CN112463892A - Early warning method and system based on risk situation - Google Patents

Early warning method and system based on risk situation Download PDF

Info

Publication number
CN112463892A
CN112463892A CN202011173427.3A CN202011173427A CN112463892A CN 112463892 A CN112463892 A CN 112463892A CN 202011173427 A CN202011173427 A CN 202011173427A CN 112463892 A CN112463892 A CN 112463892A
Authority
CN
China
Prior art keywords
data
early warning
equipment
information
network
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.)
Withdrawn
Application number
CN202011173427.3A
Other languages
Chinese (zh)
Inventor
龚彧
胥峥
李冬华
潘一璠
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Yancheng Power Supply Co of State Grid Jiangsu Electric Power Co Ltd
Original Assignee
Yancheng Power Supply Co of State Grid Jiangsu Electric Power Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Yancheng Power Supply Co of State Grid Jiangsu Electric Power Co Ltd filed Critical Yancheng Power Supply Co of State Grid Jiangsu Electric Power Co Ltd
Priority to CN202011173427.3A priority Critical patent/CN112463892A/en
Publication of CN112463892A publication Critical patent/CN112463892A/en
Withdrawn legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/28—Databases characterised by their database models, e.g. relational or object models
    • G06F16/283—Multi-dimensional databases or data warehouses, e.g. MOLAP or ROLAP
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/28—Databases characterised by their database models, e.g. relational or object models
    • G06F16/284—Relational databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/06—Management of faults, events, alarms or notifications
    • H04L41/0631—Management of faults, events, alarms or notifications using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/06—Management of faults, events, alarms or notifications
    • H04L41/0654—Management of faults, events, alarms or notifications using network fault recovery
    • H04L41/0668—Management of faults, events, alarms or notifications using network fault recovery by dynamic selection of recovery network elements, e.g. replacement by the most appropriate element after failure
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/08—Configuration management of networks or network elements
    • H04L41/0803—Configuration setting
    • H04L41/0823—Configuration setting characterised by the purposes of a change of settings, e.g. optimising configuration for enhancing reliability
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/12—Discovery or management of network topologies
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L63/00—Network architectures or network communication protocols for network security
    • H04L63/02—Network architectures or network communication protocols for network security for separating internal from external traffic, e.g. firewalls
    • 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
    • H04L67/02—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP]
    • H04L67/025—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP] for remote control or remote monitoring of applications
    • 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
    • H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
    • 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
    • H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Databases & Information Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Computer Hardware Design (AREA)
  • Computer Security & Cryptography (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Evolutionary Computation (AREA)
  • Molecular Biology (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Computer And Data Communications (AREA)

Abstract

The invention provides a risk situation-based early warning method and a risk situation-based early warning system, which are characterized in that firstly, real-time acquisition, storage, analysis and interaction of network data are realized by building a network topology structure and hierarchical division; secondly, carrying out relevance analysis between data by utilizing the construction of a neural network structure; and finally, presenting the processed result on a user interface by utilizing a visualization technology. According to the invention, through effective processing of geographic information, prediction of machine learning risk situation is realized by utilizing a neural network, so that the purposes of early warning, fault state presentation and fault risk assessment are achieved, meanwhile, dangerous work such as power grid scheduling, maintenance, emergency rescue and the like is supported, severe meteorological conditions are effectively coped with, and the power grid operation level is improved.

Description

Early warning method and system based on risk situation
Technical Field
The invention relates to a risk situation-based early warning method and system, relates to a general data processing and equipment cooperative work technology, and particularly relates to the field of neural networks based on deep learning.
Background
In recent years, with the rapid development of information technology and the vigorous advance of internet of things technology, the importance of utilizing internet technology to perform equipment collaborative work management is increasing day by day, and a power system is also undergoing a deep revolution. The large area of electric wire netting is laid and has also increaseed the risk dynamics of equipment when maintaining when improving the standard of living, surveys on the spot and reports with general trouble through the manual work, and is consuming time power, not only can not accomplish the control of cost in time, when equipment appears damaging in addition, also can not accomplish feedback and maintenance in time, increases inconveniently in actual life.
However, at present, risk estimation management aiming at an electric power information system is still in a development stage, and the existing research has no deep mining analysis equipment and hidden relation among risks caused by meteorological reasons.
Disclosure of Invention
In order to solve the problems in the prior art and improve the safe operation level of an electric power system, the invention provides a risk situation-based early warning method and a system for realizing the method.
The technical scheme is as follows: a risk situation-based early warning method comprises the following steps:
step 1, constructing a network topology structure, wherein the network topology structure comprises measuring point data, an interface machine, a one-way isolating device, a core switch, a secondary switch and a plurality of intranet clients, wherein the core switch comprises a relational database server and a computing server;
step 2, acquiring information data in a real scene through a data interface of information acquisition equipment, and establishing a multi-variable information database;
step 3, reading the stored information and deducing and analyzing the data correlation by using a neural network and a formula;
and 4, displaying the risk situation, early warning and fault state through a visual interface.
Further, the step 1 is further:
in the network construction process, a two-layer network structure, namely a core layer and an access layer, is adopted, and a gigabit Ethernet switching technology is adopted to connect through a star; the core layer is used for providing rapid forwarding of network data packets and interconnection among backbone nodes, and the access layer is used for finishing convergence of user traffic of the client, so that the network structure is clear, the topology is simple, the expansibility and the scalability are good, and each layer finishes different functions of the network.
All key components of the core switch can realize redundancy work and can be replaced on line, the recovery time of the fault is completed within a second-level interval, and the availability of the system is further improved on the basis of high reliability of single equipment by a multi-level fault-tolerant design. In order to meet the requirements of network users of the existing scale and simultaneously consider the development and scale expansion of future services, a network should be designed to have flexible expansion capability of user ports, and the number of ports of a core device is flexibly increased by adding modules. The chassis design for the core device has a strong backplane bandwidth and sufficient load slot capacity. The core switching engine can realize the non-blocking port data packet switching under the condition of meeting the maximum configuration by adopting a distributed switching structure, and the expansion of the module does not influence the switching performance. The distributed switch structure realizes the parallel data exchange processing of the switch, optimizes the performance of the network, and reduces the pressure of a core switching engine by the distributed structure combining local exchange and global exchange. To avoid single point of failure in the access layer, one hundred/gigabit interface redundancy is employed on the access switches.
The fusion frame in the related hardware equipment is a Server which adopts a deep-trust service-2200-CP series super-fusion frame, a database Server 17XS Server, a real-time library Server 17EC Server, a message Server 17Msg Server, a File Server 17File Server and a video Server 17TV Server. The concrete configuration is as follows: the height of the case is 2U rack, the CPU model is gold/silver series CPUV5, the CPU is 2 CPUs, 14C28T and 2.6GHz, the memory is 768G, the hard disk slot is 12, the standard distribution network port is 6 GE electric ports, the power is 550W/800W, and the power supply is redundant power supply.
The central switch supports 100MB twisted-pair lines, 1000MB twisted-pair lines and 1000MB optical fiber modules, is provided with a redundant power supply and a redundant fan, supports hot plug, can replace equipment components on line, adopts a three-layer switch with a store-and-forward switching mode, adopts backplane switching, is provided with independent switching engines, adopts a modular design and can be freely configured.
The firewall involved in network communication is kilomega, the firewall is connected with an external local area network, the router is provided with kilomega level, and the configured internet behavior management machine authenticated by the public security department meets the requirement that the number of managed people is more than 500, and all the management machines are installed through a rack.
The YIPC industrial computer that the interface workstation chose for use guarantees through the performance that gateway workstation exchange information can not reduce, and every gateway workstation configuration is not less than following standard:
processor and chipset: intel13, memory: greater than or equal to 2G, cache: greater than or equal to 2M, hard disk drive: 160G, optical device: DVD-RW read-write drive, network port: two 10M/100M adaptive Ethernet cards, keyboards: standard keyboard, membrane, mouse: two keys, photoelectric type.
The unidirectional physical isolation device enables data sent by the production process control system to the information platform network to normally pass through while ensuring the correctness of data transmission and the required rate, and blocks any data sent from the information platform network to the production process control system. The one-way physical isolation device has the following basic configuration performance: the hardware structure with safety isolation capability and high-reliability hardware design; the system supports dual-computer hot standby, dual power supplies and system alarm; unidirectional transmission control; blocking a penetrating TCP connection; the network interface is 4 hundred million network card interfaces and 1 dual-computer hot standby interface; the peripheral interface is 2 terminal interfaces plus 1 special alarm interface plus an intelligent IC card interface; the average failure-free time is more than 60000 hours; under the 100M LAN environment, the data packet throughput is 80 Mbps; the data packet forwarding delay is less than 5 ms; the full-load data packet loss rate is 0.
Further, the step 2 is further:
the information in the variable database comprises equipment state, real-time value, equipment parameter basic data, historical curve and historical fault information of storage equipment archive information, model names, model numbers, equipment types, associated variables and measuring points of the power transmission line and tower pole model information.
The information of the variable database is from information acquisition equipment which is erected, wherein the information acquisition equipment comprises a meteorological data sensor, a GPS/Beidou positioning sensor and a microseismic sensor; the related data access modes comprise a standard network transmission protocol TCP/IP protocol, a MODBUS protocol, an OPC protocol and a UDP protocol aiming at different hardware equipment and instrument equipment; the discrete data carries out real-time and dynamic data citation through a data client of a real-time data acquisition tool system, and a client side carries out data transmission through two protocols of Modbus and OPC.
The acquired information is stored in a general relational database in a form conforming to the adopted storage database format through Real-time database service software PIDB-Real based on the relational database.
Further, the step 3 is further:
reading and analyzing data in the database so as to obtain risk early warning assessment; the data reading is that the data is read by the mutual cooperation of the database of the service system and the database of the data platform system and the data is quoted by using a database intermediate table mode. The intermediate table access method can ensure that the database of the service system is safer and can not generate larger system pressure on the database of the service system.
The specific implementation mode is as follows: the database systems of the two parties mutually agree to establish a middle table mechanism in the database system of one party, firstly, a data unloading program is written by the service system database, data required by the central system is firstly copied into the middle table, namely, all the data need time labels as an independent attribute, and therefore, the data can be used for determining whether the data is the latest version or not in the later period. Then, the database in the background of the system can periodically and quantitatively capture data from the provided intermediate table data structure into the system center database through a standard SQL program.
The related data extraction is to extract the required data from the data source for users, and the data is loaded into the data warehouse according to a predefined data warehouse model after data cleaning. In the aspect of data extraction, the data acquisition is carried out by adopting a timestamp increment extraction mode. The method is a change data capturing mode based on snapshot comparison, a timestamp field is added on a source table, and when the data of a modification table is updated in a system, the value of the timestamp field is modified simultaneously. When data extraction is performed, it is decided which data to extract by comparing the system time with the value of the timestamp field. The timestamp of the database supports automatic updating, i.e. the value of the timestamp field is automatically updated when changes occur to the data of other fields of the table. The database does not support the automatic updating of the time stamp, and the time stamp field is manually updated when the business system updates the business data. The time stamp mode has better performance, and the data extraction is relatively clear and simple.
Analyzing data after data acquisition, firstly constructing a neural network, reading the data in a database by using a middle table access and ETL data extraction mode, firstly constructing the neural network with supervised learning by reading historical data parameters and a data set of the current equipment state, and learning the mapping from multiple data to the real-time state of the equipment;
the historical data is information related to equipment states contained in a previous-stage database and is constructed into a network training set, and the equipment states are training labels and are used as comparison references of supervised learning results; the training set is used as input, the early warning result is used as output, a weight value of connection between networks in the neural network model is obtained through training by combining a mathematical formula, and the early warning model can be obtained by bringing the connection weight value into the neural network.
Further, the step 4 is further:
displaying risk situations, early warning and fault states through a visual interface; the module utilizes a front-end development programming language to display the design of interface layout in a visual form to analyze and process the data, wherein a user can select a functional module to be selected according to an interface of a risk situation early warning center displayed on the interface, and the visual and visible functional module comprises a health monitoring center, a model library, a variable library, a model example, industry maintenance, professional maintenance, equipment classification and system management; and the user can perform corresponding operation according to the interface prompt by clicking the corresponding functional module.
A risk situation based early warning system comprising:
a first module for constructing a network data communication; the module constructs a network topology structure, wherein the network topology structure comprises measuring point data, an interface machine, a one-way isolating device, a core switch, a secondary switch and a plurality of intranet clients, wherein the core switch comprises a relational database server and a computing server; in the network construction process, a two-layer network structure, namely a core layer and an access layer, is adopted, and a gigabit Ethernet switching technology is adopted to connect through a star; the core layer is used for providing fast forwarding of network data packets and interconnection among backbone nodes, and the access layer is used for completing convergence of user traffic of the client.
The second module is used for acquiring real-time data and establishing an information base; the module acquires information data in a real scene through a data interface of information acquisition equipment and establishes a multi-variable information database; the information in the variable database comprises equipment state, real-time value, equipment parameter basic data, historical curve and historical fault information of storage equipment archive information, model names, model numbers, equipment types, associated variables and measuring points of the power transmission line and tower pole model information. The information of the variable database is from information acquisition equipment which is erected, wherein the information acquisition equipment comprises a meteorological data sensor, a GPS/Beidou positioning sensor and a microseismic sensor; the related data access modes comprise a standard network transmission protocol TCP/IP protocol, a MODBUS protocol, an OPC protocol and a UDP protocol aiming at different hardware equipment and instrument equipment; the discrete data carries out real-time and dynamic data citation through a data client of a real-time data acquisition tool system, and a client side carries out data transmission through two protocols of Modbus and OPC.
The acquired information is stored in a general relational database in a form conforming to the adopted storage database format through Real-time database service software PIDB-Real based on the relational database.
A third module for processing a data evaluation risk mechanism; the module reads data in a database by using a mode of intermediate table access and ETL data extraction, firstly, a neural network with supervised learning is constructed by reading historical data parameters and a data set of the current equipment state, and the mapping from multiple data to the real-time state of the equipment is learned.
The historical data is information related to equipment states contained in a previous-stage database and is constructed into a network training set, and the equipment states are training labels and are used as comparison references of supervised learning results; the training set is used as input, the early warning result is used as output, a weight value of connection between networks in the neural network model is obtained through training by combining a mathematical formula, and the early warning model can be obtained by bringing the connection weight value into the neural network.
A fourth module for presenting visualized data processing information; the module displays risk situation, early warning and fault state through a visual interface; the module utilizes a front-end development programming language to display the design of interface layout in a visual form to analyze and process the data, wherein a user can select a functional module to be selected according to an interface of a risk situation early warning center displayed on the interface, and the visual and visible functional module comprises a health monitoring center, a model library, a variable library, a model example, industry maintenance, professional maintenance, equipment classification and system management; and the user can perform corresponding operation according to the interface prompt by clicking the corresponding functional module.
The monitoring center displays all the subareas on a map, the boundaries of different subareas are distinguished, the head page displays the line state statistics fault number, normal number and early warning number of each area and all the areas in a table, and the subareas with the line fault are marked by different colors; the home page also displays weather information and marks abnormality in different colors; the current subarea can be highlighted when the mouse hovers the current subarea; when a single partition is zoomed and checked by a mouse, each power transmission line in the partition is displayed, a specific line is highlighted by a mouse suspension event, the normal operation number, the early warning number and the fault number of the line in the current partition are counted and displayed on a current page, and the whole line is warned by warning color identification as long as a tower or a lead in one power transmission line is abnormal; when a certain line is clicked, highlighting tower and power transmission line equipment under the line, and counting and displaying the normal operation quantity, early warning quantity and fault quantity of various equipment of the line; after the power transmission line with abnormal state is selected, only the tower and the wire with abnormal state are identified with abnormal color to distinguish abnormal state, the early warning identification is used for distinguishing early warning state, page is enlarged, the three-dimensional model of the equipment tower is displayed at the corresponding node of the tower, the name, the number and the state information of the equipment are displayed, and the detailed information can be checked by checking the file and jumping to the equipment file page,
the user can also change the information stored in the database through the operation and application of the function module in the interface, wherein the change comprises checking the basic file of the equipment, managing the model library, wherein the management comprises binding of the model name, the model type, the equipment to which the model belongs, the equipment type, the model variable and the factor, associating the variable and binding the measuring point to the newly added instance, introducing the variable number, the variable name, the equipment to which the variable belongs, the variable abbreviation and the variable description information in the variable library in batches, and adding, deleting, modifying and inquiring the corresponding function module according to the prompt interface.
Has the advantages that: according to the method, risk situation early warning and typical power disaster prediction of the danger control area based on the ubiquitous Internet of things sensing layer are researched, the technology of the Internet of things sensing layer is utilized to classify factors influencing normal operation of power facilities, the danger control area data monitoring sensing layer is constructed, a danger control area data monitoring channel is established, and typical power disaster monitoring data are obtained. The method comprises the steps of meshing the electric power facilities and the never geographic range by using informatization as means, classifying factors influencing the normal operation of the electric power facilities, and defining judgment standards of various danger control areas. Drawing a grid diagram of the danger control area by using a GIS (geographic information system) to realize visual display; different emergency plans are adopted for different danger control areas; providing support for power grid planning and equipment transformation through a control platform; the power system operation and scheduling work are realized in an auxiliary mode, large-area power failure accidents are reflected, and the safe operation level of the power system is improved.
Drawings
Fig. 1 is a flow chart of the risk situation-based early warning method of the present invention.
FIG. 2 is a functional block diagram of a system for implementing the present invention.
FIG. 3 is a flowchart of the intermediate table fetch of the present invention.
FIG. 4 is a diagram of the ETL architecture of the present invention.
FIG. 5 is a block diagram of data extraction according to the present invention.
Detailed Description
The present invention will be further described in detail with reference to the following examples and accompanying drawings.
In the application, an early warning method based on risk situation and a system for realizing the method are provided, as shown in fig. 1, by firstly constructing a network topology structure and hierarchical division, real-time acquisition, storage, analysis and interaction of network data are realized; secondly, carrying out relevance analysis between data by utilizing the construction of a neural network structure; finally, the visualization technology is utilized to present the processed result on a user interface, and the method specifically comprises the following steps:
step 1, constructing a network topology structure, wherein the network topology structure comprises measuring point data, an interface machine, a one-way isolating device, a core switch, a secondary switch and a plurality of intranet clients, and the core switch comprises a relational database server and a computing server.
In the network construction process, a two-layer network structure, namely a core layer and an access layer, is adopted, and a gigabit Ethernet switching technology is adopted to connect through a star; the core layer is used for providing fast forwarding of network data packets and interconnection among backbone nodes, and the access layer is used for completing convergence of user traffic of the client.
All key components of the related core switch can realize redundancy work and can be replaced on line, the recovery time of the fault is finished within a second-level interval, and the availability of the system is further improved on the basis of high reliability of single equipment by adopting a multi-level fault-tolerant design. In order to meet the requirements of network users of the existing scale and simultaneously consider the development and scale expansion of future services, a network should be designed to have flexible expansion capability of user ports, and the number of ports of a core device is flexibly increased by adding modules. The chassis design for the core device has a strong backplane bandwidth and sufficient load slot capacity. The core switching engine can realize the non-blocking port data packet switching under the condition of meeting the maximum configuration by adopting a distributed switching structure, and the expansion of the module does not influence the switching performance. The distributed switch structure realizes the parallel data exchange processing of the switch, optimizes the performance of the network, and reduces the pressure of a core switching engine by the distributed structure combining local exchange and global exchange. To avoid single point of failure in the access layer, one hundred/gigabit interface redundancy is employed on the access switches.
The fusion frame in the related hardware equipment adopts a deep-trust service-2200-CP series super-fusion frame, a database Server 17XS Server, a real-time library Server 17EC Server, a message Server 17Msg Server, a File Server 17File Server and a video Server 17TV Server as a Server. The concrete configuration is as follows: the height of the case is 2U rack, the CPU model is gold/silver series CPUV5, the CPU is 2 CPUs, 14C28T and 2.6GHz, the memory is 768G, the hard disk slot is 12, the standard distribution network port is 6 GE electric ports, the power is 550W/800W, and the power supply is redundant power supply.
The central switch supports 100MB twisted-pair lines, 1000MB twisted-pair lines and 1000MB optical fiber modules, is provided with a redundant power supply and a redundant fan, supports hot plug, can replace equipment components on line, adopts a three-layer switch with a store-and-forward switching mode, adopts backplane switching, is provided with independent switching engines, adopts a modular design and can be freely configured.
The firewall involved in network communication is kilomega, the firewall is connected with an external local area network, the router is provided with kilomega level, and the configured internet behavior management machine authenticated by the public security department meets the requirement that the number of managed people is more than 500, and all the management machines are installed through a rack.
The YIPC industrial computer that the interface workstation chose for use guarantees through the performance that gateway workstation exchange information can not reduce, and every gateway workstation configuration is not less than following standard:
processor and chipset: intel13, memory: greater than or equal to 2G, cache: greater than or equal to 2M, hard disk drive: 160G, optical device: DVD-RW read-write drive, network port: two 10M/100M adaptive Ethernet cards, keyboards: standard keyboard, membrane, mouse: two keys, photoelectric type.
The included unidirectional physical isolation devices allow data sent by the production process control system to the information platform network to pass through normally while ensuring the correctness and required rate of data transmission, while blocking any data sent from the information platform network to the production process control system. The one-way physical isolation device has the following basic configuration performance: the hardware structure with safety isolation capability and high-reliability hardware design; the system supports dual-computer hot standby, dual power supplies and system alarm; unidirectional transmission control; blocking a penetrating TCP connection; the network interface is 4 hundred million network card interfaces and 1 dual-computer hot standby interface; the peripheral interface is 2 terminal interfaces plus 1 special alarm interface plus an intelligent IC card interface; the average failure-free time is more than 60000 hours; under the 100M LAN environment, the data packet throughput is 80 Mbps; the data packet forwarding delay is less than 5 ms; the full-load data packet loss rate is 0.
Step 2, acquiring information data in a real scene through a data interface of information acquisition equipment, and establishing a multi-variable information database; the information in the variable database comprises equipment state, real-time value, equipment parameter basic data, historical curve and historical fault information of storage equipment archive information, model names, model numbers, equipment types, associated variables and measuring points of the power transmission line and tower pole model information.
The information of the variable database is from information acquisition equipment which is erected, wherein the information acquisition equipment comprises a meteorological data sensor, a GPS/Beidou positioning sensor and a microseismic sensor; the related data access modes comprise a standard network transmission protocol TCP/IP protocol, a MODBUS protocol, an OPC protocol and a UDP protocol aiming at different hardware equipment and instrument equipment; the discrete data carries out real-time and dynamic data citation through a data client of a real-time data acquisition tool system, and a client side carries out data transmission through two protocols of Modbus and OPC.
The acquired information is stored in a general relational database in a form conforming to the adopted storage database format through Real-time database service software PIDB-Real based on the relational database.
Step 3, reading the stored information and deducing and analyzing the data correlation by using a neural network and a formula; reading and analyzing data in the database so as to obtain risk early warning assessment; the data reading is that the data is read by the mutual cooperation of the database of the service system and the database of the data platform system and the data is quoted by using a database intermediate table mode. The intermediate table access method can ensure that the database of the service system is safer and can not generate larger system pressure on the database of the service system.
The specific implementation mode is as follows: the database systems of the two parties mutually agree to establish a middle table mechanism in the database system of one party, firstly, a data unloading program is written by the service system database, data required by the central system is firstly copied into the middle table, namely, all the data need time labels as an independent attribute, and therefore, the data can be used for determining whether the data is the latest version or not in the later period. Then, the database in the background of the system can periodically and quantitatively capture data from the provided intermediate table data structure into the system center database through a standard SQL program.
The related data extraction is to extract the required data from the data source for users, and the data is loaded into the data warehouse according to a predefined data warehouse model after data cleaning. In the aspect of data extraction, the data acquisition is carried out by adopting a timestamp increment extraction mode. The method is a change data capturing mode based on snapshot comparison, a timestamp field is added on a source table, and when the data of a modification table is updated in a system, the value of the timestamp field is modified simultaneously. When data extraction is performed, it is decided which data to extract by comparing the system time with the value of the timestamp field. The timestamp of the database supports automatic updating, i.e. the value of the timestamp field is automatically updated when changes occur to the data of other fields of the table. The database does not support the automatic updating of the time stamp, and the time stamp field is manually updated when the business system updates the business data. The time stamp mode has better performance, and the data extraction is relatively clear and simple.
Analyzing data after data acquisition, firstly constructing a neural network, reading the data in a database by using a middle table access and ETL data extraction mode, firstly constructing the neural network with supervised learning by reading historical data parameters and a data set of the current equipment state, and learning the mapping from multiple data to the real-time state of the equipment;
the historical data is information related to equipment states contained in a previous-stage database and is constructed into a network training set, and the equipment states are training labels and are used as comparison references of supervised learning results; the training set is used as input, the early warning result is used as output, a weight value of connection between networks in the neural network model is obtained through training by combining a mathematical formula, and the early warning model can be obtained by bringing the connection weight value into the neural network.
The neural network can be a multi-input/single-output single-layer neural network model, a multi-input/double-output two-layer neural network model, other multi-input/single-output multi-layer neural network models or other multi-input/double-output multi-layer neural network models. The number of hidden layers of the neural network model can be none, one or a plurality of, and the number of the hidden layers is not specifically limited in the application. Similarly, the number of nodes in each hidden layer can be set according to requirements, and the number is not limited in the application.
For clearly explaining the process of establishing the early warning model, an embodiment is described below.
Firstly, establishing a training matrix according to information acquired by information acquisition equipment
Figure BDA0002748018930000091
Each column represents a set of environment information, corresponding to the training matrix, and determines the expected matrix of the output matrix Z. Input state y1～y5Respectively indicating whether the tower pole is inclined, whether the power transmission line is waved, whether the foundation is settled, whether the foundation is damaged by external force and whether the foundation is aged; the intermediate state is a link weight sum unit, and if the output of the intermediate state is denoted as p, it can be expressed as
Figure BDA0002748018930000092
Wherein wiThe connection weight for the corresponding sensed data is an unknown quantity,
Figure BDA0002748018930000093
is the bias is unknown; the output state Z can be expressed as Z ═ f (p), and Z ═ f () is an activation function of the neuron output, and when the output values are different, normal, strong wind early warning, rainstorm early warning, equipment damage, line fault, high temperature early warning and low temperature early warning are respectively expressed.
A training stage: setting initial value of connection weight, training whole network by using initial value, solving connection weight and bias by setting iteration number or minimum error control model
Figure BDA0002748018930000094
And a finishing stage: obtaining the connection weight and the offset theta among all layers of the network through autonomous learning, and obtaining the connection weight and the offset obtained through training
Figure BDA0002748018930000095
And (5) bringing the data into a neural network model to obtain an early warning model.
Other types of neural network training are similar and will not be described in detail herein. The whole training process can be completed in an off-line mode, and after the training is finished, the obtained early warning model can be fully utilized to complete the validity judgment on whether early warning is performed or not.
Step 4, displaying risk situations, early warning and fault states through a visual interface; the user can check the displayed risk situation, early warning and fault state through a visual interface; the step is realized by presenting the design of the interface layout in a visual form by utilizing a front-end development programming language to analyze and process the data, wherein a user can select a functional module to be selected according to an interface of a risk situation early warning center presented on the interface, and the visual and visible functional module comprises a health monitoring center, a model library, a variable library, a model example, industry maintenance, professional maintenance, equipment classification and system management; and the user can perform corresponding operation according to the interface prompt by clicking the corresponding functional module.
The monitoring center displays all the subareas on a map, the boundaries of different subareas are distinguished, the head page displays the line state statistics fault number, normal number and early warning number of each area and all the areas in a table, and the subareas with the line fault are marked by different colors; the home page also displays weather information and marks abnormality in different colors; the current subarea can be highlighted when the mouse hovers the current subarea; when a single partition is zoomed and checked by a mouse, each power transmission line in the partition is displayed, a specific line is highlighted by a mouse suspension event, the normal operation number, the early warning number and the fault number of the line in the current partition are counted and displayed on a current page, and the whole line is warned by warning color identification as long as a tower or a lead in one power transmission line is abnormal; when a certain line is clicked, highlighting tower and power transmission line equipment under the line, and counting and displaying the normal operation quantity, early warning quantity and fault quantity of various equipment of the line; after the power transmission line with abnormal state is selected, only the tower and the wire with abnormal state are identified with abnormal color to distinguish abnormal state, the early warning identification is used for distinguishing early warning state, page is enlarged, the three-dimensional model of the equipment tower is displayed at the corresponding node of the tower, the name, the number and the state information of the equipment are displayed, and the detailed information can be checked by checking the file and jumping to the equipment file page,
the user can also change the information stored in the database through the operation and application of the function module in the interface, wherein the change comprises checking the basic file of the equipment, managing the model library, wherein the management comprises binding of the model name, the model type, the equipment to which the model belongs, the equipment type, the model variable and the factor, associating the variable and binding the measuring point to the newly added instance, introducing the variable number, the variable name, the equipment to which the variable belongs, the variable abbreviation and the variable description information in the variable library in batches, and adding, deleting, modifying and inquiring the corresponding function module according to the prompt interface.
Based on the method, a system for implementing the method can be constructed, which includes:
a first module for constructing a network data communication; the module performs the layout of network communication according to the network communication protocol and the parameter setting of the network equipment.
The second module is used for acquiring real-time data and establishing an information base; the module utilizes each information acquisition terminal erected on the spot to acquire and store real-time data through the arranged data transmission interface.
A third module for processing a data evaluation risk mechanism; the module reads data while ensuring data security in a mode of taking data through a middle table, and carries out risk situation assessment on the existing information through a trained neural network.
A fourth module for presenting visualized data processing information; the module presents the interface of the processed data through a visualization technology and a data interaction technology, so that a user can inquire the risk situation through a simple and easy-to-operate interface and manage basic information.
As noted above, while the present invention has been shown and described with reference to certain preferred embodiments, it is not to be construed as limited thereto. Various changes in form and detail may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.

Claims (10)

1. A risk situation-based early warning method is characterized by comprising the following steps:
step 1, constructing a network topology structure, wherein the network topology structure comprises measuring point data, an interface machine, a one-way isolating device, a core switch, a secondary switch and a plurality of intranet clients, wherein the core switch comprises a relational database server and a computing server;
step 2, acquiring information data in a real scene through a data interface of information acquisition equipment, and establishing a multi-variable information database;
step 3, reading the stored information and deducing and analyzing the data correlation by using a neural network and a formula;
and 4, displaying the risk situation, early warning and fault state through a visual interface.
2. The risk situation-based early warning method according to claim 1, wherein the step 1 further comprises:
in the process of network construction, a two-layer network structure, namely a core layer and an access layer, is adopted, and a gigabit Ethernet switching technology is adopted to connect through a star; the core layer is used for providing fast forwarding of network data packets and interconnection among backbone nodes, and the access layer is used for completing convergence of user traffic of the client.
3. The risk situation-based early warning method according to claim 1, wherein the step 2 further comprises:
the information in the variable database comprises equipment state, real-time value, equipment parameter data, historical curve and historical fault information of storage equipment archive information, model names, model numbers, equipment types, associated variables and measuring points of the power transmission line and tower model information;
the information of the variable database is from information acquisition equipment which is erected, wherein the information acquisition equipment comprises a meteorological data sensor, a GPS/Beidou positioning sensor and a microseismic sensor; the related data access modes are a standard network transmission protocol TCP/IP protocol, a MODBUS protocol, an OPC protocol and a UDP protocol aiming at different hardware equipment and instrument equipment; the discrete data carries out real-time and dynamic data reference through a DataClient of a real-time data acquisition tool system, and a client side of the discrete data carries out data transmission through two protocols of Modbus and OPC;
the acquired information is stored in a general relational database in a form conforming to the adopted storage database format through Real-time database service software PIDB-Real based on the relational database.
4. The risk situation-based early warning method according to claim 1, wherein the step 3 further comprises:
reading data in a database by using a middle table access and ETL data extraction mode, firstly, establishing a neural network with supervised learning by reading historical data parameters and a data set of the current equipment state, and learning the mapping from multiple data to the real-time state of the equipment;
the historical data is information related to equipment states contained in a previous-stage database, the historical data is constructed into a network training set, and the equipment states are training labels and are used as comparison reference objects of supervised learning results; the method comprises the steps that a training set is used as input, an early warning result is used as output, weights of connection among networks in a neural network model are obtained through training by combining a mathematical formula, and the connection weights are brought into the neural network to obtain an early warning model;
the model training process comprises the steps of establishing a training matrix
Figure FDA0002748018920000021
Wherein each column represents a set of environment information, corresponding to the training matrix, determining the expected matrix of the output matrix Z, the input state y1～y5Respectively indicating whether the tower pole is inclined, whether the power transmission line is waved, whether the foundation is settled, whether the foundation is damaged by external force and whether the foundation is aged; the intermediate state is a link weight sum unit, and if the output of the intermediate state is denoted as p, it can be expressed as
Figure FDA0002748018920000022
Wherein wiThe connection weight for the corresponding sensed data is an unknown quantity,
Figure FDA0002748018920000023
is the bias is an unknown quantity; the output state Z can be expressed as Z ═ f (p), Z ═ f () is an activation function of the output of the neuron, and when the output values are different, normal and strong wind early warning, rainstorm early warning, equipment damage, line fault, high temperature early warning and low temperature early warning are respectively expressed;
a training stage: setting initial value of connection weight, training whole network by using initial value, solving connection weight and bias by setting iteration number and minimum error control model
Figure FDA0002748018920000025
And a finishing stage: obtaining the connection weight and the offset theta among all layers of the network through autonomous learning, and obtaining the connection weight and the offset obtained through training
Figure FDA0002748018920000024
And (5) bringing the data into a neural network model to obtain an early warning model.
5. The risk situation-based early warning method according to claim 1, wherein the step 4 further comprises:
displaying the analyzed and processed data in a visual mode by utilizing the design of the interface layout by utilizing a front-end development programming language, wherein the user side performs function operation by clicking a mouse according to a function module displayed on the interface; the functional modules are a health monitoring center, a model library, a variable library, a model example, industry maintenance, professional maintenance, equipment classification and system management.
6. A risk situation-based early warning system for implementing the method of any one of claims 1-5, comprising the following modules:
a first module for constructing a network data communication;
the second module is used for acquiring real-time data and establishing an information base;
a third module for processing a data evaluation risk mechanism;
a fourth module for presenting visualized data processing information.
7. The risk situation-based early warning system according to claim 6, wherein the first module further constructs a network topology structure comprising measuring point data, an interface machine, a unidirectional isolation device, a core switch, a secondary switch and a plurality of intranet clients, wherein the core switch comprises a relational database server and a computing server; in the network construction process, a two-layer network structure, namely a core layer and an access layer, is adopted, and a gigabit Ethernet switching technology is adopted to connect through a star; the core layer is used for providing fast forwarding of network data packets and interconnection among backbone nodes, and the access layer is used for completing convergence of user traffic of the client.
8. The risk situation-based early warning system according to claim 6, wherein the second module further acquires information data in a real scene through a data interface of information acquisition equipment to establish a multi-variable information database; the information in the variable database comprises equipment state, real-time value, equipment parameter data, historical curve and historical fault information of storage equipment archive information, model names, model numbers, equipment types, associated variables and measuring points of the power transmission line and tower model information;
the information of the variable database is from information acquisition equipment which is erected, wherein the information acquisition equipment comprises a meteorological data sensor, a GPS/Beidou positioning sensor and a microseismic sensor; the related data access modes comprise a standard network transmission protocol TCP/IP protocol, a MODBUS protocol, an OPC protocol and a UDP protocol aiming at different hardware equipment and instrument equipment; the discrete data carries out real-time and dynamic data reference through a DataClient of a real-time data acquisition tool system, and a client side of the discrete data carries out data transmission through two protocols of Modbus and OPC;
the acquired information is stored in a general relational database in a form conforming to the adopted storage database format through Real-time database service software PIDB-Real based on the relational database.
9. The risk situation-based early warning system according to claim 6, wherein the third module further reads data in the database by means of intermediate table access and ETL data extraction, and first constructs a neural network with supervised learning by reading historical data parameters and a data set of the current equipment state, and learns the mapping from multiple data to the real-time state of the equipment;
the historical data is information related to equipment states contained in a previous-stage database and is constructed into a network training set, and the equipment states are training labels and are used as comparison references of supervised learning results; the method comprises the steps that a training set is used as input, an early warning result is used as output, weights of connection among networks in a neural network model are obtained through training by combining a mathematical formula, and the early warning model can be obtained by bringing the connection weights into the neural network;
the model training process comprises the steps of establishing a training matrix
Figure FDA0002748018920000031
Wherein each column represents a set of environment information, corresponding to the training matrix, determining the expected matrix of the output matrix Z, the input state y1～y5Respectively indicating whether the tower pole is inclined, whether the power transmission line is waved, whether the foundation is settled, whether the foundation is damaged by external force and whether the foundation is aged; the intermediate state is a link weight sum unit, and if the output of the intermediate state is denoted as p, it can be expressed as
Figure FDA0002748018920000032
Wherein wiIs corresponding sensingThe connection weight of the data is an unknown quantity,
Figure FDA0002748018920000033
is the bias is an unknown quantity; the output state Z can be expressed as Z ═ f (p), Z ═ f () is an activation function of the output of the neuron, and when the output values are different, normal and strong wind early warning, rainstorm early warning, equipment damage, line fault, high temperature early warning and low temperature early warning are respectively expressed;
a training stage: setting initial value of connection weight, training whole network by using initial value, solving connection weight and bias by setting iteration number and minimum error control model
Figure FDA0002748018920000041
And a finishing stage: obtaining the connection weight and the offset theta among all layers of the network through autonomous learning, and obtaining the connection weight and the offset obtained through training
Figure FDA0002748018920000042
And (5) bringing the data into a neural network model to obtain an early warning model.
10. The risk situation-based early warning system according to claim 6, wherein the fourth module further displays risk situations, early warning and fault states through a visual interface; the module utilizes a front-end development programming language to display the design of interface layout in a visual form to analyze and process the data, wherein a user selects a functional module according to an interface of a risk situation early warning center displayed on the interface, and the functional module comprises a health monitoring center, a model library, a variable library, a model example, industry maintenance, professional maintenance, equipment classification and system management;
the monitoring center displays all the subareas on a map, the boundaries of different subareas are distinguished, the head page displays the line state statistics fault number, normal number and early warning number of each area and all the areas in a table, and the subareas with the line fault are marked by different colors; the home page also displays weather information and marks abnormality in different colors; when the mouse hovers the current divided area, highlighting the current divided area; when a single partition is zoomed and checked by a mouse, each power transmission line in the partition is displayed, a specific line is highlighted by a mouse suspension event, the normal operation number, the early warning number and the fault number of the line in the current partition are counted and displayed on a current page, the state of a tower and a lead in one power transmission line is abnormal, and the whole line is warned by warning color identification; when a certain line is clicked, highlighting tower and power transmission line equipment under the line, and counting and displaying the normal operation quantity, early warning quantity and fault quantity of various equipment of the line; after the power transmission line with the abnormal state is selected, only the tower and the wire with the abnormal state are identified with the abnormal color to distinguish the abnormal state, the early warning identification distinguishes the early warning state, the page is enlarged, the three-dimensional model of the tower is displayed at the corresponding node of the tower, the name, the number and the state information of the equipment are displayed, and the user jumps to the file page of the equipment to view the detailed information by viewing the files.
CN202011173427.3A 2020-10-28 2020-10-28 Early warning method and system based on risk situation Withdrawn CN112463892A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011173427.3A CN112463892A (en) 2020-10-28 2020-10-28 Early warning method and system based on risk situation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011173427.3A CN112463892A (en) 2020-10-28 2020-10-28 Early warning method and system based on risk situation

Publications (1)

Publication Number Publication Date
CN112463892A true CN112463892A (en) 2021-03-09

Family

ID=74836002

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011173427.3A Withdrawn CN112463892A (en) 2020-10-28 2020-10-28 Early warning method and system based on risk situation

Country Status (1)

Country Link
CN (1) CN112463892A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112995196A (en) * 2021-03-23 2021-06-18 上海纽盾科技股份有限公司 Method and system for processing situation awareness information in network security level protection
CN113467349A (en) * 2021-05-13 2021-10-01 河北工程大学 Intelligent identification premonitory warning system for potential safety hazards of power transmission line
CN115460063A (en) * 2022-09-13 2022-12-09 浙江大有实业有限公司钱塘分公司 Real-time early warning system for distribution network fault
CN117435678A (en) * 2023-12-18 2024-01-23 山东山大华天软件有限公司 System integration method and system based on intermediate data pool and visual customization

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112995196A (en) * 2021-03-23 2021-06-18 上海纽盾科技股份有限公司 Method and system for processing situation awareness information in network security level protection
CN113467349A (en) * 2021-05-13 2021-10-01 河北工程大学 Intelligent identification premonitory warning system for potential safety hazards of power transmission line
CN115460063A (en) * 2022-09-13 2022-12-09 浙江大有实业有限公司钱塘分公司 Real-time early warning system for distribution network fault
CN115460063B (en) * 2022-09-13 2024-02-13 浙江大有实业有限公司钱塘分公司 Real-time early warning system for distribution network faults
CN117435678A (en) * 2023-12-18 2024-01-23 山东山大华天软件有限公司 System integration method and system based on intermediate data pool and visual customization
CN117435678B (en) * 2023-12-18 2024-04-23 山东山大华天软件有限公司 System integration method and system based on intermediate data pool and visual customization

Similar Documents

Publication Publication Date Title
CN112463892A (en) Early warning method and system based on risk situation
CN112600891B (en) Information physical fusion-based edge cloud cooperative system and working method
CN102752142B (en) A kind of method for supervising of the information system based on Conceptual Modeling and supervisory control system
CN107943668A (en) Computer server cluster daily record monitoring method and monitor supervision platform
CN109146093A (en) A kind of electric power equipment on-site exploration method based on study
CN107958337A (en) A kind of information resources visualize mobile management system
CN113176948B (en) Edge gateway, edge computing system and configuration method thereof
US20200272923A1 (en) Identifying locations and causes of network faults
CN101329564A (en) Computer room management system
CN106789412A (en) Method, the apparatus and system of monitoring information collection main website performance
CN113179190B (en) Edge controller, edge computing system and configuration method thereof
CN111259073A (en) Intelligent business system running state studying and judging system based on logs, flow and business access
CN104637265A (en) Dispatch-automated multilevel integration intelligent watching alarming system
CN112769605B (en) Heterogeneous multi-cloud operation and maintenance management method and hybrid cloud platform
CN108718108A (en) A kind of distant monitoring of photovoltaic power station based on UDP and intelligent decision system
CN112052134A (en) Service data monitoring method and device
CN112241424A (en) Air traffic control equipment application system and method based on knowledge graph
CN114070742A (en) Network topology identification method and platform for electric power monitoring system
CN111125450A (en) Management method of multilayer topology network resource object
WO2024088025A1 (en) Automated 5gc network element management method and apparatus based on multi-dimensional data
CN113395180A (en) Industrial real-time big data acquisition and release method and industrial real-time big data platform
CN113592210A (en) Internet of things integrated management platform for water supply non-negative-pressure secondary water supply facility
CN111082987A (en) Ubiquitous power Internet of things-oriented distribution network operation and maintenance system and method
CN112256490A (en) Data processing method and device
CN111769987A (en) Network information security testing system and method based on big data management model

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
WW01 Invention patent application withdrawn after publication

Application publication date: 20210309

WW01 Invention patent application withdrawn after publication