A cloud-coordinated edge node alarm system and method
By designing a cloud-coordinated edge node alarm system, the cloud computing system has solved the problems of storage expansion, network bandwidth, resource consumption and high network dependence when processing massive packet loss data, and achieved efficient data processing and system efficiency improvement.
Patent Information
- Application Number
- CN202110788080.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-07-13
- Publication Date
- 2025-05-13
- Estimated Expiration
- 2041-07-13
AI Technical Summary
When processing massive packet loss data, existing cloud computing systems have problems such as difficulty in expanding storage capacity, insufficient network bandwidth, excessive resource consumption and high network dependence, resulting in inefficient system efficiency and waste of resources.
A cloud-coordinated edge node alarm system is designed to detect and store packet loss rate data through application modules, data matching and arrangement of information service modules, data processing of security modules, edge computing modules perform data edge calculations, and monitoring modules perform abnormal alarms. The system uses cloud transmission module to achieve secure and real-time data transmission, and reduces latency through edge computing and improves system efficiency.
It realizes efficient storage and processing of massive packet loss rate data, reduces resource consumption and delay, improves the operating efficiency and accuracy of the system, and reduces the work intensity of monitoring and operation personnel.
Smart Images

Figure CN113691390B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of edge node alarm technology, and more specifically, to a cloud-coordinated edge node alarm system and method. Background Art
[0002] Load identification of electrical equipment on the residential side is an important research direction of smart grids. The electrical equipment of users is of various types, large scale, and different load characteristics of each equipment. At present, the mainstream electric energy meters installed on the user side only realize the metering function of total power consumption, and do not realize the metering function of classified power consumption according to the nature of electrical equipment. When the detailed energy efficiency composition information of the family can be analyzed, energy-saving suggestions can be made for the power consumption period and power consumption composition of each electrical equipment, so that users can understand the energy consumption status of specific electrical equipment in a timely manner, thereby guiding users to take energy-saving measures independently, reducing electricity bills for users, and effectively reducing energy consumption and unreasonable waste, achieving energy saving and consumption reduction effects.
[0003] With the technological innovation of artificial intelligence and large packet loss rate data, analyzing and extracting useful information from video images has become the direction of business development in all walks of life. The explosive growth of massive and diversified packet loss rate data has also directly promoted the transformation of storage, network, computing and other technologies. Faced with the current massive large packet loss rate data collection and storage, the system architecture based on cloud computing services has many bottlenecks, such as: packet loss rate data storage problems. The massive packet loss rate data storage system does not have the corresponding level of expansion capabilities, and storage expansion even requires downtime, which has a serious impact on the business; insufficient network bandwidth leads to limitations in front-end video and image concurrency, and cannot be efficiently expanded and adapted to large concurrent applications; the redundancy of non-available packet loss rate data stored in the cloud computing center server is too high, resulting in excessive resource consumption of the entire project; the network connection centered on the cloud server needs to transmit the image packet loss rate data back to the server center node for calculation, and then transmit the processing results back to the front end through the network. The whole process is heavily dependent on network speed and network stability, which directly affects the basic use of the view packet loss rate data, and when users connect to new devices, they often cannot correctly identify them, which brings great limitations to the use scenarios of the devices. Summary of the invention
[0004] In view of the above problems, the present invention proposes a cloud-coordinated edge node alarm system, comprising:
[0005] An application module, wherein the application module detects the packet loss rate from the edge node to the operator node, obtains the packet loss rate data, and stores the packet loss rate data in a database in a text form;
[0006] An information service module, wherein the information service module retrieves packet loss rate data stored in a database, matches the packet loss rate data, determines a matching degree according to matching features, and arranges the packet loss rate data according to the matching degree;
[0007] A security module, which is used to process the packet loss rate data and upload it to the edge computing module after the processing is completed;
[0008] An edge computing module, which performs edge computing on the processed packet loss rate data to determine whether data transmission from the edge node to the operator node is abnormal;
[0009] The monitoring module generates an alarm if it determines that data transmission from the edge node to the operator node is abnormal.
[0010] Optionally, the system further includes: a cloud transmission module, wherein the cloud transmission unit is used for data transmission and communication between the system and the cloud, and between modules within the system.
[0011] Optionally, the output end of the application module is connected to the input end of the monitoring module and the information service module, the output end of the monitoring module is connected to the input end of the security module, the output end of the information service module is connected to the input end of the cloud transmission module, the output end of the cloud transmission module is connected to the input end of the edge computing module, and the output end of the edge computing module is connected to the input end of the security module.
[0012] Optionally, application modules include: application service unit, application support unit and application platform;
[0013] The output terminals of the application service unit and the application support unit are connected to the application platform;
[0014] The application service unit is used for edge nodes to provide service component architecture in a runtime environment;
[0015] The application support unit is used to serve the requests processed by the component architecture and stored at the queue point and in the memory;
[0016] The application platform is used to provide an integrated environment for edge node information.
[0017] Optionally, the information service module includes: a fault location unit, a management server and a background controller;
[0018] The input end of the management server is connected to the output end of the application platform and the background controller, and the output end of the management server is connected to the fault location unit.
[0019] Optionally, the fault location unit is used to locate the fault position of the edge node;
[0020] The management server is used to transmit the packet loss rate data to the fault location unit through the application platform;
[0021] The background controller is used to connect the transmission control line to the cloud transmission module.
[0022] Optionally, a security module includes: a data pre-processing unit, a data classification unit and a data clustering unit;
[0023] The input end of the data preprocessing unit is connected to the fault location unit, the output end of the data preprocessing unit is connected to the data classification unit, and the output end of the data classification unit is connected to the data clustering unit.
[0024] Optionally, the data preprocessing unit is used to preprocess the fault packet loss rate data uploaded by the fault location unit to obtain a concept candidate set;
[0025] The data classification unit is used to classify the current edge node fault information under the recorded fault information table;
[0026] The data clustering unit is used to create corresponding fault alarm modes for edge node faults according to the classification results, and to establish a log record of the fault alarm.
[0027] Optionally, the monitoring module includes: a collection unit, an alarm control unit and a signal transmission unit;
[0028] The input end of the acquisition unit is connected to the application platform, the output end of the acquisition unit is connected to the signal transmission unit, and the signal transmission unit is connected to the input end of the alarm control unit.
[0029] Optionally, the collection unit uses large packet loss rate data to obtain public resources of the application platform, and stores the obtained packet loss rate data in a distributed manner.
[0030] The present invention also proposes a cloud-coordinated edge node alarm method, comprising:
[0031] The application module establishes a connection with the local engine, and the application module uploads the packet loss rate data and the fault packet loss rate data to the information service module and the monitoring module in real time;
[0032] The information service module establishes matching operations based on the collected fault information, creates local units corresponding to public safety events, obtains permissions through the cloud transmission module, and establishes a packet loss rate data backup;
[0033] The fault event is compared with the packet loss rate data on the edge side by the edge computing module, which integrates the computing load into the edge layer;
[0034] After the security module visualizes the packet loss rate data, it will simultaneously send out an alarm signal for the fault.
[0035] The cloud transmission module provided in the system of the present invention is used to provide secure, real-time IoT information transmission and intelligent information processing infrastructure capabilities through ultra-narrowband IoT, establish visual, multi-dimensional intelligent packet loss rate data transmission with the cloud, and issue reasonable scheduling instructions to edge nodes through large packet loss rate data and artificial intelligence algorithms, thereby improving the operating efficiency of the system.
[0036] The edge computing module provided in the system of the present invention is used to adopt an open platform that integrates network, computing, storage, and application core capabilities. Its application is initiated on the edge side to generate a faster network service response. The edge computing platform with computing, storage, and application core capabilities processes and analyzes the causes of faults in real time through edge computing. Since it is closer to the location where the fault occurs, it reduces latency and effectively improves program efficiency.
[0037] The present invention completely describes how to analyze and determine the faulty equipment and fault type according to the corresponding key information of the fault, and is conducive to automatic identification and analysis of information problems, intercepting the monitoring information collected by the monitoring module before and after the fault occurs, automatically matching the fault occurrence situation, and after differentiated processing, it is concluded that the fault should send out monitoring information, and the monitoring information sent by the monitoring module is automatically compared and analyzed to obtain the problems of false alarms or omissions in the information, which can achieve controllability, controllability, and controllability, reduce the cost of monitoring information management, reduce the workload of monitoring operators, and improve the efficiency and accuracy of accident handling. BRIEF DESCRIPTION OF THE DRAWINGS
[0038] Figure 1 is a flow chart of the method of the present invention;
[0039] Figure 2 It is a structural diagram of the system of the present invention. DETAILED DESCRIPTION
[0040] Now, exemplary embodiments of the present invention are described with reference to the accompanying drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. These embodiments are provided to disclose the present invention in detail and completely and to fully convey the scope of the present invention to those skilled in the art. The terms used in the exemplary embodiments shown in the accompanying drawings are not intended to limit the present invention. In the accompanying drawings, the same units / elements are marked with the same reference numerals.
[0041] Unless otherwise specified, the terms (including technical terms) used herein have the commonly understood meanings to those skilled in the art. In addition, it is understood that the terms defined in commonly used dictionaries should be understood to have the same meanings as those in the context of the relevant fields, and should not be understood as idealized or overly formal meanings.
[0042] The present invention proposes a cloud-coordinated edge node alarm system, such as Figure 1 As shown, including:
[0043] An application module, wherein the application module detects the packet loss rate from the edge node to the operator node, obtains the packet loss rate data, and stores the packet loss rate data in a database in a text form;
[0044] An information service module, wherein the information service module retrieves packet loss rate data stored in a database, matches the packet loss rate data, determines a matching degree according to matching features, and arranges the packet loss rate data according to the matching degree;
[0045] A security module, which is used to process the packet loss rate data and upload it to the edge computing module after the processing is completed;
[0046] An edge computing module, which performs edge computing on the processed packet loss rate data to determine whether data transmission from the edge node to the operator node is abnormal;
[0047] The monitoring module generates an alarm if it determines that data transmission from the edge node to the operator node is abnormal.
[0048] The cloud transmission module is used for data transmission and communication between the system and the cloud, and between modules within the system.
[0049] Among them, the output end of the application module is connected to the input end of the monitoring module and the information service module, the output end of the monitoring module is connected to the input end of the security module, the output end of the information service module is connected to the input end of the cloud transmission module, the output end of the cloud transmission module is connected to the input end of the edge computing module, and the output end of the edge computing module is connected to the input end of the security module.
[0050] Among them, the application module includes: application service unit, application support unit and application platform;
[0051] The output terminals of the application service unit and the application support unit are connected to the application platform;
[0052] The application service unit is used for edge nodes to provide service component architecture in a runtime environment;
[0053] The application support unit is used to serve the requests processed by the component architecture and stored at the queue point and in the memory;
[0054] The application platform is used to provide an integrated environment for edge node information.
[0055] Among them, the information service module includes: a fault location unit, a management server and a background controller;
[0056] The input end of the management server is connected to the output end of the application platform and the background controller, and the output end of the management server is connected to the fault location unit.
[0057] Wherein, the fault location unit is used to locate the fault position of the edge node;
[0058] The management server is used to transmit the packet loss rate data to the fault location unit through the application platform;
[0059] The background controller is used to connect the transmission control line to the cloud transmission module.
[0060] Among them, the security module includes: a data preprocessing unit, a data classification unit and a data clustering unit;
[0061] The input end of the data preprocessing unit is connected to the fault location unit, the output end of the data preprocessing unit is connected to the data classification unit, and the output end of the data classification unit is connected to the data clustering unit.
[0062] The data preprocessing unit is used to preprocess the fault packet loss rate data uploaded by the fault location unit to obtain a concept candidate set;
[0063] The data classification unit is used to classify the current edge node fault information under the recorded fault information table;
[0064] The data clustering unit is used to create corresponding fault alarm modes for edge node faults according to the classification results, and to establish a log record of the fault alarm.
[0065] Among them, the monitoring module includes: a collection unit, an alarm control unit and a signal transmission unit;
[0066] The input end of the acquisition unit is connected to the application platform, the output end of the acquisition unit is connected to the signal transmission unit, and the signal transmission unit is connected to the input end of the alarm control unit.
[0067] The collection unit uses the large packet loss rate data to obtain the public resources of the application platform, and stores the obtained packet loss rate data in a distributed manner.
[0068] Among them, the application module is used to detect the packet loss rate from the edge node to all nodes of the same operator and the abnormal service of the local container engine of the edge node, and calculate the packet loss rate = the total packet loss rate from the source node to other nodes ÷ the number of nodes. The packet loss rate data of the edge node is uploaded to the information service module and the monitoring module by wireless or wired means, and the generated packet loss rate data is in txt, excel, csv text, and copied to the mysql, oracle packet loss rate database;
[0069] Among them, the information service module is used to collect the packet loss rate data uploaded by the application module for matching and sorting the collection operations and recording them at the same time. The packet loss rate data is matched by extracting and matching the uploaded packet loss rate data with the established packet loss rate database through the character string feature quantity, and arranged in order from top to bottom according to the matching degree, and uploaded to the cloud through the cloud transmission module. Only after verification in the cloud can the use permission be obtained, and the packet loss rate data including the application module is transferred and stored;
[0070] Among them, the packet loss rate data security module is used to receive the digital collection, MPEG-compression, packet loss rate data recording and retrieval processed by the edge computing module, and visualize the packet loss rate data information sent by the monitoring module. The display screen controlled by the packet loss rate data security module is directly displayed in the form of a screen after the built-in digital processing realizes analog-to-digital conversion;
[0071] Among them, the monitoring module establishes a programming interface that matches the application module and the information service module, and monitors the functions of the application module or uses the resources of the software system in real time, and encapsulates it into a series of packet loss rate data interfaces that are easy for computers to identify and open them up. Various sensing technologies, communication means, and traditional objects are connected to the Internet to achieve remote monitoring. Finally, the monitoring computer of the video monitoring center decompresses the packet loss rate data received from the front end and monitors it in real time through the computer. When the monitored packet loss rate data exceeds the rated threshold, an alarm message is sent. When an alarm occurs, the alarm decoder will link the alarm output device and transmit the alarm signal to the monitoring center through the alarm decoder. After receiving the alarm signal, the video server of the monitoring center immediately sends a sound signal, records the alarm event, and performs hard disk recording alarm operations;
[0072] Among them, the cloud transmission module is used to provide secure, real-time IoT information transmission and intelligent information processing infrastructure capabilities through ultra-narrowband IoT. The packet loss rate data security module and the monitoring module establish visualization with the cloud, and intelligently transmit packet loss rate data in multiple dimensions by associating the terminal browser with the cloud. The packet loss rate data security module and the monitoring module request to start the server to transmit the packet loss rate data. After receiving the packet loss rate data, the cloud server transmits it to the edge computing module.
[0073] Among them, the edge computing module is used to adopt an open platform that integrates network, computing, storage, and application core capabilities. Its application is initiated on the edge side to generate faster network service response, and an edge computing platform with computing, storage, and application core capabilities.
[0074] The present invention also proposes a cloud-coordinated edge node alarm method, such as Figure 2 As shown, including:
[0075] The application module establishes a connection with the local engine, and the application module uploads the packet loss rate data and the fault packet loss rate data to the information service module and the monitoring module in real time;
[0076] The information service module establishes matching operations based on the collected fault information, creates a local module corresponding to the public safety event, obtains permissions through the cloud transmission module, and establishes a packet loss rate data backup;
[0077] The fault event is compared with the packet loss rate data on the edge side by the edge computing module, which integrates the computing load into the edge layer;
[0078] After the security module visualizes the packet loss rate data, it will simultaneously send out an alarm signal for the fault.
[0079] The cloud transmission module provided in the system of the present invention is used to provide secure, real-time IoT information transmission and intelligent information processing infrastructure capabilities through ultra-narrowband IoT, establish visual, multi-dimensional intelligent packet loss rate data transmission with the cloud, and issue reasonable scheduling instructions to edge nodes through large packet loss rate data and artificial intelligence algorithms, thereby improving the operating efficiency of the system.
[0080] The edge computing module provided in the system of the present invention is used to adopt an open platform that integrates network, computing, storage, and application core capabilities. Its application is initiated on the edge side to generate a faster network service response. The edge computing platform with computing, storage, and application core capabilities processes and analyzes the causes of faults in real time through edge computing. Since it is closer to the location where the fault occurs, it reduces latency and effectively improves program efficiency.
[0081] The present invention completely describes how to analyze and determine the faulty equipment and fault type according to the corresponding key information of the fault, and is conducive to automatic identification and analysis of information problems, intercepting the monitoring information collected by the monitoring module before and after the fault occurs, automatically matching the fault occurrence situation, and after differentiated processing, it is concluded that the fault should send out monitoring information, and the monitoring information sent by the monitoring module is automatically compared and analyzed to obtain the problems of false alarms or omissions in the information, which can achieve controllability, controllability, and controllability, reduce the cost of monitoring information management, reduce the workload of monitoring operators, and improve the efficiency and accuracy of accident handling.
[0082] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code. The scheme in the embodiments of the present application can be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.
[0083] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0084] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0085] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0086] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.
[0087] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.
Claims
1. A cloud-coordinated edge node alarm system, the system comprising: An application module, the application module is used to detect the packet loss rate from the edge node to the operator node, obtain the packet loss rate data, and store the packet loss rate data in a database in a text form; An information service module, the information service module is used to retrieve the packet loss rate data stored in the database, match it with the packet loss rate data, determine the matching degree according to the matching characteristics, and arrange the packet loss rate data according to the matching degree; A security module, which is used to process the packet loss rate data and upload it to the edge computing module after the processing is completed; An edge computing module, which is used to perform edge computing on the processed packet loss rate data to determine whether data transmission from the edge node to the operator node is abnormal; A monitoring module, the monitoring module is used to issue an alarm when it is determined that data transmission from the edge node to the operator node is abnormal; Among them, the information service module is used to collect the packet loss rate data uploaded by the application module for matching and sorting the collection operations and recording them at the same time. The packet loss rate data is matched by extracting and matching the uploaded packet loss rate data with the established packet loss rate database through the character string feature quantity, and arranged in order from top to bottom according to the matching degree, and uploaded to the cloud through the cloud transmission module. Only after verification in the cloud can the use permission be obtained, and the packet loss rate data including the application module is transferred and stored; Among them, the security module is used to receive the digital collection, MPEG-compression, packet loss rate data recording and retrieval processed by the edge computing module, and visualize the packet loss rate data information sent by the monitoring module. The display screen controlled by the packet loss rate data security module is directly displayed in the form of a screen after the built-in digital processing realizes analog-to-digital conversion; Among them, the monitoring module establishes a programming interface that matches the application module and the information service module, and monitors the functions of the application module in real time or uses the resources of the edge node alarm system, and encapsulates it into a series of packet loss rate data interfaces that are easily recognized by computers and open them up to connect with various sensor technologies, communication means, traditional objects and the Internet to achieve remote monitoring. Finally, the monitoring computer of the video monitoring center decompresses the packet loss rate data received from the front end and monitors it in real time through the computer. When the monitored packet loss rate data exceeds the rated threshold, an alarm message is sent. When an alarm occurs, the alarm decoder will link the alarm output device and transmit the alarm signal to the monitoring center through the alarm decoder. After receiving the alarm signal, the video server of the monitoring center immediately sends a sound signal, records the alarm event, and performs a hard disk recording alarm operation; Among them, the cloud transmission module is used to provide secure, real-time IoT information transmission and intelligent information processing infrastructure capabilities through ultra-narrowband IoT. The packet loss rate data security module and the monitoring module establish visualization with the cloud, and intelligently transmit packet loss rate data in multiple dimensions by associating the terminal browser with the cloud. The packet loss rate data security module and the monitoring module request to start the server to transmit the packet loss rate data. After receiving the packet loss rate data, the cloud server transmits it to the edge computing module. Among them, the edge computing module is used to adopt an open platform that integrates network, computing, storage, and application core capabilities. The open platform application is initiated on the edge side to generate network service responses, and is an edge computing platform with computing, storage, and application core capabilities.
2. The system according to claim 1, further comprising: The cloud transmission module is used for data transmission and communication between the system and the cloud, as well as between the application module, information service module, security module, edge computing module and monitoring module.
3. According to the system according to claim 1, the output end of the application module is connected to the input end of the monitoring module and the information service module, the output end of the monitoring module is connected to the input end of the security module, the output end of the information service module is connected to the input end of the cloud transmission module, the output end of the cloud transmission module is connected to the input end of the edge computing module, and the output end of the edge computing module is connected to the input end of the security module.
4. The system according to claim 1, wherein the application module comprises: Application service unit, application support unit and application platform; The output terminals of the application service unit and the application support unit are connected to the application platform; The application service unit is used for edge nodes to provide service component architecture in a runtime environment; The application support unit is used to serve the requests processed by the component architecture and stored at the queue point and in the memory; The application platform is used to provide an integrated environment for edge node information.
5. The system according to claim 1, wherein the information service module comprises: Fault location unit, management server and background controller; The input end of the management server is connected to the output end of the application platform and the background controller, and the output end of the management server is connected to the fault location unit.
6. The system according to claim 5, wherein the fault location unit is used to locate the fault position of the edge node; The management server is used to transmit the packet loss rate data to the fault location unit through the application platform; The background controller is used to connect the transmission control line to the cloud transmission module.
7. The system according to claim 1, wherein the security module comprises: Data preprocessing unit, data classification unit and data clustering unit; The input end of the data preprocessing unit is connected to the fault location unit, the output end of the data preprocessing unit is connected to the data classification unit, and the output end of the data classification unit is connected to the data clustering unit.
8. The system according to claim 7, wherein the data preprocessing unit is used to preprocess the fault packet loss rate data uploaded by the fault location unit to obtain a concept candidate set; The data classification unit is used to classify the current edge node fault information under the recorded fault information table; The data clustering unit is used to create corresponding fault alarm modes for edge node faults according to the classification results, and to establish a log record of the fault alarm.
9. The system according to claim 1, wherein the monitoring module comprises: Collection unit, alarm control unit and signal transmission unit; The input end of the acquisition unit is connected to the application platform, the output end of the acquisition unit is connected to the signal transmission unit, and the signal transmission unit is connected to the input end of the alarm control unit.
10. The system according to claim 9, wherein the acquisition unit uses large packet loss rate data to acquire public resources of the application platform, and performs distributed storage on the acquired packet loss rate data.
Citation Information
Patent Citations
Method for detecting link performance and device therefor
CN101667941A
Edge node anomaly detection method and device
CN111510345A