and information extraction services respectively; constellation resource management module, It is used to manage various resources of distributed on-orbit satellites to achieve coordinated observation, data synchronization and data fusion of distributed on-orbit satellites; the security management module is used to identify users who access the on-orbit satellites. Authentication and lightweight data protection; the communication service module is used to encapsulate the interface provided by the underlying communication network device to provide a reliable communication service interface supporting message and file transmission.

Optionally, the data organization and management module performs data life cycle management on the original observation data, processing data and basic support data; the data organization and management module provides multi-process and/or multi-thread concurrent retrieval and access methods to retrieve and access the original observation data. , processing data and basic supporting data.

Optionally, the constellation resource management module realizes data synchronization between distributed on-orbit satellites, including: the constellation resource management module controls an on-orbit satellite to publish incremental data resources and plug-in resources only to adjacent satellite nodes.

Optionally, the constellation resource management module realizes the distribution of data among the distributed on-orbit satellites by means of regular broadcast or subscription or query access.

Optionally, the communication service module implements reliable transmission of data resources based on a reception check and retransmission mechanism.

Optionally, the hardware environment layer adopts a board-type structure, including: a main control board, which is used to support the service platform layer and upper-layer applications to run software programs required for task planning services, data processing services, and information extraction services; co-processing Boards are used to encapsulate hardware resources with different processing capabilities according to standards for data processing services; storage boards are used to store data resources and processing data generated by task planning services, data processing services and information extraction services respectively.

Optionally, the interface type of the main control board can be dynamically configured according to the requirements of the orbiting satellites; the number of co-processing boards can be dynamically configured according to the data processing requirements of the payloads corresponding to the orbiting satellites.

Optionally, the application plug-in layer uses an incremental update strategy to update plug-in resources.

Optionally, the service platform layer performs task scheduling according to the priority of the task and the currently allocated computing resources.

Description of drawings

The above and other objects, features and advantages of the present invention will become more apparent from the following description of embodiments of the present invention with reference to the accompanying drawings, in which:

FIG. 1 schematically shows an architecture diagram of an on-orbit distributed information resource application service system according to an embodiment of the present invention.

FIG. 2 schematically shows an architecture diagram of a service platform layer according to an embodiment of the present invention.

FIG. 3 schematically shows a functional block diagram of an architecture of a service platform layer according to an embodiment of the present invention.

FIG. 4 schematically shows a functional block diagram of a platform resource management module according to an embodiment of the present invention.

FIG. 5 schematically shows a block diagram of a workflow of a processing engine module according to an embodiment of the present invention.

FIG. 6 schematically shows a flowchart of automatic aggregation scheduling of services according to an embodiment of the present invention.

FIG. 7 schematically shows a flowchart of fault reconstruction according to an embodiment of the present invention.

FIG. 8 schematically shows a work flow diagram of a data organization and management module according to an embodiment of the present invention.

FIG. 9 schematically shows a work flow chart of resource release and organization management according to an embodiment of the present invention.

FIG. 10 schematically shows a flowchart of processing a resource broadcast packet according to an embodiment of the present invention.

FIG. 11 schematically shows a flowchart of multi-star distributed computing resource scheduling according to an embodiment of the present invention.

FIG. 12 schematically shows a flow chart of releasing a constellation resource according to an embodiment of the present invention.

FIG. 13 schematically shows a flowchart of query and download of constellation data resources according to an embodiment of the present invention.

FIG. 14 schematically shows a flowchart of an application plug-in betting according to an embodiment of the present invention.

FIG. 15 schematically shows a flowchart of requirement submission, task planning and data processing according to an embodiment of the present invention.

FIG. 16 schematically shows a flow chart of data distribution according to an embodiment of the present invention.

Detailed ways

In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to specific embodiments and accompanying drawings. Obviously, the described embodiments are some, but not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

The terminology used herein is for the purpose of describing specific embodiments only, and is not intended to limit the present invention. The terms "comprising", "comprising" and the like as used herein indicate the presence of stated features, steps, operations and/or components, but do not preclude the presence or addition of one or more other features, steps, operations or components.

In the present invention, unless otherwise expressly specified and limited, terms such as "installation", "connection", "connection" and "fixation" should be understood in a broad sense, for example, it may be a fixed connection or a detachable connection, It can be a mechanical connection or an electrical connection or can communicate with each other; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the internal communication between the two elements or the interaction relationship between the two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

In the description of the present invention, it is to be understood that the terms "longitudinal", "length", "circumferential", "front", "rear", "left", "right", "top", "bottom", The orientation or positional relationship indicated by "inside", "outside", etc. is based on the orientation or positional relationship shown in the accompanying drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the indicated subsystem or element must be It has a specific orientation, is constructed and operates in a specific orientation, and therefore should not be construed as a limitation of the present invention.

Throughout the drawings, the same elements are denoted by the same or similar reference numbers. Conventional structures or constructions will be omitted when they may obscure the understanding of the present invention. And the shape, size and positional relationship of each component in the figure do not reflect the actual size, proportion and actual positional relationship. In addition, in the present invention, any reference signs placed between parentheses shall not be construed as limiting the present invention.

Similarly, in the above description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together into a single embodiment, figure or in the description. Description with reference to the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc. means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example includes in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

In addition, the terms "first" and "second" are only used for descriptive purposes, and should not be construed as indicating or implying relative importance or implying the number of indicated technical features. Thus, a feature defined as "first", "second" may expressly or implicitly include one or more of that feature. In the description of the present invention, "plurality" means at least two, such as two, three, etc., unless otherwise expressly and specifically defined.

In view of the deficiencies of the prior art, the embodiments of the present invention provide an on-orbit distributed information resource application service system, which integrates observation, communication, computing, storage and other resources of distributed on-orbit satellites, and performs resource encapsulation, Through the automatic aggregation and organization of various software and hardware resources, data processing integration and information services are realized. The whole system adopts the architecture of "platform + plug-in". The advantage of adopting this architecture design is that on the one hand, the system can be universally installed on each satellite, and the unified development, integration and product specifications are adopted to facilitate the construction of multi-satellite network applications; on the other hand, it can be targeted according to the characteristics of satellite loads. Customized development of data transmission and processing plug-ins, making full use of single-satellite computing and storage resources to achieve high-precision processing of payload data.

FIG. 1 schematically shows an architecture diagram of an on-orbit distributed information resource application service system according to an embodiment of the present invention.

As shown in FIG. 1 , the on-orbit distributed information resource application service system may include, for example, a service platform layer, a hardware environment layer and an application plug-in layer.

The service platform layer is used to integrate, encapsulate and manage the computing resources, storage resources, communication resources, data resources and plug-in resources of the distributed satellites in orbit to provide mission planning services, data processing services and information extraction services to the orbiting satellites.

In the embodiment of the present invention, the service platform layer is also called the space-based information resource application service platform, which is the key to realize the autonomous operation and information service of the on-orbit distributed information resource application service system. The service platform layer standardly encapsulates the computing resources, storage resources, communication resources, data resources and plug-in resources of each satellite platform (including on-orbit satellites and payloads), hides the technical implementation details, and provides a unified access scheduling interface for the above resources to the outside world, thereby Effective separation between resource calls and resource entities is achieved.

The hardware environment layer is used to support the operation of the software programs required by the service platform layer and upper-layer applications for task planning services, data processing services and information extraction services.

In the embodiment of the present invention, the hardware environment layer adopts a board-type structure, including: a main control board, a co-processing board, a storage board, and the like. The main control board is used to support the operation of the software programs required for the service platform layer and upper-layer applications to perform task planning services, data processing services and information extraction services, that is, the service platform layer software runs on the processor of the main control board to achieve various The bearer of the application service capability. The main control board is also used to realize various data and information exchanges with the satellite service computer, earth observation payload and communication payload. The co-processing board is used to encapsulate hardware resources with different processing capabilities according to standards to perform data processing services, such as computing-intensive tasks such as load data processing. The storage board is used to store various data resources, including the storage of on-orbit processing products and basic support data generated from various payload raw data, mission planning services, data processing services, and information extraction services for on-orbit satellites. Among them, the interface type of the main control board can be dynamically configured according to the requirements of the orbiting satellite. The number of co-processing boards can be dynamically configured according to the data processing requirements of the load.

The application plug-in layer is used to develop, integrate and run plug-in resources required for various task planning services, data processing services and information extraction services under the support of the service platform layer.

In the embodiment of the present invention, the application plug-in layer is a resource invocation combination method developed on the service platform layer. The application plug-in layer further encapsulates independent space-based resources towards space-based information services, and realizes the development and integration of mission planning, various payload data processing, target detection and identification, and information fusion plug-ins based on unified standard specifications, and automatically aggregates into The information service process runs automatically under the scheduling of the service platform layer.

Therefore, the on-orbit distributed information resource application service system provided by the embodiment of the present invention can be universally adapted to each satellite platform. The service platform layer can be universally deployed on the main control board of each satellite platform, and can be adapted to multi-type processors. The application plug-in layer is customized according to the characteristics of the satellite platform and observation load, and is integrated on the service platform layer according to the unified interface specification. Customize various personalized information service processes according to user needs.

The on-orbit distributed information resource application service system shown in FIG. 1 will be described in detail below with reference to the accompanying drawings.

The core of the system design of the on-orbit distributed information resource application service system is the service platform layer, that is, the space-based information resource application service platform. The space-based information resource application service platform realizes the abstract encapsulation of various underlying hardware drivers, and realizes standard satellite resources, satellite-ground communication, inter-satellite communication and data storage access interfaces. It has functions such as computing resource management, data management, plug-in management and process aggregation. At the same time, the distributed integration of multi-satellite resources is realized based on the inter-satellite communication network.

FIG. 2 schematically shows an architecture diagram of a service platform layer according to an embodiment of the present invention.

FIG. 3 schematically shows a functional block diagram of an architecture of a service platform layer according to an embodiment of the present invention.

As shown in Figures 2 and 3, the service platform layer may include, for example, a platform resource management module, a communication service module, a processing engine module, a data organization management module, a constellation resource management module, and a security management module, a total of six functional modules.

The platform resource management module is used to manage and maintain the status information of the satellites in orbit and the status information of the payload, so as to provide mission planning services and data processing services.

Specifically, the platform resource management module manages and maintains the satellite platform status information and payload working status, so that related applications such as payload data processing and autonomous mission planning can access satellite-related resource data. The platform resource management module receives the load observation raw data pushed by the earth observation load, and pushes it to each processing module for processing. The platform resource management module builds a payload proxy service according to the payload type carried by this satellite, realizes a unified description of payload parameter information and status information, provides a payload control interface, and issues observation tasks to the payload according to the upper-layer application plug-in request. That is, the platform resource management module implements the encapsulation of various resources provided by satellites and payloads to form an interface for resource access and control. The upper-layer application plug-ins can use standard interfaces to access and control resources without paying attention to the underlying details.

FIG. 4 schematically shows a functional block diagram of a platform resource management module according to an embodiment of the present invention.

As shown in FIG. 4 , the platform resource management module may, for example, include two parts: resource agent service and system hardware resource management.

The resource agent service is used to manage and maintain the status information of the satellite platform and the working status of the payload. By interacting with the satellite platform, it obtains satellite orbit, attitude, energy, storage and other information, and stores and manages various data, which facilitates the access to platform resource data for related applications such as payload data processing and mission planning. At the same time, according to the type of load carried by the platform, a load proxy service is constructed to realize the unified description of load parameter information and status information, and provide a load control interface, and issue observation tasks to the load according to the upper-layer application plug-in request.

The system hardware resource management is used to be responsible for the switch control and working state switching of various boards in the hardware environment layer. System hardware resource management realizes monitoring of hardware resource status, maintains a list of system available resource information, and controls various types of board switches and working state switching based on the system available hardware resource list. The states that can be monitored include the running state of the processor, the voltage and temperature of each main chip, and so on. By analyzing the acquired monitoring information, it is determined whether the system hardware is faulty, and the faulty hardware is powered off or restarted to achieve fault isolation and recovery. At the hardware device level, the hardware watchdog is used to monitor the status of each board. When the communication between the board and the watchdog is abnormal, the hardware device is restarted. When it is judged that the hardware has a permanent failure, the equipment is isolated.

In addition, the system hardware resource management sends the collected hardware status information to the satellite platform and downloads it to the ground, which provides decision-making basis for system fault judgment and fault-tolerant reconstruction. After receiving the system reconfiguration instruction, modify the list of available resource information of the system, and complete the functional reconfiguration of the FPGA and other chips.

The processing engine module is used to realize the aggregation, scheduling and execution of the respective task processes from computing resources and plug-in resources to task planning services, data processing services and information extraction services.

Specifically, the processing engine module implements the scheduling and execution of all processing procedures from computing resources, application plug-ins to business processes. Among them, a plug-in is a well-packaged executable software or function library that can realize specific functions. Multiple plug-ins can be aggregated to form a complete business process, and can cooperate to complete requests according to user requirements and certain rules. Aggregation of processes can leverage smaller, simpler, and easy-to-execute lightweight plug-ins to create complex processes that are richer in functionality and easier for users to customize. Various related plug-ins are organically organized into a more usable complete process to support complex applications. The processing engine module realizes the scheduling of computing resources such as CPU, FPGA, and GPU, supports load balancing control and priority scheduling, and has functions such as registration, upgrade, deployment, cancellation and version management of various processing and service plug-ins. To solve the bandwidth bottleneck of the road, an incremental update mechanism for on-orbit plug-ins is designed, based on the unified process description language, it realizes the customization of the process, and automatically creates, starts and runs the process.

FIG. 5 schematically shows a block diagram of a workflow of a processing engine module according to an embodiment of the present invention.

As shown in Figure 5, the processing engine module mainly includes a computing resource scheduling unit, a plug-in management unit and a process aggregation unit.

In the embodiment of the present invention, the computing resource scheduling unit implements unified pool management for multiple types of computing resources borne by the system hardware, performs reasonable resource allocation and balanced control, and realizes the transparency of specific computing nodes to service processing components. The computing resource scheduling unit defines a unified interface for various application plug-ins to access computing resources, shields the hardware differences between different types of computing devices, and provides a standardized parallel computing environment for the computing basic platform.

The computing resource scheduling unit can complete the status monitoring of the processing module and the scheduling and execution of tasks. The load monitoring unit of each processing module is responsible for collecting status information of the processing modules, including resources, memory usage and task execution, and sending the status information and heartbeat signals of the processing modules to the computing resource scheduling unit. The computing resource scheduling unit maintains a list of currently available resources according to the heartbeat signals of each processing module, and implements isolation processing of unavailable resources.

When there is a queuing task in the job task queue, the computing resource scheduling unit obtains the task with the highest priority in the queue, parses its resource requirement information, allocates computing resources according to the currently available resources, and schedules the task to the processing module for processing. The task execution unit of the processing module is responsible for receiving and scheduling the processing tasks, and periodically sending the task execution status to the computing resource scheduling unit during the task execution process. After the task execution is completed, the computing resource scheduling unit realizes the recovery of computing resources.

In the embodiment of the present invention, the plug-in management unit implements functions such as registration, upgrade, deployment, cancellation and version management of various processing and service plug-ins, and supports operations such as query and retrieval of registered plug-ins. Each application plug-in is developed according to the requirements of the application development specification of the space-based information resource application service platform, and is managed in a unified and integrated manner by the plug-in management unit.

Considering the bandwidth limitation of the satellite uplink, it is quite difficult to realize the registration of the complete application plug-in under orbit conditions, so the registration of the service plug-in is mainly pre-installed before the satellite is launched. Under the condition of on-orbit, it mainly completes the upgrade, deployment and logout of the plug-in, and the incremental construction mechanism of the on-orbit plug-in is specially designed for this purpose.

When the application plug-in is registered, the plug-in source code and description information are submitted to the ground plug-in management unit system, and the plug-in executable program and dependency library are deployed to the location specified by the space-based information resource application service platform. The description information of the plug-in is shown in the following table. The parameter template of the plug-in includes the input and output parameter list and processing parameter requirements of the plug-in. The resource requirements of the plug-in include the required number of computing nodes, number of processes, memory size, priority, etc., as shown in Table 1 below. Show.

Table 1

When the plug-in is logged out, change the status of the plug-in description information in the plug-in description table to abolished, and delete the plug-in entity in the corresponding deployment path.

In this embodiment of the present invention, process aggregation refers to using a registered plug-in to form a service process that implements a specific function according to process configuration information pre-defined by a user, and to archive and manage the process configuration information. The process aggregation unit manages and implements the job process based on the workflow technology, and is responsible for the creation, startup, operation and task initiation of process instances, the tracking of process status information, and the control of the execution process. By. The process task queue is used to save the process orders submitted by the upper-layer application. It has a priority queuing function and supports a priority-based dynamic queuing strategy.

FIG. 6 schematically shows a flowchart of automatic aggregation scheduling of services according to an embodiment of the present invention.

As shown in Fig. 6, this process includes two processes of automated business order generation and business process workflow scheduling.

The process of generating the automated business order may be as follows: associating the corresponding processing service process in the process template library according to the processing task information of the task planning. And call the automatic order production unit according to the planned task parameters, modify the relevant work parameters in the template such as startup time, number of processing nodes, data distribution parameters, output requirements, etc., and assign order priorities according to user needs, etc., and finally generate a processing business. Order and submit for execution.

The workflow scheduling process of the business process can be as follows: according to the previously submitted processing business order, the process aggregation unit completes the workflow scheduling of the business process. The process aggregation unit manages and implements the job process based on the workflow technology, and is responsible for the creation, startup, operation and task initiation of process instances, the tracking of process status information, and the control of the execution process. By. The process aggregation unit first extracts the process order in the process queue, generates a process instance, verifies the validity of the processing plug-in corresponding to the task in the process, and submits the task to the computing resource scheduling unit for execution. The process aggregation unit monitors the task execution status of each task node through the computing resource scheduling unit, and updates the execution status of the process.

In addition, when the system is working in orbit, the data processing mission nodes may be affected by factors such as space radiation, resulting in temporary failure of some processing nodes.

FIG. 7 schematically shows a flowchart of fault task reconstruction according to an embodiment of the present invention.

As shown in Figure 7, the working heartbeat monitoring mechanism can be used, and the computing resource scheduling unit can quickly locate the fault processing node, and perform online reconstruction of computing tasks to recover the problem of partial failure. When the overall function of the execution node fails, such as no work heartbeat or the processing process is caught in a permanent failure and cannot resume work on the execution node, the computing resource scheduling unit first removes the faulty execution node, queries the processing task information, and schedules the processing task. Continue to run on the redundant execution node, so as to realize the reconstruction and recovery of the task.

A data organization and management module is used to uniformly store, update, transmit, retrieve and access the data resources; wherein, the data resources include original observation data, the on-orbit satellite and the payload provide mission planning services, Processing data and basic support data generated by the data processing service and the information extraction service respectively.

Specifically, the data organization and management module performs unified organization management, update, transmission and access services for the original observation data of the load, processing products (processing data), and basic support data, and realizes automatic data life cycle management. Data organization and management Intelligently store all kinds of data according to business needs and operating status, so as to achieve efficient data access and efficient use of storage space; provide data retrieval and access services, data organization and management module classifies the storage of data, and prepares data in advance Store directory rules. Among them, the data products are processed on the satellite; the basic support data and characteristic data are mainly pre-loaded before the satellite is launched, and some target data are obtained through the ground annotation or on-board autonomous learning.

FIG. 8 schematically shows a work flow diagram of a data organization and management module according to an embodiment of the present invention.

As shown in Figure 8, the process mainly includes data storage and organization, data retrieval and access, and data life cycle management.

In the embodiment of the present invention, for various data organization and management requirements, a general data organization and management process is abstracted, which mainly includes: data storage, data acquisition, posting and updating, remote deletion and modification, and the like.

Data warehousing: maintain and manage newly generated or newly added data, automatically extract data keyword information, catalog data, verify data files, and then store and manage.

Data acquisition: Receive data access requests, query to obtain the corresponding data and return it to the requester.

Data update: If the data state changes, a data update operation is initiated.

Remote deletion and modification: Support authorized ground operation and control personnel to call data access and management operation functions to complete corresponding deletion and modification commands.

In the embodiment of the present invention, the process of data retrieval and access may be as follows: based on the data storage and organization module, data retrieval and access services are provided to upper-layer application plug-ins and remote resource access agents, and data online browsing is supported. Among them, data retrieval includes methods such as attribute information, geographic information or fuzzy retrieval; for data information with a small amount of data, the retrieval service directly returns the results; for data with a large amount of data such as image products, the upper-layer application plug-in needs to be based on the data address information. Direct access to the storage system. To improve retrieval efficiency, the platform provides metadata sorting and caching mechanisms to improve access hit rates.

In this embodiment of the present invention, dynamic life cycle management is performed on onboard data. In the life cycle management mechanism, the importance of data, frequency of use, generation time, data type and other factors are fully considered to ensure that the most valuable data is stored in the system. Calculate the stored value of data based on the generation time and access frequency of product data. After each platform startup, if the remaining storage capacity of the system is too low and an alarm is issued, the automatic data cleaning process will be started, the value of all product data will be calculated, and the low-value data will be cleaned up according to the predetermined strategy.

The constellation resource management module is used for network management of various resources of distributed satellites in orbit, so as to realize coordinated observation, data synchronization and data fusion of distributed satellites.

Specifically, the constellation resource management module implements network management for various resources of distributed on-orbit satellites, and abstracts and encapsulates the resources of other satellite platforms available in the network, so as to achieve efficient utilization and access to other satellite resources. , to provide basic support for multi-satellite on-orbit collaborative mission planning and information fusion services. Among them, the publishing methods of resources can be divided into three types: regular broadcast, subscription and query access. You can store and manage the received remote satellite resource description information by establishing a directory service, and provide localization for upper-layer applications by building a remote resource access agent. The remote resource usage access service supports the remote data access service.

The constellation resource management module includes resource release and organization management and remote resource access agent.

FIG. 9 schematically shows a work flow chart of resource release and organization management according to an embodiment of the present invention.

As shown in FIG. 9 , in the embodiment of the present invention, the resource publishing mechanism may be as follows: the publishing modes of local resources are divided into periodic broadcasting, subscription, and query access. The platform can adopt an appropriate publishing method according to the needs of the application to improve the utilization efficiency of the inter-satellite communication bandwidth. In order to support joint mission planning and multi-source information fusion, the released resource information includes satellite attitude and orbit status information, storage and energy margin, observation payload resource status, data product metadata information, etc. Local resource release uses a single-hop method to broadcast local resource information to adjacent nodes, and resource information broadcast is triggered by local resource information change events or service request messages. Each resource information broadcast only sends incremental information compared to the previous broadcast, thereby suppressing repeated delivery of service messages, avoiding wasting network bandwidth, and speeding up resource discovery. At the same time, each satellite forwards other satellite resource information received by this satellite to the adjacent nodes. When the routing topology of the satellite network changes, it sends all the resource information to the newly added node. The resource information published locally includes the resource validity period, after which the resource information will become invalid.

For example, the remote resource organization management can be: establishing a directory service to store and manage the received remote resource description information.

Specifically, after receiving the satellite resource broadcast information packet, the data packet is parsed.

FIG. 10 schematically shows a flowchart of processing a resource broadcast packet according to an embodiment of the present invention.

As shown in Figure 10, the remote resource organization and management stores the received resource information of other platforms by establishing a multi-star resource information directory. When the resource expires, the resource is deleted from the multi-star resource information directory. The remote resource organization and management broadcasts the currently collected resource information of other platforms to adjacent nodes in a single-hop manner, so that the satellite resource information can be quickly released to the entire satellite network. Before broadcasting, the satellite resource information to be broadcast is screened to avoid mutual forwarding of the same resource information.

In the embodiment of the present invention, the remote resource access agent includes a remote data access agent, a publish-subscribe management and a multi-star distributed computing service.

For example, the process of the remote data access agent may be: after the user obtains the meta information of the required remote data, the user accesses the remote data according to actual needs. After receiving the user's data access request, send the user's data access request to the remote data access agent. After the remote data access agent matches the corresponding remote satellite according to the metadata information, it sends the data access request to the remote satellite through the inter-satellite link. The satellite's remote data access agent obtains the required data and sends it to the user.

The goal of adopting a publish-subscribe mechanism is to efficiently distribute useful information to nodes that really need it, especially on satellites where inter-satellite and satellite-to-ground communication resources are very scarce. The publish-subscribe mechanism has the characteristics of loose coupling, many-to-many and asynchronous communication, which can effectively avoid the waste of communication bandwidth and realize the truly efficient use of communication resources.

Specifically, the space-based information resource application service platform provides a publish and subscribe mechanism for information for end users to use. The subscription-publishing model consists of publishers, subscribers, and event broker service units. When the data to be published is small, the direct subscription method can be adopted, that is, an event agent service unit is established in the constellation resource management module of each satellite to receive the user's subscription service information, and at the same time, receive the information release of the upper-layer application plug-in. After the subscription information is matched, the information is sent to the event agent service unit of the satellite where the subscriber is located, and then sent to the upper-layer application program of the subscription information through the agent. The event agent service unit has functions such as subscription management, notification service, event monitoring, and event matching. The application plug-in submits the subscription information to the event proxy service unit of the satellite, and the event proxy service unit is associated with the application plug-in ID and unified cache management, and parses the subscription type and image type, and then sends the subscription information to the corresponding satellite event proxy service. unit is managed. After the payload data processing plug-in of each satellite has processed the payload data, it will publish the metadata information of the processing result to the event proxy server of the satellite, and the event proxy server will parse it and match it with the subscription request. The result is sent to the event proxy server of the satellite where the subscriber is located, and the proxy server notifies the application plug-in that initiated the subscription request to read the data. If the application plug-in no longer subscribes to a certain information, it sends a subscription cancellation notification to the event proxy server, which notifies the event proxy server of the corresponding remote satellite to cancel the subscription.

Multi-satellite distributed computing services use the idle computing power of neighboring satellites in the network to assist in completing computing tasks.

FIG. 11 schematically shows a flowchart of multi-star distributed computing resource scheduling according to an embodiment of the present invention.

As shown in Figure 11, the multi-star distributed computing service framework consists of three units: task management, resource management, and task reception and execution.

The task management unit is responsible for receiving distributed computing task information submitted by application plug-ins, including execution plug-in information, calculation input information, computing power requirements, memory usage requirements, storage requirements, and latest completion time requirements. After receiving the computing task, the task management unit notifies the computing resource screening unit to screen the remote satellite resources, completes task scheduling according to the screening result, receives the task execution result, and counts the task completion and resource utilization.

The resource management unit filters out a list of available resources according to the available computing resources, memory, storage resource information, communication link quality, resource availability time and other information of the adjacent satellite platforms, monitors the resource status, and queries the platform's plugin deployment information in the list. . First, search whether the information is stored. If not, query the platform's plug-in deployment status through the remote resource query agent, and finally filter out the list of available resources that meet the remote computing requirements.

The task receiving and executing unit is responsible for receiving computing task information and confirming whether the task can be executed. If the task is executable, the task is submitted to the processing engine for scheduling and execution, and the task execution status information and heartbeat signal are periodically sent during the task execution process. After the execution is completed, the execution result is sent to the task management unit of the task initiation platform. If it cannot be executed, the remote task management unit is notified to reschedule.

The security management module is used to authenticate users who access the orbiting satellite and perform lightweight data protection.

Security authentication mainly refers to the identity authentication of users who access through the satellite-to-earth communication network, to block illegal intrusions, and to design a user authorization access mechanism to support seamless switching between satellite and satellite services of user authentication information to ensure business service access. Continuity and reliability, improve service efficiency. Lightweight data protection implements signature protection for business data to prevent data theft or tampering.

For example, the security management module may include security authentication and data lightweight protection.

In this embodiment of the present invention, the security authentication service includes user management and identity authentication. User management provides administrators with the functions of adding users, editing user information, locking and unlocking users, and deleting users. All kinds of users ultimately need a certain identity to request the on-orbit processing and resource service system to provide specific services, so it is necessary to verify the user's identity and authority. The security authentication service implements authentication of the identity and authority submitted by the user, and only the authenticated user can start the subsequent workflow. The platform allows administrators and multiple types of users with different permissions to log in and access. Therefore, it is necessary to perform authorized access control on users to ensure that users can access corresponding resources according to their permissions.

The space-based information resource application service platform realizes the unified management of the identity of the space network entities; uses the distributed network access identity authentication protocol to improve the efficiency of security authentication; adopts the single sign-on mode, space trust transfer and security switching mechanism to support multiple times of single authentication Access and inter-satellite services are seamlessly switched to ensure the continuity and reliability of business service access and improve service efficiency.

In the embodiment of the present invention, the lightweight data protection mechanism may be as follows: in order to protect the security of the inter-satellite and satellite-to-ground communication data itself, it is necessary to explore a lightweight data self-protection method of hierarchical and multi-category, which can be guaranteed based on business requirements The security of the data itself. The data protection algorithm can use digital signature allocation, TESLA and other algorithms.

The data sending process of the lightweight data protection mechanism is as follows:

First, determine the permission information of the user and data, create a security attribute label for the data packet according to the permission information, and fill in the permission information field.

Then, select and populate the other security attribute tag information fields for the packet, digitally sign the packet and tag, and populate the signature field.

Finally, the processed data is delivered to the communication service module for transmission.

When the space-based information resource application service platform of another satellite receives the protected data, it performs signature verification processing and sends the verified data to the upper-layer application.

The communication service module is used to encapsulate the interface provided by the underlying communication network device to provide the communication service interface.

The communication service encapsulates the interface provided by the underlying communication network equipment, shields the complex network communication details, decouples the upper-layer application and the underlying communication link, and provides the upper-layer communication service interface to achieve efficient and reliable communication between satellites and satellites. Communication services are allocated based on application application priorities and currently available communication capabilities, support dynamic adjustment of application service priorities, and provide transparent data transmission services.

Communication services include transmission task management and data sending and receiving management.

In the embodiment of the present invention, the transmission task management is responsible for the use and distribution of the communication link, and when the upper-layer application plug-in needs to use the communication network, an application for use is made. Transmission task management is responsible for reviewing link use applications and assigning links. Specific functions include: responsible for unified management of inter-satellite and satellite-to-ground communication links, receiving communication requests from application plug-ins, and assigning applications based on priorities and currently available communication capabilities; supporting dynamic adjustment of application service priorities. The transmission task management periodically synchronizes the inter-satellite routing topology with the interconnected communication equipment, maintains the topology routing table, including information such as hop count, link quality, link usage, etc.; responds to the routing query request of the upper-layer application, and feeds back the current routing topology to the application.

In the embodiment of the present invention, data sending and receiving management needs to complete the function of large-capacity data transmission, which is an important guarantee for realizing configuration data posting, application plug-in update, multi-platform information fusion and user terminal product delivery. Data transceiver management effectively solves the problem of "long delay and high bit error rate" in inter-satellite links by establishing a receiving check and automatic retransmission mechanism, ensuring efficient and accurate transmission of data files. In addition, data transceiver management also supports interrupt Point-to-point resuming ensures that the last transmission breakpoint can be accurately resumed when the link is re-established, avoids repeated starts and redundant transmissions, improves transmission efficiency, and ensures data transmission efficiency even in extremely harsh link environments.

After the upper-layer application obtains the link usage permission, the data is serialized with complex parameters and added to the check digit, and then sent to the data transmission buffer queue. At the same time, the data transceiver management sends a message to notify the peer to turn on the receiving mode, and waits for a reply confirmation. After receiving the confirmation message, the underlying driver is called in turn to download the data in the cache queue. After the transmission is completed, it will send an end sign message and wait for the peer Reply to the packet loss retransmission message, and so on and so forth, until the reception complete message is received to end the transmission.

The receiving end sequentially receives and caches the data information sent by the underlying communication module, parses the data packets, and completes the deserialization of complex parameters. The lost message packet information notifies the data sending and receiving management, and so on, until the receiving is complete, sending and receiving a complete message, and finally notifying the corresponding upper-layer application to take the data.

The typical workflow based on the aforementioned on-orbit distributed information resource application service system includes: constellation resource release process, constellation data resource query and download process, application plug-in annotation, requirement submission, task planning and data processing process, and data distribution process.

In the embodiment of the present invention, the constellation resource release process may be, for example, after each satellite in the constellation establishes a communication link through an inter-satellite routing device, synchronize the satellite and load status information with each other, so that each satellite in the constellation can obtain the entire constellation. The satellite and payload resource information in the network creates conditions for each satellite to carry out multi-satellite collaborative mission planning after receiving user requirements.

In order to release the satellite resource information to the entire constellation as soon as possible and avoid wasting bandwidth, the strategy adopted is that the satellite only releases resource information to the adjacent nodes (one hop), and after each satellite receives the information of the adjacent nodes, the current satellite obtained by the satellite will be released. The constellation satellite resource information is forwarded to adjacent nodes, and only incremental data resources and changed data resources are sent during forwarding, thus realizing the rapid release of satellite resources in the entire constellation.

FIG. 12 schematically shows a flow chart of releasing a constellation resource according to an embodiment of the present invention.

As shown in Figure 12, the constellation resource publishing process is described as follows:

(1) The space-based information resource application service platform queries the satellite orbit, attitude, energy and storage information collected by the platform, as well as information such as payload imaging capability, work plan and status.

(2) The platform regularly obtains constellation routing topology information, and publishes satellite resource information to adjacent nodes.

(3) Each satellite space-based information resource application service platform analyzes the satellite resource information received by the satellite, and organizes and manages it in a unified manner.

(4) The platform regularly queries the constellation routing topology information. If the topology connection relationship does not change, go to (5), otherwise go to (6).

(5) The platform regularly or when the resource information changes, forwards this star and the remote resource increment information it has collected to adjacent nodes, go to (3).

(6) Satellites update remote resource information and delete failed resources.

(7) The satellite forwards the satellite and the remote resource information it has collected to the newly added adjacent node, go to (3).

In the embodiment of the present invention, the constellation data resource query and download process may be as follows: after the user accesses the satellite space-based information resource application service platform through the satellite-ground link, he can obtain and use all the resources and services owned by the constellation where the satellite is located. . The space-based information resource application service platform provides constellation data resource query and download services to users who have accessed it. After receiving the query request, the platform first determines the retrieval range of the constellation according to the request type, and sequentially retrieves each satellite within the range of the constellation, obtains data that meets the requirements, and downloads it to the user terminal.

FIG. 13 schematically shows a flowchart of query and download of constellation data resources according to an embodiment of the present invention.

As shown in Figure 13, the constellation data resource query and download process is described as follows:

(1) The satellite space-based information resource service platform receives the user data retrieval request and parses the user request.

(2) The space-based information resource service platform determines the range of satellites in the constellation that perform data retrieval based on the type of user request and the remote resource information collected by this satellite.

(3) If you need to retrieve the data of this star, call the data organization management to retrieve the data information. After retrieving the data that meets the user's needs, it is sent to the user terminal through the satellite-ground link.

(4) Query the remote resource information accessible to the satellite, and send remote data retrieval requests to the satellites within the retrieval range in turn.

(5) After the remote satellite receives the data retrieval request, it queries the data resource information of the local satellite to determine whether the data exists. If the data exists, the data will be transmitted to the request initiating satellite through the inter-satellite link, otherwise it will return no existence.

(6) After the request initiating satellite receives the data information sent by the remote satellite, the data will be sent to the user through the satellite-ground link.

In the embodiment of the present invention, the process of applying plug-in registration may be as follows: users can customize application plug-ins according to their own business needs, and the space-based information resource service platform provides users with application plug-in registration services, and supports users to submit custom process descriptions information. Since the satellite-to-ground uplink resources are very limited, the version update cost of the application plug-in is relatively high. In order to utilize the satellite-ground communication link more efficiently, an incremental update strategy is adopted when the application plug-in is updated. First, the application plug-in code management library is established in the ground center. When the user updates the code, the ground center generates code increment information, which is compressed to obtain the plug-in upgrade patch. When the satellite transits, the plug-in upgrade patch is added through the satellite-ground link. After the plug-in management unit of the space-based information resource application service platform obtains the plug-in update patch, it updates the source code and the code version library, and recompiles the source code to generate an executable program and verify it.

FIG. 14 schematically shows a flowchart of an application plug-in betting according to an embodiment of the present invention.

As shown in Figure 14, the application plug-in registration process is described as follows:

(1) User submits source code.

(2) The ground center compares the source code with the previous version to generate incremental source code information.

(3) Compress the incremental source code information to generate incremental source code patches and post them through the satellite-ground link.

(4) The space-based information resource service platform obtains the plug-in update patch, decompresses it, updates the source code, and updates the code version library.

(5) Compile the source code, generate an executable program and verify it.

(6) Return the plug-in update status information to the ground center through the satellite-ground link.

(7) The ground center updates the version status of the on-board code base to keep pace with the on-board application plug-in version.

(8) The user logs in to the ground center to check the update status of the application plug-in.

In the embodiment of the present invention, the flow of requirement submission, task planning and data processing may be as follows: any satellite in the constellation can provide user access services, and users can browse satellite resource information and submit requirements. After receiving the user's request, the satellite's space-based information resource application service platform will carry out mission planning according to the constellation resource status information obtained by this satellite. After the planning is completed, the mission planning scheme will be sent to the satellite performing the observation mission. Each satellite performing the mission sends the mission plan to the satellite integrated electronics, which controls the payload to observe the earth. After receiving the original observation data sent by the payload in real time, the system initiates product production, and sends the production results to the main star for data fusion processing according to the mission planning requirements to generate the information required by the user.

FIG. 15 schematically shows a flowchart of requirement submission, task planning and data processing according to an embodiment of the present invention.

As shown in Figure 15, the flow of requirement submission, task planning and data processing is described as follows:

(1) Users log in to the satellite space-based information resource service platform after being authorized and authenticated.

(2) The user queries the constellation resource information. If the required information is not retrieved, the user submits the request to the satellite.

(3) After receiving the user's observation request, the space-based information resource application service platform analyzes and obtains the constellation status information, and calls the mission planning plug-in for mission planning.

(4) The space-based information resource application service platform sends the mission planning scheme to each mission satellite.

(5) After receiving the mission planning scheme, each satellite space-based information resource application service platform judges whether the mission planning scheme can be executed according to the satellite load work information. If it can be executed, the mission planning plan will be sent to the satellite integrated electronic, and the confirmation will be returned; if it cannot be executed, the rejection message will be returned.

(6) The space-based information resource application service platform of the mission initiating satellite parses the returned information of each satellite, and if the plan is confirmed, go to (9).

(7) If the plan is rejected, determine whether the demand has timed out. If the demand times out, it will end.

(8) If the demand has not timed out, carry out the mission planning again, and send it to each satellite executing the mission, and turn to (5).

(9) The observation payload of the mission execution satellite executes the mission planning, and at the same time sends the original observation data to the on-orbit distributed information resource application service system for data processing, and transmits the processing results according to the mission planning requirements.

(10) After the processing results of each satellite are summarized, the main satellite completes the data fusion processing to generate the information required by the user.

In the embodiment of the present invention, the data distribution process may be, for example: the space-based information resource application service platform obtains and processes various payload data, generates the data information required by the user, and distributes it to the user through the satellite-ground link. After a user submits a request or a data subscription request, the platform initiates workflows such as mission planning, earth observation, and data processing, which takes a long time. The duration of the user accessing the space-based information resource application service platform through the satellite-ground link is usually No more than 10 minutes, so users can only get the data they need when they access the platform again.

After the user accesses the satellite, the space-based information resource application service platform broadcasts the user's login information in the constellation. After each satellite receives the user's login information, it sends the user's subscription data cached by the satellite to the user.

FIG. 16 schematically shows a flow chart of data distribution according to an embodiment of the present invention.

As shown in Figure 16, the data distribution process is described as follows:

(1) The user logs in to the Space-based Information Resource Service Platform after passing the verification.

(2) The space-based information resource application service platform queries the routing information of the remote satellites accessible to this satellite, and sends the user login information to each satellite in turn.

(3) The space-based information resource application service platform queries the user demand information and data subscription information saved by this star, and retrieves whether there is any data required by the user.

(4) After retrieving the data required by the user, it is sent to the user terminal through the satellite-ground link.

(5) Each satellite space-based information resource application service platform parses the received user login information, queries the user demand information and data subscription information saved by this satellite, and retrieves whether there is any data required by the user.

(6) After retrieving the data required by the user, it is sent to the space-based information resource application service platform where the user logs in to the satellite through the inter-satellite link, and the satellite platform downloads the data through the satellite-ground link.

(7) After the data download is completed, send the data download completion notification to the space-based information resource application service platform of the data source satellite. If the data download is not completed before the user goes offline, it will return the download failure.

(8) Each satellite updates the status information after receiving the notification of completion of data download; if the notification of completion of download is not received, the data status information remains unchanged.

To sum up, the on-orbit distributed information resource application service system provided by the embodiments of the present invention can simultaneously meet application requirements such as multi-satellite collaborative mission planning, single-load data processing, and multi-satellite fusion on a set of hardware systems. In addition, the system has strong scalability and adaptability, and can be applied to different types of remote sensing satellites.

The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains one or more logical functions for implementing the specified functions executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It is also noted that each block of the block diagrams or flowchart illustrations, and combinations of blocks in the block diagrams or flowchart illustrations, can be implemented in special purpose hardware-based systems that perform the specified functions or operations, or can be implemented using A combination of dedicated hardware and computer instructions is implemented. Those skilled in the art will appreciate that various combinations and/or combinations of features recited in the various embodiments of the present invention are possible, even if such combinations or combinations are not expressly recited in the present invention. In particular, the features recited in the various embodiments of the invention may be combined and/or combined in various ways without departing from the spirit and teachings of the invention. All such combinations and/or combinations fall within the scope of the present invention.

Claims (10)

1. An on-orbit distributed information resource application service system, comprising:

the service platform layer is used for integrating, packaging and managing computing resources, storage resources, communication resources, data resources and plug-in resources of the distributed on-orbit satellite so as to provide task planning services, data processing services and information extraction services for the on-orbit satellite;

the hardware environment layer is used for supporting the service platform layer and the upper application to carry out the operation of software programs required by task planning service, data processing service and information extraction service;

and the application plug-in layer is used for developing, integrating and running plug-in resources required by the mission planning service, the data processing service and the information extraction service under the support of the service platform layer.

2. The on-orbit distributed information resource application service system of claim 1, wherein the service platform layer comprises:

the platform resource management module is used for managing and maintaining the state information of the orbiting satellite and the state information of the load corresponding to the orbiting satellite so as to provide the task planning service and the data processing service;

the processing engine module is used for realizing the aggregation, the scheduling and the execution of task flows respectively corresponding to the task planning service, the data processing service and the information extraction service from computing resources and plug-in resources;

the data organization management module is used for uniformly storing, updating, transmitting, retrieving and accessing the data resources; wherein the data resources comprise raw observation data, processing data and basic support data respectively generated by the on-orbit satellite and the load providing mission planning service, the data processing service and the information extraction service;

the satellite group resource management module is used for carrying out networking management on various resources of the distributed on-orbit satellite so as to realize cooperative observation, data synchronization and data fusion of the distributed on-orbit satellite;

the safety management module is used for performing identity authentication and lightweight data protection on a user accessed to the orbiting satellite;

and the communication service module is used for packaging the interface provided by the bottom layer communication network equipment so as to provide a communication service interface.

3. The on-orbit distributed information resource application service system of claim 2, wherein the data organization management module performs data lifecycle management on the raw observation data, the processed data, and the underlying support data;

the data organization management module provides a multi-process and/or multi-thread concurrent retrieval and access manner to retrieve and access the raw observation data, the processed data, and the underlying support data.

4. The in-orbit distributed information resource application service system of claim 2, wherein the constellation resource management module implements data synchronization between distributed in-orbit satellites, comprising:

the constellation resource management module controls an orbiting satellite to only issue incremental data resources and plug-in resources to nodes close to the orbiting satellite.

5. The in-orbit distributed information resource application service system of claim 2, wherein the constellation resource management module implements data distribution among the distributed in-orbit satellites by a distribution means of periodic broadcast or subscription or query access.

6. The on-orbit distributed information resource application service system of claim 2, wherein the communication service module enables transmission of data resources based on a receive checksum retransmission mechanism.

7. The on-orbit distributed information resource application service system of claim 1, wherein the hardware environment layer adopts a card-type structure comprising:

the main control board card is used for supporting the service platform layer and the upper application to carry out the operation of software programs required by task planning service, data processing service and information extraction service;

the co-processing board card is used for packaging hardware resources with different processing capacities according to standards so as to perform the data processing service;

and the storage board card is used for storing the data resources and the processing data respectively generated by the task planning service, the data processing service and the information extraction service.

8. The in-orbit distributed information resource application service system of claim 7, wherein the interface type of the master control board card can be dynamically configured according to the requirements of the in-orbit satellite; the number of the co-processing board cards can be dynamically configured according to the data processing requirements of the loads corresponding to the orbiting satellites.

9. The on-orbit distributed information resource application service system of claim 1, wherein the application plug-in layer updates plug-in resources with an incremental update policy.

10. The on-orbit distributed information resource application service system of claim 2, wherein the service platform layer performs task scheduling according to the priority of tasks and the currently allocable computing resources.

Images