Fault detection and resource reconstruction system for communication resource pooling equipment

Abstract

The invention relates to a fault detection and resource reconstruction system for communication resource pooling equipment, and belongs to the technical field of satellite communication. The data sensing module obtains data information such as health, communication, service and control in the terminal in real time, historical data and real-time data are sent to the intelligent prediction module to predict data changes in a period of time in the future, prediction results and the real-time data are sent to the fault decision module, and the fault decision module integrates the data information in the terminal and sends the data information to the intelligent prediction module. Modeling, analyzing and solving the fault tree model, analyzing and planning resource pooling equipment through a resource planning module if the fault is analyzed to have occurred or inevitable in a period of time in the future, obtaining a usable link, and completing seamless automatic switching of services through a resource reconstruction module. Intelligent fault detection and resource reconstruction of satellite communication resource pooling equipment are realized through an integrated process of perception, prediction, decision making, planning and execution.

Description

Technical Field

[0001] The present invention belongs to the field of satellite communication technology and is particularly suitable for intelligent fault detection and resource reconstruction of general satellite communication resource pooling equipment. Background Art

[0002] In the field of satellite communications, resource pooling terminals have a wide variety of resources and a large number of them. The resources are highly heterogeneous, the resource status changes dynamically, resource access and exit are flexible, and real-time requirements are high. The external satellite communication network topology may change at any time, and user task synchronous data, asynchronous data, voice services, etc. are different. These have brought huge challenges to the resource management and resource reconstruction of pooled terminals.

[0003] Performance demands on existing pooled terminals extend beyond the expansion and integration of various functions. These demands also include optimized allocation and rational reconfiguration of system resources; real-time, accurate, and reliable task execution; and personalized user services. Pooled terminals contain a large number of heterogeneous resources interconnected via SRIO / networks. The interconnection and interoperability between these various elements in the system require appropriate resource management and reconfiguration support to maximize the overall effectiveness of the system. Therefore, resource reconfiguration technology is one of the key technical bottlenecks affecting pooled terminal performance.

[0004] Intelligent fault diagnosis is a crucial step in triggering the reconfiguration of heterogeneous computing resources in pooled terminals. This process relies on accurate, real-time perception of the physical state of the pooled terminals. By acquiring data from sensors, AD / DA, and other sensors, the fault diagnosis module can accurately obtain terminal status information to make appropriate decisions. Intelligent fault diagnosis is an effective means of improving the stability and reliability of task processing in pooled terminals. Therefore, for heterogeneous pooled resources in the satellite communications field, research on how to trigger efficient resource reconfiguration is of great theoretical and practical significance.

[0005] Traditional resource management technologies, such as grid computing and distributed cluster systems, primarily consider homogeneous resources, such as computing or data resources. They offer limited consideration for the heterogeneous nature of software and hardware resources and the dynamic state changes found in pooled satellite communication terminals. Existing resource management systems typically focus on resource registration, discovery, and allocation, but lack sufficient consideration for heterogeneous resource management and reconstruction, as well as for dynamic changes in terminal communication and service states. Summary of the Invention

[0006] The technical problem to be solved by the present invention is to provide an intelligent fault detection and resource reconstruction system suitable for satellite communication resource pooling equipment. In view of the problems of the large variety of software and hardware resources, strong resource heterogeneity, high service real-time and reliability requirements in the resource pooling terminals in the current satellite communication field, higher requirements are put forward for the optimal configuration and reasonable reconstruction of system resources, as well as real-time, accurate and reliable task execution. Therefore, resource management and resource reconstruction are necessary for the system to be effective.

[0007] The present invention achieves the above effects through the following technical solutions:

[0008] A fault detection and resource reconstruction system for communication resource pooling equipment, used to complete fault detection, resource management and reconstruction; including a data perception module, a prediction module, a fault decision module, a resource planning module and a resource reconstruction module;

[0009] Fault detection process: The data perception module acquires health, communication, business, and control data information of the system's internal resources in real time and stores the acquired real-time status information in a database. The prediction module uses historical data and real-time status information and utilizes the LSTM algorithm to predict data changes over a period of time. Based on the data change trend, it predicts the critical point where faults will occur and issues fault warnings for resources that may fail. The fault decision module receives fault prediction results and implementation status information and integrates the terminal's internal data information to build, analyze, and solve the fault tree model. This allows for real-time status analysis and fault warnings for multi-variable faults and locates fault resources.

[0010] Resource management and reconstruction process: If the fault decision module finds through analysis that a fault has occurred or is unavoidable in the future, it will send the warning result and the fault module resource identifier to the resource planning module; the resource planning module will first search the pre-allocated link table. If there is an idle pre-allocated link, it will enable the idle pre-allocated link. If there is no idle link in the pre-allocated link table, dynamic resource planning will be carried out, traversing the idle resources, and planning all idle resources at the same time, finding available communication links and completing seamless switching of services through the resource reconstruction module.

[0011] Furthermore, the resource planning module and resource reconstruction module model the software and hardware resources of the satellite communication resource pooling equipment, use the resource model for dynamic planning, and form a mission topology. During the mission operation, idle resources not occupied by business are planned as pre-allocated links as a backup link for ongoing business communications.

[0012] The fault diagnosis results are used as external incentives to trigger real-time dynamic planning of pooled terminals, giving priority to enabling pre-planned links. The snapshot service and resource reconstruction module are used to identify faulty resources based on the received warning results and the resource identifiers of the fault module. Resource planning is performed to complete service switching without affecting other channels of running business communications.

[0013] Furthermore: the snapshot service records the mapping relationship between the current waveform operating parameters and the resource model in real time; when an abnormality or failure occurs, it quickly restores to the state of the existing snapshot.

[0014] Compared with the prior art, the present invention has the following beneficial effects:

[0015] 1. The fault detection and resource reconstruction module is integrated into the satellite communication resource pooling equipment. It has a lightweight, intelligent, and modular embedded architecture design. Through the integrated process of perception-prediction-decision-planning-execution, it realizes intelligent fault detection and resource reconstruction of satellite communication equipment.

[0016] 2. Through the resource planning module and resource reconstruction module, the rapid, efficient and reliable management, planning and reconstruction of the heterogeneous resources of the satellite communication resource pooling equipment are realized, ensuring the reliable and stable operation of the communication links and data services of the satellite communication resource pooling equipment

[0017] 3. Take data-driven, proactive perception, and autonomous detection of complex and ever-changing heterogeneous pooled resource environments, and accurately describe the operating status of resource pooled terminals through fault tree models to achieve rapid and reliable intelligent fault detection.

[0018] 4. The present invention adopts a unique channel-based parameter snapshot service and link pre-planning strategy to achieve rapid recovery and establishment of tasks when a failure occurs. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is a schematic diagram of satellite communication resource pooling equipment fault detection and resource reconstruction according to the present invention;

[0020] Figure 2 It is a schematic diagram of fault tree modeling of resource pooling equipment.

[0021] Figure 3 This is a schematic diagram of single-channel resource planning and task flow for resource pooling equipment.

[0022] Figure 4 This is a diagram of task topology planning. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below in conjunction with the embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0024] Reference Figure 1 The present invention studies the reconstruction problem of a large number of heterogeneous resources in resource pooling terminals in the field of satellite communications during the execution of tasks. It adopts data-driven, proactive fault diagnosis services, perceives and operates in complex and constantly changing dynamic heterogeneous environments, effectively utilizes terminal operation data, knowledge, information and computing resources, proposes corresponding reconstruction strategies and algorithms for different types of resources, deeply integrates resource management and resource reconstruction based on perception, and performs intelligent fault detection and resource reconstruction on satellite communication resource pooling equipment in a safe, reliable and real-time manner.

[0025] By integrating the technology of combining intelligent fault diagnosis and resource reconstruction into the pooled terminal of satellite communication equipment, the method includes five parts: data perception module, intelligent prediction module, fault decision module, resource planning module and resource reconstruction module integrated inside the satellite communication equipment. Through the integrated process of perception-prediction-decision-planning-execution, intelligent fault detection and resource reconstruction of satellite communication resource pooling equipment are realized.

[0026] The modules for completing the functions of the present invention include: a data perception module, a prediction module, a fault decision module, a resource planning module and a resource reconstruction module.

[0027] The data perception module obtains real-time data information such as health, communication, business and control inside the terminal through various modules such as sensors, FPGA, CPU and AD / DA.

[0028] The prediction module predicts data changes in the future and sends the predicted data and real-time data to the fault decision module.

[0029] The fault decision module integrates the internal data information of the terminal, models and analyzes the fault tree model, and obtains real-time fault or fault prediction results through analysis.

[0030] The resource planning module plans according to the software and hardware resource descriptions and models of the satellite communication resource pooling equipment, and adopts a pre-allocation strategy to plan idle resources not occupied by business as backup links.

[0031] Fault diagnosis and prediction results serve as external incentives to trigger real-time dynamic planning of pooled terminals. Resource reconstruction prioritizes pre-planned links, quickly enables snapshot services, and completes seamless business switching through the resource reconstruction module.

[0032] The resource planning and resource reconstruction modules model the software and hardware resources of the satellite communication resource pooling equipment, using the resource model for dynamic planning to form a mission topology. During mission execution, idle resources not occupied by business operations are allocated as pre-allocated links. Fault diagnosis results are used as external stimuli to trigger real-time dynamic planning within the pooled terminals. This planning process does not affect ongoing services or communication links. Resource reconstruction prioritizes pre-planned links, ensuring real-time, efficient, and reliable service switching.

[0033] The resource reconstruction module utilizes a unique channel-based snapshot service. This service records the mapping between the current waveform operating parameters and the model in real time. This service allows for rapid recovery to the existing snapshot state in the event of an anomaly or failure. This service is primarily used for rapid task establishment and recovery, as well as rapid failover and recovery.

[0034] The data perception module obtains the health, communication, business and control data of the terminal in real time through various modules such as sensors, FPGA, CPU and AD / DA, and adopts dynamic fault tree modeling under multivariable conditions. The fault tree modeling diagram is shown in the attached figure. Figure 2 , attached Figure 2 Fault tree modeling adopts the system reliability analysis method. First, the top event, that is, the analysis target, is determined. Then, the event decomposition is completed and the logical relationship between each event is determined to complete the fault analysis.

[0035] In order to achieve unified management of heterogeneous software and hardware resources, satellite communication resource pooling equipment uniformly addresses all resources, establishes resource identification, and models software and hardware resources. The single channel resource planning and task flow diagram is shown in the attached figure. Figure 3 As shown, attached Figure 3 It identifies the basic hardware resource components of a single channel of the device and the basic flow of satellite communication RF signals. The various software / hardware units together constitute the data channel of the satellite communication terminal.

[0036] The resource planning module first searches the pre-allocated link table and performs dynamic resource planning to achieve dynamic planning of business units, protocol units, confidentiality units and baseband units, and plans available communication links. The task topology planning diagram is shown in the attached figure. Figure 4 As shown, attached Figure 4 The interface planning and variable rules of each unit are described. Through the dynamic resource planning of the resource planning module, the connection rules of each software and hardware unit are changed to achieve dynamic available link planning.

[0037] For resource pooling terminals for satellite communications, fault detection models and manages sensor data based on satellite communications domain knowledge, employing a fault tree model to comprehensively evaluate health, communication, service, and control data. This allows for the detection of current faults while predicting future faults. Based on the evaluation results, parameter snapshot services and resource pre-planning are used to reconfigure the software and hardware resources within the pooled terminal in real time. This method supports parallel processing of multiple services and can efficiently and reliably reconfigure equipment resources based on fault detection results without impacting service data on other channels. More specific fault detection, resource management, and reconstruction are as follows:

[0038] Fault diagnosis is mainly divided into the following steps:

[0039] (101) Based on the knowledge of satellite communication, the fault tree model is used to model the data of resource pool terminal perception health, communication, business and control, such as Figure 1 shown.

[0040] (102) The data perception module obtains the health, communication, business and control data information inside the terminal in real time through various modules such as sensors, FPGA, CPU and AD / DA, and stores it in the database.

[0041] (103) The historical data and real-time data are sent to the prediction module. The prediction module uses the LSTM algorithm to predict the data changes in the future. Based on the data change trend, the critical point of failure is predicted, and a fault warning is issued for resources that may fail.

[0042] (104) The warning results and real-time status are sent to the fault decision module. The fault decision module integrates the internal data information of the terminal, models and analyzes the fault tree model, completes the multivariable fault real-time status analysis and fault warning, and completes the fault resource location.

[0043] (105) If the analysis shows that the fault has occurred or is unavoidable in the future, the warning result and the fault module resource identifier are sent to the resource planning module.

[0044] Resource management and reconstruction are mainly divided into the following steps:

[0045] (201) In order to achieve unified management of resource pooling terminal resources, the heterogeneous resources in the device are uniformly coded, resource identification is established, and the software and hardware resources are modeled, such as Figure 2 shown.

[0046] (202) After the satellite communication pool terminal is powered on, the resource reconstruction module dynamically plans based on the software and hardware resource description and model of the satellite communication resource pool device to form a task topology. At the same time, a pre-allocation strategy is adopted to plan idle resources not occupied by business operations as pre-allocated links, which serve as link backups for ongoing business communications.

[0047] (203) The channel snapshot service is enabled to quickly configure the running channel and the backup channel and take a real-time snapshot. The channel snapshot service includes the setting parameters and dynamic adjustment parameters issued by the user, such as the real-time adjustment of the transmission level parameters, etc., which are used for the rapid establishment of the pre-allocated link.

[0048] (204) The intelligent fault diagnosis result is used as an external stimulus to trigger the real-time dynamic planning of the pooled terminal. The resource reconstruction module identifies the faulty resources based on the received warning results and the resource identification of the fault module, and performs resource planning without affecting other channels of running business communications, such as Figure 3 shown.

[0049] (205) The resource planning module first searches the pre-allocated link table. If there is an idle pre-allocated link, the idle pre-allocated link is enabled. If there is no idle link in the pre-allocated link table, dynamic resource planning is performed, and the business unit, protocol unit, confidentiality unit and baseband unit are searched in turn, and the idle resources are traversed. At the same time, all idle resources are planned to find available communication links.

[0050] (206) The snapshot service is used to quickly enable the idle communication link found by the resource planning module and complete the seamless switching of the business through the resource reconstruction module.

Claims

1. A fault detection and resource reconstruction system for communication resource pooling equipment, used to complete fault detection, resource management and reconstruction; characterized in that: It includes data perception module, prediction module, fault decision module, resource planning module and resource reconstruction module; Fault detection process: The data perception module obtains health, communication, business, and control data information of the system's internal resources in real time, and stores the obtained real-time status information in the database; The prediction module uses historical data and real-time status information and the LSTM algorithm to predict data changes over a period of time. Based on the data change trend, it predicts the critical point where failures will occur and issues fault warnings for resources that may fail. The fault decision module receives fault prediction results and implementation status information and integrates the terminal's internal data information to build and analyze the fault tree model, realize multi-variable fault real-time status analysis and fault warning, and complete fault resource location; Resource management and reconstruction process: If the fault decision module determines through analysis that a fault has occurred or is unavoidable in the future, it will send the warning result and the fault module resource identifier to the resource planning module; The resource planning module first searches the pre-allocated link table. If there is an idle pre-allocated link, the idle pre-allocated link is enabled. If there is no idle link in the pre-allocated link table, dynamic resource planning is performed, the idle resources are traversed, and all idle resources are planned at the same time to find the available communication links and complete the seamless switching of services through the resource reconstruction module.

2. The intelligent fault detection and resource reconstruction method for satellite communication resource pooling equipment according to claim 1, characterized in that: The resource planning module and resource reconstruction module model the software and hardware resources of satellite communication resource pooling equipment, use the resource model for dynamic planning, and form a task topology; During task execution, idle resources not occupied by business operations are planned as pre-allocated links to serve as backup links for ongoing business communications. The fault diagnosis results are used as external incentives to trigger real-time dynamic planning of pooled terminals, giving priority to enabling pre-planned links. The snapshot service and resource reconstruction module are used to identify faulty resources based on the received warning results and the resource identifiers of the fault module. Resource planning is performed to complete service switching without affecting other channels of running business communications.

3. The intelligent fault detection and resource reconstruction method for satellite communication resource pooling equipment according to claim 2, characterized in that: The snapshot service records the mapping relationship between the current waveform operating parameters and the resource model in real time; when an abnormality or failure occurs, it quickly restores to the state of the existing snapshot.

Images