CN115081898A - Power grid operation risk identification method and device, computer equipment and storage medium - Google Patents

Abstract

The application relates to a power grid operation risk identification method, a device, computer equipment and a storage medium, wherein the method comprises the following steps: acquiring current power grid risk information and a plurality of historical power grid risk information; the historical power grid risk information has corresponding risk labels; processing the current power grid risk information through a risk prediction model to obtain predicted power grid risk information; respectively obtaining a first matching degree between each historical power grid risk information and the predicted power grid risk information, and determining screened power grid risk information of which the first matching degree meets a first preset condition from the plurality of historical power grid risk information; and determining a risk identification result aiming at the power grid based on the risk label corresponding to the screened risk information. The method is simple and rapid, and can improve the speed and accuracy of risk identification of the real-time operation of the power grid.

Description

Power grid operation risk identification method and device, computer equipment and storage medium

Technical Field

The present application relates to the field of power grid management technologies, and in particular, to a method, an apparatus, a computer device, a storage medium, and a computer program product for identifying a risk of power grid operation.

Background

The identification of the operation risk of the power grid is an important research content for the scheduling and operation of the power system. The risk identification result is used as a reference for abnormal handling of the power grid accident, and is used for scheduling operators to adjust the operation mode so as to realize risk degradation; and the method can be used as the basis for the arrangement of the operation mode and supports the analysis and decision of the scheduling personnel.

The power grid real-time operation risk identification refers to a process of identifying possible operation accidents and influences of the possible operation accidents of the power grid by referring to weather information such as precipitation and incoming wind according to the real-time operation state of the power grid. The traditional power grid real-time operation risk identification method needs panoramic modeling of a power grid, considers the failure probability of power transmission and transformation equipment under different meteorological conditions, scans accident risks after failures of different types and different probabilities occur, quantifies accident consequences, and calculates the real-time operation risk of the power grid by counting the accident risk consequences under different probabilities. However, the above process has huge calculation amount, the complete identification calculation takes a long time, and even if the model is simplified, the real-time operation requirement is still difficult to meet.

Disclosure of Invention

Therefore, it is necessary to provide a power grid operation risk identification method, a device, a computer readable storage medium, and a computer program product for solving the technical problems of huge calculation amount and long time consumption for complete identification and calculation in the power grid operation risk identification method.

In a first aspect, the application provides a power grid operation risk identification method. The method comprises the following steps:

acquiring current power grid risk information and a plurality of historical power grid risk information of a power grid; each historical power grid risk information has a corresponding risk label;

processing the current power grid risk information through a risk prediction model to obtain predicted power grid risk information;

respectively obtaining a first matching degree between each historical power grid risk information and the predicted power grid risk information, and determining screened power grid risk information of which the first matching degree meets a first preset condition from the plurality of historical power grid risk information;

and determining a risk identification result aiming at the power grid based on the risk label corresponding to the screened risk information.

In one embodiment, the determining a risk identification result for the power grid based on the risk label corresponding to the screened risk information includes:

under the condition that risk labels corresponding to historical power grid risk information included in the screened risk information are different from each other, respectively obtaining a second matching degree between each screened power grid risk information and the predicted power grid risk information;

determining target power grid risk information from the screened power grid risk information based on the first matching degree and the second matching degree;

and determining a risk identification result aiming at the power grid based on the risk label corresponding to the target power grid risk information.

In one embodiment, the respectively obtaining the second matching degrees between the screened grid risk information and the predicted grid risk information includes:

respectively splicing the screened power grid risk information with the predicted power grid risk information to obtain a plurality of spliced power grid risk information;

and inputting the spliced power grid risk information into the trained matching model respectively to obtain a second matching degree between the screened power grid risk information and the predicted power grid risk information.

In one embodiment, the determining target grid risk information from the screened grid risk information based on the first matching degree and the second matching degree includes:

obtaining the product of the first matching degree and the second matching degree;

and determining screened power grid risk information with the largest product from the screened power grid risk information as target power grid risk information.

In one embodiment, the method further comprises:

and under the condition that the first matching degrees between the historical power grid risk information and the predicted power grid risk information do not accord with a first preset condition, or the second matching degrees between the screened power grid risk information and the predicted power grid risk information do not accord with a second preset condition, inputting the predicted power grid risk information into a risk identification model to obtain a risk identification result of the power grid.

In one embodiment, the determining a risk identification result for the power grid based on the risk label corresponding to the screened risk information further includes:

and under the condition that the same risk label exists in the risk labels corresponding to the historical power grid risk information included in the screened risk information, determining a risk identification result of the power grid based on the same risk label.

In a second aspect, the application further provides a power grid operation risk identification device. The device comprises:

the acquisition module is used for acquiring current power grid risk information and a plurality of historical power grid risk information of a power grid; each historical power grid risk information has a corresponding risk label;

the prediction module is used for processing the current power grid risk information through a risk prediction model to obtain predicted power grid risk information;

the matching module is used for respectively obtaining first matching degrees between each historical power grid risk information and the predicted power grid risk information, and determining screened power grid risk information of which the first matching degrees accord with a first preset condition from the historical power grid risk information;

and the identification module is used for determining a risk identification result aiming at the power grid based on the risk label corresponding to the screened risk information.

In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor implementing the following steps when executing the computer program:

acquiring current power grid risk information and a plurality of historical power grid risk information of a power grid; each historical power grid risk information has a corresponding risk label;

processing the current power grid risk information through a risk prediction model to obtain predicted power grid risk information;

respectively obtaining a first matching degree between each historical power grid risk information and the predicted power grid risk information, and determining screened power grid risk information of which the first matching degree meets a first preset condition from the plurality of historical power grid risk information;

and determining a risk identification result aiming at the power grid based on the risk label corresponding to the screened risk information.

In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of:

acquiring current power grid risk information and a plurality of historical power grid risk information of a power grid; each historical power grid risk information has a corresponding risk label;

processing the current power grid risk information through a risk prediction model to obtain predicted power grid risk information;

respectively obtaining a first matching degree between each historical power grid risk information and the predicted power grid risk information, and determining screened power grid risk information of which the first matching degree meets a first preset condition from the historical power grid risk information;

and determining a risk identification result aiming at the power grid based on the risk label corresponding to the screened risk information.

In a fifth aspect, the present application further provides a computer program product. The computer program product comprising a computer program which when executed by a processor performs the steps of:

acquiring current power grid risk information and a plurality of historical power grid risk information of a power grid; each historical power grid risk information has a corresponding risk label;

processing the current power grid risk information through a risk prediction model to obtain predicted power grid risk information;

respectively obtaining a first matching degree between each historical power grid risk information and the predicted power grid risk information, and determining screened power grid risk information of which the first matching degree meets a first preset condition from the plurality of historical power grid risk information;

and determining a risk identification result aiming at the power grid based on the risk label corresponding to the screened risk information.

According to the power grid operation risk identification method, the power grid operation risk identification device, the computer equipment, the storage medium and the computer program product, the current power grid risk information is processed through the risk prediction model to obtain predicted power grid risk information, screened power grid risk information with the first matching degree meeting a first preset condition is determined from the plurality of historical power grid risk information based on the first matching degree between each historical power grid risk information and the predicted power grid risk information, and a risk identification result for a power grid is determined based on a risk label corresponding to the screened risk information. The method is based on the matching of historical power grid risk information and predicted power grid risk information, the real-time operation risk of the power grid is determined, the method is simple and rapid, the speed and the accuracy of power grid real-time operation risk identification can be improved, and the defects that the traditional method is large in calculation amount and long in time consumption of complete evaluation and calculation are overcome.

Drawings

FIG. 1 is a schematic flow chart of a power grid operation risk identification method in one embodiment;

FIG. 2 is a schematic diagram of a combination of risk information for a power grid according to an embodiment;

FIG. 3 is a schematic diagram of a network architecture of a risk prediction model in one embodiment;

FIG. 4a is a schematic diagram of a form before splicing of the early warning data and the current grid risk information in one embodiment;

FIG. 4b is a schematic diagram of a form after splicing of the early warning data and the current grid risk information in one embodiment;

FIG. 5 is a schematic diagram illustrating splicing of screened grid risk information and predicted grid risk information in one embodiment;

FIG. 6 is a block diagram of a grid operation risk identification system according to an embodiment;

FIG. 7 is a schematic flow chart of a power grid operation risk identification method in another embodiment;

FIG. 8 is a block diagram of a grid operation risk identification device according to an embodiment;

FIG. 9 is a diagram illustrating an internal structure of a computer device according to an embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. It should be further noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party.

In an embodiment, as shown in fig. 1, a power grid operation risk identification method is provided, and this embodiment is illustrated by applying the method to a terminal, and it is to be understood that the method may also be applied to a server, and may also be applied to a system including the terminal and the server, and is implemented by interaction between the terminal and the server. The terminal can be but not limited to various personal computers, notebook computers, smart phones, tablet computers, internet of things equipment and portable wearable equipment, and the internet of things equipment can be smart sound boxes, smart televisions, smart air conditioners, smart vehicle-mounted equipment and the like. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, and the like. The server may be implemented as a stand-alone server or as a server cluster consisting of a plurality of servers. In this embodiment, the method includes the steps of:

step S110, acquiring current power grid risk information and a plurality of historical power grid risk information of a power grid; each historical grid risk information has a corresponding risk label.

The power grid risk information comprises power grid operation information and environment information.

Wherein, the electric wire netting operating information includes: the system comprises a generator set, a transmission line, a power generation unit, a reactive power generation unit, a transmission line, a system frequency and the like.

Wherein the environment information includes: wind power, temperature, rainfall, humidity, lightning level and the like.

In the specific implementation, for the acquisition of historical power grid risk system information: after the risk identification of the power grid operation is carried out every time, the current power grid risk information and the corresponding risk label can be recorded and stored in the database, and a plurality of historical power grid risk information can be taken out from the database when new power grid risk information is identified subsequently. Obtaining current power grid risk information: the method comprises the steps that severe weather early warning information can be acquired from a meteorological platform, after the severe weather early warning information is acquired, power grid operation information is acquired through a power grid operation information acquisition submodule, environment information is acquired through an environment information acquisition submodule, and the acquired power grid operation information and environment information form current power grid risk information.

More specifically, after the early warning information of severe weather is acquired, the environment information acquisition submodule may start to acquire the relevant environment information from the current time according to the preset time interval until the severe weather is finished. For example, the relevant environmental information is collected every 5 seconds, for a total of 1round 28 times, and 1 round every 5 minutes until the end of severe weather.

Similarly, after acquiring the early warning information of severe weather, the power grid operation information acquisition submodule can acquire the relevant environmental information from the current time according to the preset time interval until the severe weather is finished. For example, the relevant grid operation information is collected every 5 seconds, the total number of the collected data is 1 round for 28 times, and the collected data is 1 round every 5 minutes until the severe weather is over.

Further, in an example, after obtaining the current grid risk information, the method further includes: and preprocessing the current power grid risk information to obtain preprocessed power grid risk information, and predicting the preprocessed power grid risk information through a risk prediction model.

More specifically, referring to fig. 2, the preprocessing of the current grid risk information includes: determining the type of information in the current power grid risk information, and assigning the character type information according to the name of the information and a preset assignment mode for the character type information to obtain preprocessed character type information; for the information of the numerical type, mapping the information between [0,1] by adopting a linear function normalization mode to obtain preprocessed numerical type information; and combining the preprocessed character type information and the preprocessed numerical type information into a matrix, wherein the rows of the matrix represent information categories, and the columns of the matrix represent 28 values obtained after information normalization.

And step S120, processing the current power grid risk information through a risk prediction model to obtain predicted power grid risk information.

The risk prediction model may be a Generic Adaptive Network (GAN) model.

In specific implementation, the risk prediction model can predict information of the future 5 minutes according to the current power grid risk information, and the specific mode is that the preprocessed power grid risk information is input into a generator which generates a countermeasure network after training is completed, and the generator generates the information of the future 5 minutes, namely the predicted power grid risk information of the future 5 minutes.

Referring to fig. 3, the schematic diagram of the network structure of the risk prediction model is shown, where the input data to be input into the model is data obtained by splicing the preprocessed power grid risk information and the pre-warning data. As shown in fig. 3, the risk prediction model is generated as a pairwise reactive network, and the generator network structure includes 1 down-sampling structure and 1 up-sampling structure, wherein each down-sampling structure includes 3 down-convolution layers and the up-sampling structure includes 3 anti-convolution layers; and splicing the up-sampling result and the down-sampling feature every time, passing the data through a 3-time fully-connected neural network after passing through 3 deconvolution layers, and finally obtaining predicted power grid risk information, wherein the form of the predicted power grid risk information is equivalent to one column of the acquired current power grid risk information.

The line number of the early warning data needs to be consistent with the line number of the collected power grid risk information, each line represents the type of severe weather, 1 represents the type of severe weather, 0 represents the type of severe weather, the type of severe weather does not occur, the sequence of the early warning data can be preset, and a risk prediction model is obtained through training after the sequence is set, so that the sequence during prediction is consistent with the preset sequence. When the number of rows of the early warning data is less than that of the power grid risk information, the number of the parts exceeding the severe weather types is all represented by 1, the number of columns is 1, when one or more severe weather is early warned, 1 is taken at the corresponding position, and 0 is taken at other positions which do not correspond.

For example, it is assumed that the early warning data has 5 severe weather types as shown in fig. 4a, corresponding to 5 lines, the acquired grid risk information has n lines, and the number of lines of the early warning data is less than the number of lines of the acquired grid risk information, and splicing cannot be performed, so that the early warning data needs to be expanded (an expansion part has no practical significance, and therefore all lines are represented by 1), so that the expanded early warning data is consistent with the number of lines of the acquired grid risk information, splicing is performed, and spliced data as shown in fig. 4b can be obtained after splicing.

Step S130, respectively obtaining first matching degrees between each historical power grid risk information and the predicted power grid risk information, and determining screened power grid risk information of which the first matching degrees accord with a first preset condition from the plurality of historical power grid risk information.

The first preset condition may be that the first matching degree is greater than a first threshold, where the first threshold may be 0.65.

In the concrete implementation, after obtaining a plurality of historical power grid risk information from a database, each historical power grid risk information and the predicted power grid risk information can be respectively substituted into a matching degree calculation relational expression to obtain a first matching degree between each historical power grid risk information and the predicted power grid risk information, wherein the matching degree calculation relational expression is as follows:

wherein CosSim represents a first matching degree between historical grid risk information and predicted grid risk information, X_G Representing predicted grid risk information, X_h Representing historical grid risk information, X_h^T And the larger the first matching degree CosSim value is, the higher the matching degree between the historical power grid risk information and the predicted power grid risk information is.

After the first matching degrees between the historical power grid risk information and the predicted power grid risk information are obtained, the first matching degrees are respectively matched with a first threshold, if the first matching degrees larger than the first threshold do not exist, namely the first matching degrees corresponding to the historical power grid risk information are all smaller than or equal to the first threshold, the fact that the historical power grid risk information matched with the predicted power grid risk information does not exist is indicated, the predicted power grid risk information can be processed through a risk identification model, and a risk identification result of the power grid is obtained. And if the first matching degree which is greater than the first threshold exists, screening the historical power grid risk information of which the first matching degree is greater than the first threshold from the historical power grid risk information to serve as the screened power grid risk information.

More specifically, if the number P of historical grid risk information with the first matching degree greater than the first threshold is greater than a preset value N (for example, N is 3), the historical grid risk information may be sorted according to the value of the first matching degree, and the top N historical grid risk information with the highest first matching degree may be screened out as the screened grid risk information. If the number P of the historical power grid risk information with the first matching degree larger than the first threshold is smaller than the preset value N, the P pieces of historical power grid risk information can be screened out and used as the screened power grid risk information.

And step S140, determining a risk identification result aiming at the power grid based on the risk label corresponding to the screened risk information.

In specific implementation, after the screened risk information is obtained, a risk identification result for the power grid can be further determined according to a comparison result between risk labels corresponding to historical power grid risk information included in the screened risk information.

More specifically, if risk labels corresponding to historical power grid risk information included in the screened risk information are different from each other, obtaining a second matching degree between the screened power grid risk information and the predicted power grid risk information; determining target power grid risk information from the screened power grid risk information based on the first matching degree and the second matching degree; and determining a risk identification result aiming at the power grid based on the risk label corresponding to the target power grid risk information. And if the same risk label exists in the risk labels corresponding to the historical power grid risk information included in the screened risk information, determining a risk identification result of the power grid based on the same risk label.

According to the power grid operation risk identification method, current power grid risk information is processed through a risk prediction model to obtain predicted power grid risk information, screened power grid risk information with the first matching degree meeting a first preset condition is determined from a plurality of historical power grid risk information on the basis of the first matching degree between each historical power grid risk information and the predicted power grid risk information, and a risk identification result for a power grid is determined on the basis of a risk label corresponding to the screened risk information. The method aims at power grid real-time operation risk identification in severe weather, determines the power grid real-time operation risk based on the matching of historical power grid risk information and predicted power grid risk information, is simple and rapid, can improve the speed and accuracy of power grid real-time operation risk identification, and overcomes the defects of large calculation amount and long time consumption of complete evaluation and calculation in the traditional method.

In an exemplary embodiment, in step S140, determining a risk identification result for the power grid based on the risk label corresponding to the screened risk information includes:

step 1401, under the condition that risk labels corresponding to historical power grid risk information included in the screened risk information are different from each other, respectively obtaining a second matching degree between each screened power grid risk information and the predicted power grid risk information;

step S1402, determining target power grid risk information from the screened power grid risk information based on the first matching degree and the second matching degree;

step S1403, a risk identification result for the power grid is determined based on the risk label corresponding to the target power grid risk information.

The number of the screened power grid risk information can be one or more.

In the specific implementation, if the risk labels corresponding to the historical power grid risk information included in the screened risk information are different from each other, a second matching degree between the historical power grid risk information and the predicted power grid risk information can be calculated through a matching model obtained through pre-training, and the second matching degree is matched with a second threshold value.

If the second matching degree which is greater than the second threshold value does not exist, namely the second matching degree corresponding to each screened power grid risk information is smaller than or equal to the second threshold value, it is indicated that no historical power grid risk information matched with the predicted power grid risk information exists, the predicted power grid risk information can be processed through the risk identification model, and a risk identification result of the power grid is obtained.

If the second matching degree which is larger than the second threshold exists, calculating the product of the first matching degree and the second matching degree, and determining target power grid risk information from the screened power grid risk information based on the product; and determining the risk label corresponding to the target power grid risk information as the risk label of the power grid.

In this embodiment, when risk labels corresponding to historical power grid risk information included in the screened risk information are different from each other, the screened power grid risk information is further screened through the first matching degree and the second matching degree to obtain target power grid risk information, a risk identification result for the power grid is determined based on the risk label corresponding to the target power grid risk information, and accuracy of power grid risk identification can be improved.

In an exemplary embodiment, in the step S1401, respectively obtaining the second matching degrees between the screened grid risk information and the predicted grid risk information includes:

step 1401A, splicing the screened power grid risk information and the predicted power grid risk information to obtain a plurality of spliced power grid risk information;

step 1401B, inputting each spliced power grid risk information into the trained matching model respectively, and obtaining a second matching degree between each screened power grid risk information and the predicted power grid risk information.

Wherein the matching model may be a convolutional neural network.

In the specific implementation, referring to fig. 5, a partial schematic diagram of the second matching degree obtaining step in one embodiment is shown in fig. 5, and taking any one of the screened power grid risk information as an example, the screened power grid risk information is spliced with the predicted power grid risk information, and then the obtained spliced power grid risk information is transmitted to the trained convolutional neural network to obtain a matching value as the second matching degree. The convolution neural network adopts 3 layers of effective one-dimensional convolution and 2 layers of full connection layers, and finally outputs a numerical value, wherein the numerical value is between 0 and 1.

In the embodiment, the second matching degree is determined by adopting the matching model with the first matching degree calculation mode, and the obtained matching result is more accurate, so that the screened power grid risk information can be further screened according to the second matching degree, and the accuracy of the subsequent risk identification result is improved.

In an exemplary embodiment, in step S1402, determining the target grid risk information from the screened grid risk information based on the first matching degree and the second matching degree includes:

step S1402A, obtaining a product of the first matching degree and the second matching degree;

step S1402B, determining the screened power grid risk information with the largest product from the screened power grid risk information as the target power grid risk information.

In specific implementation, if a second matching degree larger than a second threshold exists, the product of the first matching degree and the second matching degree is calculated, and screened power grid risk information with the largest product is determined from the screened power grid risk information and serves as target power grid risk information.

In this embodiment, the screened power grid risk information with the largest product is determined from the screened power grid risk information by the product of the first matching degree and the second matching degree, and the screened power grid risk information is used as the target power grid risk information, so that the obtained target power grid risk information is the historical power grid risk information which is most matched with the predicted power grid risk information, and the accuracy of the risk identification result for the power grid determined based on the target power grid risk information can be ensured.

In an exemplary embodiment, the method further comprises: and under the condition that the first matching degree between each historical power grid risk information and the predicted power grid risk information does not accord with a first preset condition, or the second matching degree between each screened power grid risk information and the predicted power grid risk information does not accord with a second preset condition, inputting the predicted power grid risk information into a risk identification model to obtain a risk identification result of the power grid.

The second preset condition may be that the second matching degree is greater than a second threshold, and the second threshold may be 0.6.

Wherein the risk identification model may be a deep neural network.

In the specific implementation, if the first matching degrees between the historical power grid risk information and the predicted power grid risk information do not accord with a first preset condition, that is, the first matching degrees are all smaller than or equal to a first threshold, or the second matching degrees of the screened power grid risk information and the predicted power grid risk information do not accord with a second preset condition, that is, the second matching degrees are all smaller than or equal to a second threshold, it is indicated that the historical power grid risk information does not match with the predicted power grid risk information, at this time, the predicted power grid risk information can be input into a deep neural network for risk identification, and the deep neural network is used for processing, so that a risk identification result of the power grid is obtained.

In this embodiment, when the first matching degrees between the historical power grid risk information and the predicted power grid risk information do not meet the first preset condition, or the second matching degrees between the screened power grid risk information and the predicted power grid risk information do not meet the second preset condition, the predicted power grid risk information is input into the risk identification model to obtain a risk identification result of the power grid, so that risk identification under the condition that the historical power grid risk information matched with the predicted power grid risk information does not exist is realized.

In an exemplary embodiment, in step S140, determining a risk identification result for the power grid based on the risk label corresponding to the screened risk information, further includes:

in step S1404, when the risk labels corresponding to the historical grid risk information included in the screened risk information have the same risk label, a risk identification result of the grid is determined based on the same risk label.

In specific implementation, when the same risk label exists in the risk labels corresponding to the historical grid risk information included in the screened risk information, the same risk label can be determined as the risk label of the grid. More specifically, if the same risk label has multiple groups, the risk label with the maximum number of the corresponding historical grid risk information is determined as the risk label of the grid.

For example, it is assumed that the screened risk information includes 5 pieces of historical grid risk information, where the risk labels having 3 pieces of historical grid risk information are all first risk labels, and the risk labels having 2 pieces of historical grid risk information are all second risk labels, the first risk labels are determined as the risk labels of the grid.

In this embodiment, when the same risk label exists in the risk labels corresponding to the historical power grid risk information included in the screened risk information, it indicates that the power grid risk information matched with the predicted power grid risk information occurs, and the power grid has a higher probability of being under the same risk label, so that the risk identification result of the power grid is determined based on the same risk label, and the risk identification efficiency can be improved under the condition of ensuring the accuracy of the risk identification result.

In one embodiment, to facilitate understanding of embodiments of the present application by those skilled in the art, reference will now be made to the specific examples illustrated in the drawings.

Referring to fig. 6, a block diagram of a grid operation risk identification system according to an exemplary embodiment is shown, including:data acquisition module 610,data processing module 620,risk identification module 630 andstorage module 640, wherein:

and thedata acquisition module 610 is used for acquiring environmental information and power grid operation information.

And thedata processing module 620 is used for preprocessing the acquired environmental information and the power grid operation information, so that subsequent application is facilitated.

And therisk identification module 630 is used for rapidly identifying the power grid operation risk.

And thestorage module 640 is used for storing historical grid risk information and storing new grid risk information. In addition, the storage module can also store historical power grid risk information and risk labels processed by the data processing module, and meanwhile, the storage module can also store predicted power grid risk information and risk labels thereof processed by the data processing module.

Thedata acquisition module 610 includes an environment information acquisition submodule and a power grid operation information acquisition submodule, which are respectively used for acquiring environment information and power grid operation information.

Thedata processing module 620 is configured to convert the collected different types of information into numerical values meeting the specification, and then combine the numerical values into a set of matrix, and includes the following specific steps:

step 1, if the information is the information of the character type, assigning according to the name of the information and a preset assignment mode; if the information is the information of the numerical value type, the information is mapped between [0,1] by adopting a linear function normalization method.

And 2, combining all the acquired information into a matrix, wherein the row of the matrix represents the information category, and the column of the matrix represents 28 values after the information is normalized.

Therisk assessment module 630 includes an information prediction sub-module, a historical risk matching sub-module, and a risk assessment sub-module.

And the information prediction submodule is used for predicting the power grid risk information of 5 minutes in the future according to the currently acquired power grid risk information, and specifically, the information processed by thedata processing module 620 is transmitted into a trained risk prediction model (a countermeasure network is generated), and the power grid risk information of 5 minutes is generated by the risk prediction model.

And the historical risk matching submodule is used for matching the historical power grid risk information with the predicted power grid risk information.

And the risk evaluation submodule is used for carrying out risk evaluation on the predicted power grid risk information which is not successfully matched with the historical power grid risk information, and the specific mode is that the predicted power grid risk information is input into a trained risk evaluation model for risk identification.

As shown in fig. 3, the historical grid risk information and the predicted grid risk information stored in the storage module have only 1 column, the number of rows is consistent with the number of rows of the collected grid risk information, and each column of stored data has a tag for matching with the stored data, and the tag represents a risk identification result.

Referring to fig. 7, a schematic flow chart of the matching step of the historical risk matching sub-module is shown, and the specific steps include:

step 1, sequentially taking out a plurality of historical power grid risk information from a database, and then respectively calculating a first matching degree CosSim between each historical power grid risk information and predicted power grid risk information generated by an information prediction submodule.

And 2, comparing the first matching degree with a first threshold value of 0.65. And if the CosSim values corresponding to the historical power grid risk information are all smaller than or equal to the first threshold value 0.65, indicating that no historical power grid risk information matched with the predicted power grid risk information exists, and entering step 8.

And 3, if the first matching degree which is greater than the first threshold value of 0.65 exists, selecting historical power grid risk information with a CosSim value of greater than 0.65 as the screened power grid risk information. The number of the historical grid risk information included in the screened grid risk information is less than or equal to a preset threshold value N (N may be 3).

And 4, judging whether the screened power grid risk information has the same risk label or not. If the risk labels of at least 2 historical power grid risk information are consistent, the predicted power grid risk information is summarized into the risk, otherwise, thestep 5 is carried out.

And 5, splicing the screened power grid risk information and the predicted power grid risk information, and inputting the information into a trained matching model (convolutional neural network) to obtain a second matching degree.

And 6, comparing the second matching degree with a second threshold value of 0.6. If the second matching degrees corresponding to the screened power grid risk information are all smaller than or equal to the second threshold value 0.6, it is indicated that no historical power grid risk information matched with the predicted power grid risk information exists, and the step 8 is executed.

And 7, if the second matching degree which is greater than the second threshold value by 0.6 exists, determining historical power grid risk information of which the second matching degree is greater than 0.6 from the screened power grid risk information, calculating the product of the first matching degree and the second matching degree of the historical power grid risk information of which the second matching degree is greater than 0.6, taking the historical power grid risk information with the largest product as target power grid risk information, and further determining a risk label corresponding to the target power grid risk information as a risk identification result aiming at the power grid.

And 8, performing risk assessment on the predicted power grid risk information which is not successfully matched with the historical power grid risk information, wherein the specific mode is to input the predicted power grid risk information into a trained risk assessment model for risk identification.

According to the risk assessment method and device, for power grid real-time operation risk assessment under severe weather, a risk assessment model based on historical data matching and a deep neural network is simpler, power grid real-time operation risk can be rapidly assessed, and meanwhile the accuracy of power grid real-time operation risk assessment is improved.

It should be understood that, although the steps in the flowcharts related to the embodiments as described above are sequentially displayed as indicated by arrows, the steps are not necessarily performed sequentially as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in the flowcharts related to the embodiments described above may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the execution order of the steps or stages is not necessarily sequential, but may be rotated or alternated with other steps or at least a part of the steps or stages in other steps.

Based on the same inventive concept, the embodiment of the application also provides a power grid operation risk identification device for realizing the power grid operation risk identification method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the method, so that specific limitations in one or more embodiments of the grid operation risk identification device provided below can be referred to the limitations on the grid operation risk identification method in the above, and details are not described herein again.

In one embodiment, as shown in fig. 8, there is provided a grid operation risk identification device, including: an obtainingmodule 810, a predictingmodule 820, amatching module 830, and an identifyingmodule 840, wherein:

an obtainingmodule 810, configured to obtain current grid risk information and multiple historical grid risk information of a power grid; each historical power grid risk information has a corresponding risk label;

theprediction module 820 is used for processing the current power grid risk information through a risk prediction model to obtain predicted power grid risk information;

thematching module 830 is configured to obtain first matching degrees between the historical power grid risk information and the predicted power grid risk information, and determine screened power grid risk information with the first matching degree meeting a first preset condition from the historical power grid risk information;

theidentification module 840 is configured to determine a risk identification result for the power grid based on the risk label corresponding to the screened risk information.

In one embodiment, theidentification module 840 includes:

the obtaining submodule is used for respectively obtaining a second matching degree between each screened power grid risk information and the predicted power grid risk information under the condition that risk labels corresponding to historical power grid risk information included in the screened risk information are different;

the determining submodule is used for determining target power grid risk information from the screened power grid risk information based on the first matching degree and the second matching degree;

and the identification submodule is used for determining a risk identification result aiming at the power grid based on the risk label corresponding to the target power grid risk information.

In an embodiment, the obtaining sub-module is further configured to splice the screened power grid risk information and the predicted power grid risk information to obtain multiple spliced power grid risk information; and inputting the spliced power grid risk information into the trained matching model respectively to obtain a second matching degree between the screened power grid risk information and the predicted power grid risk information.

In an embodiment, the determining sub-module is configured to obtain a product of the first matching degree and the second matching degree; and determining screened power grid risk information with the largest product from the screened power grid risk information as target power grid risk information.

In an embodiment, theidentification module 840 is further configured to input the predicted power grid risk information into the risk identification model to obtain a risk identification result of the power grid when the first matching degrees between the historical power grid risk information and the predicted power grid risk information do not meet a first preset condition, or when the second matching degrees between the screened power grid risk information and the predicted power grid risk information do not meet a second preset condition.

In an embodiment, theidentification module 840 is further configured to determine a risk identification result of the power grid based on the same risk label when the same risk label exists in the risk labels corresponding to the historical power grid risk information included in the screened risk information.

The modules in the grid operation risk identification device can be wholly or partially implemented by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 9. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless communication can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a grid operational risk identification method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.

Those skilled in the art will appreciate that the architecture shown in fig. 9 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, a computer device is further provided, which includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above method embodiments when executing the computer program.

In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.

In an embodiment, a computer program product is provided, comprising a computer program which, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high-density embedded nonvolatile Memory, resistive Random Access Memory (ReRAM), Magnetic Random Access Memory (MRAM), Ferroelectric Random Access Memory (FRAM), Phase Change Memory (PCM), graphene Memory, and the like. Volatile Memory can include Random Access Memory (RAM), external cache Memory, and the like. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others. The databases referred to in various embodiments provided herein may include at least one of relational and non-relational databases. The non-relational database may include, but is not limited to, a block chain based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing based data processing logic devices, etc., without limitation.

The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims (10)

1. A power grid operation risk identification method is characterized by comprising the following steps:

acquiring current power grid risk information and a plurality of historical power grid risk information of a power grid; each historical power grid risk information has a corresponding risk label;

processing the current power grid risk information through a risk prediction model to obtain predicted power grid risk information;

respectively obtaining a first matching degree between each historical power grid risk information and the predicted power grid risk information, and determining screened power grid risk information of which the first matching degree meets a first preset condition from the plurality of historical power grid risk information;

and determining a risk identification result aiming at the power grid based on the risk label corresponding to the screened risk information.

2. The method according to claim 1, wherein the determining a risk identification result for the power grid based on the risk label corresponding to the screened risk information comprises:

under the condition that risk labels corresponding to historical power grid risk information included in the screened risk information are different from each other, respectively obtaining a second matching degree between each screened power grid risk information and the predicted power grid risk information;

determining target power grid risk information from the screened power grid risk information based on the first matching degree and the second matching degree;

and determining a risk identification result aiming at the power grid based on the risk label corresponding to the target power grid risk information.

3. The method of claim 2, wherein the separately obtaining a second degree of matching between each of the filtered grid risk information and the predicted grid risk information comprises:

respectively splicing the screened power grid risk information with the predicted power grid risk information to obtain a plurality of spliced power grid risk information;

and inputting the spliced power grid risk information into the trained matching model respectively to obtain a second matching degree between the screened power grid risk information and the predicted power grid risk information.

4. The method of claim 2, wherein determining target grid risk information from the screened grid risk information based on the first matching degree and the second matching degree comprises:

obtaining the product of the first matching degree and the second matching degree;

and determining screened power grid risk information with the largest product from the screened power grid risk information as target power grid risk information.

5. The method of claim 2, further comprising:

and under the condition that the first matching degrees between the historical power grid risk information and the predicted power grid risk information do not accord with a first preset condition, or the second matching degrees between the screened power grid risk information and the predicted power grid risk information do not accord with a second preset condition, inputting the predicted power grid risk information into a risk identification model to obtain a risk identification result of the power grid.

6. The method according to claim 1, wherein the determining a risk identification result for the power grid based on the risk label corresponding to the screened risk information further comprises:

and under the condition that the same risk label exists in the risk labels corresponding to the historical power grid risk information included in the screened risk information, determining a risk identification result of the power grid based on the same risk label.

7. An electrical grid operational risk identification apparatus, the apparatus comprising:

the acquisition module is used for acquiring current power grid risk information and a plurality of historical power grid risk information of a power grid; each historical power grid risk information has a corresponding risk label;

the prediction module is used for processing the current power grid risk information through a risk prediction model to obtain predicted power grid risk information;

the matching module is used for respectively obtaining first matching degrees between each historical power grid risk information and the predicted power grid risk information, and determining screened power grid risk information of which the first matching degrees accord with a first preset condition from the historical power grid risk information;

and the identification module is used for determining a risk identification result aiming at the power grid based on the risk label corresponding to the screened risk information.

8. Computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the grid operation risk identification method according to any of claims 1 to 6.

9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the grid operational risk identification method according to any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, realizes the steps of the grid operational risk identification method of any of claims 1 to 6.

Images