CN112600891B - Information physical fusion-based edge cloud cooperative system and working method - Google Patents
Information physical fusion-based edge cloud cooperative system and working method Download PDFInfo
- Publication number
- CN112600891B CN112600891B CN202011415129.0A CN202011415129A CN112600891B CN 112600891 B CN112600891 B CN 112600891B CN 202011415129 A CN202011415129 A CN 202011415129A CN 112600891 B CN112600891 B CN 112600891B
- Authority
- CN
- China
- Prior art keywords
- data
- edge
- cooperative
- model
- cloud
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/06—Protocols specially adapted for file transfer, e.g. file transfer protocol [FTP]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
- H04L69/24—Negotiation of communication capabilities
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computer Security & Cryptography (AREA)
- Information Transfer Between Computers (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides an edge cloud cooperative work method based on information physical fusion. Comprising the following steps: collecting side equipment data, storing and processing the side equipment data, and taking the processed side equipment data as cooperative data; according to the cooperative data, an edge cloud cooperative model is built, edge node optimization model information is obtained, and the edge node optimization model is updated through the edge cloud cooperative model; and waiting for updating feedback of the edge node, constructing an edge cloud cooperation platform according to a feedback result by combining the cooperation data and the edge cloud cooperation model, acquiring user data, and managing the user data according to the edge cloud cooperation platform. The method helps to carry out multi-level and multi-element management on the user data by obtaining the cooperative data and constructing the edge cloud cooperative model and the edge cloud cooperative platform, improves the system compatibility and the system working efficiency, and improves the user experience.
Description
Technical Field
The invention relates to the technical field of computer software, in particular to an edge cloud cooperative system based on information physical fusion and a working method.
Background
The information physical fusion system (Cyber physical systems, CPS) is an intelligent system integrating control, communication and calculation. Based on intelligent perception and information communication, CPS realizes deep fusion and real-time interaction of calculation, communication and control through the mutual influence of information calculation and physical processes, detects and controls a physical system in a safe, reliable, efficient and real-time mode, and realizes coordinated operation of the whole system. The method supports the deep integration of informatization and industrialization, builds a complex system with mutual mapping, timely interaction and efficient cooperation of elements such as human, machine, object, environment and information in a physical space and an information space by integrating advanced information technologies such as sensing, computing, communication and control and automatic control technologies, and realizes on-demand response, rapid iteration and dynamic optimization of resource configuration and operation in the system.
The existing edge cloud system cooperative system faces the problems of multiple data acquisition types, poor acquisition instantaneity and high protocol compatibility difficulty, and lacks a model and a cooperative mechanism capable of being efficiently migrated between cloud and edge, so that an edge cloud cooperative system and a working method based on information physical fusion are needed.
The foregoing is provided merely for the purpose of facilitating understanding of the technical solutions of the present invention and is not intended to represent an admission that the foregoing is prior art.
Disclosure of Invention
In view of the above, the invention provides an edge cloud cooperation system based on information physical fusion and a working method thereof, which aim to solve the technical problem that the elastic scheduling and cluster management of the edge cloud cooperation system to resources cannot be realized by utilizing a model cooperation and platform cooperation mode in the prior art.
The technical scheme of the invention is realized as follows:
in one aspect, the invention provides an edge cloud cooperative work method based on information physical fusion, which comprises the following steps:
s1, acquiring side equipment data, storing and processing the side equipment data, and taking the processed side equipment data as cooperative data;
s2, constructing an edge cloud cooperative model according to the cooperative data, acquiring edge node optimization model information, and updating the edge node optimization model through the edge cloud cooperative model;
and S3, waiting for updating feedback of the edge node, constructing an edge cloud cooperation platform according to a feedback result by combining the cooperation data and the edge cloud cooperation model, acquiring user data, and managing the user data according to the edge cloud cooperation platform.
On the basis of the above technical solution, preferably, in step S1, edge device data is collected, the edge device data is stored and processed, the processed edge device data is used as cooperative data, and further the method further includes the steps of collecting edge device data, obtaining a local abnormal data judgment model, judging the edge device data according to the abnormal data judgment model, screening out abnormal data and normal data, respectively establishing an abnormal data set and a normal data set, and using the abnormal data set as cooperative data.
On the basis of the technical scheme, an abnormal data set and a normal data set are preferably established respectively, the abnormal data set is used as cooperative data, the method further comprises the steps of uploading the abnormal data set and the normal data set to a cloud end, generating a corresponding alarm grade according to the abnormal data, binding the alarm grade with the abnormal data set, and detecting data uploaded by a user in real time.
On the basis of the above technical solution, preferably, in step S2, an edge cloud cooperative model is constructed according to the cooperative data, edge node optimization model information is obtained, the edge node optimization model is updated through the edge cloud cooperative model, and the method further includes the steps that the edge node establishes an optimization model through short-term learning according to the cooperative data, the cloud end establishes an edge cloud cooperative model through long-term learning according to the cooperative data, and sends the edge cloud cooperative model to the edge node, and the edge node optimization model is updated.
On the basis of the technical scheme, preferably, the cloud end establishes an edge cloud cooperative model through long-term learning according to the cooperative data, transmits the edge cloud cooperative model to an edge node, updates an edge node optimization model, further comprises the following steps of continuously acquiring new edge equipment parameters, training the new edge equipment parameters, establishing a new edge cloud cooperative model, updating the edge cloud cooperative model through the new edge cloud cooperative model to obtain a final edge cooperative model, transmitting the final edge cooperative model to the edge node, and updating the edge node optimization model.
On the basis of the above technical solution, preferably, in step S3, waiting for the update feedback of the edge node, constructing an edge cloud collaboration platform according to the feedback result by combining the collaboration data and the edge cloud collaboration model, obtaining user data, managing the user data according to the edge cloud collaboration platform, and further comprising the steps of waiting for the update feedback of the edge node, and when receiving the feedback of the update completion of the edge node, constructing the edge cloud collaboration platform by combining the collaboration data and the edge cloud collaboration model, obtaining the user data, and managing the user data according to the edge cloud collaboration platform; and when the feedback that the updating of the edge node is incomplete is received, the feedback of the edge node is waited again.
On the basis of the technical scheme, preferably, the method comprises the steps of constructing an edge cloud collaboration platform by combining collaboration data and an edge cloud collaboration model, acquiring user data, managing the user data according to the edge cloud collaboration platform, constructing the edge cloud collaboration platform by combining the collaboration data and the edge cloud collaboration model, acquiring the user data and user demands, managing the user data, and generating a solution corresponding to the user demands.
Still further preferably, the edge cloud collaboration system based on information physical fusion includes:
the acquisition module is used for acquiring the data of the side equipment, storing and processing the data of the side equipment and taking the processed data of the side equipment as cooperative data;
the updating module is used for constructing an edge cloud cooperative model according to the cooperative data, acquiring edge node optimization model information and updating the edge node optimization model through the edge cloud cooperative model;
the management module is used for waiting for updating feedback of the edge node, constructing an edge cloud cooperation platform according to a feedback result by combining the cooperation data and the edge cloud cooperation model, acquiring user data, and managing the user data according to the edge cloud cooperation platform.
In a second aspect, the method for cooperative edge cloud operation based on information physical fusion further includes a terminal device, where the terminal device includes: the system comprises a memory, a processor and an information physical fusion-based edge cloud cooperative work method program stored on the memory and capable of running on the processor, wherein the information physical fusion-based edge cloud cooperative work method program is configured to realize the steps of the information physical fusion-based edge cloud cooperative work method.
In a third aspect, the information physical fusion-based edge cloud cooperative working method further includes a storage medium, where the storage medium is a computer medium, and an information physical fusion-based edge cloud cooperative working method program is stored on the computer medium, and when the information physical fusion-based edge cloud cooperative working method program is executed by a processor, the steps of the information physical fusion-based edge cloud cooperative working method are implemented as described above.
Compared with the prior art, the edge cloud cooperative work method based on information physical fusion has the following beneficial effects:
(1) The data are processed and analyzed last time, so that data collaboration is realized, assistance can be provided for later model collaboration, model collaboration slope is improved, and user experience is improved.
(2) Different collaborative models can be constructed to manage different models, so that the method can adapt to various complex environments and greatly improves user experience.
(3) By means of data collaboration and model collaboration, the construction of a shared interconnection system supports industrial Internet platform butt joint of the edge cloud collaboration system industry, the requirements of edge cloud collaboration application sharing, service multiplexing, scene interconnection and network intercommunication can be met, and professional edge cloud collaboration services are provided for industrial Internet platforms of different industries.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic structural diagram of a terminal device of a hardware running environment according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a first embodiment of an edge cloud cooperative work method based on information physical fusion;
fig. 3 is a schematic diagram of a functional module of a first embodiment of an edge cloud cooperative working method based on information physical fusion.
Detailed Description
The following description of the embodiments of the present invention will clearly and fully describe the technical aspects of the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, are intended to fall within the scope of the present invention.
As shown in fig. 1, the apparatus may include: a processor 1001, such as a central processing unit (Central Processing Unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, a memory 1005. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a WIreless interface (e.g., a WIreless-FIdelity (WI-FI) interface). The Memory 1005 may be a high-speed random access Memory (Random Access Memory, RAM) Memory or a stable nonvolatile Memory (NVM), such as a disk Memory. The memory 1005 may also optionally be a storage system separate from the processor 1001 described above.
It will be appreciated by those skilled in the art that the structure shown in fig. 1 does not constitute a limitation of the apparatus, and in actual practice the apparatus may include more or less components than those illustrated, or certain components may be combined, or different arrangements of components.
As shown in fig. 1, the memory 1005 as a medium may include an operating system, a network communication module, a user interface module, and an edge cloud cooperative method program based on physical fusion of information.
In the device shown in fig. 1, the network interface 1004 is mainly used for establishing a communication connection between the device and a server storing all data required in the edge cloud cooperative working method system based on information physical fusion; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the information physical fusion-based edge cloud cooperative work method device can be arranged in the information physical fusion-based edge cloud cooperative work method device, and the information physical fusion-based edge cloud cooperative work method device invokes an information physical fusion-based edge cloud cooperative work method program stored in the memory 1005 through the processor 1001 and executes the information physical fusion-based edge cloud cooperative work method provided by the implementation of the invention.
With reference to fig. 2, fig. 2 is a schematic flow chart of a first embodiment of an edge cloud cooperative working method based on information physical fusion.
In this embodiment, the method for cooperative operation of edge and cloud based on information physical fusion includes the following steps:
s10: and acquiring the side equipment data, storing and processing the side equipment data, and taking the processed side equipment data as cooperative data.
It should be understood that, in the embodiment of the present invention, by collecting the data of the edge device, then acquiring a local abnormal data judgment model, judging the data of the edge device according to the abnormal data judgment model, screening out abnormal data and normal data, and respectively establishing an abnormal data set and a normal data set, where the local abnormal data judgment model is preset by a manager, the system can directly call, then the system uploads the abnormal data set and the normal data set to the cloud, generates a corresponding alarm level according to the abnormal data, binds the alarm level with the abnormal data set, and detects the data uploaded by the user in real time.
It should be understood that, in this embodiment, the Bian Yun cooperative intelligent gateway supports more industrial protocols, and can provide multiple edge cloud interaction data services, and meanwhile, the Bian Yun cooperative intelligent gateway can also implement management of edge nodes, implement data caching and secondary processing, and provide alarm services and emergency processing when the behavior is abnormal. The collection engineering can be configured at any time and any place through the network, so that the management configuration of the industrial gateway is completed. The method can conveniently connect different communication networks to form an integral factory transparent information flow, and is an important node for realizing edge cloud cooperation. The method mainly comprises the following steps: support more industry protocols, provide a variety of edge cloud interaction data services, edge node management, wire break caching services, scripting services, logging services, alarm services, trigger services, and remote management services.
Among other things, supporting more industrial protocols includes: bian Yun in conjunction with the intelligent gateway support the collection of various industrial equipment protocols in the industrial field, including: international standard protocols such as OPC, MODBUS, IEC61850, IEC60870, DNP3, BACNET, etc., proprietary protocols of equipment manufacturers such as hotlink, etc., proprietary protocols of various intelligent meters and intelligent equipment, various relational databases such as ORACLE, MSSQL, MYSQL, etc., support analysis of various data files such as TXT, CSV, etc., and simultaneously continuously expand protocol libraries so as to support more equipment data access.
Providing a plurality of edge cloud interaction data services includes: as a data transmission unit of the cloud-side cooperative industrial internet, the Bian Yun cooperative intelligent gateway can collect data of millions of devices and can forward the collected data according to a protocol required by an upper-layer service system. The provided basic protocol comprises 10 data services such as OPC Server, MODBUS SLAVE, DNP3, BACnet, IEC60870-5-101/102/103/104 Slave, CDT Slave, DNP Slave, IEC61850 Server, DDE Server and the like.
The edge node management includes: the system can perform centralized management, configuration, monitoring and maintenance on all edge devices in one system through the graphical device centralized management and maintenance platform software, so that the fault processing time of the system can be shortened, and the labor cost is saved.
The broken line cache service comprises the following steps: when the communication link of data distribution encounters a fault or loses contact with an upper software system, the industrial gateway can store the data in a fault time period in a storage unit, and after the fault is cleared, the cached data in the fault period is supplemented to the upper system, so that the integrity and the continuity of the data are ensured to the greatest extent.
The script service includes: and performing secondary operation processing on the collected original data to process various business logics. The computing capacity of the distributed data acquisition of the gateway is effectively utilized, the hardware requirement and the computing pressure of the core server can be reduced, and the investment cost is saved.
The log service includes: all behaviors generated by the system can be recorded and expressed according to the specification, and the basis can be provided for system debugging through the information recorded by the log system.
The alarm service comprises: the alarm information is notified to staff in the forms of sound, light and electricity, so that the predictive judging capability of fault accidents is provided for system maintenance staff, the economic loss of enterprises is reduced, and the economic benefit is improved.
The trigger service includes: if something happens, corresponding emergency treatment is carried out, and the trigger supports combination judgment (time, numerical value, event and the like) of various conditions, so that the operation of the system has higher flexibility and stability, and operation maintenance personnel are helped to improve the working efficiency and reduce the working pressure.
The remote management service includes: by using the configuration management tool, engineers can configure the acquisition engineering at any time and any place through the network, and the management configuration of the industrial gateway is completed.
It should be appreciated that data collaboration also includes: the distributed mode stores data, data management and platform management.
The distributed storage data comprises high-performance distributed real-time data storage and hierarchical classification storage of different types of edge cloud data. According to the requirements of specific business analysis, a local storage mode or a cloud storage mode is flexibly adopted, and on the selection of a database, different data processing methods are adopted to deal with batch data processing and real-time data processing according to the characteristics of data of equipment and a data transmission mode. The data storage module is designed in a distributed, extensible and multi-data redundancy mode, a distributed shared-nothing architecture is supported, parallel mass data writing with high throughput rate is supported, and efficient parallel query optimization, indexing and analysis pushing are realized. All data storage services have the capability of horizontal expansion under massive data, can realize online capacity expansion, and ensure high availability of data when hardware fails.
The high-performance distributed real-time data storage is used for rapidly increasing collected data of the edge nodes, and a management function of mass real-time events is provided by adopting the high-performance distributed real-time data storage. The method specifically comprises the steps of data acquisition, data processing, display and instruction acquisition through a data release interface, and finally comprehensive management and display of stored data through drawing a spreadsheet and establishing an analysis display platform.
The data acquisition can realize data transmission, configuration change, connection monitoring, buffering, breakpoint continuous transmission and breakpoint precompression; the data processing can realize data source management and communication management, and provide computing service, backup service, configuration service, relational database dump service, statistics service, alarm service and variable grouping service, thereby laying a solid foundation for the stable and efficient operation of the whole system; the data can be rendered and displayed by utilizing various platforms of an application layer through the data release interface, and various control instructions sent by the client application can be obtained and executed at the same time; the electronic form provides five functions of data management, data source management, connection management, digital quantity state set management and error code inquiry, so that a user can conveniently use the functions to manufacture various reports, and the data analysis and statistics functions of the EXCEL are combined, so that the data analysis and processing capacity of the real-time database is greatly expanded; the analysis display platform can conduct data analysis, data mining, graphic display and report integration on real-time historical data generated by a real-time database background.
The hierarchical classification storage of different types of edge cloud data supports the storage of various data types such as time sequence, relation, objects, graph databases and the like, and PB-level data storage can be realized; the cloud relational database service, the object storage service and the semi-structured data storage service can realize quick and efficient data index inquiry, can perform real-time stream processing and complete distributed computing processing, and provide a distributed message subscription and publishing mechanism. The storage of different types of data includes time series storage and graph database services.
The time sequence data storage can realize data acquisition, storage, modeling and subscription, the receiving and caching of the data are realized by adopting a distributed message queue, the subscription, snapshot and persistence processing of the real-time data are realized by a real-time flow computing framework, the memory snapshot is stored by a distributed caching system, and the persistence of the data is realized by a semi-structured data service.
The graph database service stores and queries data in a data structure such as "graph" making the data model very expressive, suitable for recording large amounts of event-based data (e.g., log entries or sensor data), processing large-scale distributed data, binary data storage, structured data stored in relational databases, etc.
The data storage and management mode comprises a cloud relation database service, an object storage service and a semi-structured data storage service.
The cloud relational database service can realize relational database service management, a multi-tenant-based isolation function and a Web management function, can improve the reliability of relational data storage through data redundancy based on a relational database, can provide high availability by using a Master-Slave mode, and can improve performance through read-write separation;
the object storage service can solve the storage and retrieval problems of mass picture files, realize efficient cluster storage through load balancing, ensure multiple redundant storage of data, improve the safety and reliability of the data, and simultaneously ensure real-time retrieval of mass data through the distributed search engine service;
the semi-structured data has huge storage capacity, is oriented to column storage and has sparse list, the searching and inquiring functions are provided, the inquiring performance is improved, the data searching of different types is realized, the upgrading and reconstruction of an old system and the support of a relational database in a special scene can be facilitated, and the development workload of a user is effectively reduced.
And (3) data management: modeling, storing, managing and analyzing the data management layer and data mining based on big data analysis technology are carried out through visual configuration and operation means.
Platform management and control: the data management and control matrix is formed by using a platform management and control mechanism and a management and control means, so that management and control and cooperation capacity of each level of the data management architecture can be orderly and efficiently improved.
The data collaboration can provide multi-tenant sharing support of partial services, users of different tenants can multiplex the same large data cluster, and high-efficiency utilization of resources is realized; the monitoring and automatic operation and maintenance capability of the big data platform assembly is provided, and the effective management and control of the platform is realized.
S20: and constructing an edge cloud cooperative model according to the cooperative data, acquiring edge node optimization model information, and updating the edge node optimization model through the edge cloud cooperative model.
It should be understood that after that, the edge node of the system establishes an optimization model through short-term learning according to the cooperative data, the cloud continuously acquires new edge equipment parameters, trains the new edge equipment parameters, establishes a new edge cloud cooperative model, updates the edge cloud cooperative model through the new edge cloud cooperative model to obtain a final edge cooperative model, and issues the final edge cooperative model to the edge node to update the edge node optimization model.
It should be understood that, the system of the embodiment can construct an industrial model, a model deployment and management tool and the like with cooperative edge cloud, the edge node establishes a simple optimization model through short-term learning, and the cloud trains a more accurate optimization model through long-term learning and sends the model to the edge side to update the optimization model of the edge. Meanwhile, the cloud end continuously receives the data of the on-site technological process parameters to perform new model training, and the optimization effect of the model is further improved. The model side cloud cooperation in the operation process of the industrial enterprise is realized, and the capability sinking of the cloud computing center is realized. The method mainly comprises the steps of constructing an industrial model library according to related data, constructing a computing framework for processing an industrial model, and deploying and managing the industrial model according to the established computing framework.
Wherein, construct the industrial model base: the method comprises the steps of constructing a general industrial algorithm model library and an industrial mechanism model library. The industrial model library can provide data analysis and application development services which are more suitable for industrial scene requirements, improves the accuracy of data analysis results, and supports comprehensive industrial application forming fitting business requirements.
The general industrial algorithm model library comprises information such as model names, model types, model function descriptions, core algorithms, model use fields and the like, and can realize functions such as general algorithm model information statistics, keyword inquiry, paging display, designated page skip and the like.
The industrial mechanism model library comprises information such as model names, model types, model function descriptions, core algorithms, model use fields and the like, sharing multiplexing of the models can be achieved through model-based modeling, a visual modeling environment is provided, modeling templates are provided for industrial modeling scenes, a mature technical path is solidified, and the supporting models are quickly built and optimized.
A computing framework is then built: the industrial mechanism model imports data through a data access gateway of the cloud platform, calculates through a calculation frame provided by the platform, and integrates the data, the algorithm and the calculation frame.
And finally, the deployment and management of the industrial model: the container cloud platform is constructed by adopting an advanced container and large-scale cluster management technology, and the industrial model is subjected to standardized packaging and effective automatic management by means of the lightweight, standardized, elastic resource supply and other capabilities of the container, so that the cloud loading speed and the cloud loading capability of the application are improved. And synchronously carrying out iterative updating of the model algorithm at the platform end, and feeding back the updated model algorithm to the edge so as to further improve the optimization effect.
The mechanism model is stored inside a mechanism model repository of the container cloud platform in the form of a Docker Image. The mechanism model is deployed on the container cloud platform in the form of application, and can provide services through unified calling APIs. By hosting user code, user applications can be automatically executed using user-configured triggers, based on trigger events of the triggers. The functions are performed by event triggers, event sources, i.e., triggers, typically by timers, ioT devices, etc., as triggers. The user submits the codes and the configuration to the platform for storage, and after the real event is generated, a function instance is pulled up for each event, so that triggered operation is realized. When the real event comes, the user function can be operated, and when the user code is operated, the data operation and the cost calculation of the code are carried out, the industrial model is packaged into a container, and the management of the container comprises container management, cluster scheduling, mirror image warehouse, monitoring management and alarm management.
The cluster scheduling refers to unified management and container scheduling of resources, can realize access management, node role control and cluster state management of hosts in a cluster, makes flexible container scheduling strategies, and can match related networks and storage resources while carrying out container resource quota management and control.
The mirror image warehouse provides perfect mirror image management capability, supports grouping display through a mirror image space, can set access rights, supports construction of a mirror image through application codes or uploading application packages, supports mirror image management, and comprises version, description, access rights, automatic construction and the like.
The monitoring management is to provide data collection, summarization analysis and information display of the running states of clusters, hosts and containers on the basic framework platform, and to provide a customizable monitoring data billboard for supporting the inquiry of state data through inquiry language.
And the alarm management provides the alarm capability based on the container monitoring data, supports the self-defined and flexible alarm strategy, automatically detects the matching degree of the alarm strategy according to the container operation data, and can issue an alarm according to preset rules when the condition conforming to the alarm strategy occurs.
S30: and waiting for updating feedback of the edge node, constructing an edge cloud cooperation platform according to a feedback result by combining the cooperation data and the edge cloud cooperation model, acquiring user data, and managing the user data according to the edge cloud cooperation platform.
It should be understood that, finally, the system waits for the update feedback of the edge node, and when receiving the feedback of the completion of the update of the edge node, the system combines the collaboration data and the edge cloud collaboration model to construct an edge cloud collaboration platform, obtains the user data and the user demand, manages the user data, and generates a solution corresponding to the user demand; and when the feedback that the updating of the edge node is incomplete is received, the feedback of the edge node is waited again.
It should be understood that the system can construct a shared interconnection system to support industrial internet platform butt joint of the edge cloud cooperative system industry according to data cooperation and model cooperation of the edge cloud cooperative system obtained before, so as to meet requirements of edge cloud cooperative application sharing, service multiplexing, scene interconnection and network intercommunication and provide professional edge cloud cooperative services for industrial internet platforms of different industries.
It should be understood that, from four dimensions of network, edge device, application service, and business scenario, the shared interconnect system includes four functions of network interworking, edge node management, application and service sharing, and business multiplexing. Providing a network link channel shared by the edge cloud cooperative system and the industrial internet platform network interconnection resources through a network intercommunication module; through the edge node management platform, full life cycle management of the edge node is realized, including pushing, installing, unloading, updating, monitoring, logging and the like of the application; various components are served into different Open cloud services through different modes such as a management console based on an Open API, a command line and the like, and unified support and scheduling management are provided for development and use of data processing capacity of data application; and the access and multiplexing of the edge cloud cooperative system and the business layer of the industrial Internet platform are realized through the business multiplexing template, and the sharing interconnection is realized.
The network intercommunication refers to a network link channel for sharing interconnection resources between an edge cloud cooperative system and an industrial internet platform network through a network intercommunication module, and the module consists of a cloud platform and a client.
The cloud platform comprises a cloud control node, a cloud access node and a cloud agent node, and the three nodes perform their roles respectively. The cloud control node manages the platform node topology, dynamically distributes routing rules and calculates the quality of a communication link; the cloud access node strictly controls terminal access, protects the terminal flow of authorized access and controls session parameters of terminal connection; the cloud agent node selects an optimal communication link for the client, transmits the link quality information back to the cloud control node, and performs link optimization in real time according to the calculation result.
The core functionality of the client includes three aspects. Firstly, providing acceleration guarantee service for unstable cross-domain links; secondly, providing a secure encryption service for the terminal flow in the un-trusted intranet environment; thirdly, interconnection sharing is carried out on the registered resource components.
And then, through the edge node management platform, full life cycle management of the edge node can be realized, including pushing, installing, uninstalling, updating, monitoring, logging and the like of the application. The method mainly comprises edge node management, remote configuration, log management, version management and component management. The edge node management provides unified management of edge devices and supports functions of device modeling, data package editing, viewing and the like. And (3) remote configuration, wherein information such as an edge node model, an access protocol and the like is set through a Web interface. Log management, viewing the operation log through a simple log service of the container service. Version management, which manages the version of the edge application by means of a Web interface. Component management, wherein the component management function uniformly manages system components and optional components installed in the cluster, including upgrading, uninstalling, reinstalling and the like.
The management console based on the Open API can provide API service management and monitoring according to the actual business of the user, and provides unified support and scheduling management for the development of the application. Including service administration, service security management and control, unified configuration center, and service monitoring and tracking.
Wherein, the service governance includes: service governance centers providing API services such as load balancing, current limiting, degradation, fault tolerance, fusing, gray scale publishing, rollback, and the like, including service load balancing, flow control policies, and service degradation in particular.
Service load balancing includes: when the access quantity and the flow are large, the flow can be distributed to a plurality of servers in a balanced manner by setting the load balancing mode under the condition that one server cannot load, so that the response time is optimized, and the overload of the servers is prevented. The load balancing strategy can be configured through the newly added rule, and parameters are set to support various load balancing strategies such as polling, randomness, response time weight, session viscosity and the like.
The flow control strategy refers to flow control that a user can select a cluster or a single gateway node according to requirements. Configuration of API traffic thresholds, such as: the number of requests per second, per minute and per hour is limited, when the flow exceeds a threshold value, new requests can be intercepted by the gateway, and the back-end service can be ensured to normally run.
In service degradation, degradation is a special form of fault tolerance, and when conditions such as huge service throughput, insufficient resources and the like occur, a degradation mechanism can be used for turning off partial unimportant service with poor performance, so that resources are prevented from being occupied, and normal use of main service functions is ensured.
Service security management refers to providing multiple authentication modes, such as: token, basic, IP addresses, etc., only authenticated clients can further access gateway-exposed services. And after passing the authentication, detecting whether the client has authority to access the appointed API.
And uniformly configuring the center. Support for publication, modification, and notification of service configuration items. Including environment and version management and service auditing in particular.
The environment and version management are provided with three environments of testing, pre-publishing and publishing, and different interface management can be performed in different environments; and (3) checking the service, and checking and publishing the API service information, the interface, the state and other contents provided by the service provider.
Service monitoring and tracking support real-time QPS, response time, error rate and other monitoring statistics of micro service instance and interface level.
And finally, realizing service access and multiplexing of the side cloud cooperative system and the business layer of the industrial Internet platform by constructing a business multiplexing module, and realizing sharing and interconnection of application systems such as unit operation monitoring, key equipment fatigue and aging management, real-time intelligent monitoring of important equipment in a factory and the like in the business layer. The user side can call related applications and related service templates of the edge cloud system through a single user interaction side, and the service scene integrated generation function is realized.
The module obtains service application state through the service interface plug-in deployed in the Bian Yun cooperative system, issues service system multiplexing tasks, the service multiplexing module comprises service templates registered in a service multiplexing pool for unit operation monitoring, key equipment fatigue and aging management, factory important equipment real-time intelligent monitoring and the like, the service templates are issued to a scene interconnection module and a scene template for the service, and the templates call Bian Yun scenes and analysis services corresponding to the cooperative system.
And then, establishing a shared interconnection system to support the industrial Internet platform butt joint of the side cloud cooperation system industry by establishing side cloud cooperation data cooperation and model cooperation, and providing professional side cloud cooperation services for industrial Internet platforms of different industries.
And finally, APP application, solutions and the like are formed, online transaction service and service management are provided for users, professional service capacity of the edge cloud cooperative system is improved, and professional edge cloud cooperative service is provided for industrial Internet platforms of different industries.
The platform user comprises an administrator, a developer and a visitor use the side cloud cooperative system through application service and portals, and can obtain applications, specific analysis reports, solutions and the like after inputting side equipment data, information and the like, wherein the application comprises an equipment operation monitoring scheme and analysis, an optimization operation scheme, a remote operation and maintenance scheme, an environment monitoring analysis, a deduction simulation scheme, online simulation and results, an APP application and the like.
It should be understood that the edge cloud collaboration system based on information physical fusion in this embodiment adopts a four-layer architecture of an edge layer, a data center, a business center, an application service and a portal. Around key problems of data, model, application coordination and the like in the edge cloud coordination application, a set of edge cloud coordination system is constructed, and the edge cloud coordination system has multi-type industrial data edge cloud interaction, multi-type industrial model interaction, multi-scene industrial application edge cloud interaction and multi-platform adaptation capability, and finally an application solution is formed.
It should be noted that the foregoing is merely illustrative, and does not limit the technical solution of the present application in any way.
As can be easily found from the above description, in this embodiment, by collecting the edge device data, the edge device data is stored and processed, and the processed edge device data is used as the cooperative data; according to the cooperative data, an edge cloud cooperative model is built, edge node optimization model information is obtained, and the edge node optimization model is updated through the edge cloud cooperative model; and waiting for updating feedback of the edge node, constructing an edge cloud cooperation platform according to a feedback result by combining the cooperation data and the edge cloud cooperation model, acquiring user data, and managing the user data according to the edge cloud cooperation platform. According to the method, the device and the system, the user data are managed in a multi-level and multi-variational mode by obtaining the cooperative data and constructing the edge cloud cooperative model and the edge cloud cooperative platform, so that the system compatibility and the system working efficiency are improved, and the user experience is improved.
In addition, the embodiment of the invention also provides an edge cloud cooperative system based on information physical fusion. As shown in fig. 3, the edge cloud collaboration system based on information physical fusion includes: the system comprises an acquisition module 10, an updating module 20 and a management module 30.
The acquisition module 10 is configured to acquire side equipment data, store and process the side equipment data, and use the processed side equipment data as cooperative data;
the updating module 20 is configured to construct an edge cloud coordination model according to the coordination data, obtain edge node optimization model information, and update the edge node optimization model through the edge cloud coordination model;
the management module 30 is configured to wait for update feedback of the edge node, construct an edge cloud collaboration platform according to the feedback result in combination with the collaboration data and the edge cloud collaboration model, obtain user data, and manage the user data according to the edge cloud collaboration platform.
In addition, it should be noted that the above-described system embodiments are merely illustrative, and do not limit the scope of the present invention, and in practical applications, one skilled in the art may select some or all modules according to actual needs to achieve the purpose of the embodiment, which is not limited herein.
In addition, technical details which are not described in detail in the embodiment can be referred to the edge cloud cooperative working method based on information physical fusion provided in any embodiment of the present invention, and are not described here again.
In addition, the embodiment of the invention also provides a storage medium, which is a computer medium, wherein the computer medium is stored with an edge cloud cooperative work method program based on information physical fusion, and the edge cloud cooperative work method program based on information physical fusion realizes the following operations when being executed by a processor:
s1, acquiring side equipment data, storing and processing the side equipment data, and taking the processed side equipment data as cooperative data;
s2, constructing an edge cloud cooperative model according to the cooperative data, acquiring edge node optimization model information, and updating the edge node optimization model through the edge cloud cooperative model;
and S3, waiting for updating feedback of the edge node, constructing an edge cloud cooperation platform according to a feedback result by combining the cooperation data and the edge cloud cooperation model, acquiring user data, and managing the user data according to the edge cloud cooperation platform.
Further, the edge cloud cooperative work method program based on information physical fusion further realizes the following operations when being executed by a processor:
Acquiring side equipment data, acquiring a local abnormal data judging model, judging the side equipment data according to the abnormal data judging model, screening out abnormal data and normal data, respectively establishing an abnormal data set and a normal data set, and taking the abnormal data set as cooperative data.
Further, the edge cloud cooperative work method program based on information physical fusion further realizes the following operations when being executed by a processor:
uploading the abnormal data set and the normal data set to a cloud, generating a corresponding alarm grade according to the abnormal data, binding the alarm grade with the abnormal data set, and detecting the data uploaded by a user in real time.
Further, the edge cloud cooperative work method program based on information physical fusion further realizes the following operations when being executed by a processor:
and the edge node establishes an optimization model through short-term learning according to the cooperative data, and the cloud establishes an edge cloud cooperative model through long-term learning according to the cooperative data, and transmits the edge cloud cooperative model to the edge node to update the edge node optimization model.
Further, the edge cloud cooperative work method program based on information physical fusion further realizes the following operations when being executed by a processor:
The cloud end continuously acquires new side equipment parameters, trains the new side equipment parameters, establishes a new side cloud cooperative model, updates the side cloud cooperative model through the new side cloud cooperative model to obtain a final edge cooperative model, and sends the final edge cooperative model to an edge node to update an edge node optimization model.
Further, the edge cloud cooperative work method program based on information physical fusion further realizes the following operations when being executed by a processor:
waiting for updating feedback of the edge node, and when receiving feedback of the updating completion of the edge node, constructing an edge cloud cooperation platform by combining the cooperation data and the edge cloud cooperation model, acquiring user data, and managing the user data according to the edge cloud cooperation platform; and when the feedback that the updating of the edge node is incomplete is received, the feedback of the edge node is waited again.
Further, the edge cloud cooperative work method program based on information physical fusion further realizes the following operations when being executed by a processor:
and constructing an edge cloud cooperation platform by combining the cooperation data and the edge cloud cooperation model, acquiring user data and user requirements, managing the user data, and generating a solution corresponding to the user requirements.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (9)
1. An edge cloud cooperative work method based on information physical fusion is characterized in that: comprises the following steps of;
s1, acquiring side equipment data, storing and processing the side equipment data, and taking the processed side equipment data as cooperative data;
in step S1, collecting edge equipment data, storing and processing the edge equipment data, taking the processed edge equipment data as cooperative data, and further comprising the steps of collecting the edge equipment data, acquiring a local abnormal data judgment model, judging the edge equipment data according to the abnormal data judgment model, screening out abnormal data and normal data, respectively establishing an abnormal data set and a normal data set, and taking the abnormal data set as cooperative data;
s2, constructing an edge cloud cooperative model according to the cooperative data, acquiring edge node optimization model information, and updating the edge node optimization model through the edge cloud cooperative model;
And S3, waiting for updating feedback of the edge node, constructing an edge cloud cooperation platform according to a feedback result by combining the cooperation data and the edge cloud cooperation model, acquiring user data, and managing the user data according to the edge cloud cooperation platform.
2. The information physical fusion-based edge cloud cooperative work method as claimed in claim 1, wherein: and respectively establishing an abnormal data set and a normal data set, taking the abnormal data set as cooperative data, uploading the abnormal data set and the normal data set to a cloud end, generating a corresponding alarm grade according to the abnormal data, binding the alarm grade with the abnormal data set, and detecting the data uploaded by a user in real time.
3. The information physical fusion-based edge cloud cooperative work method as claimed in claim 2, wherein: in step S2, an edge cloud cooperative model is built according to the cooperative data, edge node optimization model information is obtained, the edge node optimization model is updated through the edge cloud cooperative model, the edge node builds an optimization model through short-term learning according to the cooperative data, a cloud end builds an edge cloud cooperative model through long-term learning according to the cooperative data, and the edge cloud cooperative model is issued to the edge node to update the edge node optimization model.
4. The information physical fusion-based edge cloud cooperative work method as claimed in claim 3, wherein: the cloud end establishes an edge cloud cooperative model through long-term learning according to the cooperative data, sends the edge cloud cooperative model to an edge node, and updates an edge node optimization model.
5. The information physical fusion-based edge cloud cooperative work method as claimed in claim 4, wherein: in step S3, waiting for updating feedback of the edge node, constructing an edge cloud cooperation platform according to a feedback result by combining the cooperation data and an edge cloud cooperation model, acquiring user data, managing the user data according to the edge cloud cooperation platform, waiting for updating feedback of the edge node, and constructing the edge cloud cooperation platform by combining the cooperation data and the edge cloud cooperation model when receiving the feedback of the updating completion of the edge node, acquiring the user data, and managing the user data according to the edge cloud cooperation platform; and when the feedback that the updating of the edge node is incomplete is received, the feedback of the edge node is waited again.
6. The information physical fusion-based edge cloud cooperative work method as claimed in claim 5, wherein: the method comprises the steps of combining the cooperative data and the side cloud cooperative model to construct a side cloud cooperative platform, obtaining user data, managing the user data according to the side cloud cooperative platform, further comprising the steps of combining the cooperative data and the side cloud cooperative model to construct the side cloud cooperative platform, obtaining the user data and user demands, managing the user data and generating a solution corresponding to the user demands.
7. An edge cloud cooperative system based on information physical fusion, which is characterized by comprising:
the acquisition module is used for acquiring the data of the side equipment, storing and processing the data of the side equipment and taking the processed data of the side equipment as cooperative data;
the method comprises the steps of collecting the data of the side equipment, acquiring a local abnormal data judging model, judging the data of the side equipment according to the abnormal data judging model, screening out abnormal data and normal data, respectively establishing an abnormal data set and a normal data set, and taking the abnormal data set as cooperative data;
The updating module is used for constructing an edge cloud cooperative model according to the cooperative data, acquiring edge node optimization model information and updating the edge node optimization model through the edge cloud cooperative model;
the management module is used for waiting for updating feedback of the edge node, constructing an edge cloud cooperation platform according to a feedback result by combining the cooperation data and the edge cloud cooperation model, acquiring user data, and managing the user data according to the edge cloud cooperation platform.
8. A terminal device, characterized in that the terminal device comprises: a memory, a processor and an information-physical-fusion-based edge-cloud co-operating method program stored on the memory and executable on the processor, the information-physical-fusion-based edge-cloud co-operating method program configured to implement the steps of the information-physical-fusion-based edge-cloud co-operating method according to any one of claims 1 to 6.
9. A storage medium, characterized in that the storage medium is a computer medium, on which an information physical fusion-based edge cloud cooperative method program is stored, which when executed by a processor, implements the steps of the information physical fusion-based edge cloud cooperative method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011415129.0A CN112600891B (en) | 2020-12-07 | 2020-12-07 | Information physical fusion-based edge cloud cooperative system and working method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011415129.0A CN112600891B (en) | 2020-12-07 | 2020-12-07 | Information physical fusion-based edge cloud cooperative system and working method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112600891A CN112600891A (en) | 2021-04-02 |
| CN112600891B true CN112600891B (en) | 2023-09-19 |
Family
ID=75188972
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011415129.0A Active CN112600891B (en) | 2020-12-07 | 2020-12-07 | Information physical fusion-based edge cloud cooperative system and working method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112600891B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113515263B (en) * | 2021-04-26 | 2022-06-17 | 中国汽车技术研究中心有限公司 | Industrial APP mechanism model deployment method, apparatus, device and readable storage medium |
| CN113485257B (en) * | 2021-06-02 | 2023-03-03 | 杭州电子科技大学 | Industrial protocol analysis built-in program optimization method |
| CN113589096A (en) * | 2021-06-30 | 2021-11-02 | 国网电力科学研究院武汉南瑞有限责任公司 | Edge calculation system and method for multi-state-quantity configurable power transformation equipment |
| CN113806070B (en) * | 2021-08-10 | 2022-10-21 | 中标慧安信息技术股份有限公司 | Data management method and device for edge computing and cloud computing |
| CN114189516B (en) * | 2021-11-23 | 2023-03-10 | 中国科学院软件研究所 | A method and system for edge-cloud data collaboration |
| CN114417079A (en) * | 2021-12-23 | 2022-04-29 | 苏州迈科网络安全技术股份有限公司 | Cloud edge collaborative application real-time identification method and system |
| CN114862178A (en) * | 2022-04-29 | 2022-08-05 | 国网江苏省电力有限公司 | Multi-stage scheduling plan collaborative adjustment method and system |
| CN114928587B (en) * | 2022-05-18 | 2023-05-09 | 山东浪潮科学研究院有限公司 | AIoT equipment multiplexing modeling method based on cloud edge cooperative system |
| CN115967732A (en) * | 2022-12-23 | 2023-04-14 | 中国联合网络通信集团有限公司 | Container cloud chemical engineering control system and method |
| CN116260699A (en) * | 2023-04-03 | 2023-06-13 | 中国电子技术标准化研究院 | An industrial Internet system based on cloud-edge-device collaboration and its implementation method |
| CN117079262B (en) * | 2023-10-16 | 2023-12-26 | 北京睿企信息科技有限公司 | Instrument panel display method for request times |
| CN117251825B (en) * | 2023-11-20 | 2024-02-09 | 浙江大学 | A multi-sensor data fusion platform for new energy power stations |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111160616A (en) * | 2019-12-05 | 2020-05-15 | 广东工业大学 | A predictive maintenance system and method for kitchen electrical equipment based on edge-cloud collaboration |
-
2020
- 2020-12-07 CN CN202011415129.0A patent/CN112600891B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111160616A (en) * | 2019-12-05 | 2020-05-15 | 广东工业大学 | A predictive maintenance system and method for kitchen electrical equipment based on edge-cloud collaboration |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112600891A (en) | 2021-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112600891B (en) | Information physical fusion-based edge cloud cooperative system and working method | |
| CN104506632B (en) | One kind is based on distributed polycentric resource sharing system and method | |
| CN105843182B (en) | A kind of power scheduling accident prediction system and method based on OMS | |
| KR101891506B1 (en) | Methods and systems for portably deploying applications on one or more cloud systems | |
| CN111274001B (en) | Micro-service management platform | |
| CN113176948B (en) | Edge gateway, edge computing system and configuration method thereof | |
| CN112925646A (en) | Electric power data edge calculation system and calculation method | |
| CN105339941B (en) | Projector and selector assembly type are used for ETL Mapping Design | |
| CN115102827A (en) | A general Internet platform for real-time monitoring of digital products in small and medium-sized manufacturing industries | |
| US20070204007A1 (en) | Centralized processing and management system | |
| CN106161644B (en) | Distributed system for data processing and data processing method thereof | |
| CN112148578A (en) | IT fault defect prediction method based on machine learning | |
| CN115115329B (en) | Intelligent production line-oriented manufacturing middleware device and cloud manufacturing architecture system | |
| CN112269690B (en) | Data backup method and device | |
| CN107682209A (en) | A kind of SDP big datas automatically dispose monitor supervision platform | |
| Zeydan et al. | Recent advances in data engineering for networking | |
| CN111338893A (en) | Process log processing method and device, computer equipment and storage medium | |
| CN114169579A (en) | Nuclear power industry internet comprehensive intelligent platform | |
| CN113179190A (en) | Edge controller, edge computing system and configuration method thereof | |
| CN108848132A (en) | A kind of distribution scheduling station system based on cloud | |
| CN102819478A (en) | Agent-free data processing system monitoring and management method | |
| Trunov et al. | Legacy applications model integration to support scientific experiment | |
| Jiang et al. | Research and design of infrastructure monitoring platform of intelligent high speed railway | |
| CN113824801A (en) | A unified access management component system for intelligent fusion terminals | |
| CN111711695B (en) | Distributed equipment management system based on cloud platform |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CB03 | Change of inventor or designer information |
Inventor after: Sang Yanjuan Inventor after: Zhou Yanyuan Inventor after: Sheng Jie Inventor before: Liu Wei Inventor before: Dong Wei Inventor before: Xu Huan Inventor before: Sheng Jie |
|
| CB03 | Change of inventor or designer information |