A knowledge modeling method and system for intelligent calculation and adjustment of power grid flow

Abstract

This application discloses a knowledge modeling method and system for intelligent calculation and adjustment of power grid currents. The method includes: dividing the knowledge involved in intelligent calculation and adjustment of power grid currents into power grid data knowledge, power grid status knowledge, and adjustment rule knowledge; representing the power grid data knowledge, power grid status knowledge, and adjustment rule knowledge in the form of triples to construct a knowledge base; and, based on currently known facts, utilizing the power grid data knowledge, power grid status knowledge, and adjustment rule knowledge in the knowledge base to perform reasoning according to reasoning methods and control strategies, updating and improving the knowledge base to ensure the correctness and completeness of the knowledge.

Description

Technical Field

[0001] The present application relates to the technical field of power systems, and in particular to a knowledge modeling method and system for intelligent calculation and adjustment of power grid currents. Background Art

[0002] With the development of China's power system, especially the full-scale implementation of smart grid and ultra-high voltage (UHV) projects, the grid structure is becoming increasingly complex, the number of grid components is gradually increasing, and the amount of grid data is exploding. The amount of data in the system is surging. If the excess data cannot be processed in a timely manner, it can lead to decision delays, errors, and even power accidents. Therefore, it is necessary to extract massive amounts of grid data and further abstract this information to the knowledge level. This involves analyzing the representation, storage, and synergy of grid knowledge and building a grid knowledge base based on this. This will not only make grid-related calculations, analysis, decision-making, and management systems more intelligent, but also enable grid personnel to obtain the knowledge and information they need more quickly.

[0003] Power flow calculation is one of the most fundamental and important calculations in power system research and forms the foundation for grid planning and operation. As power grids continue to expand, the number of variables in the power flow equation increases dramatically. Furthermore, various constraints, such as voltage and power, must be met. Consequently, power flow calculations often fail to converge. In these cases, adjustments to the operating mode are necessary, such as by changing generator output or switching capacitors and reactors, to return the power flow to a reasonable, feasible solution and ensure a reasonable power flow distribution. However, the power flow calculation and adjustment process often relies on the accumulated experience of power flow calculators, resulting in limited accuracy, errors, and omissions, leading to low efficiency. Therefore, it is necessary to summarize the knowledge and experience gained during power flow calculation and adjustment, and to express this knowledge in a specific format to guide and assist power flow calculators in making more accurate decisions about adjustment directions and measures, thereby effectively reducing their burden.

[0004] In terms of knowledge representation, power grid simulation knowledge currently primarily uses three forms: relational, XML, and ontology languages. The earliest and easiest-to-understand approach is to construct a relational knowledge base based on the relationships between various units (busbars, transformers, generators, switches, circuit breakers, etc.) in power grid calculation data. The construction of an XML-based power grid simulation knowledge base stems from the need to store event data in power systems. However, the power grid domain knowledge representation based on the aforementioned two methods suffers from drawbacks such as obscure knowledge representation, low reasoning efficiency, poor visualization, and difficulty in collaborative processing of dynamic knowledge. With the development of the ontology language OWL, knowledge graphs have become the mainstream form of knowledge representation. Knowledge graphs use graph structures to represent entities and their associations, where entities are represented as points in the graph and associations are represented as edges in the graph. Researchers are gradually adopting ontology languages to express power grid simulation knowledge.

[0005] While ontology languages and graph-based knowledge representations are widely recognized, they still face numerous challenges, such as computational efficiency and data sparsity, that need to be addressed. In power grid simulation, there is still a lack of modeling methods for complex knowledge structures. Furthermore, because power grid simulations incorporate both qualitative and quantitative knowledge, as well as relational and factual knowledge, current ontology and knowledge graph models are insufficient to effectively represent them. Summary of the Invention

[0006] The embodiments of the present disclosure provide a knowledge modeling method and system for intelligent calculation and adjustment of power grid currents, so as to at least solve the technical problem that the knowledge representation of ontology language and graph structure in the prior art still lacks a modeling method for complex knowledge structures in power grid simulation; and since qualitative and quantitative knowledge, associative and factual knowledge coexist in power grid simulation, the current ontology and knowledge graph models are not sufficient to effectively express them.

[0007] According to one aspect of an embodiment of the present disclosure, a knowledge modeling method for intelligent calculation and adjustment of power grid flows is provided, including: dividing the knowledge involved in the intelligent calculation and adjustment of power grid flows into power grid data knowledge, power grid status knowledge, and adjustment rule knowledge; expressing the power grid data knowledge, the power grid status knowledge, and the adjustment rule knowledge in the form of triples to construct a knowledge base; based on currently known facts, using the power grid data knowledge, power grid status knowledge, and adjustment rule knowledge in the knowledge base, reasoning is performed according to reasoning methods and control strategies, and the knowledge base is updated and improved to ensure the correctness and completeness of the knowledge.

[0008] According to another aspect of the embodiment of the present disclosure, a knowledge modeling system for intelligent calculation and adjustment of power grid flows is also provided, including: a knowledge division module, used to divide the knowledge involved in the intelligent calculation and adjustment of power grid flows into power grid data knowledge, power grid status knowledge and adjustment rule knowledge; a knowledge base construction module, used to express the power grid data knowledge, the power grid status knowledge and the adjustment rule knowledge in the form of triples to construct a knowledge base; and a reasoning module, used to reason according to the currently known facts, using the power grid data knowledge, power grid status knowledge and adjustment rule knowledge in the knowledge base, and according to the reasoning method and control strategy to update and improve the knowledge base to ensure the correctness and completeness of the knowledge.

[0009] In the present invention, the power grid data knowledge, power grid status knowledge and adjustment rule knowledge are represented in the form of <node, relationship, node> triples, different node types and relationships are defined according to different knowledge, and the complex adjustment means in the power grid adjustment process are encapsulated into independent functional functions. This can not only accurately describe the relationship between power grid elements and parameters, and between elements, and effectively characterize the current state of the power grid, but also flexibly perform corresponding adjustment operations for different states. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The drawings described herein are used to provide a further understanding of the present disclosure and constitute a part of this application. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation of the present disclosure. In the drawings:

[0011] Figure 1 This is a flow chart of a knowledge modeling method for intelligent calculation and adjustment of power grid currents according to an embodiment of the present disclosure;

[0012] Figure 2 This is a schematic diagram of the knowledge representation of the intelligent calculation and adjustment of power flow according to an embodiment of the present disclosure;

[0013] Figure 3 This is a schematic diagram of a knowledge graph for intelligent calculation and adjustment of power grid currents according to an embodiment of the present disclosure;

[0014] Figure 4 1 is a schematic diagram of adjustment results of a CEPRI 36-node example according to an embodiment of the present disclosure;

[0015] Figure 5 This is a flow chart of a knowledge modeling system for intelligent calculation and adjustment of power grid currents according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0016] Exemplary embodiments of the present invention will now be described with reference to the accompanying drawings. However, the present invention may be embodied in many different forms and is not limited to the embodiments described herein. These embodiments are provided to provide a thorough and complete disclosure of the present invention and to fully convey the scope of the present invention to those skilled in the art. The terminology used in the exemplary embodiments shown in the accompanying drawings is not intended to limit the present invention. In the accompanying drawings, identical elements are denoted by the same reference numerals.

[0017] Unless otherwise specified, the terms used herein (including technical terms) have the meanings commonly understood by those skilled in the art. In addition, it is understood that terms defined in commonly used dictionaries should be understood to have the same meanings as those in the context of the relevant fields, and should not be understood as idealized or overly formal meanings.

[0018] According to a first aspect of this embodiment, a knowledge modeling method 100 for intelligent calculation and adjustment of power grid flow is provided. Figure 1 As shown, the method 100 includes:

[0019] S102: Divide the knowledge involved in intelligent calculation and adjustment of power grid flow into power grid data knowledge, power grid status knowledge, and adjustment rule knowledge;

[0020] S104: constructing a knowledge base by expressing the power grid data knowledge, the power grid status knowledge, and the adjustment rule knowledge in the form of triples;

[0021] S106: Based on currently known facts, using the power grid data knowledge, power grid status knowledge and adjustment rule knowledge in the knowledge base, reasoning is performed according to the reasoning method and control strategy to update and improve the knowledge base to ensure the correctness and completeness of the knowledge.

[0022] Specifically, a knowledge modeling method for intelligent calculation and adjustment of power flow includes three parts: classification and extraction of power flow calculation and adjustment knowledge, knowledge representation, and knowledge reasoning. Classification and extraction of power flow calculation and adjustment knowledge is the foundation of knowledge modeling, knowledge representation is the core of knowledge modeling, and knowledge reasoning is an important means of ensuring knowledge correctness and completeness.

[0023] The knowledge representation is a description of knowledge, a data structure that can be accepted by computers and used to describe knowledge. Representing knowledge means expressing knowledge into a data structure that is convenient for computer storage and utilization. The present invention uses triples to represent power grid flow calculation and adjustment knowledge.

[0024] refer to Figure 2 and Figure 3As shown, a triple is composed of <node, relationship, node>. A node is described by a string, which is called the node's name. Nodes include: state nodes, feature nodes, operation nodes, grid component nodes, grid parameter nodes, location nodes, function nodes, weight nodes, and node type description nodes.

[0025] The state node has a name that describes a state, such as "non-convergence state", "power flow exceeding limit state", etc. The state node must have the relationship "featured", "operation" and its corresponding subsequent node to form a triple.

[0026] The name of the feature node describes a characteristic extracted from power grid data and used to determine the power grid's current state. The feature description is an expression that can be evaluated as True or False. If the expression is true, the knowledge base intelligently determines whether the power grid meets the characteristic based on the expression.

[0027] The operation node, whose name describes an operation, is the tail node of the relationship "operation". After the knowledge base finds the corresponding state based on the characteristics, it will find the operation corresponding to the state and execute it. Since the specific operations involved in the calculation and adjustment of power grid flow are relatively complex, various operations are encapsulated into corresponding functional functions, and the knowledge base selects the corresponding function to call based on the triple. When the operation is performed in this way, the operation node has two relationships and corresponding tail nodes: 1) The relationship "is", and the tail node is "function call". It indicates that the operation will specify the function to call. 2) The relationship "call", the tail node is "function node", which specifies the function to be called by the operation.

[0028] The grid component node is used to describe a grid component entity, such as a "generator" or "transformer." The "has attributes" relationship can be used to connect the component's parameters used in power flow calculation and adjustment, such as "generator active power" or "transformer ratio."

[0029] The grid parameter node is used to describe the parameters used in the grid flow calculation and adjustment process. A "location" relationship is required to connect the "location node" to find the location of the file where the parameter is located.

[0030] The position node is used to describe the position of a parameter that may be used in power grid adjustment, and the specific value corresponding to the parameter can be obtained from the position.

[0031] The function node represents a function, and its name is the function name. The triple containing the function node needs to provide necessary supplementary descriptions on the function's parameters and return value types.

[0032] The weight node, as the tail node of the relationship "weight", has a name that is a numerical value, which defaults to 1 and is used to define the priority of each operation or state.

[0033] The node type description node, as the tail node of the relationship "is", describes the type of a node, such as <(state node), "is", "state">, <(operation node), "is", "function call">.

[0034] A relationship is a name that connects two nodes in a knowledge base, representing a direct logical relationship between them. It can be thought of as a directed arrow, allowing one node to find another. Relationships include: features, operations, is, calls, attributes, location, and weight.

[0035] The said features, the head node is a state node, the tail node is a feature node, which indicates what features a state has. The knowledge base determines the current state of the power grid by checking whether the power grid data meets the features.

[0036] The head node of the operation is the state node, and the tail node is the operation node, indicating which operations need to be performed for a state. A state can have multiple operations. After the knowledge base checks the state, it will execute each operation in order according to the weight.

[0037] It is described that the head node is an arbitrary node, and the tail node is a node type description node, indicating the type of a node.

[0038] In the call, the head node is an operation node, and the tail node is a function node, indicating which function an operation calls, and the function node indicates the called function.

[0039] The attributes are: the head node is a grid component node; the tail node is a grid parameter node, which indicates the attributes of the grid components. These attributes are generally parameters that are used in the process of power flow calculation and adjustment and can be located.

[0040] The position is described, the head node is the power grid parameter node, and the tail node is the position node, which indicates the specific position of a parameter that may be used in the power grid adjustment process in the file. The knowledge base can find the parameter in the file through the position relationship and perform corresponding operations.

[0041] The weight, the head node is an operation node or a state node, and the tail node is a weight node. If there are multiple operations or multiple states, the weight relationship can assign weights to the operations or states to define the priority of execution or search.

[0042] The knowledge reasoning mechanism is to use the knowledge in the knowledge base based on the currently known facts, and to perform reasoning according to certain reasoning methods and control strategies to obtain the answer to the question or prove the correctness of a certain hypothesis.

[0043] The reasoning methods include deductive reasoning, inductive reasoning, uncertain reasoning, non-monotonic reasoning and qualitative reasoning, etc. The reasoning method adopted in the present invention is deductive reasoning.

[0044] The deductive reasoning is to draw new conclusions based on the newly added facts of the actual problem. These conclusions do not conflict with the existing knowledge and conclusions. It derives the facts contained in the known facts of a problem as conclusions based on the axiomatic system.

[0045] The control strategy of the reasoning process mainly solves the knowledge selection and application order of the entire problem-solving process. There are three commonly used control strategies for the reasoning process: forward reasoning strategy, backward reasoning strategy and forward-backward mixed reasoning strategy. The present invention adopts the forward-backward mixed reasoning strategy.

[0046] The hybrid forward-inverse inference control strategy works by first generating a batch of objectives based on the partial problem information provided by the user. Further information is then collected for each generated objective, and each objective is tested individually. This strategy is designed to eliminate solutions that are inconsistent with the current problem data constraints at an early stage.

[0047] This was verified using a CEPRI 36-node example. Using the method of this embodiment, based on the grid knowledge expressed in triples and invoking corresponding operation functions, the method intelligently calculated and adjusted the power flow for non-convergent samples, thereby achieving convergence. The test results verified the effectiveness of the present invention.

[0048] Furthermore, taking one set of data as an example, the initial power flow of the data does not converge, that is, the power flow calculation is performed on the data, and the convergence flag = 1. According to the knowledge <non-convergence state, has characteristics, convergence flag = 1> and <non-convergence state, subsequent state, check parameter state>, the data is judged to be in a non-convergence state and enters the parameter check state. According to the knowledge <check parameter state, operation, check transformer ratio>, start to check whether the transformer ratio in the data is within a reasonable range. According to the knowledge <check transformer ratio, yes, function call>, <check transformer ratio, call, r = CheckTransTk (transformer ratio upper limit, transformer ratio lower limit, transformer ratio adjustment log structure, transformer ratio adjustment number)>, <transformer ratio upper limit, parameter value, 1.3>, <transformer ratio lower limit, parameter value, 0.7>, by calling the transformer ratio check function CheckTransTk, the transformer ratios greater than 1.3 and less than 0.7 in the data are adjusted to the default value of 1.0. Adjustment result reference Figure 4 shown.

[0049] Therefore, the power grid data knowledge, power grid status knowledge and adjustment rule knowledge are represented in the form of <node, relationship, node> triples. Different node types and relationships are defined according to different knowledge, and the complex adjustment means in the power grid adjustment process are encapsulated into independent functional functions. This can not only accurately describe the relationship between power grid components and parameters, and between components, and effectively characterize the current state of the power grid, but also flexibly perform corresponding adjustment operations for different states.

[0050] Optionally, the grid data knowledge refers to knowledge related to grid components and their attributes, parameters and characteristics; the grid state knowledge refers to knowledge related to grid state, including normal state, non-convergence state, section adjustment state and flow over-limit state; the adjustment rule knowledge refers to knowledge related to the adjustment measures taken and the adjustment rules applied when the grid transitions from one state to another for adjustment.

[0051] Optionally, the triple is composed of <node, relationship, node>; the node is a string, the string is called the name node of the node, the nodes include: status node, feature node, operation node, grid element node, grid parameter node, position node, function node, weight node and node type description node; the relationship is used to connect two nodes, representing the name of the direct logical relationship between the two nodes, the relationship includes: has features, operation, is, call, has attributes, has position, weight.

[0052] Optionally, based on currently known facts, using the power grid data knowledge, power grid status knowledge and adjustment rule knowledge in the knowledge base, reasoning is performed according to the reasoning method and control strategy to obtain the answer to the problem or prove the correctness of a hypothesis, including: deriving new conclusions based on new facts added to the actual problem, and deriving facts contained in known facts in a problem as conclusions based on the axiomatic system, and the new conclusions do not conflict with existing knowledge and conclusions.

[0053] Optionally, based on currently known facts, using the power grid data knowledge, power grid status knowledge and adjustment rule knowledge in the knowledge base, reasoning is performed according to the reasoning method and control strategy to obtain the answer to the problem or prove the correctness of a hypothesis, which also includes: generating a batch of targets based on partial problem information provided by the user; obtaining further information on each generated target, testing them one by one, and eliminating solutions that are inconsistent with the current problem data constraints.

[0054] Therefore, the power grid data knowledge, power grid status knowledge and adjustment rule knowledge are represented in the form of <node, relationship, node> triples. Different node types and relationships are defined according to different knowledge, and the complex adjustment means in the power grid adjustment process are encapsulated into independent functional functions. This can not only accurately describe the relationship between power grid components and parameters, and between components, and effectively characterize the current state of the power grid, but also flexibly perform corresponding adjustment operations for different states.

[0055] According to another aspect of this embodiment, a knowledge modeling system 500 for intelligent calculation and adjustment of power grid flow is also provided. Figure 5 As shown, the system 500 includes: a knowledge division module 510, which is used to divide the knowledge involved in the intelligent calculation and adjustment of power grid currents into power grid data knowledge, power grid status knowledge and adjustment rule knowledge; a knowledge base construction module 520, which is used to express the power grid data knowledge, the power grid status knowledge and the adjustment rule knowledge in the form of triples to construct a knowledge base; and a reasoning module 530, which is used to perform reasoning based on currently known facts, using the power grid data knowledge, power grid status knowledge and adjustment rule knowledge in the knowledge base, in accordance with reasoning methods and control strategies, to update and improve the knowledge base to ensure the correctness and completeness of the knowledge.

[0056] Optionally, the grid data knowledge refers to knowledge related to grid components and their attributes, parameters and characteristics; the grid state knowledge refers to knowledge related to grid state, including normal state, non-convergence state, section adjustment state and flow over-limit state; the adjustment rule knowledge refers to knowledge related to the adjustment measures taken and the adjustment rules applied when the grid transitions from one state to another for adjustment.

[0057] Optionally, the triple is composed of <node, relationship, node>; the node is a string, the string is called the name node of the node, the nodes include: status node, feature node, operation node, grid element node, grid parameter node, position node, function node, weight node and node type description node; the relationship is used to connect two nodes, representing the name of the direct logical relationship between the two nodes, the relationship includes: has features, operation, is, call, has attributes, has position, weight.

[0058] Optionally, the reasoning module 530 includes: a deduction submodule, which is used to deduce new conclusions based on new facts added to the actual problem, and to deduce facts contained in known facts in a problem as conclusions based on the axiom system, and the new conclusions do not conflict with existing knowledge and conclusions.

[0059] Optionally, the reasoning module 530 also includes: a target generation submodule, which is used to generate a batch of targets based on the partial problem information provided by the user; and a test exclusion submodule, which is used to obtain further information about each generated target, perform tests one by one, and exclude solutions that are inconsistent with the current problem data constraints.

[0060] A knowledge modeling system 500 for intelligent calculation and adjustment of power grid currents in an embodiment of the present invention corresponds to a knowledge modeling method 100 for intelligent calculation and adjustment of power grid currents in another embodiment of the present invention, and will not be described in detail here.

[0061] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code. The scheme in the embodiment of the present application can be implemented in various computer languages, for example, object-oriented programming language Java and literal translation scripting language JavaScript, etc.

[0062] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0063] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0064] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0065] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present application.

[0066] Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include these modifications and variations.

Claims

1. A knowledge modeling method for intelligent calculation and adjustment of power grid flow, characterized in that: include: The knowledge involved in intelligent calculation and adjustment of power grid flow is divided into power grid data knowledge, power grid status knowledge and adjustment rule knowledge; The power grid data knowledge, the power grid state knowledge, and the adjustment rule knowledge are expressed in the form of triples to construct a knowledge base; Based on currently known facts, the knowledge base is updated and improved by utilizing the knowledge of power grid data, power grid status, and adjustment rules in the knowledge base and reasoning according to the reasoning method and control strategy to ensure the correctness and completeness of the knowledge. The triple is composed of <node, relationship, node>; The node is a string, which is called the name node of the node. The node includes: state node, feature node, operation node, grid element node, grid parameter node, position node, function node, weight node and node type description node; The relationship is used to connect two nodes and represents the name of the direct logical relationship between the two nodes. The relationship includes: has features, operation, is, call, has attributes, has position, and weight.

2. The method according to claim 1, characterized in that The power grid data knowledge refers to the knowledge related to the components of the power grid and their attributes, parameters and characteristics; The grid state knowledge refers to knowledge related to the grid state, including normal state, non-convergence state, section adjustment state and power flow over-limit state; The adjustment rule knowledge refers to the knowledge related to the adjustment measures taken and the adjustment rules applied when the power grid is adjusted from one state to another.

3. The method according to claim 1, characterized in that Based on currently known facts, the knowledge base is updated and improved using the grid data knowledge, grid status knowledge, and adjustment rule knowledge in the knowledge base, according to the reasoning method and control strategy, to ensure the correctness and completeness of the knowledge, including: Based on the newly added facts of the actual problem, new conclusions are drawn. According to the axiomatic system, the facts contained in the known facts of a problem are deduced as conclusions, and the new conclusions do not conflict with the existing knowledge and conclusions.

4. The method according to claim 1, wherein Based on currently known facts, using the grid data knowledge, grid status knowledge, and adjustment rule knowledge in the knowledge base, reasoning is performed according to reasoning methods and control strategies to find the answer to the question or prove the correctness of a hypothesis, which also includes: Generate a batch of goals based on the partial question information provided by the user; Obtain further information about each generated target, test them one by one, and eliminate solutions that are inconsistent with the data constraints of the current problem.

5. A knowledge modeling system for intelligent calculation and adjustment of power grid flow, characterized in that: include: A knowledge division module is used to divide the knowledge involved in intelligent calculation and adjustment of power grid flow into power grid data knowledge, power grid status knowledge, and adjustment rule knowledge; Constructing a knowledge base module, for expressing the power grid data knowledge, the power grid state knowledge and the adjustment rule knowledge in the form of triples to construct a knowledge base; The reasoning module is used to update and improve the knowledge base based on currently known facts, using the power grid data knowledge, power grid status knowledge, and adjustment rule knowledge in the knowledge base, in accordance with the reasoning method and control strategy, to ensure the correctness and completeness of the knowledge; The triple is composed of <node, relationship, node>; The node is a string, which is called the name node of the node. The node includes: state node, feature node, operation node, grid element node, grid parameter node, position node, function node, weight node and node type description node; The relationship is used to connect two nodes and represents the name of the direct logical relationship between the two nodes. The relationship includes: has features, operation, is, call, has attributes, has position, and weight.

6. The system according to claim 5, characterized in that The power grid data knowledge refers to the knowledge related to the components of the power grid and their attributes, parameters and characteristics; The grid state knowledge refers to knowledge related to the grid state, including normal state, non-convergence state, section adjustment state and power flow over-limit state; The adjustment rule knowledge refers to the knowledge related to the adjustment measures taken and the adjustment rules applied when the power grid is adjusted from one state to another.

7. The system according to claim 5, characterized in that Reasoning module, including: The derivation submodule is used to deduce new conclusions based on newly added facts in the actual problem. The facts contained in the known facts of a problem are deduced as conclusions based on the axiomatic system, and the new conclusions do not conflict with the existing knowledge and conclusions.

8. The system according to claim 5, wherein: The reasoning module also includes: The target generation submodule is used to generate a batch of targets based on the partial problem information provided by the user; The test exclusion submodule is used to obtain further information about each generated target, conduct tests one by one, and exclude solutions that are inconsistent with the data constraints of the current problem.

Images