CN117150040A - Safety control strategy knowledge graph construction method and system for AC/DC power grid - Google Patents
Safety control strategy knowledge graph construction method and system for AC/DC power grid Download PDFInfo
- Publication number
- CN117150040A CN117150040A CN202311111609.1A CN202311111609A CN117150040A CN 117150040 A CN117150040 A CN 117150040A CN 202311111609 A CN202311111609 A CN 202311111609A CN 117150040 A CN117150040 A CN 117150040A
- Authority
- CN
- China
- Prior art keywords
- security
- power grid
- control strategy
- security control
- graph
- 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
- 238000011217 control strategy Methods 0.000 title claims abstract description 116
- 238000010276 construction Methods 0.000 title claims abstract description 45
- 238000000034 method Methods 0.000 claims abstract description 54
- 238000000605 extraction Methods 0.000 claims abstract description 19
- 238000013515 script Methods 0.000 claims abstract description 15
- 230000033228 biological regulation Effects 0.000 claims abstract description 12
- 230000009471 action Effects 0.000 claims description 25
- 238000010586 diagram Methods 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 19
- 238000003860 storage Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000008676 import Effects 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 4
- 238000012800 visualization Methods 0.000 claims description 4
- 230000000903 blocking effect Effects 0.000 claims description 3
- 238000009960 carding Methods 0.000 claims description 3
- 238000009434 installation Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 description 8
- 230000006872 improvement Effects 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000005096 rolling process Methods 0.000 description 4
- 230000001960 triggered effect Effects 0.000 description 4
- 239000000203 mixture Substances 0.000 description 3
- 230000008520 organization Effects 0.000 description 3
- 230000001105 regulatory effect Effects 0.000 description 3
- 241000282414 Homo sapiens Species 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000000692 anti-sense effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9024—Graphs; Linked lists
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
-
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Water Supply & Treatment (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Public Health (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a security control strategy knowledge graph construction method and system for an alternating current/direct current power grid, which belong to the field of power grid dispatching, wherein the method comprises the following steps: establishing an security policy ontology model; obtaining structured data and unstructured data of an alternating current/direct current power grid; knowledge extraction is carried out on the structured data and the unstructured data to obtain security control strategy entities, attributes and relations; writing an input script based on the constructed security policy ontology model, and storing security policy entities, attributes and relations into a graph database to complete construction of a security policy knowledge graph. The method assists the regulation personnel to carry out fault handling decision, and provides powerful technical support for new generation engineering construction.
Description
Technical Field
The invention belongs to the field of power grid dispatching, and particularly relates to a safety control strategy knowledge graph construction method and system for an alternating current/direct current power grid.
Background
The power grid dispatching automation system has the advantages that the structured modeling and relational database data storage of data such as power grid equipment model information and power grid operation results are realized, when power grid equipment fails and the condition of triggering protection measures of the security control system is reached, a regulation and control professional combines a security control policy manual (text documents which are summarized by dispatcher and stored in a text form for a long time) and expertise experience, and emergency treatment is carried out on the power grid after the failure so as to maintain power balance of a power system and control the safe and stable operation of the power grid.
Along with the formation of new energy high-duty ratio and high-proportion outgoing type power transmission end power grid and multi-direct current feed-in and high-proportion distributed type power transmission end power grid with new energy access in recent years, the safety control system forms a relatively complex extra-high voltage cross-region direct current safety control system gradually besides the safety and stability automatic device of the traditional power grid. Because of the difference of protection functions of the direct current receiving end power grid system, each direct current safety control system adopts a mode of respectively making a policy table, the online safety analysis of the national center for regulating and applying the extra-high voltage direct current expected fault rolling scanning function module can support a plurality of direct current calculations at present, and each direct current safety control system is unique with one set of safety control policy and is provided with one set of background safety control program. The development and maintenance of the new DC function consumes a certain labor cost, and similar problems exist in the protection of the traditional AC power grid safety and stability automatic device.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides an AC/DC power grid-oriented security control strategy knowledge graph construction method and system.
The aim of the invention is at least realized by the following technical scheme:
the first aspect of the invention provides a security control strategy knowledge graph construction method for an alternating current/direct current power grid, which comprises the following steps:
establishing an security policy ontology model;
obtaining structured data and unstructured data of an alternating current/direct current power grid;
knowledge extraction is carried out on the structured data and the unstructured data to obtain security control strategy entities, attributes and relations;
writing an input script based on the constructed security policy ontology model, and storing security policy entities, attributes and relations into a graph database to complete construction of a security policy knowledge graph.
As a further improvement of the invention, the establishment of the security policy ontology model comprises the following steps:
adopting a top-down knowledge graph in the security control strategy field, wherein a body layer and a knowledge graph layer in the knowledge graph in the security control strategy field are correspondingly arranged; the method specifically comprises the following steps:
extracting important concepts of the protection strategy of the ultra-high voltage cross-region direct current safety control system and the alternating current safety self-device, and obtaining the concept definition of the following safety control strategy body: the system comprises a safety control system, a safety control strategy, safety control measures, mode constraints, fault modes, operation modes, sections, operation mode members, section members and fault members;
relationships in the atlas are established in connection with the experience of performing the security actions, including "entity-relationship-entity" and "entity-attribute value".
As a further improvement of the present invention, the obtaining the structured data and the unstructured data of the ac/dc power grid includes:
acquiring a power grid equipment model, a grid structure and operation data from a regulation and control cloud platform to form structured data;
and extracting and arranging an alternating current power grid self-installation device protection strategy document and a cross-region direct current security control system strategy document as unstructured data.
As a further improvement of the invention, the knowledge extraction of structured data and unstructured data to obtain security policy entities, attributes and relations comprises:
directly acquiring the structured data of the power grid equipment model from a database, carrying out unified language specification description on the unstructured data of the text, combining specific security and control examples, corresponding to ontology concepts and attributes, and creating a node dictionary and an edge relation dictionary by id mapping entity relations; and describing the fault phenomenon and the security control strategy by adopting a unified language mode to obtain security control strategy entities, attributes and relations.
As a further improvement of the invention, the security control strategy ontology model based on construction writes an input script, and the security control strategy entity, attribute and relationship are stored in a graph database to complete construction of a security control strategy knowledge graph; comprising the following steps:
resolving the knowledge graph in the security policy field into a power grid equipment entity graph and a business logic concept graph;
based on the extraction result of the obtained entity and relation, writing corresponding data import script based on the structured data to adapt to the entity map and service logic conceptual map of the power grid equipment, so as to realize the visualization of security control service logic;
and obtaining constraint conditions required to be met by triggering the security policies and association relations among different security policies, and constructing a security policy knowledge graph by combining the relation between the entity graph of the power grid equipment and the service logic concept graph.
As a further improvement of the invention, the method for constructing the entity map of the power grid equipment comprises the following steps:
converting a relational database of the power grid topology into a graph database based on triple representation, and carrying out knowledge inquiry, reasoning and graph calculation on complex association relations of massive data of the power grid by adopting a representation mode based on a graph;
and extracting entity triples from the existing relational database for the structured data of the power dispatching system, and converting the entity triples into a graph database, thereby constructing the entity graph of the power grid equipment.
As a further improvement of the invention, the business logic conceptual diagram construction method comprises the following steps:
summarizing service flows of a cross-region direct current safety and stability control system and an alternating current power grid safety and stability control system, carding commonalities and characteristics of the cross-region direct current system protection safety and control strategy and an alternating current power grid safety and stability automatic device action strategy, extracting key constraints, establishing a unified model, and obtaining specific safety and control measures based on the same set of service logic reasoning;
based on the security policy knowledge model, combining with the security policy business flow to construct a security business logic conceptual diagram.
As a further improvement of the present invention, the security policy service flow includes:
inputting fault equipment or a fault equipment group, and if the fault equipment or the fault equipment group has a security control strategy, directly triggering a specific strategy of a corresponding security control system after the fault equipment or the fault equipment group fails; if the fault equipment or the fault equipment group has a triggering condition, and the triggering condition is not reached, a security control strategy is not required to be provided;
if the input fault equipment or the fault equipment group has and meets the triggering condition or does not have the triggering condition, inquiring a security control system policy table of the fault equipment or the fault equipment group;
judging whether the security control system has a plurality of security control strategies, if so, acquiring a section, inquiring the current system operation mode, and carrying out the next step based on the current system operation mode; if not, the next step is directly carried out,
acquiring a security control strategy;
and inquiring specific security measures according to the security policy, and executing actions of the security device.
As a further improvement of the invention, the triggering conditions need to meet respective corresponding fault constraints and monitoring constraints; for a cross-zone direct current fault, the trigger condition also needs to determine whether it is a single-pole or double-pole blocking fault of the direct current end or the receiving end.
The second aspect of the invention provides a security control strategy retrieval method for an alternating current/direct current power grid, which comprises the following steps:
selecting a fault group and a power grid section;
judging whether triggering conditions are met or not according to the search data, and carrying out matching identification to search a security control strategy and security control measures from a security control strategy knowledge graph constructed by the method;
outputting the security control strategy and security control measures.
The third aspect of the invention provides an ac/dc power grid-oriented security control strategy knowledge graph construction system, comprising:
the building module is used for building a security policy ontology model;
the acquisition module is used for acquiring structured data and unstructured data of the AC/DC power grid;
the extraction module is used for carrying out knowledge extraction on the structured data and the unstructured data to obtain security control strategy entities, attributes and relations;
the construction module is used for writing an input script based on the constructed security policy ontology model, storing security policy entities, attributes and relations into the graph database, and completing construction of the security policy knowledge graph.
The fourth aspect of the present invention provides an ac/dc grid-oriented security policy retrieval system, comprising:
the selection module is used for selecting fault groups and power grid sections;
the retrieval module is used for judging whether the triggering condition is met or not according to the retrieval data, and carrying out matching identification retrieval of the security control strategy and security control measures from the security control strategy knowledge graph constructed by the method;
and the output module outputs the security control strategy and security control measures.
The fifth aspect of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the processor implements the method for constructing a security policy knowledge graph for an ac/dc power grid or the method for retrieving a security policy for an ac/dc power grid when executing the computer program.
The sixth aspect of the present invention provides a computer readable storage medium, where the computer readable storage medium stores a computer program, where the computer program when executed by a processor implements the method for constructing a security control policy knowledge graph for an ac/dc power grid or the method for retrieving a security control policy for an ac/dc power grid.
Compared with the prior art, the invention has the following beneficial effects:
aiming at the problem that knowledge driving is needed in digital construction of a power grid, the invention combines a knowledge graph with a security control strategy based on a protection security control strategy of a trans-regional direct current system and an action strategy of an alternating current power grid security and stability automatic device, provides a security control strategy knowledge modeling method considering the difference of the alternating current and direct current security control system, converts a discrete and unstructured information organization mode such as a fault mode, an operation mode, an action fixed value, an action mode and the like into a relational and mapped knowledge organization mode, provides a security control strategy knowledge model and constructs a knowledge graph in the security control strategy field. The invention provides powerful technical support for assisting the regulation personnel to carry out fault handling decisions and for new generation engineering construction.
Drawings
FIG. 1 is a flow chart of a method for constructing an AC/DC power grid-oriented security control strategy retrieval model;
FIG. 2 is a schematic diagram of a security policy knowledge modeling and application flow;
FIG. 3 is a schematic diagram of the relationship between the ontology layer and the knowledge-graph layer
FIG. 4 is a specific business flow diagram of a fail-safe security protection action
FIG. 5 is a schematic diagram of a security control business logic concept;
FIG. 6 is a schematic diagram (partially cut) of a security policy knowledge graph;
fig. 7 is a schematic diagram of a security policy retrieval system for an ac/dc power grid in an embodiment of the present invention;
fig. 8 is a schematic diagram of an electronic device according to the present invention.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative only and are not to be construed as limiting the invention. The step numbers in the following embodiments are set for convenience of illustration only, and the order between the steps is not limited in any way, and the execution order of the steps in the embodiments may be adaptively adjusted according to the understanding of those skilled in the art.
Term interpretation:
general knowledge graph: the data sources are encyclopedia, such as hundred degrees encyclopedia, wikipedia and the like, which are mainly common fact knowledge, become one of the core knowledge sources of human beings, and are commonly contributed by a large number of participants distributed around the world, so that the maintenance and updating costs are low.
Domain knowledge graph: only knowledge of a specific field is covered, and the method is often constructed and maintained by a small number of field knowledge experts, and the updating cost is high.
And the safety control system comprises: the power grid safety and stability control system is a second defense line for guaranteeing the safety of the power grid, and a large number of power grid safety and control systems are generally built in a matched mode for guaranteeing the safe operation of the ultra-high voltage alternating current and direct current large power grid.
The current regulation and control system is undergoing digital and intelligent transformation, how to mine the potential value of multiple data, extract the knowledge in the power grid regulation and control professional field and construct a knowledge model is the foundation and premise of constructing a brand new power grid intelligent regulation and control system with double dense information and knowledge in the future. The knowledge graph is used as a knowledge organization and construction method based on an artificial intelligence technology, the information expression of the knowledge graph is closer to the form of human cognition world, complex association relations can be expressed from a semantic level, and the knowledge graph provides better capability of managing and understanding mass information and is suitable for data management in the field of electric power regulation and control.
As shown in fig. 1, a first object of the present invention is to provide a security policy retrieval method for an ac/dc power grid, which includes the following steps:
s1, establishing a security policy ontology model;
s2, obtaining structured data and unstructured data of an alternating current/direct current power grid;
s3, knowledge extraction is carried out on structured data and unstructured data to obtain security policy entities, attributes and relations;
s4, writing an input script based on the constructed security policy ontology model, and storing security policy entities, attributes and relations into a graph database to complete construction of a security policy knowledge graph.
The invention solves the problem of knowledge of the security control strategy, and provides a security control strategy modeling method based on a knowledge graph, which realizes the retrieval of the security control strategy integrated with the AC/DC power grid through the knowledge management of the security control strategy.
The invention provides an intelligent method for rapidly matching a security control strategy for application of theories and technologies in knowledge representation, knowledge maps and the like in intelligent analysis and optimization decision of a large power grid and accumulation of experience, and provides a new generation of scheduling technology support system expected fault rolling scanning and other applications.
The following specific steps of the embodiments of the present invention will be described with reference to the accompanying drawings and specific examples:
the invention provides a unified knowledge model for the safety control strategy of the alternating current safety control system and the direct current safety control system, and designs a set of general retrieval logic for triggering the safety control device to retrieve the protection action after the fault. The steps adopted in the construction process are shown in fig. 2:
first, a security policy ontology model is established.
The pattern construction of the pattern belongs to the category of knowledge modeling, the pattern construction is a process of constructing a concept pattern of the knowledge pattern, and a good pattern can improve the utilization efficiency of the pattern and reduce redundancy. The knowledge graph construction technology is divided into a bottom-up construction mode and a top-down construction mode, wherein the mode needs category induction of all entities, is firstly induced into the most detailed subclass, and then is gradually and upwards formed into a large class concept, and is generally suitable for the construction of a general knowledge graph. The other is a top-down construction mode, which needs to define a data pattern for the atlas, and define the atlas from the top concept, refine the atlas gradually downwards to form an atlas pattern similar to a tree structure, and finally correspond the entity to the concept, wherein the construction mode is generally applicable to construction of knowledge atlas in the field or industry. The knowledge graph in the security policy field adopts a top-down construction mode, and the corresponding relationship between the ontology layer and the knowledge graph layer is shown in fig. 3. The method specifically comprises the following steps:
firstly, extracting important concepts of an extra-high voltage cross-region direct current safety control system and an alternating current safety self-device protection strategy, and obtaining the following concept definition of a safety control strategy body:
1) And the safety control system comprises: refers to a control system comprising a set of all security policies for a given region.
2) Security control strategy: refers to a control strategy after the fault triggering of a certain area.
3) Safety control measures: and means the action measures of the safety self-device after the safety control strategy is triggered.
4) Mode constraint: and the constraint conditions of the security control strategy mode after the fault triggers the security control system comprise an operation mode and a tide section.
5) Failure mode: and the fault form triggers the security control system to execute the security control strategy.
6) The operation mode is as follows: refers to the system operation mode.
7) Section: refers to a tidal current section.
8) Operation mode member: refers to the mode conditions that constitute the specified mode of operation of the system.
9) Section member: refers to a device that constitutes a section, typically in plurality.
10 A failed member: refers to the devices that make up the fault group, typically in plurality.
Second, relationships in the atlas are established, including "entity-relationship-entity" and "entity-attribute value", in conjunction with experience of the administration of actions. Wherein the "entity-relationship-entity" concept definition is abstracted into the following classes:
1) Comprising: the inclusion relationship between entities may also be understood as the relationship between a whole set and a subset of two entities, for example, a security control system includes a plurality of different policies, a mode constraint includes an operation mode constraint condition and a section constraint condition, and a specific security device performs an action after triggering the security control policy, so that the security control policy includes a plurality of security control measures.
2) Constraint: the constraint relation between the entities indicates that some attributes of the entity A are constrained by the entity B, and after the security control system is triggered by failure, the corresponding security control strategy needs to be searched according to the constraint of the mode.
3) Triggering: the trigger relation between the entities indicates that the entity A is a precondition of the entity B, for example, the trigger condition of the security policy is that the failure mode reaches the trigger value.
4) The composition is as follows: the composition relationship between entities means that a plurality of child entities form a parent entity, and the composition relationship is not only a simple antisense, but also a child entity is not necessary for the parent entity. If the fault form A is composed of n (n is greater than or equal to 1) fault members, the custom section B is composed of n (n is greater than or equal to 1) section members, and the operation mode C is composed of n (n is greater than or equal to 1) operation mode members.
"entity-attribute value" concept definition:
1) And the safety control system comprises: the attributes include id, chinese name, status, policy search results, whether there are any way constraints.
2) Security control strategy: the attributes comprise id, combination mode, whether there are calculation measures, control quantity expression, strategy type, security control action threshold value, undercut power, maximum action quantity, action strategy model and measure set.
3) Safety control measures: the attributes include id, executing device Chinese name, station id of executing device, station Chinese name of executing device, action delay, value type, control active amount, control inactive amount, control signal amount, safety control measure model, maximum DC adjustment amount and rated power.
4) Mode constraint: the attributes include id, mode name, member expression.
5) Failure mode: the attributes include fault id, fault name, number of fault members, measurement value, trigger condition, and trigger value.
6) The operation mode is as follows: the attributes include id, chinese name, member expression.
7) Section: the attributes include id, chinese name, member expression.
8) Operation mode member: the attributes include equipment id, equipment Chinese name, station id, station Chinese name, equipment type, measurement type, trigger condition, trigger value and trigger value type.
9) Section member: the attributes include equipment id, equipment Chinese name, station id, station Chinese name, equipment type, measurement type, trigger condition, trigger value and trigger value type.
10 A failed member: the attributes include equipment id, equipment Chinese name, station id, station Chinese name, equipment type, measurement type, trigger condition, trigger value and trigger value type.
Second, structured and unstructured data is acquired
And the structured data is obtained from the regulation and control cloud platform, such as a power grid equipment model, a grid structure, operation data and the like.
Unstructured data are extracted and arranged from regulatory operators to protect policy documents of the automatic device of the alternating current power grid and policy documents of the cross-region direct current safety control system, and the document content is queried to professional regulatory operators, so that accurate understanding of safety control execution action logic is ensured, and basic corpus is provided for map construction.
Third, extracting entity, attribute and relation from the data
Domain knowledge extraction includes extraction of entities, relationships, and attributes within the domain. In the aspect of knowledge acquisition, the domain knowledge graph needs more specialized domain knowledge, and often needs an expert to participate in the acquisition and the auditing of the knowledge, so that the degree of specialized requirements is higher. The structured data of the power grid equipment model can be directly obtained from a database, the unstructured data of the text can be firstly subjected to unified language specification description, the corresponding ontology concepts and attributes are combined with specific security examples, and a node dictionary and an edge relation dictionary are created through id mapping entity relations. And describing the fault phenomenon and the security control strategy by adopting a unified language mode.
Fourth, knowledge graph construction in security and control strategy field
Based on the extracted results of the obtained entities and relations, corresponding data import scripts are written based on the structured data so as to adapt to the pattern. And (3) decomposing the knowledge graph in the security and control strategy field into two sub-graphs, namely a power grid equipment entity graph and a business logic concept graph.
1) Entity map construction of power grid equipment
The traditional relational database of the power grid topology is converted into the graph database based on the triplet representation, and the connection relation of the graph representation equipment is more visual and easier to expand due to the natural similarity between the data model of the graph database and the topology structure of the power grid, and the complex association relation of the massive data of the power grid is convenient to query, infer and calculate the graph by adopting the graph-based representation mode.
For the structured data of the power dispatching system, the data can be directly extracted from the existing relational database and converted into entity triples, and the entity triples are imported into the graph database, so that the entity graph of the power grid equipment is constructed. The power system equipment entities mainly comprise plant stations, buses, units, loads, transformers, alternating current lines, converters, circuit breakers and the like, and various equipment entities are shown in tables 1-5.
Table 1 device entity example table
Table 2 station_load relationship table
| st_id | st_connect_load_id | load_id |
| 10001 | 140001 | 40001 |
st_connect_load relationship attribute representation
Table 3 factory station entity attribute table example
| st_id | st_name | st_type | st_vol | st_area | …… |
| 10001 | Zhongzhou converter station | Converter station | 500kV | Henan electric network | …… |
| …… | …… | …… | …… | …… | …… |
Table 4 example breaker entity attributes table
Table 5 load entity attribute table example
| load_id | load_name | load_vol | load_st | …… |
| 40001 | Polar 1 equivalent load | 500kV | Zhongzhou converter station | …… |
| …… | …… | …… | …… | …… |
2) Construction of business logic concept graph
The invention summarizes the business processes of the cross-region direct current safety and stability control system and the alternating current power grid safety and stability control system, combines the commonality and the characteristics of the cross-region direct current system protection and security and stability automatic device action strategy based on the cross-region direct current system protection and security and stability automatic device action strategy of the alternating current power grid, extracts key constraints and builds a unified model, and obtains specific security and control measures based on the same set of business logic reasoning, wherein the business process diagram is shown in figure 4.
The specific flow comprises the following steps:
firstly, a fault device or a fault device group is required to be input, and if the fault device (group) has a security policy, the specific policy of a corresponding security system can be triggered after the device (group) fails.
It should be noted that, some faults (groups) have trigger conditions, and if the trigger conditions are not met, a security control strategy is not required to be provided. The triggering conditions of different self-installed devices are different, and the corresponding fault constraint and monitoring constraint conditions are required to be met; the cross-zone dc fault also requires a single or double pole blocking fault to determine whether it is a dc link or a receiver.
If a fault (group) is entered and a trigger condition is met, or no trigger condition is entered, then the security system policy table for the fault (group) may be queried.
Judging whether the security control system has a plurality of security control strategies, if so, acquiring a section, inquiring the current system operation mode, and carrying out the next step; if not, the next step is directly carried out,
acquiring a security control strategy;
and inquiring specific security measures according to the security policy, and executing actions of the security device.
It should be noted that, under different operation modes, such as a normal mode and an overhaul mode, the triggered security control strategies are not necessarily the same, and the corresponding topology constraint conditions need to be satisfied.
In addition, the safety control strategies of the cross-region direct current fault under different tide sections of the normal operation mode are different, for example, the tide value of the jaw relaxation section is required to be judged when the direct current receiving end fault in the day occurs.
Based on the above-mentioned unified security policy knowledge model, in combination with the security policy specific business process, a security business logic conceptual diagram is constructed (see fig. 5).
And writing a data import script to adapt to the pattern mode, so that the visualization of the security control business logic can be realized. Fig. 6 is a schematic diagram of a partial service of a dc security control system in the sky, which is convenient for a reader to quickly know the constraint conditions required to be satisfied for triggering the security control policy and the association relationship between different security control policies of the security control system.
On the basis, the invention also provides a security control strategy retrieval method facing the AC/DC power grid, which comprises the following steps:
selecting a fault group and a power grid section;
judging whether triggering conditions are met or not according to the search data, and carrying out matching identification to search a security control strategy and security control measures from a security control strategy knowledge graph constructed by the method;
outputting the security control strategy and security control measures.
Fifthly, designing application of knowledge graph in security and control field
And constructing a security policy knowledge graph and developing an intelligent analysis decision application of the expected faults. And the D5000 system DC rolling scanning calculation result is compared and consistent, so that the accuracy of the knowledge model is verified. The security control strategy knowledge graph management page can edit and visually inquire the entity and the relation, and the reasoning result can provide support for static security analysis, expected fault rolling scanning and other applications to assist the regulation and control personnel in carrying out fault treatment decisions.
As shown in fig. 7, a third object of the present invention is to provide a system for constructing a security control strategy knowledge graph for an ac/dc power grid, which includes:
the building module is used for building a security policy ontology model;
the acquisition module is used for acquiring structured data and unstructured data of the AC/DC power grid;
the extraction module is used for carrying out knowledge extraction on the structured data and the unstructured data to obtain security control strategy entities, attributes and relations;
the construction module is used for writing an input script based on the constructed security policy ontology model, storing security policy entities, attributes and relations into the graph database, and completing construction of the security policy knowledge graph.
As an optional embodiment, in the foregoing building module, the building a security policy ontology model includes:
adopting a top-down knowledge graph in the security control strategy field, wherein a body layer and a knowledge graph layer in the knowledge graph in the security control strategy field are correspondingly arranged; the method specifically comprises the following steps:
extracting important concepts of the protection strategy of the ultra-high voltage cross-region direct current safety control system and the alternating current safety self-device, and obtaining the concept definition of the following safety control strategy body: the system comprises a safety control system, a safety control strategy, safety control measures, mode constraints, fault modes, operation modes, sections, operation mode members, section members and fault members;
in connection with the operation of the security actions, relationships in the map are established, including 'entity-relationship-entity' and 'entity-attribute value'.
As an optional embodiment, in the obtaining module, the obtaining structured data and unstructured data of the ac/dc power grid includes:
acquiring a power grid equipment model, a grid structure and operation data from a regulation and control cloud platform to form structured data;
and extracting and arranging an alternating current power grid self-installation device protection strategy document and a cross-region direct current security control system strategy document as unstructured data.
In an optional embodiment, in the foregoing extraction module, knowledge extraction is performed on structured data and unstructured data to obtain a security policy entity, an attribute, and a relationship, where the method includes:
directly acquiring the structured data of the power grid equipment model from a database, carrying out unified language specification description on the unstructured data of the text, combining specific security and control examples, corresponding to ontology concepts and attributes, and creating a node dictionary and an edge relation dictionary by id mapping entity relations; and describing the fault phenomenon and the security control strategy by adopting a unified language mode to obtain security control strategy entities, attributes and relations.
As an optional embodiment, in the above building module, the security policy ontology model based on the building is written into an input script, and the security policy entity, attribute and relationship are stored into a graph database to complete the building of the security policy knowledge graph; comprising the following steps:
resolving the knowledge graph in the security policy field into a power grid equipment entity graph and a business logic concept graph;
based on the extraction result of the obtained entity and relation, writing corresponding data import script based on the structured data to adapt to the entity map and service logic conceptual map of the power grid equipment, so as to realize the visualization of security control service logic;
and obtaining constraint conditions required to be met by triggering the security policies and association relations among different security policies, and constructing a security policy knowledge graph by combining the relation between the entity graph of the power grid equipment and the service logic concept graph.
The method for constructing the entity map of the power grid equipment comprises the following steps of:
converting a relational database of the power grid topology into a graph database based on triple representation, and carrying out knowledge inquiry, reasoning and graph calculation on complex association relations of massive data of the power grid by adopting a representation mode based on a graph;
and extracting entity triples from the existing relational database for the structured data of the power dispatching system, and converting the entity triples into a graph database, thereby constructing the entity graph of the power grid equipment.
The business logic concept graph construction method comprises the following steps:
summarizing service flows of a cross-region direct current safety and stability control system and an alternating current power grid safety and stability control system, carding commonalities and characteristics of the cross-region direct current system protection safety and control strategy and an alternating current power grid safety and stability automatic device action strategy, extracting key constraints, establishing a unified model, and obtaining specific safety and control measures based on the same set of service logic reasoning;
based on the security policy knowledge model, combining with the security policy business flow to construct a security business logic conceptual diagram.
As a more specific embodiment, the security policy service flow includes:
inputting fault equipment or a fault equipment group, and if the fault equipment or the fault equipment group has a security control strategy, directly triggering a specific strategy of a corresponding security control system after the fault equipment or the fault equipment group fails; if the fault equipment or the fault equipment group has a triggering condition, and the triggering condition is not reached, a security control strategy is not required to be provided;
if the input fault equipment or the fault equipment group has and meets the triggering condition or does not have the triggering condition, inquiring a security control system policy table of the fault equipment or the fault equipment group;
judging whether the security control system has a plurality of security control strategies, if so, acquiring a section, inquiring the current system operation mode, and carrying out the next step based on the current system operation mode; if not, the next step is directly carried out,
acquiring a security control strategy;
and inquiring specific security measures according to the security policy, and executing actions of the security device.
The fourth object of the present invention is to provide a security control policy retrieval system for an ac/dc power grid, comprising:
the selection module is used for selecting fault groups and power grid sections;
the retrieval module is used for judging whether the triggering condition is met or not according to the retrieval data, and carrying out matching identification retrieval of the security control strategy and security control measures from the security control strategy knowledge graph constructed by the method;
and the output module outputs the security control strategy and security control measures.
The fifth object of the present invention is to provide an electronic device, which includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the processor implements the method for constructing the security control policy knowledge graph for the ac/dc power grid or the method for retrieving the security control policy for the ac/dc power grid when executing the computer program.
The sixth object of the present invention is to provide a computer readable storage medium, where the computer readable storage medium stores a computer program, where the computer program when executed by a processor implements the method for constructing a security control policy knowledge graph for an ac/dc power grid or the method for retrieving a security control policy for an ac/dc power grid.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention 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 invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations 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.
Finally, it should be noted that: the above embodiments are only for illustrating the technical aspects of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the above embodiments, it should be understood by those of ordinary skill in the art that: modifications and equivalents may be made to the specific embodiments of the invention without departing from the spirit and scope of the invention, which is intended to be covered by the claims.
Claims (14)
1. The utility model provides an alternating current-direct current power grid oriented security control strategy knowledge graph construction method which is characterized by comprising the following steps:
establishing an security policy ontology model;
obtaining structured data and unstructured data of an alternating current/direct current power grid;
knowledge extraction is carried out on the structured data and the unstructured data to obtain security control strategy entities, attributes and relations;
writing an input script based on the constructed security policy ontology model, and storing security policy entities, attributes and relations into a graph database to complete construction of a security policy knowledge graph.
2. The method for constructing the security control strategy knowledge graph for the ac/dc power grid according to claim 1, wherein the constructing the security control strategy ontology model comprises:
adopting a top-down knowledge graph in the security control strategy field, wherein a body layer and a knowledge graph layer in the knowledge graph in the security control strategy field are correspondingly arranged; the method specifically comprises the following steps:
extracting important concepts of the protection strategy of the ultra-high voltage cross-region direct current safety control system and the alternating current safety self-device, and obtaining the concept definition of the following safety control strategy body: the system comprises a safety control system, a safety control strategy, safety control measures, mode constraints, fault modes, operation modes, sections, operation mode members, section members and fault members;
relationships in the atlas are established in connection with the experience of performing the security actions, including "entity-relationship-entity" and "entity-attribute value".
3. The method for constructing the security control strategy knowledge graph for the ac/dc power grid according to claim 1, wherein the step of obtaining the structured data and the unstructured data of the ac/dc power grid comprises:
acquiring a power grid equipment model, a grid structure and operation data from a regulation and control cloud platform to form structured data;
and extracting and arranging an alternating current power grid self-installation device protection strategy document and a cross-region direct current security control system strategy document as unstructured data.
4. The method for constructing the security control strategy knowledge graph for the ac/dc power grid according to claim 1, wherein the performing knowledge extraction on structured data and unstructured data to obtain security control strategy entities, attributes and relationships comprises:
directly acquiring the structured data of the power grid equipment model from a database, carrying out unified language specification description on the unstructured data of the text, combining specific security and control examples, corresponding to ontology concepts and attributes, and creating a node dictionary and an edge relation dictionary by id mapping entity relations; and describing the fault phenomenon and the security control strategy by adopting a unified language mode to obtain security control strategy entities, attributes and relations.
5. The method for constructing the security control strategy knowledge graph for the alternating current and direct current power grid according to claim 1, wherein the security control strategy ontology model based on construction is characterized in that an input script is written, security control strategy entities, attributes and relations are stored in a graph database, and the construction of the security control strategy knowledge graph is completed; comprising the following steps:
resolving the knowledge graph in the security policy field into a power grid equipment entity graph and a business logic concept graph;
based on the extraction result of the obtained entity and relation, writing corresponding data import script based on the structured data to adapt to the entity map and service logic conceptual map of the power grid equipment, so as to realize the visualization of security control service logic;
and obtaining constraint conditions required to be met by triggering the security policies and association relations among different security policies, and constructing a security policy knowledge graph by combining the relation between the entity graph of the power grid equipment and the service logic concept graph.
6. The method for constructing the security control strategy knowledge graph for the alternating current and direct current power grid according to claim 5, wherein the method for constructing the power grid equipment entity graph comprises the following steps:
converting a relational database of the power grid topology into a graph database based on triple representation, and carrying out knowledge inquiry, reasoning and graph calculation on complex association relations of massive data of the power grid by adopting a representation mode based on a graph;
and extracting entity triples from the existing relational database for the structured data of the power dispatching system, and converting the entity triples into a graph database, thereby constructing the entity graph of the power grid equipment.
7. The method for constructing the security control strategy knowledge graph for the alternating current and direct current power grid according to claim 5, wherein the method for constructing the business logic concept graph comprises the following steps:
summarizing service flows of a cross-region direct current safety and stability control system and an alternating current power grid safety and stability control system, carding commonalities and characteristics of the cross-region direct current system protection safety and control strategy and an alternating current power grid safety and stability automatic device action strategy, extracting key constraints, establishing a unified model, and obtaining specific safety and control measures based on the same set of service logic reasoning;
based on the security policy knowledge model, combining with the security policy business flow to construct a security business logic conceptual diagram.
8. The method for constructing the security control strategy knowledge graph for the ac/dc power grid according to claim 7, wherein the security control strategy business process comprises:
inputting fault equipment or a fault equipment group, and if the fault equipment or the fault equipment group has a security control strategy, directly triggering a specific strategy of a corresponding security control system after the fault equipment or the fault equipment group fails; if the fault equipment or the fault equipment group has a triggering condition, and the triggering condition is not reached, a security control strategy is not required to be provided;
if the input fault equipment or the fault equipment group has and meets the triggering condition or does not have the triggering condition, inquiring a security control system policy table of the fault equipment or the fault equipment group;
judging whether the security control system has a plurality of security control strategies, if so, acquiring a section, inquiring the current system operation mode, and carrying out the next step based on the current system operation mode; if not, the next step is directly carried out,
acquiring a security control strategy;
and inquiring specific security measures according to the security policy, and executing actions of the security device.
9. The method for constructing the safety control strategy knowledge graph for the alternating current and direct current power grid according to claim 8, wherein the triggering conditions are required to meet respective corresponding fault constraint and monitoring constraint conditions; for a cross-zone direct current fault, the trigger condition also needs to determine whether it is a single-pole or double-pole blocking fault of the direct current end or the receiving end.
10. A security control strategy retrieval method for an AC/DC power grid is characterized by comprising the following steps:
selecting a fault group and a power grid section;
judging whether triggering conditions are met or not according to the search data, and carrying out matching identification search on a security control strategy and security control measures from the security control strategy knowledge graph constructed by the method according to any one of claims 1 to 9;
outputting the security control strategy and security control measures.
11. An ac/dc power grid-oriented security control strategy knowledge graph construction system is characterized by comprising:
the building module is used for building a security policy ontology model;
the acquisition module is used for acquiring structured data and unstructured data of the AC/DC power grid;
the extraction module is used for carrying out knowledge extraction on the structured data and the unstructured data to obtain security control strategy entities, attributes and relations;
the construction module is used for writing an input script based on the constructed security policy ontology model, storing security policy entities, attributes and relations into the graph database, and completing construction of the security policy knowledge graph.
12. An ac/dc grid-oriented security control policy retrieval system, comprising:
the selection module is used for selecting fault groups and power grid sections;
the retrieval module is used for judging whether the triggering condition is met or not according to the retrieval data, and carrying out matching identification retrieval of the security control strategy and security control measures from the security control strategy knowledge graph constructed by the method of any one of claims 1 to 9;
and the output module outputs the security control strategy and security control measures.
13. An electronic device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the ac-dc grid-oriented security policy knowledge graph construction method according to any one of claims 1 to 9 or the ac-dc grid-oriented security policy retrieval method according to claim 10 when executing the computer program.
14. A computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program when executed by a processor implements the method for constructing a security policy knowledge graph for an ac/dc power grid according to any one of claims 1 to 9 or the method for retrieving a security policy for an ac/dc power grid according to claim 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311111609.1A CN117150040A (en) | 2023-08-30 | 2023-08-30 | Safety control strategy knowledge graph construction method and system for AC/DC power grid |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311111609.1A CN117150040A (en) | 2023-08-30 | 2023-08-30 | Safety control strategy knowledge graph construction method and system for AC/DC power grid |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117150040A true CN117150040A (en) | 2023-12-01 |
Family
ID=88909412
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311111609.1A Pending CN117150040A (en) | 2023-08-30 | 2023-08-30 | Safety control strategy knowledge graph construction method and system for AC/DC power grid |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117150040A (en) |
-
2023
- 2023-08-30 CN CN202311111609.1A patent/CN117150040A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | Enhancing distribution system resilience with proactive islanding and RCS-based fast fault isolation and service restoration | |
| Sun et al. | Network partitioning strategy for parallel power system restoration | |
| Huang et al. | Knowledge model for electric power big data based on ontology and semantic web | |
| CN108390371B (en) | Power grid system protection control strategy modeling method in online analysis | |
| CN102930479A (en) | Formalization method for procedure knowledge of power system and formalization system thereof | |
| Lin et al. | Stochastic optimal dispatch of PV/wind/diesel/battery microgrids using state‐space approximate dynamic programming | |
| CN115730749B (en) | Power dispatching risk early warning method and device based on fusion power data | |
| CN115033704A (en) | Distribution network fault plan knowledge graph design method and system based on graph database | |
| CN112685570A (en) | Multi-label graph-based power grid network frame knowledge graph construction method | |
| CN109710775A (en) | A kind of knowledge mapping dynamic creation method based on more rules | |
| Zhang et al. | A strategy for intentional islanding of distribution networks based on node electrical relevance and artificial bee colony algorithm | |
| Jiang et al. | Coordinative frequency-constrained unit commitment model for HVDC interconnected AC systems | |
| Zhao et al. | Construction and application of digital twin model of hydropower plant based on data-driven | |
| CN103258255A (en) | Knowledge discovery method applicable to power grid management system | |
| CN110086166B (en) | Method and system for representing stable operation quota of power grid | |
| Jiang et al. | Construction of substation engineering design knowledge graph based on “ontology seven-step method” | |
| Li et al. | Determination of optimal opening scheme for electromagnetic loop networks based on fuzzy analytic hierarchy process | |
| CN117150040A (en) | Safety control strategy knowledge graph construction method and system for AC/DC power grid | |
| Jiang et al. | Research on load transfer strategy optimisation with considering the operation of distributed generations and secondary dispatch | |
| Zhou et al. | Power failure risk assessment and management based on stochastic line failures in distribution network including distributed generation | |
| Xu et al. | Fault recovery of distribution network containing distributed generation based on heuristic search algorithm and multi-population genetic algorithm | |
| Yisong et al. | Study on the relationship between transmission line failure rate and lightning information based on Neo4j | |
| CN115549075A (en) | Power supply recovery method and system for power distribution network containing micro-grid | |
| Le et al. | Cuckoo search algorithm for minimization of power loss and voltage deviation | |
| Liu et al. | Research on text classification method of distribution network equipment fault based on deep learning |
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 |