CN115347674A - Distribution network virtual production command system and method - Google Patents
Distribution network virtual production command system and method Download PDFInfo
- Publication number
- CN115347674A CN115347674A CN202211000087.3A CN202211000087A CN115347674A CN 115347674 A CN115347674 A CN 115347674A CN 202211000087 A CN202211000087 A CN 202211000087A CN 115347674 A CN115347674 A CN 115347674A
- Authority
- CN
- China
- Prior art keywords
- distribution network
- scheduling
- entity
- distribution
- virtual production
- 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.)
- Pending
Links
Images
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00001—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by the display of information or by user interaction, e.g. supervisory control and data acquisition systems [SCADA] or graphical user interfaces [GUI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- 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
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/04—Circuit arrangements for ac mains or ac distribution networks for connecting networks of the same frequency but supplied from different sources
- H02J3/06—Controlling transfer of power between connected networks; Controlling sharing of load between connected networks
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- 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
Abstract
The invention discloses a distribution network virtual production command system and a distribution network virtual production command method, wherein the distribution network virtual production command AI intelligent engine module is used for constructing a corresponding distribution network regulation knowledge graph through an existing power grid regulation, the distribution network regulation knowledge graph comprises an entity and an entity part, and the entity comprises the type and the name of a power station, the type and the name of equipment, the equipment state type and the operation type; extracting entity features from the knowledge graph, taking the entity features as input, and taking a scheduling text as target output to train a preset machine learning model; inputting voice information about the real-time state of the power grid on site, identifying the voice information, extracting entity information from the voice information, obtaining a real-time scheduling text by using a machine learning model obtained by training, and generating a corresponding scheduling instruction. The invention strengthens the management and control of the power distribution operation process and improves the man-machine cooperation efficiency.
Description
Technical Field
The invention relates to the field of distribution network virtual production command service design and application, in particular to a distribution network virtual production command system and a distribution network virtual production command method.
Background
With rapid progress of social economy, the scale of a power distribution network is continuously increased, the number of power users is continuously increased, and a distribution network production command center is used as a distribution network service hub aiming at the requirements of the whole society for continuously improving power supply quality and high-quality service level under new situation. With the rapid development of the internet, the information society is promoted to enter the big data era, and the big data prompts artificial intelligence. Many industries have demonstrated success in conjunction with AI applications, particularly in replacing human repetitive labor. In the field of power distribution networks, how to draw reference to autonomous learning modes such as international mainstream artificial intelligence (such as Google AlphaGo) and the like, explore service fusion of artificial intelligence and the professional field of power grids, and realize intelligent application in the fields of power grid dispatching operation command, fault emergency repair, intelligent service and the like needs to be developed for deep research and application verification.
The distribution network dispatching command center is used as a distribution network service hub, and in the distribution network production command center, in the morning and evening peak periods, a large number of field workers need to report and permit to a dispatcher during overhauling and rush-repair work. Production commander needs to look over a plurality of systems while working, contacts with the scene according to the work ticket in proper order, and whole work flow must strictly carry out according to the scheduling regulation, and the flow is loaded down with trivial details, and all work can only be accomplished in series, need invest a large amount of manpower and time, cause the work repetition rate high, and efficiency is on the low side.
How to utilize machine intelligence to replace a large amount of unnecessary artifical repetition work, effectively exert the effect of electric wire netting commander, promote the whole operation efficiency of enterprise and become the technical problem that this field need be solved.
Disclosure of Invention
Aiming at the technical problems in the prior art, the invention provides a distribution network virtual production command method.
In order to achieve the technical purpose, the invention adopts the following technical scheme.
In one aspect, the present invention provides a distribution network virtual production command system, including: the distribution network virtual production director AI intelligent engine module is used for constructing a corresponding distribution network regulation knowledge graph through an existing power grid regulation, wherein the distribution network regulation knowledge graph comprises an entity and an entity part relationship, and the entity comprises the type and name of a power station, the type and name of equipment, the equipment state type and the operation type;
extracting entity features from the knowledge graph, taking the entity features as input, and taking a scheduling text as target output to train a preset machine learning model;
inputting on-site voice information about the real-time state of the power grid, identifying the voice information, extracting entity information from the voice information, obtaining a real-time scheduling text by using a machine learning model obtained by training, and generating a corresponding scheduling instruction.
Further, the AI intelligent engine of the distribution network virtual production director is also used for displaying alarm information.
Furthermore, the distribution network virtual production director AI intelligent engine is set to be fused with the distribution automation safety IV area master station system, and is integrated and interacted with the distribution automation safety I area master station, the distribution automation safety III area master station, the dispatching telephone system and the OMS system in an interface mode.
And the distribution network virtual production director AI intelligent engine is also used for generating an automatic scheduling instruction by using the acquired machine learning model, verifying according to the instruction and the scheduling rule to ensure compliance, and sending the instruction to a distribution automation safety I area master station or a distribution automation safety III area master station if the verification is passed.
And the distribution network virtual production director AI intelligent engine is used for calling an operation ticket of the OMS through an interface, identifying the telephone voice accessed by the scheduling telephone system and executing man-machine voice conversation based on the operation ticket.
The system further comprises a power distribution operation agent service module, wherein the power distribution operation agent service module comprises a production control area agent module constructed in the safety area I and an information management area agent module constructed in the safety area III, the two agent modules are communicated through a forward isolation device and a reverse isolation device, and the power distribution operation agent service module provides data conversion, coding, transmission and receiving functions and simultaneously provides a service interface.
In a second aspect, the present invention provides a distribution network virtual production command method, including: constructing a corresponding distribution network regulation knowledge graph through an existing power grid regulation, wherein the distribution network regulation knowledge graph comprises a relation between an entity and an entity, and the entity comprises the type and name of a power station, the type and name of equipment, the state type of the equipment and the operation type;
extracting entity features from the knowledge graph, taking the entity features as input, and taking a scheduling text as target output to train a preset machine learning model;
inputting voice information of field personnel, extracting entity information from the voice information, and obtaining a corresponding scheduling text by using a machine learning model obtained by training.
And further, generating an automatic scheduling instruction by using the acquired machine learning model, verifying according to the instruction and the scheduling rule to ensure compliance, and sending the instruction to a distribution automation safety I area master station or a distribution automation safety III area master station if the verification is passed.
Further, after the distribution automation safety I area master station or the distribution automation safety III area master station receives the automatic scheduling instruction, general verification is carried out on the automatic scheduling instruction of which the scheduling operation service contains a set or the listing safety level meets the set requirement, the general verification is that whether the state is locked or not is only checked, and automatic execution is carried out if the verification is passed.
Further, after the distribution automation safety I area master station or the distribution automation safety III area master station receives the automatic scheduling instruction, strong verification is carried out on the automatic scheduling instruction of which the safety level of remote monitoring meets the set requirement, the strong verification comprises topology error prevention and power flow verification, and the verification is executed after manual confirmation is still needed after the verification is passed.
The invention has the following beneficial technical effects:
in order to adapt to a new development form represented by 'Internet plus', the development planning of an intelligent operation inspection technology is taken as guidance, the management and control of a power distribution operation process are strengthened, the man-machine cooperation efficiency is improved, and an artificial intelligence technology and a modern communication technology are taken as carriers, so that an intelligent technology and equipment are comprehensively applied. The invention develops the research of the key technology of the power supply service command virtual seat based on artificial intelligence. According to the invention, autonomous learning modes such as international mainstream artificial intelligence (such as Google AlphaGo) are used for reference, the service fusion of the artificial intelligence and the professional field of the power grid is explored, the intelligent application in the fields of power grid dispatching operation command, fault first-aid repair, intelligent service and the like is realized, machine intelligence is used for replacing a large amount of unnecessary manual repeated labor, the effect of power grid command is effectively exerted, and the overall operation efficiency of an enterprise is improved. Through joining in marriage net virtual production commander AI intelligent engine module, really realize the virtual commander seat of intelligence of artificial intelligence meaning, effectively help the site operation personnel to promote user experience, for joining in marriage net production commander decompression.
Drawings
Fig. 1 is an architecture diagram of a distribution network virtual production command system according to an embodiment;
FIG. 2 is a power distribution network knowledge graph in an exemplary embodiment;
FIG. 3 is a schematic diagram of an application architecture of the AI smart engine module in the embodiment;
in the embodiment of fig. 4, the AI intelligence engine module performs artificial intelligence to assist the scheduling decision making framework;
FIG. 5 illustrates a security architecture in an embodiment.
Detailed Description
The distribution network virtual production command system and method of the present invention are described in detail below.
Example 1
A distribution network virtual production command system, as shown in fig. 1, includes: the distribution network virtual production director AI intelligent engine module is used for constructing a corresponding distribution network regulation knowledge graph through an existing power grid regulation, wherein the distribution network regulation knowledge graph comprises an entity and an entity part relationship, and the entity comprises the type and name of a power station, the type and name of equipment, the equipment state type and the operation type;
extracting entity features from the knowledge graph, taking the entity features as input, and taking a scheduling text as target output to train a preset machine learning model;
inputting on-site voice information about the real-time state of the power grid, identifying the voice information, extracting entity information from the voice information, obtaining a real-time scheduling text by using a machine learning model obtained by training, and generating a corresponding scheduling instruction.
The natural language identification of the procedure text is needed to be carried out on the construction of the distribution network procedure knowledge graph, a corresponding word bank in the power field is needed, but the corresponding word bank in the industry is relatively lacked and needs to be constructed step by step at present. The basic process of extracting the knowledge graph data is as follows: language segmentation, part of speech tagging, named entity recognition, syntactic analysis, and higher-level writing applications also include semantic dependency analysis, but the common knowledge extraction tools have a common disadvantage in that: extraction according to a given pattern using a trained model of others may be sufficient for open-field knowledge extraction. However, for knowledge extraction in a professional field, such as the power industry, a tool may not be provided to cover the industry field, the accuracy of knowledge extraction by the tool is relatively low, an adaptive model for updating knowledge extraction is required, the accuracy of knowledge extraction is gradually improved in a continuous iteration mode, and the iteration process allows manual participation.
In the embodiment, a power distribution Network rule knowledge graph is constructed, feature matrixes of actual scheduling texts and knowledge graph entities are constructed from three dimensions of semantics, pronunciation and parts of speech respectively, and a model structure of LSF-SCNN (LSF-SCNN) is improved from a Feature calculation method and an attention machine method, so that a power distribution scheduling text entity linking method facing the power distribution Network knowledge graph is provided, and texts input by field personnel in a voice mode can be automatically linked to corresponding entities of the power distribution Network knowledge graph. Since the power distribution network scheduling information reported by the field personnel generally relates to the states or related operations of various power distribution equipment, the knowledge graph for power distribution network scheduling mainly comprises entities such as the types and names of power stations, the types and names of equipment, the states of equipment and the types of operations, and the relationships between the entities, as shown in fig. 2.
In fig. 2, the square boxes represent entities, arrows between the square boxes represent relationships between the entities, a middle column represents power stations and equipment types, such as switchyards, substations, stations and equipment types, lines, switches, each station or equipment includes a plurality of specific station or equipment names, as shown in a left column, such as city stations, eastern stations, temporary changes, xiayu changes, and the like; at the same time, each equipment type has corresponding state or operation, as shown in the right column, such as correct phase, name removal, operation change from cold standby, and exact disconnection position. Before the power distribution network knowledge graph is used for analyzing the scheduling information, the information of power stations, equipment, states, operations and the like contained in the power distribution scheduling text needs to be mapped to corresponding entities of the knowledge graph, and a foundation is laid for analyzing and verifying the scheduling information by means of the knowledge graph.
Fig. 3 is a schematic diagram of an application architecture of the AI intelligence engine module in an embodiment. As shown in fig. 3 to 5, the AI intelligent engine of the distribution network virtual production director is further configured to display alarm information.
The distribution network virtual production director AI intelligent engine is set to be fused with the distribution automation safety IV area master station system, and is integrated and interacted with the distribution automation safety I area master station, the distribution automation safety III area master station, the dispatching telephone system and the OMS system in an interface mode.
The distribution network virtual production director AI intelligent engine is also used for generating an automatic scheduling instruction by utilizing the acquired machine learning model, checking according to the instruction and the scheduling rule to ensure compliance, and sending the instruction to a distribution automation safety I area master station or a distribution automation safety III area master station if the checking is passed.
And the distribution network virtual production director AI intelligent engine is used for calling an operation ticket of the OMS through an interface, identifying the telephone voice accessed by the scheduling telephone system and executing man-machine voice conversation based on the operation ticket.
The system also comprises a power distribution operation agent service module, wherein the power distribution operation agent service module comprises a production control area agent module constructed in the safety area I and an information management area agent module constructed in the safety area III, the two agent modules are communicated through a forward isolation device and a reverse isolation device, and the power distribution operation agent service module provides data conversion, coding, transmission and receiving functions and simultaneously provides a service interface.
Example 2
Corresponding to the distribution network virtual production command system provided in the above embodiment, this embodiment provides a distribution network virtual production command method, including: constructing a corresponding distribution network regulation knowledge graph through an existing power grid regulation, wherein the distribution network regulation knowledge graph comprises a relation between an entity and an entity, and the entity comprises the type and name of a power station, the type and name of equipment, the state type of the equipment and the operation type;
extracting entity features from the knowledge graph, taking the entity features as input, and taking a scheduling text as target output to train a preset machine learning model;
inputting voice information of field personnel, extracting entity information from the voice information, and obtaining a corresponding scheduling text by using a machine learning model obtained by training.
The business application of the AI intelligent scheduling engine for intelligent production and command of the distribution network comprises the steps of judging the execution decision of maintenance scheduling business, layering screen monitoring alarm information and processing the execution decision, integrating with a telephone system, calling or answering a site telephone, understanding conversation voice through voice recognition, carrying out voice interaction and work content check according to an operation ticket, generating man-machine conversation voice, and transferring to the telephone system to realize real-time voice conversation.
The decision making of scheduling speciality in the artificial intelligence conversation process comprises two aspects: firstly, a scheduling professional decision based on static information is made, and before a virtual dispatcher sends an instruction to an automatic system, the instruction and a scheduling procedure are checked to ensure operation compliance; and secondly, based on the scheduling professional decision of the real-time state of the power grid, after the virtual scheduler sends the operation instruction to the automatic system, the automatic system needs to check the operation instruction and the running state of the power grid to ensure the operation safety.
The dispatching operation service comprises setting/registering instructions with lower security level to carry out 'general verification', only whether the state is locked or not needs to be checked, and the verification is directly and automatically executed. And supporting intelligent professional scheduling decisions by artificial intelligence dialogue interaction and adopting a regulation and control operation safety check technology considering capacity constraints. Information of the project in the interaction process of artificial intelligence and the power distribution automation system adopts an intelligent checking mechanism, so that the defects of artificial interaction and low calculation efficiency are overcome, and the regulation and control operation efficiency of the power distribution network is improved.
The remote monitoring security level is high, strong verification is required, including topology anti-misoperation and tide verification, and the verification can be executed by a manual confirmation party after passing. According to the distribution network regulation operation specification, the operation execution analysis and the operation overtime alarm of the automatic system are combined with the distribution network intelligent production command AI intelligent engine, the field operation execution condition management and control are realized, and the remote control closed-loop management is completed by the participation of a virtual dispatcher in the remote control monitoring.
Decision judgment in the intelligent monitoring screen realizes alarm layering through support of a knowledge graph, automatically confirms signals caused by planned work, informs known defect signals, identifies events through abnormal signals, and performs disposal operation according to types. The AI intelligent engine is combined with the alarm information intelligent layering, the distribution network alarm grading is customized, the layered information is assigned with intelligent tasks, and the AI intelligent engine is commanded to carry out telephone work notification through distribution network intelligent production.
As shown in fig. 5, in the design of the virtual production command engine of the distribution network, the consideration of the security architecture is performed in the aspect of information cross-region. And a power distribution operation service agent is constructed between the production control area and the information area, so that the transmission of a power distribution scheduling operation instruction and the feedback of an instruction execution result can run through the safety area I and the safety area III in a service mode, and the virtual production command engine can realize data exchange and function calling in a service calling mode.
The power distribution operation agent service module comprises a production control area agent module constructed in a safety area I and an information management area agent module constructed in a safety area III, the two agent modules are communicated through a forward isolation device and a reverse isolation device, and the power distribution operation agent service module provides data conversion, coding, transmission and receiving functions and a service interface.
In the invention, the AI intelligent engine of the distribution network virtual production director is deployed in the main station of the distribution automation IV area as a sub-functional module to provide the function of the AI intelligent engine of the distribution network intelligent production director for the main station of the distribution automation IV area, thereby realizing the intelligent monitoring of the virtual dispatching command of the distribution network, the alarm information monitoring and disposal of the automation system and the remote control processing of the equipment.
The intelligent engine of the intelligent production command AI of the distribution network is deeply integrated with the system of the distribution automation IV area master station, and a virtual commander is constructed through the system integration interaction of the interface mode and the distribution automation I area master station, the dispatching telephone system and the OMS system (operation order and outage application form) to assist and take over the manual work, so that the services of distribution network scheduled maintenance dispatching command, intelligent remote control monitoring, intelligent monitor screen and the like are realized, and the intelligent distribution network command is realized.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While the present invention has been described with reference to the embodiments shown in the drawings, the present invention is not limited to the embodiments, which are illustrative and not restrictive, and it will be apparent to those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (10)
1. Join in marriage net virtual production command system, its characterized in that includes: the distribution network virtual production director AI intelligent engine module is used for constructing a corresponding distribution network regulation knowledge graph through an existing power grid regulation, wherein the distribution network regulation knowledge graph comprises an entity and an entity part relationship, and the entity comprises the type and name of a power station, the type and name of equipment, the equipment state type and the operation type;
extracting entity features from the knowledge graph, taking the entity features as input, and taking a scheduling text as target output to train a preset machine learning model;
inputting voice information about the real-time state of the power grid on site, identifying the voice information, extracting entity information from the voice information, obtaining a real-time scheduling text by using a machine learning model obtained by training, and generating a corresponding scheduling instruction.
2. The distribution network virtual production command system of claim 1, wherein the distribution network virtual production director AI intelligent engine is further configured to display an alarm message.
3. The distribution network virtual production command system of claim 1, wherein the distribution network virtual production commander AI intelligent engine is configured to be integrated with the distribution automation safety IV area master station system, and is integrated and interacted with the distribution automation safety I area master station, the distribution automation safety III area master station, the dispatch telephone system and the OMS system in an interface manner.
4. The distribution network virtual production command system according to claim 3, wherein the distribution network virtual production commander AI intelligent engine is further configured to generate an automated scheduling instruction using the obtained machine learning model, perform verification with a scheduling procedure according to the instruction to ensure compliance, and send the instruction to a distribution automation safety I area master station or a distribution automation safety III area master station if verification is passed.
5. The distribution network virtual production command system of claim 3,
and the distribution network virtual production director AI intelligent engine is used for calling an operation ticket of the OMS through an interface, identifying telephone voice accessed by a scheduling telephone system and executing a man-machine voice conversation based on the operation ticket.
6. The virtual production command system for the distribution network according to claim 3, wherein the system further comprises a power distribution operation agent service module, the power distribution operation agent service module comprises a production control area agent module constructed in the safety area I and an information management area agent module constructed in the safety area III, the two agent modules communicate with each other through a forward isolation device and a reverse isolation device, and the power distribution operation agent service module provides data conversion, encoding, transmission and reception functions and provides a service interface.
7. The distribution network virtual production command method is characterized by comprising the following steps: constructing a corresponding distribution network regulation knowledge graph through an existing power grid regulation, wherein the distribution network regulation knowledge graph comprises a relation between an entity and an entity, and the entity comprises the type and name of a power station, the type and name of equipment, the state type of the equipment and the operation type;
extracting entity features from the knowledge graph, taking the entity features as input, and taking a scheduling text as target output to train a preset machine learning model;
inputting voice information of field personnel, extracting entity information from the voice information, and obtaining a corresponding scheduling text by using a machine learning model obtained by training.
8. The distribution network virtual production command method according to claim 7, wherein an automatic scheduling instruction is generated by using an acquisition machine learning model, verification is performed according to the instruction and a scheduling rule to ensure compliance, and the instruction is sent to a distribution automation safety area I master station or a distribution automation safety area III master station when the verification is passed.
9. The distribution network virtual production commanding method according to claim 7, characterized in that after the distribution automation safety I area master station or the distribution automation safety III area master station receives the automation scheduling command, the automation scheduling command of which the scheduling operation service includes a set or a listing safety level meeting the set requirement is subjected to a general verification, wherein the general verification is to check whether the state is blocked or not only, and the automatic execution is performed if the verification is passed.
10. The distribution network virtual production commanding method according to claim 7, characterized in that after the distribution automation safety I area master station or the distribution automation safety III area master station receives the automation scheduling command, strong verification is performed on the automation scheduling command in which the safety level of remote monitoring meets the set requirement, wherein the strong verification includes topology error prevention and power flow verification, and the verification is executed after manual confirmation is still needed after passing the verification.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211000087.3A CN115347674A (en) | 2022-08-19 | 2022-08-19 | Distribution network virtual production command system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211000087.3A CN115347674A (en) | 2022-08-19 | 2022-08-19 | Distribution network virtual production command system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115347674A true CN115347674A (en) | 2022-11-15 |
Family
ID=83954584
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211000087.3A Pending CN115347674A (en) | 2022-08-19 | 2022-08-19 | Distribution network virtual production command system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115347674A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115622816A (en) * | 2022-12-19 | 2023-01-17 | 国网江苏省电力有限公司信息通信分公司 | Communication method based on dispatching telephone and man-machine workstation fusion system |
-
2022
- 2022-08-19 CN CN202211000087.3A patent/CN115347674A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115622816A (en) * | 2022-12-19 | 2023-01-17 | 国网江苏省电力有限公司信息通信分公司 | Communication method based on dispatching telephone and man-machine workstation fusion system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102880123B (en) | System and method for controlling production process of petrochemical enterprise on basis of manufacturing execution system (MES) workflow | |
| CN108971807A (en) | A kind of site welding construction technology intelligent management control method and management system | |
| CN109345072A (en) | Dispatching method for distribution branch line scheduling scenario | |
| CN110020967A (en) | The information processing method and device of a kind of dispatching of power netwoks end substation intelligent alarm | |
| CN113258669B (en) | Networked intelligent scheduling method and terminal based on distribution network maintenance | |
| CN108804630A (en) | A kind of big data intellectual analysis service system of Industry-oriented application | |
| CN111428958A (en) | Wisdom sewage plant management and control platform based on multisource information fusion | |
| CN107611969A (en) | Possess the regulation and control anti-error system and method for transfer order binding function | |
| CN104851052A (en) | Intelligent error preventing method and system used for outputting dispatching operation ticket | |
| CN106878466A (en) | A kind of Hydropower Unit data management and equipment control unified platform | |
| CN104517194A (en) | Power operation-maintenance dispatching list generating method based on dynamic planning | |
| CN104953707A (en) | Intelligent error prevention method and system for monitoring operation order | |
| CN115347674A (en) | Distribution network virtual production command system and method | |
| CN113361970B (en) | Virtual dispatcher system and dispatching method based on power intelligent dispatching engine | |
| CN112348345A (en) | Intelligent automatic order dispatching method and system | |
| CN109711572A (en) | A kind of mobile O&M task processing system of photovoltaic plant | |
| CN111275397A (en) | Processing method and system for simulation training service data | |
| CN104036372A (en) | Method for identifying suspected repeating data of electrical equipment | |
| CN113822585A (en) | Intelligent smelting factory informatization management system | |
| CN110007901A (en) | A kind of development system collecting regimental wind-powered electricity generation monitor supervision platform and its operation method and development approach | |
| CN115423152A (en) | Nuclear fuel loading and unloading and position automatic tracking method, device and system | |
| CN211906341U (en) | Power grid dispatching management system | |
| CN110866708A (en) | Power grid dispatching management system and application method thereof | |
| CN109032085A (en) | A kind of million kilowatt nuclear power station emergency command monitoring system | |
| CN116317110B (en) | Power grid dispatching operation previewing method and system considering source load bilateral fluctuation |
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 |