CN111368387B - Electric power system simulation data textualization method - Google Patents

Abstract

The invention relates to a method for textualizing simulation data of a power system, which comprises the following steps: step S1, constructing a conceptual model generated by the text; step S2, performing data text preparation on the simulation calculation data; step S3, a data textualization task is performed. The invention can convert massive calculation data which has complex structure and is difficult to be directly observed into a knowledge text with clear and definite natural language characters as contents in a universal and convenient way; in the field of power flow simulation analysis, calculation data is converted into texts, customized data reading and analysis rules are performed for the calculation data conversion, and template languages for supporting rule operation are formulated and analyzed.

Description

A Textual Method of Power System Simulation Data

【Technical field】

The invention belongs to the technical field of electric power automation, and in particular relates to a method for textualizing power system simulation data.

【Background technique】

The power system simulation calculation will generate a large amount of real-time data and result data. The structure of the data is complex, and it is difficult to directly observe and draw conclusions. In the past power system simulation calculation and analysis, professional analysts analyze and summarize these data to generate conclusive opinions. Most analysts will first perform some general statistical calculations on the result data, based on these intermediate results, and then find important information from the intermediate results according to different analysis strategies or perspectives, relying on the professional experience of the analysts. It can be seen from this that there is a lot of repetitive work in the simulation analysis process, and the essence of this repetitive work is the lack of data extraction. There is a need for a method that can parse simulation data with a special structure, extract and condense knowledge information from the parsed data, and express the information in the form of natural language texts. At the same time, in order to support applications such as text mining, we should also consider constructing data structures that support text mining. The invention can convert massive, complex structure and difficult to directly observe calculation data into clear and clear natural language and text knowledge text in a general and convenient way; in the field of power flow simulation analysis, the calculation data is converted into text , and customized data reading and parsing rules, as well as the formulation and parsing of a template language supporting the operation of the rules, are carried out for the textualization of the computing data.

[Content of the invention]

In order to solve the above problems in the prior art, the present invention provides a method for textualizing power system simulation data, the method comprising:

Step S1: the construction of the conceptual model of text generation;

Step S2: carry out data textual preparation to the simulation calculation data;

Step S3: Execute the task of data textualization.

Further, the step S1 is specifically: setting the corresponding relationship between the data reading template, the data analysis template, and the textual template based on the logical relationship among conceptual objects, relationships, and entities.

Further, the step S2 is specifically: performing specific settings of a data reading template, a data parsing template, and a textual template.

Further, the step S3 is specifically: read the original simulation data file, read the original simulation data file based on the data reading template, analyze the read data based on the data analysis file, and fill in the text according to the textual template information file.

Further, by setting the corresponding relationship between the data reading template, the data parsing template, and the textual template, the attributes in the concept object, the relationship between attributes, etc., and the relationship between template items are constructed.

Further, the step S1 specifically includes the following steps:

Step S11: constructing a concept object;

Step S12: constructing the horizontal relationship between conceptual objects;

Step S13: entity construction of the data textualization task;

Step S14: Generate a data textual information file.

Further, the step S11 is specifically: setting a concept object for the electrical components targeted by the power system simulation data, and constructing a data reading template based on the concept object, and using the data reading template as a carrier of the concept object.

Further, the step S12 is specifically: selecting the referenced concept object, performing relationship analysis of the concept object, and filling the data analysis template based on the relationship analysis result.

Further, the step S13 specifically includes: constructing an entity according to the attributes of the data textualization task, and correspondingly constructing a textualization template.

Further, the step S14 is specifically: initializing the data textualization information file, and saving the data textualization related information based on the textualization template in the subsequent textualization process.

The beneficial effects of the present invention include: the massive, complex structure, and difficult to directly observe calculation data can be converted into clear and clear natural language knowledge texts in a general and convenient way; in the field of power flow simulation analysis, The calculation data is textualized, and customized data reading and parsing rules are carried out for the textualization of the calculation data, as well as the formulation and analysis of a template language supporting the operation of the rules.

【Description of drawings】

The accompanying drawings described here are used to provide a further understanding of the present invention and constitute a part of this application, but do not constitute an improper limitation of the present invention. In the accompanying drawings:

FIG. 1 is a schematic diagram of a data analysis template of the present invention.

FIG. 2 is a schematic diagram of a data reading template of the present invention.

FIG. 3 is a schematic time sequence diagram of a textualization task execution process of the present invention.

FIG. 4 is a schematic diagram of the calling relationship during the execution of the textualization task of the present invention.

【Detailed ways】

The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments, wherein the exemplary embodiments and descriptions are only used to explain the present invention, but are not intended to limit the present invention.

As shown in FIG. 1 , a method for textualizing power system simulation data applied by the present invention is described in detail;

Carry out the execution of simulated data text based on the logical relationship between conceptual objects, relationships and entities; regard the data text task as an entity, called E, and set the entity to exist; the entity is composed of several facts, and the fact It is derived from a priori judgment or logical reasoning; there is no relationship between the facts, and the facts are only a description or listing;

Facts are composed of conceptual objects and the relationship between conceptual objects; conceptual objects contain one or more conceptual object attributes; conceptual objects can span facts and become constituent elements of different facts, but they cannot be used to directly constitute entities, but only exist based on facts. ; attributes are used to describe the state of a concept object;

A fact is a collection of one or more conceptual objects, the collection of facts constitutes an entity, and the facts are recorded as:

E = {Fact1{O1, O2, O3...}, Fact2{O1, O2, O3...}...} (1);

Preferably: the relationship is a horizontal relationship between conceptual objects; the horizontal relationship includes a logical operation relationship, a numerical operation relationship, a self-defined function relationship, etc.; assuming that the concept object is x _n , n is a positive integer greater than 1, then about The horizontal relation expression of x _n can be written as:

For example: for the textualization of power flow computing data, a textualization task of power flow computing data is an entity; regardless of the content of the entity, the textualization task will exist innately; only factual sentences are output in the entity, that is, the logical value in the horizontal relationship Statements (including probabilistic truth values) are true statements; statements are the basis of facts, and are regular expressions set by system users, which are in line with formal logic; for the textualization of power flow calculation data, due to its large amount of data, The structure is complex, and the concept object needs to be constructed by using the data reading template;

Preferred: integrate expert experience in the construction of horizontal relations, convert numerical data into knowledge texts, and use data analysis templates to construct horizontal relations;

The textualization task first needs to build a textual model, use software design to maintain the model, and make the model run; use the textual template as the carrier of the entities in the textual model; use the data parsing template as the carrier of facts, in the data parsing template, you can Set the horizontal relationship; for power system simulation data, the key to building a textual model is the construction of textual templates, data analysis templates, data reading templates, etc.;

The power system simulation data textualization method specifically includes the following steps:

Step S1: the construction of the conceptual model of text generation; carry out the corresponding relationship setting of data reading template, data analysis template, textual template based on the logical relationship between conceptual objects, relationships, and entities;

By setting the corresponding relationship between the data reading template, data parsing template, and textual template, the attributes in the concept object, the relationship between attributes, and the relationship between template items are constructed. In the process of textualization, the instantiation setting of the above template file needs to be performed according to the characteristics of the simulation data file;

Step S11: constructing a concept object, specifically: setting a concept object for the electrical components targeted by the power system simulation data, and constructing a data reading template based on the concept object, and using the data reading template as a carrier of the concept object; It can be seen that by constructing a data reading template, the purpose of constructing a concept object is achieved;

Preferably: the data reading template includes several key items, and the key items correspond to several attributes of the concept object;

In the process of data textualization, the data textualization task is an entity. The entity is composed of several facts (Facts), and the facts are obtained by a priori judgment or logical reasoning; there is no relationship between the facts, and the fact is only a description or list;

Preferred: the conceptual objects to be constructed include: busbars, AC lines, DC lines, generators, transformers, loads and other electrical components;

Preferably: the attributes of the conceptual object include: the row and column of the electrical component related data, the read data set, the unique identifier of the data set, the data read across rows, and the data association read;

Preferably: according to the characteristics of the conceptual object model, a number of template items are set in the data read template to correspond to the attributes of the conceptual object; the specific corresponding relationship is as shown in the following table;

Template item A conceptual object name Concept Object Properties conceptual object name Template item B result set Concept Object Properties read data set Template item C primary key Concept Object Properties Unique identifier for the dataset Template item D read step Concept Object Properties Read data across rows Template item E outer join Concept Object Properties data association read

Step S12: constructing a horizontal relationship between conceptual objects; specifically: selecting a referenced conceptual object, performing relationship analysis of the conceptual object, and filling a data analysis template based on the relationship analysis result;

The construction of horizontal relationship is the extraction of data knowledge. The knowledge in the data mainly exists in the relationship between the data, so the horizontal relationship includes the extraction of the numerical relationship, logical relationship, equation relationship or self-defined relationship between the data;

Preferred: Integrate experts' experience in analyzing data relationships, perform data mining on knowledge texts formed according to horizontal relationships, and use the results of data mining for the construction of horizontal relationships;

Preferably: the horizontal relationship between conceptual objects includes: logical operation relationship (HRL), numerical operation relationship (HRN), self-defined function relationship (HRF), etc.;

Preferably: multiple horizontal relationships can be set in one parsing template, and the concept object can be called in the horizontal relationship;

The corresponding items of template items and horizontal relationships are shown in the following table;

Step S13: entity construction of the data textualization task, specifically: constructing the entity according to the attributes of the data textualization task, and correspondingly constructing a textualization template;

The entity building according to the attributes of the data textualization task is specifically: setting the set of facts contained in the entity corresponding to the data textualization task; that is, the set formed by the set of conceptual objects and the horizontal relationship between the conceptual objects; Build the corresponding relationship between template items, template items, custom information and horizontal relationships of the textual template based on the entity; achieve the purpose of outputting the textual report by constructing the textual template;

The entity is the entire content of the report document, and the construction of the entity model is to determine the content set of the document output. According to the design of the textual model, the content set is the truth-valued item that outputs all horizontal relationships; the design of the entity model tends to report The flexibility of documents and the convenience of defining relationship collections; while the entity model includes: custom information, horizontal relationship calls;

Preferably: the textual template includes custom information of text entities and horizontal relationship calls;

The textual template items and several items of the entity model correspond to the following table;

Step S14: generating a data textualization information file; specifically: initializing the data textualization information file, and saving the data textualization related information based on the textualization template in the subsequent textualization process;

The initialization data textual information file is specifically: creating a new textual information file, and setting the size of the textual information file according to the size of the original simulation data file;

The data text information file is a data file with a data structure that supports text mining provided by the data text prototype system; in order to support text mining, the data structure of the information file will record all the facts when each fact statement is generated in the next text task. Correlation information; at the same time, it provides a storage form in units of fact sentences to facilitate the search in the dimension of fact sentences;

Step S2: carry out data textual preparation to the simulation calculation data; specifically: carry out data reading template, data analysis template, and the specific setting of the textual template;

The preparation of data text for the simulation calculation data includes the following steps:

Step S21: Set the name of the horizontal relationship group and the conceptual object name referenced in the horizontal relationship in the data analysis template;

Preferably: the name of the horizontal relationship group and the name of the referenced concept object are all English characters;

Step S22: setting the horizontal relationship name in the data analysis template;

Preferred: the name of the horizontal relationship is in English characters;

Step S23: setting the horizontal relationship description in the data analysis template;

Preferably: the description of the horizontal relationship can be Chinese characters, English, numbers and other characters;

Step S24: setting a horizontal relationship expression in the data analysis template;

Preferred: the horizontal relational expression supports logical expressions, function names, and the like. Among them, numerical operations and logical relation operations are supported in logical expressions;

Step S215 sets the conceptual object name in the data read template;

Preferred: the name of the concept object is in English characters;

Step S26: setting the conceptual object description field in the data reading template;

Preferably: the description content of the concept object can be Chinese characters, English, numbers and other characters;

Step S27: setting the file name of the conceptual object data source and the returned result set name in the data reading template;

Step S28: set the primary key of the conceptual object dataset in the data read template;

Preferably: the primary key is the column number of the conceptual object data file;

Step S29: setting the associated read data of the concept object in the data read template;

Preferably: according to the unique structure of the simulation data, between conceptual objects A and B, the association between the data content of the specified row and column of object A and the row serial number of object B can be set;

Step S210: configure and call the set horizontal relationship name in the textual template, and fill in custom information as required;

Step S3: performing a data textualization task; specifically: read the original simulation data file, read the original simulation data file based on the data reading template, analyze the read data based on the data analysis file, and follow the textualization template Fill textual information files;

Preferably: the original simulation data file is a power flow simulation calculation data file; the power flow simulation calculation data file is stored in a calculation example folder according to different electrical components, and the content of a single file is the simulation calculation data of a class of electrical components ;The content of each file is in the form of a two-dimensional table, the row of the two-dimensional table represents the simulation data generated by a certain physical quantity of an electrical component in the unit simulation time, and the column of the two-dimensional table represents the observable physical quantity of this type of component; In addition, the change in the data form is that it is possible to display the observable physical quantities of electrical components and simulation data per unit time in multiple lines;

Preferably: the power flow simulation calculation data file has the characteristics of association between files, and the data value of a certain row and column in the first file can be associated with the data value of a certain row and column in the second file; the two associated data values are equal; for example: by In the electrical component data of A, the value of a row and column L _a C _a is related to the data value of a row and column L _b C _b in the electrical component data of B, which can be abbreviated as A(L _a C _a )=B(L _b C _b );

The reading of the original simulation data file based on the data reading template is specifically: according to the characteristics of the conceptual object model, in the data reading template, based on the corresponding relationship between the template item and the conceptual object attribute, the template item is filled;

After the data reading template is completed, the data textualization task reads all the calling functions required for template parsing for subsequent template parsing;

The parsing of the read data based on the data parsing file is specifically: performing a cyclic call of the template parsing function, and in each calling process, the template parsing function reads the data parsing file to perform a conceptual object and its horizontal relationship. Parse; parse all template items through loop calls until all template items are parsed;

The filling of the textual information file according to the textualized template is specifically: filling the textualized information file with the data analysis result according to the textualized template;

Preferably; after initiating the execution of the textualization task, initialize the textualized information file;

Preferably: the textual information file is located on a distributed storage device; in a big data environment suitable for current power system simulation computing;

Taking the prepared data "36-node calculation example data" as the original data file, the folder size is 2.66M, which contains data description files and data result files such as busbar, AC line, transformer, DC line, generator, load, etc.; In the process of data textualization, you need to configure the reading template, the last shift analysis, and the textual template first, then select "Scenario Management" on the textual system interface, create a new scene "Job 2", select the corresponding template, and import the original template. data files. Click Analysis on the main interface to get the analysis results; check the local project folder "project path name" + "resultData", you can see the temporary file generated according to the rules, the size of the temporary file is 50.26KB;

Preferably: the data text is considered to be completed by distributed equipment; for example, it runs on two node machines to achieve the experimental purpose of multi-machine distributed processing; at the same time, in the process of text generation, it realizes the possibility of generating templates and generating processes. The configuration features, and at the same time, only about 2M data can be used to generate relatively accurate text cases, which achieves the design requirements and purposes;

In the several embodiments provided by the present invention, it should be understood that the disclosed method and terminal may be implemented in other manners. For example, the apparatus embodiments described above are only illustrative. For example, the division of the modules is only a logical function division, and there may be other division manners in actual implementation.

In addition, the technical solutions in the above-mentioned embodiments can be combined and replaced with each other under the condition that no contradiction occurs.

The modules described as separate components may or may not be physically separated, and components shown as modules may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware, or can be implemented in the form of hardware plus software function modules.

It will be apparent to those skilled in the art that the present invention is not limited to the details of the above-described exemplary embodiments, but that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments are to be regarded in all respects as illustrative and not restrictive, and the scope of the invention is defined by the appended claims rather than the foregoing description, which are therefore intended to fall within the scope of the appended claims. All changes within the meaning and range of the equivalents of , are included in the present invention. Any reference signs in the claims shall not be construed as limiting the involved claim. Furthermore, it is clear that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. Several modules or means recited in the system claims can also be implemented by one module or means by means of software or hardware. The terms first, second, etc. are used to denote names and do not denote any particular order.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be Modifications or equivalent substitutions can be made without departing from the spirit and scope of the technical solutions of the present invention.

Claims (4)

1. A power system simulation data textualization method, the method comprising:

step S1, constructing a conceptual model generated by the text;

step S2, performing data text preparation on the simulation calculation data;

step S3, executing data text task;

the step S1 specifically includes the following steps:

step S11: constructing a concept object;

step S12: constructing a horizontal relation between concept objects;

step S13: entity construction of a data textualization task;

step S14: generating a data text information file;

the step S11 specifically includes: setting a concept object for an electric appliance component aimed by power system simulation data, constructing a data reading template based on the concept object, and taking the data reading template as a carrier of the concept object;

the data reading template comprises a plurality of key items, and the key items correspond to a plurality of attributes of the concept object;

the constructed concept objects comprise: the system comprises a bus, an alternating current line, a direct current line, a generator, a transformer and load electrical components;

the attributes of the conceptual object include: the method comprises the following steps of row and column of electric component related data, read data set, unique identification of the data set, data cross-row reading and data association reading;

the step S12 specifically includes: selecting the referred concept object, performing relation analysis of the concept object, and filling a data analysis template based on a relation analysis result;

the horizontal relation construction comprises the following steps: extracting data knowledge;

the analysis experience of the data relation is fused, data mining is carried out on the knowledge text formed according to the horizontal relation, and the result of the data mining is used for constructing the horizontal relation;

the horizontal relationship between conceptual objects includes: a logical operation relationship, a numerical operation relationship and a custom function relationship;

the step S13 specifically includes: entity construction is carried out according to the attribute of the data textualization task, and a textualization template is correspondingly constructed;

the entity construction is carried out according to the attribute of the data text task, and specifically comprises the following steps: setting a set of facts contained in the entity corresponding to the data textualization task; constructing corresponding relations among template items, user-defined information and horizontal relations of the textual templates based on the entities; the purpose of outputting the textual report is achieved by constructing a textual template;

the step S14 specifically includes: initializing a data text information file, and storing data text related information based on a text template in a subsequent text process;

the step S3 specifically includes: reading an original simulation data file, reading the original simulation data file based on a data reading template, analyzing the read data based on a data analyzing file, and filling a textual information file according to a textual template; the original simulation data file is a load flow simulation calculation data file;

the reading of the original simulation data file based on the data reading template specifically comprises the following steps: filling template items in the data reading template based on the corresponding relation between the template items and the concept object attributes according to the characteristics of the concept object model;

after the data reading template is subjected to analysis, the data textualization task reads all calling functions required by the template analysis to perform subsequent template analysis;

the analyzing of the read data based on the data analyzing file specifically comprises the following steps: circularly calling the template analysis function, wherein in each calling process, the template analysis function analyzes the concept object and the horizontal relation thereof by reading the data analysis file; analyzing all the template items by circularly calling until all the template items are analyzed;

the filling of the textual information file according to the textual template specifically comprises: and filling the textual information file according to the data analysis result by a textual template.

2. The power system simulation data textualization method according to claim 1, wherein the step S1 is specifically: and setting the corresponding relation of the data reading template, the data analysis template and the textualization template based on the logical relation among the concept objects, the relation and the entities.

3. The electric power system simulation data textualization method according to claim 2, wherein the step S2 is specifically: and performing specific setting of a data reading template, a data analysis template and a textualization template.

4. The electric power system simulation data textualization method according to claim 1, wherein the attributes in the conceptual object, the relationships between the attributes and the relationships between the template items are constructed by setting the corresponding relationships of the data reading template, the data parsing template and the textualization template.

Images