CN116822462A

CN116822462A - Method and device for generating simulation report of power system

Info

Publication number: CN116822462A
Application number: CN202310556570.8A
Authority: CN
Inventors: 郭海平; 郭琦; 卢远宏; 郭天宇; 张�杰; 黄立滨; 胡云; 罗超; 刘宇嫣; 洪泽祺; 苏明章; 伍文聪; 陈智豪; 涂亮; 李书勇; 朱益华; 林雪华; 蔡海青
Original assignee: CSG Electric Power Research Institute; China Southern Power Grid Co Ltd
Current assignee: CSG Electric Power Research Institute; China Southern Power Grid Co Ltd
Priority date: 2023-05-16
Filing date: 2023-05-16
Publication date: 2023-09-29

Abstract

The application provides a method and a device for generating a simulation report of a power system. The method comprises the following steps: preprocessing the simulation result data of the power system by adopting a data preprocessing method to obtain target simulation data; processing the target simulation data based on a natural language processing model to obtain target natural language data, wherein the natural language processing model is obtained by training a target data set, and the target data set is obtained by performing data enhancement on an initial data set by adopting a preset data enhancement method; and filling the target natural language data into a target simulation report template by adopting a text automatic filling method to obtain a target simulation report, wherein the target simulation report template is a simulation report template which corresponds to a target simulation scene and has the highest score. The generation method solves the problem of low efficiency of generating the simulation report based on the simulation result of the power system in the prior art.

Description

Method and device for generating simulation report of power system

Technical Field

The present application relates to the field of power systems, and in particular, to a method and apparatus for generating a simulation report of a power system, and a computer readable storage medium.

Background

As the scale of the power system is continuously increased, the complexity of the power system is continuously increased, so that simulation analysis of the power system by simulation software is also becoming more and more important in the field of power engineering.

However, simulation analysis of a power system by simulation software generally involves a large amount of data and complex analysis, and requires expertise and experience to perform correct interpretation.

The generation of simulation reports for conventional power systems is typically manually analyzed and written, which also makes the entire process of obtaining corresponding simulation reports time consuming based on simulation results for the power system. Therefore, a method for obtaining the simulation result of the power system and the corresponding simulation report rapidly and accurately is needed.

Disclosure of Invention

The application mainly aims to provide a method and a device for generating a simulation report of a power system and a computer readable storage medium, so as to at least solve the problem that the efficiency of generating the simulation report based on the simulation result of the power system is low in the prior art.

In order to achieve the above object, according to one aspect of the present application, there is provided a method for generating a simulation report of an electric power system, including: preprocessing electric power system simulation result data by adopting a data preprocessing method to obtain target simulation data, wherein the electric power system simulation result data are obtained by simulating an electric power system by adopting simulation software, and the data preprocessing method comprises data cleaning, data normalization and feature extraction; processing the target simulation data based on a natural language processing model to obtain target natural language data, wherein the natural language processing model is obtained by training a target data set, the target data set is obtained by performing data enhancement on an initial data set by adopting a preset data enhancement method, and the preset data enhancement method comprises synonym replacement, sentence structure adjustment and noise injection; and filling the target natural language data into a target simulation report template by adopting a text automatic filling method to obtain a target simulation report, wherein the target simulation report template is a simulation report template which corresponds to a target simulation scene and has the highest score, and the target simulation scene is a simulation scene corresponding to the simulation result data of the power system.

Optionally, the training the natural language processing model based on the target data set includes: model fusion is carried out on a plurality of initial natural language processing models to obtain preset natural language processing models, and the plurality of initial natural language processing models are constructed by adopting different neural networks; training the preset natural language processing model by adopting the target data set to obtain the natural language processing model.

Optionally, the process of performing data enhancement on the initial data set to obtain the target data set by adopting the preset data enhancement method includes: performing synonym replacement processing on sentences to which the target keywords belong in the initial dataset to obtain the initial dataset after the synonym replacement processing; sentence structure adjustment is carried out on sentences in the initial data set, and the initial data set with the structure adjusted is obtained; processing the initial data set by adopting a generating countermeasure network to obtain a preset data set; performing interpolation processing on the initial data set to obtain the initial data set after interpolation processing; and combining the initial data set subjected to synonym replacement processing, the initial data set subjected to structure adjustment, the preset data set and the initial data set subjected to interpolation processing to obtain the target data set.

Optionally, a text automatic filling method is adopted to fill the target natural language data into a target simulation report template to obtain a target simulation report, including: based on the target natural language data, adjusting the layout and the structure of the target simulation report template to obtain an adjusted target simulation report; filling the target natural language data into the adjusted target simulation report by adopting the text automatic filling method to obtain a preset simulation report; generating corresponding visual elements based on the power system simulation result data corresponding to the target natural language data, wherein the visual elements comprise charts, images and formulas; and filling the visual elements into the preset simulation report, and carrying out context correlation analysis on the preset simulation report filled with the visual elements to obtain the target simulation report.

Optionally, scoring the simulation report template by using a scoring rule includes: determining a first weight based on the content correlation in the simulation report template, determining a second weight based on the structural rationality in the simulation report template, and determining a third weight of the simulation report template based on feedback information of a user; determining the product of the content relevance score of the simulation report template and the first weight to obtain a first score value, determining the product of the structure rationality score of the simulation report template and the second weight to obtain a second score value, and determining the product of the user score of the simulation report template and the third weight to obtain a third score value; and determining the first grading value, the second grading value and the third grading value as the grading of the corresponding simulation report template.

Optionally, determining the target simulation report template matching the target simulation scenario from a plurality of the simulation report templates includes: and determining the simulation report template corresponding to the meta tag information matched with the target simulation scene as the target simulation report template, wherein one simulation report template corresponds to one meta tag information, and the meta tag information is used for representing the simulation scene applicable to the corresponding simulation report template.

Optionally, the target data set is a data set with tag information, and the target data set includes sentence type data, chart type data, and image type data.

Optionally, after filling the target natural language data into a target simulation report template by adopting a text automatic filling method to obtain a target simulation report, the generating method further comprises: receiving adjustment information in response to a predetermined operation acting on a display screen, wherein the adjustment information is information for adjusting fonts, font sizes, font colors and paragraph formats in the target simulation report; and adjusting the target simulation report based on the adjustment information to obtain the adjusted target simulation report.

According to another aspect of the present application, there is provided an apparatus for generating a simulation report of a power system, including: the preprocessing unit is used for preprocessing the simulation result data of the power system by adopting a data preprocessing method to obtain target simulation data, wherein the simulation result data of the power system is obtained by simulating the power system by adopting simulation software, and the data preprocessing method comprises data cleaning, data normalization and feature extraction; the processing unit is used for processing the target simulation data based on a natural language processing model to obtain target natural language data, the natural language processing model is obtained by training a target data set, the target data set is obtained by adopting a preset data enhancement method to carry out data enhancement on an initial data set, and the preset data enhancement method comprises synonym replacement, sentence structure adjustment and noise injection; the generating unit is used for filling the target natural language data into a target simulation report template by adopting a text automatic filling method to obtain a target simulation report, wherein the target simulation report template is a simulation report template which corresponds to a target simulation scene and has the highest score, and the target simulation scene is a simulation scene corresponding to the simulation result data of the power system.

According to still another aspect of the present application, there is provided a computer readable storage medium, where the computer readable storage medium includes a stored program, and when the program runs, the device where the computer readable storage medium is controlled to execute any one of the methods for generating a simulation report of a power system.

By applying the technical scheme of the application, firstly, data preprocessing such as data cleaning, data normalization and feature extraction is carried out on simulation result data of the power system to obtain target simulation data; then, inputting the target simulation data into a natural language processing model to obtain target natural language data, namely, interpreting the target simulation data into the target natural language data through the natural language processing model; and finally, filling the target natural language data into a target simulation report template by adopting a text automatic filling method to obtain a target simulation report. The method and the system realize that the professional target simulation report is automatically generated based on the simulation result data of the power system, lighten the analysis and writing burden of a user, enable the user to obtain the target simulation report relatively quickly after obtaining the simulation result data of the power system, reduce the time for writing the simulation report by the user, and solve the problem of low efficiency for generating the simulation report based on the simulation result of the power system in the prior art.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application. In the drawings:

fig. 1 is a block diagram showing a hardware configuration of a mobile terminal for performing a method of generating a simulation report of a power system according to an embodiment of the present application;

fig. 2 is a flow chart of a method for generating a simulation report of a power system according to an embodiment of the present application;

FIG. 3 is a flow diagram of a simulation report generation scheme for a specific power system provided in accordance with an embodiment of the present application;

fig. 4 is a schematic structural diagram of a simulation report generating apparatus of a power system according to an embodiment of the present application.

Wherein the above figures include the following reference numerals:

102. a processor; 104. a memory; 106. a transmission device; 108. and an input/output device.

Detailed Description

It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other. The application will be described in detail below with reference to the drawings in connection with embodiments.

In order that those skilled in the art will better understand the present application, a technical solution in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, shall fall within the scope of the present application.

It should be noted that the terms "first," "second," and the like in the description and the claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe the embodiments of the application herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

As described in the background art, in the prior art, the efficiency of generating the simulation report based on the simulation result of the power system is low, and in order to solve the above-mentioned problems, the embodiments of the present application provide a method, an apparatus, and a computer readable storage medium for generating the simulation report of the power system.

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application.

The method embodiments provided in the embodiments of the present application may be performed in a mobile terminal, a computer terminal or similar computing device. Taking the mobile terminal as an example, fig. 1 is a block diagram of a hardware structure of the mobile terminal of a method for generating a simulation report of a power system according to an embodiment of the present application. As shown in fig. 1, a mobile terminal may include one or more (only one is shown in fig. 1) processors 102 (the processor 102 may include, but is not limited to, a microprocessor MCU or a processing device such as a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 for communication functions and an input-output device 108. It will be appreciated by those skilled in the art that the structure shown in fig. 1 is merely illustrative and not limiting of the structure of the mobile terminal described above. For example, the mobile terminal may also include more or fewer components than shown in fig. 1, or have a different configuration than shown in fig. 1.

The memory 104 may be used to store a computer program, for example, a software program of application software and a module, such as a computer program corresponding to a method for generating a simulation report of a power system in an embodiment of the present invention, and the processor 102 executes the computer program stored in the memory 104 to perform various functional applications and data processing, that is, implement the above-mentioned method. Memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory remotely located relative to the processor 102, which may be connected to the mobile terminal via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or transmit data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, simply referred to as NIC) that can connect to other network devices through a base station to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module, which is configured to communicate with the internet wirelessly.

In the present embodiment, a method of generating a simulation report of a power system operating on a mobile terminal, a computer terminal, or a similar computing device is provided, it should be noted that the steps shown in the flowchart of the drawings may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is shown in the flowchart, in some cases the steps shown or described may be performed in an order different from that shown herein.

Fig. 2 is a flowchart of a method of generating a simulation report of a power system according to an embodiment of the present application. As shown in fig. 2, the generating method includes the steps of:

step S201, preprocessing electric power system simulation result data by adopting a data preprocessing method to obtain target simulation data, wherein the electric power system simulation result data are obtained by simulating an electric power system by adopting simulation software, and the data preprocessing method comprises data cleaning, data normalization and feature extraction;

specifically, data cleaning, data normalization, feature extraction and the like are performed on the power system simulation result data, so that irrelevant data in the power system simulation result data, data units and ranges of the power system simulation result data can be deleted, key parameters and indexes of the power system simulation result data are extracted, the data structure of the obtained target simulation data is simpler, and the target simulation data is more suitable for a subsequent natural language processing model (NLP model). In the practical application process, the data preprocessing method is not limited to data cleaning, data normalization and special extraction, and can be any feasible data preprocessing method in the prior art. In a specific embodiment, the data preprocessing method further comprises principal component analysis, missing value processing and the like.

Step S202, processing the target simulation data based on a natural language processing model to obtain target natural language data, wherein the natural language processing model is obtained by training a target data set, the target data set is obtained by performing data enhancement on an initial data set by a preset data enhancement method, and the preset data enhancement method comprises synonym substitution, sentence structure adjustment and noise injection;

in the step S202, the target simulation data obtained through the data preprocessing is interpreted (i.e., processed) by using the trained natural language processing model, so that the key information of the target simulation data can be extracted and the target simulation data can be converted into the natural language which is easy to understand. In a specific embodiment, parameters such as active power, reactive power, voltage and the like in the load flow calculation result are converted into text descriptions so as to help a user to better understand the simulation result data of the power system.

In the practical application process, the data enhancement is not limited to the preset data enhancement method such as the above-mentioned synonym substitution, sentence structure adjustment, noise injection and the like, and the initial data set is subjected to data enhancement to obtain the target data set. The initial data set can be subjected to data enhancement by any feasible preset data enhancement method in the prior art to obtain a target data set, so that the model generalization capability of the natural language processing model is improved. In a specific embodiment, the preset data enhancement method may include random insertion, random adjustment, random deletion, and so on.

In addition, in the stage of constructing the target data set, an expert in the field of the electric power system can be invited to participate in the labeling process, so that the quality and accuracy of the obtained target data set can be determined, and the trained natural language processing model is ensured to be more accurate and reliable.

Step S203, filling the target natural language data into a target simulation report template by adopting a text automatic filling method to obtain a target simulation report, wherein the target simulation report template is a simulation report template corresponding to a target simulation scene and having the highest score, and the target simulation scene is a simulation scene corresponding to the simulation result data of the power system.

In a specific embodiment, the target simulation scenario may be a load flow calculation simulation scenario, a short circuit fault analysis simulation scenario, and a power system stability analysis simulation scenario.

Through the embodiment, firstly, data preprocessing such as data cleaning, data normalization and feature extraction is performed on simulation result data of a power system to obtain target simulation data; then, inputting the target simulation data into a natural language processing model to obtain target natural language data, namely, interpreting the target simulation data into the target natural language data through the natural language processing model; and finally, filling the target natural language data into a target simulation report template by adopting a text automatic filling method to obtain a target simulation report. The method and the system realize that the professional target simulation report is automatically generated based on the simulation result data of the power system, lighten the analysis and writing burden of a user, enable the user to obtain the target simulation report relatively quickly after obtaining the simulation result data of the power system, reduce the time for writing the simulation report by the user, and solve the problem of low efficiency for generating the simulation report based on the simulation result of the power system in the prior art.

It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is illustrated in the flowcharts, in some cases the steps illustrated or described may be performed in an order other than that illustrated herein.

In a specific implementation process, the training the natural language processing model based on the target data set in the step S202 includes: model fusion is carried out on a plurality of initial natural language processing models to obtain preset natural language processing models, and the plurality of initial natural language processing models are constructed by adopting different neural networks; training the preset natural language processing model by using the target data set to obtain the natural language processing model. In the embodiment, the preset natural language processing model is obtained by carrying out model fusion on the plurality of initial natural language processing models, so that the advantages of the plurality of initial natural language processing models can be combined, and the obtained natural language model is higher in accuracy and robustness. And training the preset natural language processing model by adopting the target data set, namely fine tuning the preset natural language processing model, so that the training time of the model is greatly shortened, and the overall performance of the model can be improved.

In a specific embodiment of the present application, the initial natural language processing model may be BERT or GPT, or the like.

Of course, in the process of training the preset natural language processing model by adopting the target data set, multiple forms (such as numerical data, charts, images and the like) of the simulation result data of the electric power system can be integrated together, and the preset natural language processing model is trained, so that the understanding and expression capability of the natural language processing model is further improved. Meanwhile, in the process of training the preset natural language processing model, the interpretability optimization can be introduced, so that the conversion result of the natural language processing model is more interpretable, and the electric power engineer can understand and verify conveniently.

In order to further improve the generalization capability of the natural language processing model obtained by the subsequent training and further ensure that the robustness of the obtained natural language processing model is higher, the process of obtaining the target data set by performing data enhancement on the initial data set by adopting the preset data enhancement method in the step S202 of the present application may be implemented by the following steps: performing synonym replacement processing on sentences to which the target keywords belong in the initial data set to obtain the initial data set after the synonym replacement processing; sentence structure adjustment is carried out on sentences in the initial data set, and the initial data set with the structure adjusted is obtained; processing the initial data set by adopting a generating countermeasure network to obtain a preset data set; performing interpolation processing on the initial data set to obtain the initial data set after interpolation processing; and combining the initial data set after synonym replacement processing, the initial data set after structure adjustment, the preset data set and the initial data set after interpolation processing to obtain the target data set.

In a specific embodiment, one sentence has a target keyword, i.e. LCC-HVDC; the other sentence has a target keyword, namely, high-voltage direct-current transmission; also included in the sentence is a target keyword, i.e. conventional dc transmission. In order to make the terminology used throughout consistent and further to ensure that the resulting natural language processing model is accurate, and since LCC-HVDC, HVDC and HVDC are essentially the same as those represented by conventional dc transmission, LCC-HVDC and conventional dc transmission can be replaced by HVDC.

In the embodiment, the synonym replacement is performed on the target keywords in the sentences in the initial dataset, so that the natural language processing model is facilitated to learn the same meaning under different expression modes, and the understanding capability of the natural language processing model is improved. The sentence structure of the sentence is adjusted, for example, the active and passive states of the sentence are changed, the word sequence is adjusted, and the like, so that the natural language processing model is suitable for different sentence structures, and the robustness of the natural language processing model is improved. The predetermined data set with certain difficulty (the content in the predetermined data set has the same meaning as the content in the initial data set) is generated by using the generation countermeasure network (Generative Adversarial Network, GAN for short), so that the natural language processing model can be forced to learn to solve the complex problem more effectively in the training process, and the generalization capability of the natural language processing model is improved. The initial data set is interpolated to generate an initial data set which is subjected to interpolation processing and is between the initial data sets in semantic space, so that a natural language processing model can learn the structure of the semantic space better, and the generalization capability of unseen data is improved.

Of course, the initial data set with richer background information can also be generated by combining the initial data set with external data (such as text, knowledge patterns, etc. related to the field), which helps the natural language processing model to better understand the related knowledge in the field of the power system. And adding certain noise (such as randomly scrambling word order, adding spelling error and the like) into the initial data set, so that the natural language processing model learns to ignore insignificant information in the training process, and the robustness of the natural language processing model to interference is improved.

In order to further increase the efficiency of generating the target simulation report and reduce the occurrence of human errors, in some embodiments, the step S203 may be specifically implemented by the steps S2031, S2032, S2033, and S2034. Step S2031, adjusting the layout and structure of the target simulation report template based on the target natural language data, to obtain the adjusted target simulation report; step S2032, filling the target natural language data into the adjusted target simulation report by adopting the text automatic filling method to obtain a preset simulation report; step S2033, generating corresponding visual elements based on the power system simulation result data corresponding to the target natural language data, where the visual elements include a chart, an image and a formula; step S2034, filling the visualization element into the predetermined simulation report, and performing context correlation analysis on the predetermined simulation report after filling the visualization element, to obtain the target simulation report.

In a particular embodiment, the corresponding graph may be generated based on numerical data in the power system simulation result data, such as, for example, values of load, power, voltage, etc. of each device. In particular, the types of charts may include one or more of a line chart, a bar chart, a pie chart, and the like. For example, a line graph may be generated to show the load over time based on the load data for different time periods in the power system simulation result data.

In another specific embodiment, the corresponding image may be generated based on spatial information such as topology, device distribution, etc. in the power system simulation result data. In particular, the image may include a topology map of the power system, a device distribution thermodynamic diagram, and so forth. For example, a topology map may be generated according to the connection relationship of the power system, so as to intuitively demonstrate the connection condition between devices in the system.

In yet another specific embodiment, the corresponding formulas may be generated based on a computational process and a mathematical model in the power system simulation result data. The formulas may include device parameter calculation formulas, power flow calculation formulas, and the like. For example, for the output power of a generator, a calculation formula may be generated that contains generator parameters and operating conditions.

In the above embodiment, according to the target natural language data and the user requirements, the style of the target simulation report template, such as font, word size, color, paragraph format, etc., may be automatically adjusted, and according to the importance and relevance of the target natural language data, the chapter sequence, hierarchy structure and content distribution of the target simulation report template may be automatically adjusted, so as to improve the logic and readability of the target simulation report, and meanwhile, it may be ensured that the target simulation report obtained later has visual consistency and professional, and improve the reading experience of the user. And automatically creating visual elements such as charts, images and formulas according to the target natural language data, and inserting the visual elements into corresponding positions in a preset simulation report. These visual elements help the user to more intuitively understand the power system simulation result data and improve the readability of the target simulation report. When the target simulation report is generated, the logical relationship and continuity between the interpreted target natural language data and other contents in the target simulation report can be ensured by analyzing the context association of each part. This may improve the overall quality and legibility of the report.

In addition, the user can be allowed to view and modify the content in the target simulation report in real time in the process of generating the target simulation report. Through interaction and feedback with the user, the personalized requirements of the user can be better met, and the quality and satisfaction degree of the target simulation report are improved.

In some specific implementation processes, the scoring the simulation report template using the scoring rule in the step S203 may further be implemented by the following steps: determining a first weight based on the content correlation in the simulation report template, determining a second weight based on the structural rationality in the simulation report template, and determining a third weight of the simulation report template based on feedback information of a user; determining the product of the content relevance score of the simulation report template and the first weight to obtain a first score value, determining the product of the structure rationality score of the simulation report template and the second weight to obtain a second score value, and determining the product of the user score of the simulation report template and the third weight to obtain a third score value; and determining the first grading value, the second grading value and the third grading value as the grading of the corresponding simulation report template, so that a user can be helped to quickly select a target simulation report template with reasonable layout.

In the above embodiment, a scoring mechanism may be designed for each simulation report template, and the simulation report templates may be scored according to the matching degree between the simulation report templates and the requirements of the simulation tasks. The highest scoring simulation report template may then be selected as the best matching template. The scoring criteria for scoring each simulation report module may include content relevance, structural rationality, etc. of the simulation report templates. The scoring mechanism may be updated in two cases: updating a template library: when a simulation report template is newly added or modified, the scores of all simulation report templates need to be reevaluated. At this time, scoring all simulation report templates according to the new simulation report template metadata tags and scoring criteria; and (3) scoring standard adjustment: when the user or system adjusts the scoring criteria, the scores of all the simulated report templates need to be recalculated. For example, when the importance of a certain class of simulation tasks changes, the scoring weights associated therewith may need to be adjusted.

In addition, the method for generating the simulation report further comprises a user feedback mechanism, and the user is allowed to evaluate the generated simulation report and the target simulation report template used by the generated simulation report by introducing the user feedback mechanism, so that the satisfaction degree of the user on the target simulation report template is helped to be known, and the scoring standard and the template selection are further optimized. The templates with similar characteristics can be grouped by clustering the simulation report templates, so that the calculated amount can be reduced in the template matching stage, and the template selection efficiency can be improved. And the scoring weight can be automatically adjusted according to the historical selection and feedback of the user, so that the template selection meets the user requirement. For example, if a user frequently selects a simulated report template with more detailed content, the system may adjust the scoring weights for the content correlations accordingly. Template recommendation can be performed, and simulation report templates which are possibly interested are recommended to the user according to historical selection and feedback of the user, so that the user satisfaction degree is improved, and the use experience of the system is improved. The template library can be maintained and updated regularly, so that the content and the structure of the template are always consistent with the development of the simulation field of the power system. Meanwhile, new simulation report templates can be collected and arranged so as to improve the accuracy and diversity of template matching.

In order to further easily match the target simulation report templates, the step 203 of determining the target simulation report template matching the target simulation scene from among the plurality of simulation report templates may be performed by determining the simulation report template corresponding to meta tag information matching the target simulation scene as the target simulation report template, one of the simulation report templates corresponding to one of the meta tag information, and the meta tag information representing a simulation scene to which the corresponding simulation report template is applied.

In the above embodiment, meta tag information is added for each simulation report template. The meta-tag information may include simulation task type, analysis method, application scenario, etc. When the simulation report template is selected, the simulation report template of corresponding meta-tag information is matched according to the specific requirements of the simulation task.

In a specific embodiment of the present application, the target data set is a data set with tag information, and the target data set includes sentence type data, chart type data, and image type data, so that a model generalization capability of a natural language training model obtained by subsequent training is further ensured to be stronger.

In the actual application process, the method for generating the target simulation report further comprises the steps of: and receiving adjustment information in response to a preset operation acted on a display screen, wherein the adjustment information is information for adjusting fonts, font sizes, font colors and paragraph formats in the target simulation report, and adjusting the target simulation report based on the adjustment information to obtain an adjusted target simulation report, so that the personalized requirements of a user can be further met, and the quality and satisfaction degree of the target simulation report are further improved.

In a specific embodiment of the present application, the target simulation report obtained finally by the generating method of the present application may be output in a WORD form or a PDF form.

In order to enable those skilled in the art to more clearly understand the technical solution of the present application, the implementation procedure of the simulation report generating method of the electric power system of the present application will be described in detail with reference to specific embodiments.

The embodiment relates to a specific power system simulation report generation scheme, as shown in fig. 3, including the following steps:

A power company performs a power system simulation project. The power system simulation project comprises tasks such as load flow calculation, short circuit fault analysis, power system stability analysis and the like. After the simulation project of the power system is completed, engineers need to generate a detailed simulation analysis report.

By using the method for generating the simulation report of the power system, which is provided by the application, an engineer firstly acquires simulation result data of the power system from simulation software.

Step S1: and carrying out data preprocessing on the simulation result data of the power system to obtain target simulation data.

Step S2: inputting the target simulation data into a trained natural language processing model, and explaining the target simulation data after the data preprocessing by adopting the natural language processing model, thereby extracting key information in the target simulation data and converting the target simulation data into target natural language data.

Step S3: the engineer selects a target simulation report template that is appropriate for the needs of the power system simulation project. And filling the interpreted target natural language data into a target simulation report template by adopting a text automatic filling method to generate a complete simulation analysis report. The simulation analysis report comprises detailed analysis of the load flow calculation result, fault type and influence of short-circuit fault analysis, conclusion of power system stability analysis and the like.

Step S4: the engineer performs format adjustment on the generated simulation analysis report according to the requirement, such as changing fonts and font sizes, adjusting paragraph samples, and the like, so as to obtain an adjusted simulation analysis report.

Step S5: and the adjusted simulation analysis report is output in a PDF format, so that the simulation analysis report is convenient to view and share.

By the method for generating the simulation report of the power system, engineers can quickly and accurately generate the simulation analysis report, and work load can be reduced while work efficiency is improved.

The embodiment of the application also provides a device for generating the simulation report of the power system, and the device for generating the simulation report of the power system can be used for executing the method for generating the simulation report of the power system. The device is used for realizing the above embodiments and preferred embodiments, and is not described in detail. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.

The following describes a device for generating a simulation report of a power system provided by an embodiment of the present application.

Fig. 4 is a schematic structural view of a simulation report generating apparatus of a power system according to an embodiment of the present application. As shown in fig. 4, the generating device includes:

the preprocessing unit 10 is configured to preprocess simulation result data of the power system by using a data preprocessing method, to obtain target simulation data, where the simulation result data of the power system is obtained by simulating the power system by using simulation software, and the data preprocessing method includes data cleaning, data normalization and feature extraction;

The processing unit 20 is configured to process the target simulation data based on a natural language processing model to obtain target natural language data, where the natural language processing model is obtained by training a target data set, and the target data set is obtained by performing data enhancement on an initial data set by using a preset data enhancement method, and the preset data enhancement method includes synonym substitution, sentence structure adjustment, and noise injection;

in the processing unit, the target simulation data obtained through data preprocessing is interpreted (i.e. processed) by using a trained natural language processing model, so that key information of the target simulation data can be extracted, and the target simulation data can be converted into natural language which is easy to understand. In a specific embodiment, parameters such as active power, reactive power, voltage and the like in the load flow calculation result are converted into text descriptions so as to help a user to better understand the simulation result data of the power system.

And the generating unit 30 is configured to fill the target natural language data into a target simulation report template by using a text automatic filling method, so as to obtain a target simulation report, where the target simulation report template is a simulation report template corresponding to a target simulation scene and having the highest score, and the target simulation scene is a simulation scene corresponding to the simulation result data of the power system.

According to the embodiment, the preprocessing unit is used for preprocessing data such as data cleaning, data normalization and feature extraction on simulation result data of the power system to obtain target simulation data; the processing unit is used for inputting the target simulation data into the natural language processing model to obtain target natural language data, namely, the target simulation data is interpreted as the target natural language data through the natural language processing model; the generating unit is used for filling the target natural language data into the target simulation report template by adopting a text automatic filling method to obtain a target simulation report. The method and the system realize that the professional target simulation report is automatically generated based on the simulation result data of the power system, lighten the analysis and writing burden of a user, enable the user to obtain the target simulation report relatively quickly after obtaining the simulation result data of the power system, reduce the time for writing the simulation report by the user, and solve the problem of low efficiency for generating the simulation report based on the simulation result of the power system in the prior art.

In a specific implementation process, the processing unit comprises a model fusion module and a training module, wherein the fusion module is used for carrying out model fusion on a plurality of initial natural language processing models to obtain preset natural language processing models, and the plurality of initial natural language processing models are constructed by adopting different neural networks; the training module is used for training the preset natural language processing model by adopting the target data set to obtain the natural language processing model. In the embodiment, the preset natural language processing model is obtained by carrying out model fusion on the plurality of initial natural language processing models, so that the advantages of the plurality of initial natural language processing models can be combined, and the obtained natural language model is higher in accuracy and robustness. And training the preset natural language processing model by adopting the target data set, namely fine tuning the preset natural language processing model, so that the training time of the model is greatly shortened, and the overall performance of the model can be improved.

In order to further improve generalization capability of a natural language processing model obtained by subsequent training and further ensure that robustness of the obtained natural language processing model is higher, the processing unit further comprises a first processing module, a first adjusting module, a second processing module, a third processing module and a combination module, wherein the first processing module is used for carrying out synonym replacement processing on sentences to which target keywords belong in the initial dataset to obtain the initial dataset after the synonym replacement processing; the first adjusting module is used for adjusting the sentence structure of sentences in the initial data set to obtain the initial data set with the structure adjusted; the second processing module is used for processing the initial data set by adopting a generation countermeasure network to obtain a preset data set; the third processing module is used for carrying out interpolation processing on the initial data set to obtain the initial data set after interpolation processing; the combination module is used for combining the initial data set after synonym replacement processing, the initial data set after structure adjustment, the preset data set and the initial data set after interpolation processing to obtain the target data set.

In the embodiment, the synonym replacement is performed on the target keywords in the sentences in the initial dataset, so that the natural language processing model is facilitated to learn the same meaning under different expression modes, and the understanding capability of the natural language processing model is improved. The sentence structure of the sentence is adjusted, for example, the active and passive states of the sentence are changed, the word sequence is adjusted, and the like, so that the natural language processing model is suitable for different sentence structures, and the robustness of the natural language processing model is improved. The initial dataset is interpolated to generate an interpolated initial dataset that is semantically intermediate between the initial datasets, which helps the natural language processing model to learn better the structure of the semantic space and improves the generalization ability of the unseen data.

In order to further improve the efficiency of generating the target simulation report and reduce the occurrence rate of human errors, in some embodiments, the generating unit includes a second adjusting module, a filling module, a generating module, and an analyzing module, where the second adjusting module is configured to adjust the layout and structure of the target simulation report template based on the target natural language data, to obtain the adjusted target simulation report; the filling module is used for filling the target natural language data into the adjusted target simulation report by adopting the text automatic filling method to obtain a preset simulation report; the generation module is used for generating corresponding visual elements based on the power system simulation result data corresponding to the target natural language data, wherein the visual elements comprise charts, images and formulas; the analysis module is used for filling the visual elements into the preset simulation report, and carrying out context correlation analysis on the preset simulation report filled with the visual elements to obtain the target simulation report.

In some specific implementation processes, the generating unit includes a first determining module, a second determining module and a third determining module, where the first determining module is configured to determine a first weight based on a content correlation in the simulation report template, determine a second weight based on a structural rationality in the simulation report template, and determine a third weight of the simulation report template based on feedback information of a user; the second determining module is configured to determine a product of the score of the content relevance of the simulation report template and the first weight to obtain a first score value, determine a product of the score of the structural rationality of the simulation report template and the second weight to obtain a second score value, and determine a product of the user score of the simulation report template and the third weight to obtain a third score value; the third determining module is configured to determine the first score value, the second score value, and the third score value as scores of the corresponding simulation report templates, so that a user can be assisted to quickly select a target simulation report template with a reasonable layout.

In order to further more simply match the target simulation report templates, the generating unit further includes a fourth determining module configured to determine, as the target simulation report templates, the simulation report templates corresponding to meta tag information matched with the target simulation scene, one of the simulation report templates corresponding to one of the meta tag information, where the meta tag information is used to characterize a simulation scene to which the corresponding simulation report template is applicable.

In an actual application process, the generating device further comprises a receiving unit and an adjusting unit, wherein the receiving unit is used for filling the target natural language data into a target simulation report template by adopting a text automatic filling method, and after a target simulation report is obtained, receiving adjusting information in response to a preset operation acted on a display screen, wherein the adjusting information is information for adjusting fonts, font sizes, font colors and paragraph formats in the target simulation report; the adjusting unit is used for adjusting the target simulation report based on the adjusting information to obtain the adjusted target simulation report, so that the personalized requirements of the user can be further met, and the quality and satisfaction degree of the target simulation report can be further improved.

The simulation report generating device for the electric power system comprises a processor and a memory, wherein the preprocessing unit, the processing unit, the generating unit and the like are all stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions. The modules are all located in the same processor; alternatively, the above modules may be located in different processors in any combination.

The processor includes a kernel, and the kernel fetches the corresponding program unit from the memory. The kernel can be provided with one or more than one kernel, and the problem of low efficiency of generating a simulation report based on a simulation result of the power system in the prior art is solved by adjusting kernel parameters.

The memory may include volatile memory, random Access Memory (RAM), and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM), among other forms in computer readable media, the memory including at least one memory chip.

The embodiment of the application provides a computer readable storage medium, which comprises a stored program, wherein the program is used for controlling equipment where the computer readable storage medium is located to execute a method for generating a simulation report of an electric power system.

Specifically, the method for generating the simulation report of the power system comprises the following steps:

An embodiment of the present invention provides an electronic device including a memory and a processor, where the memory stores a computer program, and the processor is configured to execute the method for generating a simulation report of a power system by using the computer program.

The embodiment of the invention provides equipment, which comprises a processor, a memory and a program stored in the memory and capable of running on the processor, wherein the processor realizes at least the following steps when executing the program:

The device herein may be a server, PC, PAD, cell phone, etc.

The application also provides a computer program product adapted to perform, when executed on a data processing device, a program initialized with at least the following method steps:

It will be appreciated by those skilled in the art that the modules or steps of the invention described above may be implemented in a general purpose computing device, they may be concentrated on a single computing device, or distributed across a network of computing devices, they may be implemented in program code executable by computing devices, so that they may be stored in a storage device for execution by computing devices, and in some cases, the steps shown or described may be performed in a different order than that shown or described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple modules or steps of them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the 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.

In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, etc., such as Read Only Memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises an element.

From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

1) In the method for generating the simulation report of the power system, firstly, data preprocessing such as data cleaning, data normalization and feature extraction is carried out on simulation result data of the power system to obtain target simulation data; then, inputting the target simulation data into a natural language processing model to obtain target natural language data, namely, interpreting the target simulation data into the target natural language data through the natural language processing model; and finally, filling the target natural language data into a target simulation report template by adopting a text automatic filling method to obtain a target simulation report. The method and the system realize that the professional target simulation report is automatically generated based on the simulation result data of the power system, lighten the analysis and writing burden of a user, enable the user to obtain the target simulation report relatively quickly after obtaining the simulation result data of the power system, reduce the time for writing the simulation report by the user, and solve the problem of low efficiency for generating the simulation report based on the simulation result of the power system in the prior art.

2) In the device for generating the simulation report of the power system, the preprocessing unit is used for preprocessing data such as data cleaning, data normalization and feature extraction on simulation result data of the power system to obtain target simulation data; the processing unit is used for inputting the target simulation data into the natural language processing model to obtain target natural language data, namely, the target simulation data is interpreted as the target natural language data through the natural language processing model; the generating unit is used for filling the target natural language data into the target simulation report template by adopting a text automatic filling method to obtain a target simulation report. The method and the system realize that the professional target simulation report is automatically generated based on the simulation result data of the power system, lighten the analysis and writing burden of a user, enable the user to obtain the target simulation report relatively quickly after obtaining the simulation result data of the power system, reduce the time for writing the simulation report by the user, and solve the problem of low efficiency for generating the simulation report based on the simulation result of the power system in the prior art.

The above description is only of the preferred embodiments of the present application and is not intended to limit the present application, but various modifications and variations can be made to the present application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method of generating a simulation report for an electrical power system, comprising:

preprocessing electric power system simulation result data by adopting a data preprocessing method to obtain target simulation data, wherein the electric power system simulation result data are obtained by simulating an electric power system by adopting simulation software, and the data preprocessing method comprises data cleaning, data normalization and feature extraction;

processing the target simulation data based on a natural language processing model to obtain target natural language data, wherein the natural language processing model is obtained by training a target data set, the target data set is obtained by performing data enhancement on an initial data set by adopting a preset data enhancement method, and the preset data enhancement method comprises synonym replacement, sentence structure adjustment and noise injection;

and filling the target natural language data into a target simulation report template by adopting a text automatic filling method to obtain a target simulation report, wherein the target simulation report template is a simulation report template which corresponds to a target simulation scene and has the highest score, and the target simulation scene is a simulation scene corresponding to the simulation result data of the power system.

2. The method of generating of claim 1, wherein training the natural language processing model based on the target data set comprises:

model fusion is carried out on a plurality of initial natural language processing models to obtain preset natural language processing models, and the plurality of initial natural language processing models are constructed by adopting different neural networks;

training the preset natural language processing model by adopting the target data set to obtain the natural language processing model.

3. The generating method according to claim 1, wherein the process of data enhancing the initial data set to obtain the target data set by using the preset data enhancing method includes:

performing synonym replacement processing on sentences to which the target keywords belong in the initial dataset to obtain the initial dataset after the synonym replacement processing;

sentence structure adjustment is carried out on sentences in the initial data set, and the initial data set with the structure adjusted is obtained;

processing the initial data set by adopting a generating countermeasure network to obtain a preset data set;

performing interpolation processing on the initial data set to obtain the initial data set after interpolation processing;

And combining the initial data set subjected to synonym replacement processing, the initial data set subjected to structure adjustment, the preset data set and the initial data set subjected to interpolation processing to obtain the target data set.

4. The generating method according to claim 1, wherein the filling the target natural language data into a target simulation report template by using a text automatic filling method to obtain a target simulation report comprises:

based on the target natural language data, adjusting the layout and the structure of the target simulation report template to obtain an adjusted target simulation report;

filling the target natural language data into the adjusted target simulation report by adopting the text automatic filling method to obtain a preset simulation report;

generating corresponding visual elements based on the power system simulation result data corresponding to the target natural language data, wherein the visual elements comprise charts, images and formulas;

and filling the visual elements into the preset simulation report, and carrying out context correlation analysis on the preset simulation report filled with the visual elements to obtain the target simulation report.

5. The method of generating of claim 1, wherein scoring the simulated report template using scoring rules comprises:

determining a first weight based on the content correlation in the simulation report template, determining a second weight based on the structural rationality in the simulation report template, and determining a third weight of the simulation report template based on feedback information of a user;

determining the product of the content relevance score of the simulation report template and the first weight to obtain a first score value, determining the product of the structure rationality score of the simulation report template and the second weight to obtain a second score value, and determining the product of the user score of the simulation report template and the third weight to obtain a third score value;

and determining the first grading value, the second grading value and the third grading value as the grading of the corresponding simulation report template.

6. The generation method according to any one of claims 1 to 5, wherein the process of determining the target simulation report template matching the target simulation scene from among the plurality of simulation report templates includes:

And determining the simulation report template corresponding to the meta tag information matched with the target simulation scene as the target simulation report template, wherein one simulation report template corresponds to one meta tag information, and the meta tag information is used for representing the simulation scene applicable to the corresponding simulation report template.

7. The generating method according to any one of claims 1 to 5, wherein the target data set is a data set having tag information, and the target data set includes sentence-type data, chart-type data, and image-type data.

8. The generating method according to any one of claims 1 to 5, wherein after the target natural language data is filled into a target simulation report template by using a text automatic filling method to obtain a target simulation report, the generating method further comprises:

receiving adjustment information in response to a predetermined operation acting on a display screen, wherein the adjustment information is information for adjusting fonts, font sizes, font colors and paragraph formats in the target simulation report;

and adjusting the target simulation report based on the adjustment information to obtain the adjusted target simulation report.

9. A simulation report generation apparatus for an electric power system, comprising:

the preprocessing unit is used for preprocessing the simulation result data of the power system by adopting a data preprocessing method to obtain target simulation data, wherein the simulation result data of the power system is obtained by simulating the power system by adopting simulation software, and the data preprocessing method comprises data cleaning, data normalization and feature extraction;

the processing unit is used for processing the target simulation data based on a natural language processing model to obtain target natural language data, the natural language processing model is obtained by training a target data set, the target data set is obtained by adopting a preset data enhancement method to carry out data enhancement on an initial data set, and the preset data enhancement method comprises synonym replacement, sentence structure adjustment and noise injection;

the generating unit is used for filling the target natural language data into a target simulation report template by adopting a text automatic filling method to obtain a target simulation report, wherein the target simulation report template is a simulation report template which corresponds to a target simulation scene and has the highest score, and the target simulation scene is a simulation scene corresponding to the simulation result data of the power system.

10. A computer-readable storage medium, characterized in that the computer-readable storage medium comprises a stored program, wherein the program, when run, controls a device in which the computer-readable storage medium is located to perform the method of generating a simulation report of the power system according to any one of claims 1 to 8.