A method, device, equipment and medium for determining power grid situation risk level

Abstract

The present invention discloses a method, device, equipment and medium for determining the risk level of a power grid situation. The method comprises: obtaining a power grid situation data set of a power grid to be tested; generating a fuzzy relationship matrix corresponding to the power grid situation data set based on similarity factors between two power grid situation data, and calculating a transitive closure matrix corresponding to the fuzzy relationship matrix; inputting each column of the transitive closure matrix into a pre-trained situation awareness model to obtain risk level description data corresponding to each power grid situation data; and determining the power grid situation risk level corresponding to each power grid situation data based on the risk level description data. The present invention solves the problem of difficulty in predicting power grid situation and determining power grid situation risk level, realizes accurate prediction of power grid situation risk level, and effectively avoids accidents caused by excessively high risk level in the power grid.

Description

Technical Field

[0001] The present invention relates to the field of power grid technology, and in particular to a method, device, equipment and medium for determining a power grid situation risk level. Background Art

[0002] The growing demand for electricity has become a key focus of power grid operation and control. A key challenge facing power companies is a secure and reliable power supply. Even minor disruptions can cause system outages. With the integration of the Internet of Things (IoT) into power information networks and the increasing complexity of services, traditional power security technologies are no longer adequate, necessitating strengthened monitoring and control. Furthermore, threats to power information networks are typically not single, fixed, but rather dynamically evolving, further complicating security monitoring. Applying situational awareness to power information networks—using security equipment to collect and extract raw network data and perform situational awareness—can provide a basis for secure monitoring of power information networks.

[0003] The increasing complexity and uncertainty of power grids have made it more difficult to assess and predict grid conditions, and to determine their levels. To better prevent grid accidents, it is necessary to more accurately determine grid risk levels, which is crucial for predicting grid conditions. Summary of the Invention

[0004] The present invention provides a method, device, equipment and medium for determining the risk level of a power grid situation, which solves the problems of difficulty in predicting the power grid situation and determining the power grid situation level, so as to accurately predict the power grid situation risk level.

[0005] In a first aspect, the present invention provides a method for determining a power grid situation risk level, comprising:

[0006] Obtaining a power grid status data set of the power grid to be tested, wherein the power grid status data set includes multiple power grid status data, each power grid status data is collected under different collection time parameters, and each power grid status data includes collection parameters of multiple dimensions;

[0007] Generate a fuzzy relationship matrix corresponding to the power grid status data set according to the similarity factor between the two power grid status data, and calculate the transitive closure matrix corresponding to the fuzzy relationship matrix;

[0008] Wherein, each data column in the transitive closure matrix is ​​used to describe the transitive relationship between each power grid status data and other power grid status data;

[0009] Inputting each column of the transitive closure matrix into a pre-trained situation awareness model to obtain risk level description data corresponding to each piece of power grid situation data;

[0010] The power grid situation risk level corresponding to each piece of power grid situation data is determined according to the risk level description data.

[0011] In a second aspect, the present invention further provides a device for determining a power grid situation risk level, the device comprising:

[0012] The power grid situation data set acquisition module is used to obtain the power grid situation data set of the power grid to be tested. The power grid situation data set contains multiple power grid situation data. Each power grid situation data is collected under different collection time parameters. Each power grid situation data includes collection parameters of multiple dimensions.

[0013] A transitive closure matrix calculation module is used to generate a fuzzy relationship matrix corresponding to the power grid situation data set based on the similarity factor between the two power grid situation data, and calculate the transitive closure matrix corresponding to the fuzzy relationship matrix;

[0014] Wherein, each data column in the transitive closure matrix is ​​used to describe the transitive relationship between each power grid status data and other power grid status data;

[0015] A risk level description data acquisition module is used to input each column of the transitive closure matrix into a pre-trained situation awareness model to obtain risk level description data corresponding to each power grid situation data;

[0016] The power grid situation risk level determination module is used to determine the power grid situation risk level corresponding to each power grid situation data according to the risk level description data.

[0017] In a third aspect, the present invention also provides a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for determining the grid situation risk level as described in any embodiment of the present invention is implemented.

[0018] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the method for determining the power grid situation risk level as described in any embodiment of the present invention is implemented.

[0019] The technical solution provided by the present invention obtains a grid situation data set of the power grid to be tested; generates a fuzzy relationship matrix corresponding to the grid situation data set based on the similarity factors between each pair of grid situation data, and calculates a transitive closure matrix corresponding to the fuzzy relationship matrix; inputs each column of the transitive closure matrix into a pre-trained situation awareness model to obtain risk level description data corresponding to each piece of grid situation data; and determines the grid situation risk level corresponding to each piece of grid situation data based on the risk level description data. The present invention solves the problems of difficulty in predicting grid situation and determining grid situation level, achieves accurate prediction of grid situation risk level, and effectively avoids accidents caused by excessively high risk levels in the grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A flowchart of a method for determining a power grid situation risk level provided in the first embodiment of the present invention;

[0021] Figure 2 A flowchart of another method for determining a power grid situation risk level provided in the second embodiment of the present invention;

[0022] Figure 3 This is a schematic diagram of the structure of a device for determining a power grid situation risk level provided by a third embodiment of the present invention;

[0023] Figure 4 This is a structural diagram of a computer device provided in Example 4 of the present invention. DETAILED DESCRIPTION

[0024] The present invention will be further described in detail below with reference to the accompanying drawings and examples. It will be understood that the specific embodiments described herein are intended only to illustrate the present invention and are not intended to limit the present invention. It should also be noted that, for ease of description, the accompanying drawings only illustrate portions relevant to the present invention, not all structures.

[0025] Example 1

[0026] Figure 1 This is a flowchart of a method for determining a power grid situation risk level, provided in Example 1 of the present invention. This embodiment is applicable to situations involving power grid situation prediction and power grid situation level determination. The method of this embodiment can be performed by a power grid situation risk level determination device, which can be implemented via software and / or hardware and configured in a server or terminal device.

[0027] Accordingly, the method specifically includes the following steps:

[0028] S110: Obtain a power grid status data set of the power grid to be tested.

[0029] The power grid status data set includes multiple power grid status data. Each power grid status data is collected under different collection time parameters. Each power grid status data includes collection parameters of multiple dimensions.

[0030] The power grid status data set may be a data set consisting of status data of the power grid at different times. The power grid status data set includes multiple power grid status data, and each power grid status data is multi-dimensional and includes different acquisition parameters.

[0031] For example, it is assumed that the acquired grid status data set of the power grid to be tested includes N grid status data, which is represented by M={m1,m2,m3,…,m N}; Each power grid status data can be set to K dimensions, which is expressed as m i ={m i1 ,m i2 ,m i3 ,…,m iK}(i=1,2,…,N), each dimension represents an acquisition parameter.

[0032] S120 , generating a fuzzy relation matrix corresponding to the power grid status data set according to similarity factors between pairwise power grid status data, and calculating a transitive closure matrix corresponding to the fuzzy relation matrix.

[0033] Wherein, each data column in the closure matrix is ​​used to describe the transmission relationship between each power grid status data and other power grid status data.

[0034] The similarity factor can be a similarity value calculated based on two pieces of grid status data. The fuzzy relationship matrix can be a relationship matrix constructed based on multiple calculated similarity factors. The transitive closure matrix can represent a transitive relationship, that is, a transitive relationship reflecting the similarity between each piece of grid status data.

[0035] Optionally, based on the similarity factors between pairwise power grid status data, a fuzzy relationship matrix corresponding to the power grid status data set is generated, including: constructing an N-order matrix based on the number N of power grid status data included in the power grid status data set; filling the similarity factors between pairwise power grid status data into the N-order matrix to form the fuzzy relationship matrix; wherein the matrix element in the i-th row and j-th column of the N-order matrix is ​​the similarity factor between the i-th power grid status data and the j-th power grid status data.

[0036] For example, it is assumed that the acquired grid status data set of the power grid to be tested includes N grid status data, which is represented by M={m1,m2,m3,…,m N}; where m i ={m i1 ,mi2 , m i3 , …, m iK}(i = 1, 2, …, N). Assume the similarity factor between m1 and m2 is represented by x 12 . Therefore, N * N similarity factors can be obtained. Thus, by filling the similarity factors between pairwise grid situation data into an N-order matrix, a fuzzy relation matrix can be obtained as

[0037] Optionally, calculating the transitive closure matrix corresponding to the fuzzy relation matrix includes: According to the convolution calculation formula of the fuzzy relation matrix When k = 1, judge whether it satisfies X 2k = X k . If so, the transitive closure matrix of the to-be-detected situation data is obtained as X k ; if not, k is incremented by 1, and return to judge whether it satisfies X 2k = X k until it is satisfied and the transitive closure matrix of the to-be-detected situation data is determined.

[0038] Among them, the convolution calculation can be called the convolution calculation.

[0039] Specifically, when k = 1, according to the formula it can be determined as judge whether there is X 2 = X. If X 2 ≠ X, then k is incremented by 1, that is, k = 2. Continue to calculate to get judge whether there is X 4 = X 2 . If X 4 ≠ X 2 , then k is incremented by 1, that is, k = 3. And so on, it can continue to judge until k = N + 1, then the judgment ends.

[0040] Furthermore, assume that when k = m (m < N + 1), it satisfies X 2m = X m , then X m is the transitive closure matrix of the to-be-detected situation data.

[0041] The advantage of such a setting is that: by calculating the similarity factors between pairwise grid situation data to obtain a fuzzy relation matrix, and obtaining the transitive closure matrix according to the fuzzy relation matrix, the transitive closure matrix can more accurately reflect the similarity factors of pairwise grid situation data in different dimensions.

[0042] S130. Input each column data of the transitive closure matrix into a pre-trained situation awareness model respectively, and obtain the risk level description data corresponding to each grid situation data respectively.

[0043] The situational awareness model can derive corresponding risk level description data based on the input transitive closure matrix data, and perform situational awareness on the input data. The risk level description data can be data describing the risk level. Generally, the risk level description data is between 0 and 1, with different values ​​corresponding to different risk levels.

[0044] S140 . Determine, based on the risk level description data, the power grid situation risk level corresponding to each piece of power grid situation data.

[0045] The grid situation risk level may be a risk level describing grid situation data. Generally speaking, the grid situation risk level may include normal state, subnormal state, abnormal state, and alarm state.

[0046] Optionally, based on the risk level description data, the power grid situation risk level corresponding to each power grid situation data is determined, including: when the risk level description data is greater than or equal to 0 and less than 0.5, the output power grid situation risk level is normal; when the risk level description data is greater than or equal to 0.5 and less than 0.65, the output power grid situation risk level is sub-normal; when the risk level description data is greater than or equal to 0.65 and less than 0.80, the output power grid situation risk level is abnormal; when the risk level description data is greater than or equal to 0.80 and less than 1, the output power grid situation risk level is an alarm.

[0047] For example, assuming that the corresponding risk level description data obtained from the input closure matrix data is 0.25, it can be determined that the output power grid situation risk level is normal; assuming that the risk level description data is 0.51, it can be determined that the output power grid situation risk level is sub-normal; assuming that the risk level description data is 0.7, it can be determined that the output power grid situation risk level is abnormal; assuming that the risk level description data is 0.9, it can be determined that the output power grid situation risk level is an alarm state.

[0048] The benefit of this setup is that it uses risk level description data to determine whether the power grid's risk level is normal, subnormal, abnormal, or alarm. This allows for more accurate feedback to relevant personnel for action, effectively preventing accidents caused by excessively high risk levels.

[0049] The technical solution provided by the embodiment of the present invention obtains a grid situation data set of the power grid to be tested; generates a fuzzy relationship matrix corresponding to the grid situation data set based on the similarity factors between the two grid situation data, and calculates the transitive closure matrix corresponding to the fuzzy relationship matrix; inputs each column of the transitive closure matrix into a pre-trained situation awareness model to obtain the risk level description data corresponding to each grid situation data; and determines the grid situation risk level corresponding to each grid situation data based on the risk level description data. The embodiment of the present invention solves the problem of difficulty in predicting the grid situation and determining the grid situation level, realizes accurate prediction of the grid situation risk level, and effectively avoids accidents caused by excessively high risk levels in the grid.

[0050] Optionally, before inputting each column of data of the closure matrix into a pre-trained situational awareness model, the method further includes: obtaining a training sample data set; wherein each piece of training sample data includes a transitive closure matrix sample corresponding to the grid situation data set of a set grid, and a risk level description data label value corresponding to each data column in the transitive closure matrix sample; inputting each data column in each transitive closure matrix sample into the neural network model to be trained; and adjusting the parameters of each node in the neural network model according to the error value between the risk level description data output value of the neural network model and the matched risk level description data label value, so as to train and obtain the situational awareness model.

[0051] The training sample dataset may be a dataset comprising multiple training sample data. The transitive closure matrix sample may be a sample of a transitive closure matrix stored in a sample library. The risk level description data label value may be any number between 0 and 1, reflecting the size of the current transitive closure matrix sample data. The risk level description data output value may be the data output value obtained after the transitive closure matrix sample is input into the neural network model.

[0052] Neural network models can be complex network models formed by extensively interconnecting a large number of simple processing units. Neural networks possess large-scale parallelism, distributed storage and processing, self-organization, self-adaptation, and self-learning capabilities, making them particularly well-suited for handling imprecise and ambiguous information processing problems that require simultaneous consideration of numerous factors and conditions. Specifically, by inputting each data column from each transitive closure matrix sample into the neural network model, the corresponding risk level descriptive data output value can be obtained.

[0053] For example, the initialization weight t of each situation sample data is obtained according to the formula Input each situation sample data u into the situation awareness model to be trained, and obtain the risk level description data output value y, where s is the bias, is the activation function.

[0054] Furthermore, according to the formula Calculate the difference between the risk level description data output value of the neural network model and the matching risk level description data label value, as well as the situation sample output value of the current network node, where d is the risk level description data label value, e is the difference, is the derivative of the activation function. Then, according to the formula Calculate the situation sample output value of the adjacent nodes associated with the current network node until the situation sample output value of all adjacent nodes associated with the current network node is calculated; where D T is the transpose of the initialization weight matrix of each situation sample data, k is the number of network nodes, θ k Output value for the situation sample of the adjacent node.

[0055] Accordingly, according to the formula Adjust the weight value, where p kj is the weight value, q is the learning rate, f j is the actual output data of the situation sample of input node j;

[0056] Finally, you need to return to execute according to the formula Calculate the difference between the risk level description data output value of the neural network model and the matching risk level description data label value, as well as the situation sample output value of the current network node, until the weight value is equal to 0, and the situation awareness model is trained.

[0057] The advantage of this setting is that by adjusting the parameters of the neural network model, a trained situational awareness model is obtained, so that after inputting each column of data in the transfer closure matrix, more accurate risk level description data can be obtained, which can more accurately predict the power grid situation risk level.

[0058] Example 2

[0059] Figure 2 This is a flow chart of a method for determining the risk level of a power grid situation provided by the second embodiment of the present invention. Based on the above embodiments, this embodiment further optimizes the generation of a fuzzy relationship matrix corresponding to the power grid situation data set based on the similarity factor between the two power grid situation data. Figure 2 , the method specifically comprises the following steps:

[0060] S210: Obtain a power grid status data set of the power grid to be tested.

[0061] S220 , obtaining the first power grid status data and the second power grid status data currently being processed.

[0062] The first power grid status data may be a power grid status data in the power grid status data set. The second power grid status data may be a power grid status data in the power grid status data set, and may be the same as or different from the first power grid status data.

[0063] S230: If the first power grid situation data and the second power grid situation data are different pieces of data, multiply the acquisition parameters of the same dimension in the first power grid situation data and the second power grid situation data to obtain an acquisition parameter similarity index corresponding to each dimension.

[0064] The acquisition parameter similarity index may be an index describing the acquisition parameters of the same dimension in the first power grid status data and the second power grid status data. For example, assuming that the first power grid status data is m1 and the second power grid status data is m2, the acquisition parameter similarity index is m1*m2.

[0065] S240 , cumulatively summing the similarity indexes of the acquisition parameters of each dimension in the first power grid status data and the second power grid status data to obtain a current sum value.

[0066] Specifically, assuming that the obtained grid status data set of the power grid to be tested includes N grid status data, each grid status data can be set to K dimensions. The similarity index of the collected parameters of each dimension calculated can be summed up to obtain the current sum value

[0067] S250 , normalize the current sum value to obtain a similarity factor between the first power grid status data and the second power grid status data.

[0068] The normalization process may be to perform weighted processing on the calculated current sum value to obtain a similarity factor.

[0069] Optionally, the current sum value is normalized, including: obtaining the maximum sum value obtained by accumulating and summing the similarity indexes of the acquisition parameters of each dimension in the pairwise power grid status data; dividing the current sum value by the ratio of the maximum sum value as the normalization result of the current sum value.

[0070] According to the formula The maximum sum value T can be obtained by accumulating and summing the similarity index of the acquisition parameters of each dimension in the two-dimensional power grid status data. The normalized result can be obtained by dividing the current sum value by the ratio of the maximum sum value.

[0071] The advantage of this setting is that by normalizing the calculated current sum value, the obtained similarity factor can be made more accurate, thereby better determining the grid situation risk level.

[0072] S260: If the first power grid status data and the second power grid status data are the same piece of data, determine that the similarity factor between the first power grid status data and the second power grid status data is 1.

[0073] Specifically, when the first power grid status data and the second power grid status data are the same piece of data, it means that the first power grid status data and the second power grid status data are completely similar, and therefore the similarity factor is 1. It can be determined that the more similar the two power grid status data are, the larger the similarity factor is, with a maximum value of 1. Conversely, the smaller the similarity factor is, the less similar the two power grid status data are.

[0074] S270 , generating a fuzzy relationship matrix corresponding to the power grid status data set according to similarity factors between pairwise power grid status data, and calculating a transitive closure matrix corresponding to the fuzzy relationship matrix.

[0075] S280: Input each column of the transitive closure matrix into a pre-trained situation awareness model to obtain risk level description data corresponding to each piece of power grid situation data.

[0076] S290. Determine the power grid situation risk level corresponding to each piece of power grid situation data according to the risk level description data.

[0077] The technical solution provided by the embodiment of the present invention obtains a power grid status data set of the power grid to be tested; obtains the first power grid status data and the second power grid status data currently being processed; if the first power grid status data and the second power grid status data are different pieces of data, the acquisition parameters of the same dimension in the first power grid status data and the second power grid status data are correspondingly multiplied to obtain the acquisition parameter similarity index corresponding to each dimension; the acquisition parameter similarity index of each dimension in the first power grid status data and the second power grid status data is accumulated and summed to obtain the current sum value; the current sum value is normalized to obtain the first power grid status data and the second power grid status data. The similarity factor between the first power grid situation data and the second power grid situation data is determined to be 1 if the first power grid situation data and the second power grid situation data are the same data; based on the similarity factor between the two power grid situation data, a fuzzy relationship matrix corresponding to the power grid situation data set is generated, and a transitive closure matrix corresponding to the fuzzy relationship matrix is ​​calculated; each column of the transitive closure matrix is ​​input into a pre-trained situation awareness model to obtain risk level description data corresponding to each power grid situation data; based on the risk level description data, the power grid situation risk level corresponding to each power grid situation data is determined. This can make the obtained similarity factor more accurate, thereby better determining the power grid situation risk level, and thus accurately predicting the power grid situation risk level.

[0078] Example 3

[0079] Figure 3 This is a schematic diagram of the structure of a power grid situation risk level determination device provided by the third embodiment of the present invention. The power grid situation risk level determination device provided by this embodiment can be implemented by software and / or hardware, and can be configured in a server to implement a power grid situation risk level determination method in the embodiment of the present invention. Figure 3 As shown, the device may specifically include: a power grid situation data set acquisition module 310, a transitive closure matrix calculation module 320, a risk level description data acquisition module 330 and a power grid situation risk level determination module 340.

[0080] The power grid status data set acquisition module 310 is used to acquire a power grid status data set of the power grid to be tested. The power grid status data set includes multiple power grid status data. Each power grid status data is collected under different collection time parameters. Each power grid status data includes collection parameters of multiple dimensions.

[0081] The transitive closure matrix calculation module 320 is used to generate a fuzzy relationship matrix corresponding to the power grid status data set based on the similarity factor between the two power grid status data, and calculate the transitive closure matrix corresponding to the fuzzy relationship matrix;

[0082] Wherein, each data column in the transitive closure matrix is ​​used to describe the transitive relationship between each power grid status data and other power grid status data;

[0083] The risk level description data acquisition module 330 is used to input each column of the transitive closure matrix into a pre-trained situation awareness model to obtain risk level description data corresponding to each piece of power grid situation data;

[0084] The power grid situation risk level determination module 340 is configured to determine the power grid situation risk level corresponding to each piece of power grid situation data according to the risk level description data.

[0085] The technical solution provided by the embodiment of the present invention obtains a grid situation data set of the power grid to be tested; generates a fuzzy relationship matrix corresponding to the grid situation data set based on the similarity factors between the two grid situation data, and calculates the transitive closure matrix corresponding to the fuzzy relationship matrix; inputs each column of the transitive closure matrix into a pre-trained situation awareness model to obtain the risk level description data corresponding to each grid situation data; and determines the grid situation risk level corresponding to each grid situation data based on the risk level description data. The embodiment of the present invention solves the problem of difficulty in predicting the grid situation and determining the grid situation level, realizes accurate prediction of the grid situation risk level, and effectively avoids accidents caused by excessively high risk levels in the grid.

[0086] On the basis of the above embodiments, it also includes a similarity factor determination module, which may specifically include: before generating a fuzzy relationship matrix corresponding to the power grid situation data set based on the similarity factor between the two power grid situation data, a power grid situation data acquisition unit is used to acquire the first power grid situation data and the second power grid situation data currently being processed; an acquisition parameter similarity index determination unit is used to multiply the acquisition parameters of the same dimension in the first power grid situation data and the second power grid situation data if the first power grid situation data and the second power grid situation data are different data, to obtain the acquisition parameter similarity index corresponding to each dimension; a current sum value determination unit is used to accumulate and sum the acquisition parameter similarity indexes of each dimension in the first power grid situation data and the second power grid situation data to obtain a current sum value; a similarity factor determination unit is used to normalize the current sum value to obtain the similarity factor between the first power grid situation data and the second power grid situation data; a similarity factor judgment unit is used to determine that the similarity factor between the first power grid situation data and the second power grid situation data is 1 if the first power grid situation data and the second power grid situation data are the same data.

[0087] Based on the above embodiments, the similarity factor determination unit can be specifically used to: obtain the maximum sum value obtained by accumulating and summing the similarity indexes of the acquisition parameters of each dimension in the pairwise power grid status data; divide the current sum value by the ratio of the maximum sum value as the normalization processing result of the current sum value.

[0088] Based on the above embodiments, the transitive closure matrix calculation module 320 can be specifically used to: construct an N-order matrix according to the number N of power grid status data included in the power grid status data set; fill the similarity factors between the two power grid status data in the N-order matrix to form the fuzzy relationship matrix; wherein the matrix element in the i-th row and j-th column of the N-order matrix is ​​the similarity factor between the i-th power grid status data and the j-th power grid status data.

[0089] Based on the above embodiments, the transitive closure matrix calculation module 320 can be specifically used to: calculate the convolution formula of the fuzzy relationship matrix according to When k=1, determine whether X is satisfied. 2k =X k If so, the transitive closure matrix of the situation data to be tested is X k ,in, Is the convolution operator; if not, k is incremented by 1 and the result is returned to determine whether X is satisfied. 2k =X k , until the transitive closure matrix of the situation data to be tested is satisfied and determined.

[0090] Based on the above embodiments, the power grid situation risk level determination module 340 can be specifically used to: when the risk level description data is greater than or equal to 0 and less than 0.5, the output power grid situation risk level is a normal state; when the risk level description data is greater than or equal to 0.5 and less than 0.65, the output power grid situation risk level is a sub-normal state; when the risk level description data is greater than or equal to 0.65 and less than 0.80, the output power grid situation risk level is an abnormal state; when the risk level description data is greater than or equal to 0.80 and less than 1, the output power grid situation risk level is an alarm state.

[0091] On the basis of the above embodiments, it also includes a situation awareness model training module, which can be specifically used to: obtain a training sample data set before inputting each column of data of the transitive closure matrix into a pre-trained situation awareness model; wherein each training sample data includes a transitive closure matrix sample corresponding to the power grid situation data set of a set power grid, and a risk level description data label value corresponding to each data column in the transitive closure matrix sample; input each data column in each transitive closure matrix sample into the neural network model to be trained; according to the error value between the risk level description data output value of the neural network model and the matched risk level description data label value, adjust the parameters of each node in the neural network model to train the situation awareness model.

[0092] The above-mentioned power grid situation risk level determination device can execute the power grid situation risk level determination method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0093] Example 4

[0094] Figure 4 This is a structural diagram of a computer device provided by the fourth embodiment of the present invention. Figure 4 As shown, the device includes a processor 410, a memory 420, an input device 430, and an output device 440; the number of processors 410 in the device can be one or more. Figure 4 In the embodiment, a processor 410 is used as an example; the processor 410, memory 420, input device 430 and output device 440 in the device can be connected via a bus or other means. Figure 4 The bus connection is taken as an example.

[0095] The memory 420, as a computer-readable storage medium, can be used to store software programs, computer executable programs and modules, such as the program instructions / modules corresponding to the power grid situation risk level determination method in the embodiment of the present invention (for example, the power grid situation data set acquisition module 310, the transitive closure matrix calculation module 320, the risk level description data acquisition module 330 and the power grid situation risk level determination module 340). The processor 410 executes various functional applications and data processing of the device by running the software programs, instructions and modules stored in the memory 420, that is, implements the above-mentioned method for determining the grid situation risk level, which includes: obtaining a grid situation data set of the grid to be tested, each grid situation data in the grid situation data set corresponds to a set acquisition time parameter, and each grid situation data includes acquisition parameters of multiple dimensions; based on the similarity factor between each pair of grid situation data, generating a fuzzy relationship matrix corresponding to the grid situation data set, and calculating a transitive closure matrix corresponding to the fuzzy relationship matrix; wherein each data column in the transitive closure matrix is ​​used to describe the transitive relationship between each grid situation data and other grid situation data; inputting each column of data of the transitive closure matrix into a pre-trained situation awareness model to obtain risk level description data corresponding to each grid situation data; and determining the grid situation risk level corresponding to each grid situation data according to the risk level description data.

[0096] The memory 420 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and applications required for at least one function; the data storage area may store data created based on the use of the terminal, etc. In addition, the memory 420 may include a high-speed random access memory and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 420 may further include a memory remotely located relative to the processor 410, and these remote memories may be connected to the device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0097] The input device 430 may be used to receive input digital or character information and generate key signal input related to user settings and function control of the device. The output device 440 may include a display device such as a display screen.

[0098] Example 5

[0099] Embodiment 5 of the present invention also provides a method comprising a computer-readable storage medium, wherein the computer-readable instructions are used to execute a method for determining a power grid situation risk level when executed by a computer processor, the method comprising: obtaining a power grid situation data set of the power grid to be tested, wherein each power grid situation data in the power grid situation data set corresponds to a set acquisition time parameter, and each power grid situation data includes acquisition parameters of multiple dimensions; generating a fuzzy relationship matrix corresponding to the power grid situation data set based on similarity factors between two power grid situation data, and calculating a transitive closure matrix corresponding to the fuzzy relationship matrix; wherein each data column in the transitive closure matrix is ​​used to describe the transitive relationship between each power grid situation data and other power grid situation data; inputting each column of data of the transitive closure matrix into a pre-trained situation awareness model to obtain risk level description data corresponding to each power grid situation data; and determining the power grid situation risk level corresponding to each power grid situation data based on the risk level description data.

[0100] Of course, the computer-executable instructions of a storage medium containing computer-readable instructions provided in an embodiment of the present invention are not limited to the operations of the method described above, but can also execute related operations in the method for determining the power grid situation risk level provided in any embodiment of the present invention.

[0101] Through the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented with the help of software and necessary general-purpose hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0102] It is worth noting that in the embodiment of the above-mentioned power grid situation risk level determination device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0103] Note that the above are only preferred embodiments of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments, and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments and may include many other equivalent embodiments without departing from the concept of the present invention. The scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for determining the risk level of a power grid situation, characterized in that: include: Obtaining a power grid status data set of the power grid to be tested, wherein the power grid status data set includes multiple power grid status data, each power grid status data is collected under different collection time parameters, and each power grid status data includes collection parameters of multiple dimensions; Generate a fuzzy relationship matrix corresponding to the power grid status data set according to the similarity factor between the two power grid status data, and calculate the transitive closure matrix corresponding to the fuzzy relationship matrix; Wherein, each data column in the transitive closure matrix is used to describe the transitive relationship between each power grid status data and other power grid status data; Inputting each column of the transitive closure matrix into a pre-trained situation awareness model to obtain risk level description data corresponding to each piece of power grid situation data; Determining the grid situation risk level corresponding to each piece of grid situation data according to the risk level description data; The generating of a fuzzy relationship matrix corresponding to the power grid situation data set according to the similarity factors between the two power grid situation data sets includes: Constructing an N-order matrix according to the number N of power grid status data included in the power grid status data set; Filling the similarity factors between the two power grid status data into the N-order matrix to form the fuzzy relationship matrix; The matrix element in the i-th row and j-th column of the N-order matrix is the similarity factor between the i-th power grid situation data and the j-th power grid situation data; Before inputting each column of data of the closure matrix into the pre-trained situation awareness model, the method further includes: Obtain training sample dataset; Each piece of training sample data includes a transitive closure matrix sample corresponding to a power grid status data set of a set power grid, and a risk level description data label value corresponding to each data column in the transitive closure matrix sample; wherein the transitive closure matrix sample is a sample of the transitive closure matrix stored in the sample library; Input each data column in each transitive closure matrix sample into the neural network model to be trained; According to the error value between the risk level description data output value of the neural network model and the matched risk level description data annotation value, the parameters of each node in the neural network model are adjusted to train the situation awareness model.

2. The method according to claim 1, characterized in that Before generating a fuzzy relationship matrix corresponding to the power grid situation data set based on similarity factors between two power grid situation data sets, the method further includes: Acquire the first power grid status data and the second power grid status data currently being processed; If the first power grid situation data and the second power grid situation data are different pieces of data, then correspondingly multiplying the acquisition parameters of the same dimension in the first power grid situation data and the second power grid situation data to obtain an acquisition parameter similarity index corresponding to each dimension; Accumulate and sum the similarity indexes of the acquisition parameters of each dimension in the first power grid status data and the second power grid status data to obtain a current sum value; Normalizing the current summed value to obtain a similarity factor between the first power grid status data and the second power grid status data; If the first power grid situation data and the second power grid situation data are the same piece of data, then the similarity factor between the first power grid situation data and the second power grid situation data is determined to be 1.

3. The method according to claim 2, characterized in that Normalizing the current sum value includes: Obtaining the maximum sum value obtained by accumulating and summing the similarity indexes of the acquisition parameters of each dimension in the pairwise power grid status data; A ratio of the current sum value divided by the maximum sum value is used as a normalization result of the current sum value.

4. The method according to claim 1, wherein Calculating a transitive closure matrix corresponding to the fuzzy relation matrix includes: According to the convolution calculation formula of the fuzzy relationship matrix X 2k =X k °X k (k=1, 2, ..., N), when k=1, determine whether X is satisfied 2k =X k If so, the transitive closure matrix of the situation data to be tested is X k , where ° is the convolution operator; If not, k is incremented by 1 and the result is returned to determine whether X is satisfied. 2k =X k , until the transitive closure matrix of the situation data to be tested is satisfied and determined.

5. The method according to claim 1, wherein Determining the grid situation risk level corresponding to each piece of grid situation data according to the risk level description data includes: When the risk level description data is greater than or equal to 0 and less than 0.5, the output power grid situation risk level is normal; When the risk level description data is greater than or equal to 0.5 and less than 0.65, the output power grid situation risk level is subnormal; When the risk level description data is greater than or equal to 0.65 and less than 0.80, the output power grid situation risk level is abnormal; When the risk level description data is greater than or equal to 0.80 and less than 1, the output power grid situation risk level is an alarm state.

6. A device for determining the risk level of a power grid situation, characterized in that: include: The power grid situation data set acquisition module is used to obtain the power grid situation data set of the power grid to be tested. The power grid situation data set contains multiple power grid situation data. Each power grid situation data is collected under different collection time parameters. Each power grid situation data includes collection parameters of multiple dimensions. A transitive closure matrix calculation module is used to generate a fuzzy relationship matrix corresponding to the power grid situation data set based on the similarity factor between the two power grid situation data, and calculate the transitive closure matrix corresponding to the fuzzy relationship matrix; Wherein, each data column in the transitive closure matrix is used to describe the transitive relationship between each power grid status data and other power grid status data; A risk level description data acquisition module is used to input each column of the transitive closure matrix into a pre-trained situation awareness model to obtain risk level description data corresponding to each power grid situation data; A power grid situation risk level determination module is used to determine the power grid situation risk level corresponding to each power grid situation data according to the risk level description data; The transitive closure matrix calculation module is specifically used for: Constructing an N-order matrix according to the number N of power grid status data included in the power grid status data set; Filling the similarity factors between the two power grid status data into the N-order matrix to form the fuzzy relationship matrix; The matrix element in the i-th row and j-th column of the N-order matrix is the similarity factor between the i-th power grid situation data and the j-th power grid situation data; The device further comprises: The situation awareness model training module is specifically used to: obtain a training sample data set before inputting each column of data of the transitive closure matrix into a pre-trained situation awareness model; wherein each training sample data includes a transitive closure matrix sample corresponding to the power grid situation data set of a set power grid, and a risk level description data label value corresponding to each data column in the transitive closure matrix sample; wherein the transitive closure matrix sample is a sample of the transitive closure matrix stored in a sample library; input each data column in each transitive closure matrix sample into the neural network model to be trained; according to the error value between the risk level description data output value of the neural network model and the matched risk level description data label value, adjust the parameters of each node in the neural network model to train the situation awareness model.

7. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method for determining the power grid situation risk level according to any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for determining the power grid situation risk level as described in any one of claims 1 to 5 is implemented.

Images