Smart power grid identification state monitoring method and system

Abstract

The invention relates to the technical field of smart power grids, and discloses a smart power grid identification state monitoring method and system, and the system comprises a data collection module, a data preprocessing module, a real-time operation state obtaining module, an identification state recognition module, an identification information risk analysis module, an early warning module, and a man-machine interaction module. The real-time operation state acquisition module, the identification state identification module and the identification information risk analysis module are arranged, so that the real-time operation state of the power grid can be acquired by constructing a convolutional neural network model; comparing the real-time operation state of the power grid with the state of the power grid identifier, judging the accuracy of the power grid identifier, monitoring the state of the smart power grid identifier to ensure the accuracy of the identifier so as to prevent the condition detection of the power grid from being influenced by an identifier error, carrying out risk monitoring on the power grid identifier information, and carrying out timely early warning on the identifier information with risks. Therefore, safety measures can be taken in a more targeted manner, and the operation safety of the smart power grid is improved.

Description

Technical Field

[0001] The present invention relates to the field of smart grid technology, and more specifically to a smart grid identification status monitoring method and system. Background Art

[0002] With the continuous growth of my country's energy demand, the safe and stable operation of the power grid system is of great significance to ensuring social development. In power grid enterprises, power grid identification is an important part of the power infrastructure, which is used to indicate the power grid status, line name, equipment voltage level, name, location, number, etc. When reorganizing power infrastructure equipment, it is necessary to change the equipment, name, location and number on the sign to prevent equipment identification errors. Equipment identification errors will cause the modules in the smart grid to fail to operate normally.

[0003] In a public document with publication number CN110492618A, a smart grid sign is disclosed, including a display module, a light intensity detection module, a wireless communication module and a central processing module respectively connected to the display module, the light intensity detection module and the wireless communication module; wherein the central processing module controls the display module to display the identification information received through the wireless communication module; after the power facilities are changed or modified, the information on the sign needs to be consistent with the modified drawings, and the identification information can be modified online in real time, which saves a lot of manpower and material resources, reduces the cost of making the sign, and improves the economic benefits of the power grid company.

[0004] Therefore, the accuracy of the identification information status is extremely important. How to accurately monitor the identification status of the smart grid has become an urgent problem to be solved. Therefore, it is necessary to monitor the identification status of the smart grid to ensure the accuracy of the identification after modification and prevent the identification status error from affecting the detection of abnormal conditions in the power grid. At the same time, there are certain risks in the identification information of the power grid. Monitoring the risks of the identification information of the power grid can enable more targeted safety measures and response strategies to be formulated. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, the present invention provides a smart grid identification status monitoring method and system to solve the problems existing in the above-mentioned background technology.

[0006] The present invention provides the following technical solution: a method for monitoring the status of a smart grid identification, comprising the following steps:

[0007] Step S01: Collecting grid operation data: Collecting historical grid operation data and real-time grid operation data through sensors, denoted as D = {D 1 ,D 2 ,D 3 …D n}, where Di is the operation data of the ith power grid;

[0008] Step S02: pre-processing the power grid operation data collected in step S01 to obtain power grid operation data that can be directly used;

[0009] Step S03: construct a convolutional neural network model to obtain the real-time operating status of the power grid;

[0010] Step S04: Compare the real-time operation status of the power grid with the identification status of the power grid. If they are inconsistent, execute step S06. If they are consistent, further distinguish the identification status. If the distinction result is a risk identification, continue to execute step S05. Otherwise, execute step S07.

[0011] Step S05: Perform risk analysis on the identification information of the power grid based on static safety analysis, obtain the identification risk coefficient, and make a judgment, and divide the risk level based on the judgment result. If the classification level is a low level, execute step S07, otherwise execute step S06;

[0012] Step S06: issuing an early warning for the power grid identification status, the early warning content including display status early warning and risk status early warning;

[0013] Step S07: Display the data in a human-computer interactive manner.

[0014] Preferably, the power grid operation data is power data during the operation of the power grid, including voltage, current, temperature and power consumption; the preprocessing includes cleaning, denoising, standardization and normalization of the power grid operation data to remove noise and abnormal values ​​in the data;

[0015] The display status warning warns of the accuracy of the power grid identification status display based on the data in step S04; the risk status warning warns of the risk status of the power grid identification based on the data in step S05.

[0016] Preferably, the specific method of preprocessing the power grid operation data in step S02 is:

[0017] De-noising: Use Gaussian filter G for denoising, the formula is: D i ′=G(D i ), where D i ′ is the denoised i-th power grid operation data;

[0018] Standardization processing: The formula is expressed as: Among them, D i ″ is the standardized i-th power grid operation data, μ i ′ is D i The mean of ′, σ i ′ is D i′ standard deviation;

[0019] Normalization processing: The formula is expressed as: Among them, D i ″′ is the normalized operation data of the ith power grid.

[0020] Preferably, the convolutional neural network model includes an output layer, two convolutional layers, two activation layers, two pooling layers, a fully connected layer and an output layer;

[0021] The input layer is used to convert the input data into a format suitable for processing by the convolutional neural network model;

[0022] The convolution layer is divided into convolution layer 1 and convolution layer 2. Convolution layer 1 mainly extracts primary features from input data, and convolution layer 2 extracts higher-level abstract features.

[0023] The activation layer is divided into activation layer 1 and activation layer 2, and the activation layers both use ReLu function;

[0024] The pooling layer is divided into pooling layer 1 and pooling layer 2. The pooling layer 1 enables the network to pay more attention to the key features in the power grid operation data, and the pooling layer 2 further reduces the spatial dimension of the features extracted by the convolution layer 2.

[0025] The fully connected layer is responsible for integrating all features extracted from the original data;

[0026] The output layer is used to output the operation status of the power grid; the operation status of the power grid includes normal operation status, warning status and emergency status.

[0027] Preferably, the convolutional layer 1 can be expressed by the formula: 1 =W 1 *X input +b 1 , where Z 1 is the output data of convolutional layer 1, W 1 is the weight matrix of the convolution kernel in convolution layer 1, * is the convolution operation, b 1 is the bias vector of convolutional layer 1;

[0028] The activation layer 1 processes the data of the convolution layer 1, and the formula is expressed as: A 1 =max(0,Z 1 ), where A 1 is the output data of activation layer 1;

[0029] The pooling layer 1 processes the output data of the activation layer 1, and the formula is expressed as: 1 =pool(A 1 ), where P 1is the output data of pooling layer 1, and pool(·) is the pooling function;

[0030] The convolutional layer 2 formula is expressed as: Z 2 =W 2 *P 1 +b 2 , where Z 2 is the output data of convolutional layer 2, W 2 is the weight matrix of the convolution kernel in convolution layer 2, b 2 is the bias vector of convolutional layer 2;

[0031] The activation layer 2 processes the data of the convolution layer 2, and the formula is expressed as: A 2 =max(0,Z 2 ), where A 2 is the output data of activation layer 2;

[0032] The pooling layer 2 processes the data of the activation layer 2, and the formula is expressed as: 2 =pool(A 2 ), where P 2 is the output data of pooling layer 2.

[0033] Preferably, the step S04 compares the real-time operating status of the power grid with the power grid identification status. If the real-time operating status of the power grid output in step S03 is consistent with the power grid identification status, the identification status is distinguished, and the distinction results include risk identification and non-risk identification. When the power grid identification status is a normal operating status, the distinction result is a non-risk identification, and when the power grid identification status is a warning status or an emergency status, the distinction result is a risk identification; if the distinction result is a risk identification, step S05 is executed, otherwise step S07 is executed; if the real-time operating status of the power grid output in step S03 is inconsistent with the power grid identification, an early warning is issued for the power grid identification status, and the early warning content at this time is a display status warning.

[0034] Preferably, obtaining the identification risk coefficient in step S05 includes the following steps:

[0035] Step S11: Calculate the risk allocation coefficient: Wherein, K is the risk allocation coefficient, J is the risk warning index, when the power grid identification state is the warning state, J value satisfies 60%≤J<85%, when the power grid identification state is the emergency state, J value satisfies J≥85%, Yu is the margin constant of information security inspection, and P is the startup probability of the power grid identification;

[0036] Step S12: Analyze the risk parameters using power flow calculation. The calculation formula of the risk parameters is expressed as: Among them, χ is the risk parameter, δ is the power loss of the power grid, Im is the current of the mth line, r m is the resistance of the mth line, M is the total number of grid lines;

[0037] Step S13: Calculate the identification risk factor: Among them, λ is the identification risk coefficient, D is the power grid operation data, q min is the minimum value of the grid embedding parameter.

[0038] A smart grid identification status monitoring system, comprising a data acquisition module, a data preprocessing module, a real-time operation status acquisition module, an identification status recognition module, an identification information risk analysis module, an early warning module and a human-computer interaction module;

[0039] The data acquisition module is used to collect power grid operation data and transmit it to the data preprocessing module;

[0040] The data preprocessing module is used to preprocess the data of the data acquisition module;

[0041] The real-time operation status acquisition module is used to acquire the real-time operation status of the power grid by constructing a convolutional neural network model;

[0042] The identification status recognition module is used to identify whether the real-time operation status of the power grid is consistent with the identification status of the power grid. If they are inconsistent, a display status warning instruction is sent to the warning module. If they are consistent, the identification status is further distinguished. If the distinction result is a risk identification, the data is transmitted to the identification information risk analysis module for further analysis. Otherwise, the data is directly transmitted to the human-computer interaction module for display;

[0043] The identification information risk analysis module performs risk analysis on the identification information of the power grid based on static safety analysis, obtains the identification risk coefficient, and makes a judgment, and divides the risk level based on the judgment result. If the classification level is a low level, the data is transmitted to the human-computer interaction module for display, otherwise, a risk status warning instruction is sent to the warning module;

[0044] The warning module is used to receive warning instructions and issue corresponding warnings;

[0045] The human-computer interaction module is used to perform human-computer interaction display on the data.

[0046] Technical effects and advantages of the present invention:

[0047] The present invention is provided with step S03, step S04 and step S05, which is conducive to obtaining the real-time operation status of the power grid by constructing a convolutional neural network model; comparing the real-time operation status of the power grid with the power grid identification status, judging the accuracy of the power grid identification, and further distinguishing the identification status on the premise of ensuring the accuracy of the power grid identification. If the distinction result is a risk identification, a risk analysis of the power grid identification information is performed based on static safety analysis to obtain the identification risk coefficient, and at the same time, a judgment is made, and a risk level is divided based on the judgment result. The smart grid identification status is monitored to ensure the accuracy of the identification to prevent the identification error from affecting the detection of the power grid condition. At the same time, the risk monitoring of the power grid identification information is performed, and timely warning is given to the identification information with risks, so that more targeted safety measures can be taken to improve the safety of the operation of the smart grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 This is a flow chart of the smart grid identification status monitoring method of the present invention.

[0049] Figure 2 This is a structural diagram of the smart grid identification status monitoring system of the present invention. DETAILED DESCRIPTION

[0050] The technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the present invention. In addition, the forms of the various structures recorded in the following embodiments are merely illustrative. The smart grid identification status monitoring method and system involved in the present invention are not limited to the various structures recorded in the following embodiments. All other implementations obtained by ordinary technicians in this field without making creative work belong to the scope of protection of the present invention.

[0051] like Figure 1 As shown, the present invention provides a method for monitoring the status of a smart grid identification, comprising the following steps:

[0052] Step S01: Collecting grid operation data: Collecting historical grid operation data and real-time grid operation data through sensors, denoted as D = {D 1 ,D 2 ,D 3 …D n}, where Di is the i-th grid operation data; the grid operation data is the power data during the grid operation process, including but not limited to voltage, current, temperature and power consumption; illustratively, if the voltage data is the first grid operation data, then D 1 Indicates the voltage data in the power grid operation data;

[0053] Step S02: pre-processing the power grid operation data collected in step S01 to obtain power grid operation data that can be directly used; the pre-processing includes cleaning, denoising, standardization and normalization of the power grid operation data to remove noise and abnormal values ​​in the data;

[0054] Step S03: construct a convolutional neural network model to obtain the real-time operation status of the power grid; the convolutional neural network model can learn the operation mode of the power grid from historical and real-time power grid operation data, provide accurate feedback when abnormal events occur, and monitor the operation status of the power grid in real time;

[0055] Step S04: Compare the real-time operation status of the power grid with the identification status of the power grid. If they are inconsistent, execute step S06. If they are consistent, further distinguish the identification status. If the distinction result is a risk identification, continue to execute step S05. Otherwise, execute step S07.

[0056] Step S05: Perform risk analysis on the identification information of the power grid based on static safety analysis, obtain the identification risk coefficient, and make a judgment, and divide the risk level based on the judgment result. If the classification level is low, execute step S07, otherwise execute step S06; analyzing the risk of the identification information of the power grid can more comprehensively monitor the security of the power grid system and improve the perception and management capabilities of potential risks;

[0057] Step S06: Early warning of the power grid identification status, the early warning content includes display status early warning and risk status early warning; the display status early warning is based on the data in step S04 to early warning the accuracy of the power grid identification status display, and can timely detect and correct the wrong identification status to ensure its accuracy; the risk status early warning is based on the data in step S05 to early warning the risk status of the power grid identification, and can timely formulate and take safety measures and response strategies, thereby ensuring the safe operation of the power grid;

[0058] Step S07: Display the data in a human-computer interactive manner.

[0059] In this embodiment, it should be specifically explained that the specific method of preprocessing the power grid operation data in step S02 is:

[0060] De-noising: Apply a filter or denoising algorithm to reduce the noise in the data. Use a Gaussian filter G for denoising. The formula is: D i ′=G(D i ), where D i ′ is the denoised i-th power grid operation data;

[0061] Standardization: convert the data into a form with zero mean and unit variance. The formula is: Among them, D i ″ is the standardized i-th power grid operation data, μ i ′ is D i The mean of ′, σ i ′ is D i ′ standard deviation;

[0062] Normalize the data to the range of [0, 1] using the formula: Among them, D i ″′ is the normalized operation data of the ith power grid;

[0063] Through the above preprocessing operations, the quality and consistency of the data are ensured, laying the foundation for the subsequent convolutional neural network model to recognize the data.

[0064] In this embodiment, it should be specifically stated that the convolutional neural network model includes an output layer, two convolutional layers, two activation layers, two pooling layers, a fully connected layer and an output layer;

[0065] The input layer is used to convert the input data into a format suitable for processing by the convolutional neural network model;

[0066] The convolution layer is divided into convolution layer 1 and convolution layer 2. Convolution layer 1 mainly extracts primary features from the input data, and convolution layer 2 extracts higher-level abstract features from the features extracted by the previous layer, which helps to reduce computational complexity and enhance the generalization ability of the model.

[0067] The activation layer is divided into activation layer 1 and activation layer 2, and the activation layers both use the ReLu function; the ReLu function enables the network to enhance the ability to learn complex functions while keeping the calculation simple by setting all negative values ​​to zero;

[0068] The pooling layer is divided into pooling layer 1 and pooling layer 2. The pooling layer 1 enables the network to pay more attention to the key features in the power grid operation data, thereby more effectively capturing the key indicators of the power grid status; the pooling layer 2 further reduces the spatial dimension of the features extracted by the convolution layer 2, which helps to reduce the computational complexity and enhance the generalization ability of the model;

[0069] The fully connected layer is responsible for integrating all features extracted from the raw data to form a comprehensive understanding of the current state of the power grid;

[0070] The output layer is used to output the operation status of the power grid; the power grid operation status includes normal operation status, warning status and emergency status;

[0071] The historical power grid operation data is divided into a training set and a validation set. In this embodiment, 80% of the data is selected as the training set and 20% of the data is selected as the validation set to train the convolutional neural network model. The real-time power grid operation data is input into the trained convolutional neural network model to output the real-time operation status of the power grid.

[0072] In this embodiment, it should be specifically explained that the convolution layer 1 can be expressed by the formula: 1 =W 1 *X input +b 1 , where Z 1 is the output data of convolutional layer 1, W 1 is the weight matrix of the convolution kernel in convolution layer 1, * is the convolution operation, b 1 is the bias vector of convolution layer 1; the convolution operation extracts features by sliding the convolution kernel on the input data and calculating the dot product;

[0073] The activation layer 1 processes the data of the convolution layer 1, and the formula is expressed as: A 1 =max(0,Z 1 ), where A 1 is the output data of activation layer 1;

[0074] The pooling layer 1 processes the output data of the activation layer 1, and the formula is expressed as: 1 =pool(A 1 ), where P 1 is the output data of pooling layer 1, pool(·) is the pooling function, which can be either maximum pooling or average pooling;

[0075] The convolutional layer 2 extracts higher-level abstract features from the extracted features, and the formula is expressed as: Z 2 =W 2 *P 1 +b 2 , where Z 2 is the output data of convolutional layer 2, W 2 is the weight matrix of the convolution kernel in convolution layer 2, b 2 is the bias vector of convolutional layer 2;

[0076] The activation layer 2 processes the data of the convolution layer 2, and the formula is expressed as: A 2 =max(0,Z 2 ), where A 2 is the output data of activation layer 2;

[0077] The pooling layer 2 processes the data of the activation layer 2, and the formula is expressed as: 2 =pool(A 2), where P 2 is the output data of pooling layer 2;

[0078] Through convolution, activation, and pooling operations, the convolutional neural network model can gradually extract and simplify the key features in the power grid operation data.

[0079] In this embodiment, it should be specifically explained that step S04 compares the real-time operation status of the power grid with the identification status of the power grid. If the real-time operation status of the power grid output in step S03 is consistent with the identification status of the power grid, the identification status is distinguished, and the distinction results include risk identification and non-risk identification. When the identification status of the power grid is in normal operation, the distinction result is non-risk identification, and when the identification status of the power grid is in an alert state or an emergency state, the distinction result is a risk identification; if the distinction result is a risk identification, step S05 is executed, otherwise step S07 is executed; if the identification status of the power grid is in an alert state or an emergency state, it means that there is an abnormal situation in the operation of the power grid at this time, and the network security protection is reduced and the risk is increased. Therefore, the risk of the power grid identification information is further analyzed to monitor the security of the power grid identification information; if the real-time operation status of the power grid output in step S03 is inconsistent with the power grid identification, the power grid identification status is warned, indicating that the power grid identification status may be wrong. At this time, the warning content is a display status warning, and the power grid identification status needs to be detected to ensure the accuracy of the identification;

[0080] The warning state indicates that the grid voltage, frequency, etc. are within the specified range, but the security of the grid operation system is greatly reduced, and the ability to resist external disturbances is weakened. At this time, if a disturbance occurs or the load increases to a certain extent, the voltage and frequency deviations will exceed the specified range, and the equipment will be overloaded, making the system unable to operate safely; the emergency state indicates that the load of certain lines or other components in the system exceeds the limit value, the system voltage and frequency exceed or fall below the allowable value, and the grid system cannot operate normally at this time.

[0081] In this embodiment, it should be specifically explained that obtaining the identification risk coefficient in step S05 includes the following steps:

[0082] Step S11: Calculate the risk allocation coefficient: Wherein, K is the risk allocation coefficient. Different grid identification states have different risk states. The risk allocation coefficient allocates different risk metrics to different grid identification states, thereby improving the accuracy of the identification risk coefficient; J is the risk alert index. When the grid identification state is the alert state, the value of J satisfies 60%≤J<85%. When the grid identification state is the emergency state, the value of J satisfies J≥85%. The specific value of J can be set by technical personnel in the field based on different grid identification states. This embodiment does not specifically limit the specific value; Yu is the margin constant of the information security inspection, and P is the startup probability of the grid identification. In this embodiment, P=1 is preferably selected;

[0083] Step S12: Analyze the risk parameters using power flow calculation. Power flow calculation can obtain the voltage and power information of each node in the system by solving the equations of network topology and power equipment parameters. Compared with the simple traditional analysis method, power flow calculation is more accurate and can provide accurate power information under complex network topology. The calculation formula of the risk parameter is expressed as: Among them, χ is the risk parameter, δ is the power loss of the power grid, I m is the current of the mth line, r m is the resistance of the mth line, M is the total number of grid lines;

[0084] Step S13: Calculate the identification risk factor: Among them, λ is the identification risk coefficient, D is the power grid operation data, q min is the minimum value of the grid embedding parameter.

[0085] In this embodiment, it should be specifically explained that the specific method of determining the identification risk coefficient in step S05 is:

[0086] If the identification risk coefficient satisfies λ≤LE1, the judgment result is low risk, and the risk level is classified as low level; if the identification risk coefficient satisfies LE1<λ≤LE2, the judgment result is medium risk, and the risk level is classified as medium level; if the identification risk coefficient satisfies λ>LE2, the judgment result is high risk, and the risk level is classified as high level; LE1 is the first threshold value, LE2 is the second threshold value, satisfying LE1≤30%, LE2≥80%, the specific values ​​of LE1 and LI2 can be set by technical personnel in this field, and this embodiment does not specifically limit the specific values ​​of LE1 and LI2.

[0087] like Figure 2 As shown, the present invention provides a smart grid identification status monitoring system, including a data acquisition module, a data preprocessing module, a real-time operation status acquisition module, an identification status recognition module, an identification information risk analysis module, an early warning module and a human-computer interaction module;

[0088] The data acquisition module is used to collect power grid operation data and transmit it to the data preprocessing module;

[0089] The data preprocessing module is used to preprocess the data of the data acquisition module;

[0090] The real-time operation status acquisition module is used to acquire the real-time operation status of the power grid by constructing a convolutional neural network model;

[0091] The identification status recognition module is used to identify whether the real-time operation status of the power grid is consistent with the identification status of the power grid. If they are inconsistent, a display status warning instruction is sent to the warning module. If they are consistent, the identification status is further distinguished. If the distinction result is a risk identification, the data is transmitted to the identification information risk analysis module for further analysis. Otherwise, the data is directly transmitted to the human-computer interaction module for display;

[0092] The identification information risk analysis module performs risk analysis on the identification information of the power grid based on static safety analysis, obtains the identification risk coefficient, and makes a judgment, and divides the risk level based on the judgment result. If the classification level is a low level, the data is transmitted to the human-computer interaction module for display, otherwise, a risk status warning instruction is sent to the warning module;

[0093] The warning module is used to receive warning instructions and issue corresponding warnings;

[0094] The human-computer interaction module is used to perform human-computer interaction display on the data.

[0095] In this embodiment, it should be specifically explained that the difference between this embodiment and the prior art lies mainly in that this embodiment has a real-time operation status acquisition module, an identification status recognition module and an identification information risk analysis module, which is conducive to obtaining the real-time operation status of the power grid by constructing a convolutional neural network model; comparing the real-time operation status of the power grid with the identification status of the power grid, judging the accuracy of the power grid identification, and further distinguishing the identification status on the premise of ensuring the accuracy of the power grid identification. If the distinction result is a risk identification, a risk analysis of the power grid identification information is performed based on static safety analysis to obtain the identification risk coefficient, and at the same time, a judgment is made, and a risk level is divided based on the judgment result, and the identification status of the smart grid is monitored to ensure the accuracy of the identification, so as to prevent the identification error from affecting the detection of the power grid condition. At the same time, the risk monitoring of the power grid identification information is performed, and timely warning is given to the identification information with risks, so that more targeted safety measures can be taken to improve the safety of smart grid operation.

[0096] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0097] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for monitoring the status of a smart grid identification, characterized in that: The following steps are involved: Step S01: Collecting grid operation data: Collecting historical grid operation data and real-time grid operation data through sensors, denoted as D = {D1, D2, D3 ... D n }, where Di is the operation data of the ith power grid; Step S02: pre-processing the power grid operation data collected in step S01 to obtain power grid operation data that can be directly used; Step S03: construct a convolutional neural network model to obtain the real-time operating status of the power grid; Step S04: Compare the real-time operation status of the power grid with the identification status of the power grid. If they are inconsistent, execute step S06. If they are consistent, further distinguish the identification status. If the distinction result is a risk identification, continue to execute step S05. Otherwise, execute step S07. Step S05: Perform risk analysis on the identification information of the power grid based on static safety analysis, obtain the identification risk coefficient, and make a judgment, and divide the risk level based on the judgment result. If the classification level is a low level, execute step S07, otherwise execute step S06; Step S06: issuing an early warning for the power grid identification status, the early warning content including display status early warning and risk status early warning; Step S07: Display the data in a human-computer interactive manner.

2. A smart grid identification status monitoring method according to claim 1, characterized in that: The grid operation data is the power data during the grid operation process, including voltage, current, temperature and power consumption; the preprocessing includes cleaning, denoising, standardization and normalization of the grid operation data to remove noise and abnormal values ​​in the data; The display status warning is based on the data in step S04 to warn the accuracy of the power grid identification status display; The risk status warning is based on the data in step S05 to warn the risk status of the power grid identification.

3. A smart grid identification status monitoring method according to claim 1, characterized in that: The specific method of preprocessing the power grid operation data in step S02 is: De-noising: Use Gaussian filter G for denoising, the formula is: D i ′=G(D i ), where D i ′ is the denoised i-th power grid operation data; Standardization processing: The formula is expressed as: Among them, D i ″ is the standardized i-th power grid operation data, μ i ′ is D i The mean of ′, σ i ′ is D i ′ standard deviation; Normalization processing: The formula is expressed as: Among them, D i ″′ is the normalized operation data of the ith power grid.

4. A smart grid identification status monitoring method according to claim 1, characterized in that: The convolutional neural network model includes an output layer, two convolutional layers, two activation layers, two pooling layers, a fully connected layer and an output layer; The input layer is used to convert the input data into a format suitable for processing by the convolutional neural network model; The convolution layer is divided into convolution layer 1 and convolution layer 2. Convolution layer 1 mainly extracts primary features from input data, and convolution layer 2 extracts higher-level abstract features. The activation layer is divided into activation layer 1 and activation layer 2, and the activation layers both use ReLu function; The pooling layer is divided into pooling layer 1 and pooling layer 2. The pooling layer 1 enables the network to pay more attention to the key features in the power grid operation data, and the pooling layer 2 further reduces the spatial dimension of the features extracted by the convolution layer 2. The fully connected layer is responsible for integrating all features extracted from the original data; The output layer is used to output the operation status of the power grid; the operation status of the power grid includes normal operation status, warning status and emergency status.

5. A smart grid identification status monitoring method according to claim 4, characterized in that: The convolutional layer 1 can be expressed by the formula: Z1 = W1*X input +b1, where Z1 is the output data of convolution layer 1, W1 is the weight matrix of the convolution kernel in convolution layer 1, * is the convolution operation, and b1 is the bias vector of convolution layer 1; The activation layer 1 processes the data of the convolution layer 1, and the formula is expressed as: A1=max(0,Z1), where A1 is the output data of the activation layer 1; The pooling layer 1 processes the output data of the activation layer 1, and the formula is expressed as: P1=pool(A1), where P1 is the output data of the pooling layer 1, and pool(·) is the pooling function; The formula of the convolution layer 2 is expressed as: Z2=W2*P1+b2, where Z2 is the output data of the convolution layer 2, W2 is the weight matrix of the convolution kernel in the convolution layer 2, and b2 is the bias vector of the convolution layer 2; The activation layer 2 processes the data of the convolution layer 2, and the formula is expressed as: A2=max(0,Z2), where A2 is the output data of the activation layer 2; The pooling layer 2 processes the data of the activation layer 2, and the formula is expressed as: P2=pool(A2), where P2 is the output data of the pooling layer 2.

6. A smart grid identification status monitoring method according to claim 1, characterized in that: The step S04 compares the real-time operation state of the power grid with the identification state of the power grid. If the real-time operation state of the power grid output in step S03 is consistent with the identification state of the power grid, the identification state is distinguished, and the distinction result includes two types: risk identification and non-risk identification. When the identification state of the power grid is a normal operation state, the distinction result is a non-risk identification, and when the identification state of the power grid is a warning state or an emergency state, the distinction result is a risk identification; if the distinction result is a risk identification, step S05 is executed, otherwise step S07 is executed; If the real-time operation status of the power grid output in step S03 is inconsistent with the power grid identification, an early warning is issued for the power grid identification status, and the early warning content is a display status early warning.

7. A smart grid identification status monitoring method according to claim 1, characterized in that: The step S05 of obtaining the identified risk coefficient includes the following steps: Step S11: Calculate the risk allocation coefficient: Wherein, K is the risk allocation coefficient, J is the risk warning index, when the power grid identification state is the warning state, J value satisfies 60%≤J<85%, when the power grid identification state is the emergency state, J value satisfies J≥85%, Yu is the margin constant of information security inspection, and P is the startup probability of the power grid identification; Step S12: Analyze the risk parameters using power flow calculation. The calculation formula of the risk parameters is expressed as: Among them, χ is the risk parameter, δ is the power loss of the power grid, I m is the current of the mth line, r m is the resistance of the mth line, M is the total number of grid lines; Step S13: Calculate the identification risk coefficient: Among them, λ is the identification risk coefficient, D is the power grid operation data, q min is the minimum value of the grid embedding parameter.

8. A smart grid identification status monitoring system, used to implement a smart grid identification status monitoring method according to any one of claims 1 to 7, characterized in that: It includes data acquisition module, data preprocessing module, real-time operation status acquisition module, identification status recognition module, identification information risk analysis module, early warning module and human-computer interaction module; The data acquisition module is used to collect power grid operation data and transmit it to the data preprocessing module; The data preprocessing module is used to preprocess the data of the data acquisition module; The real-time operation status acquisition module is used to acquire the real-time operation status of the power grid by constructing a convolutional neural network model; The identification status recognition module is used to identify whether the real-time operation status of the power grid is consistent with the identification status of the power grid. If they are inconsistent, a display status warning instruction is sent to the warning module. If they are consistent, the identification status is further distinguished. If the distinction result is a risk identification, the data is transmitted to the identification information risk analysis module for further analysis. Otherwise, the data is directly transmitted to the human-computer interaction module for display; The identification information risk analysis module performs risk analysis on the identification information of the power grid based on static safety analysis, obtains the identification risk coefficient, and makes a judgment, and divides the risk level based on the judgment result. If the classification level is a low level, the data is transmitted to the human-computer interaction module for display, otherwise, a risk status warning instruction is sent to the warning module; The warning module is used to receive warning instructions and issue corresponding warnings; The human-computer interaction module is used to perform human-computer interaction display on the data.

Images