Power grid operation risk management and control method and system

Abstract

The present invention relates to the technical field of data processing, and particularly relates to a power grid operation risk management and control method and system. The method comprises the steps of: collecting electrical data during the operation of a power grid and each electrical parameter sequence; acquiring historical data of each piece of data in each electrical parameter sequence, and on the basis of the deviation of each piece of data in each electrical parameter sequence relative to the historical data thereof, acquiring the degree of deviation of each piece of data in each electrical parameter sequence; on the basis of the degree of deviation of each piece of data in each electrical parameter sequence, acquiring the degree of anomaly of each electrical parameter; on the basis of a plurality of electrical parameters of all electrical data, constructing a plurality of isolation trees; on the basis of the degree of anomaly of the electrical parameter which corresponds to the layer where each piece of electrical data in each isolation tree is located, acquiring a weighted path length of each piece of electrical data in each isolation tree; and on the basis of the weighted path length of each piece of electrical data in each isolation tree, acquiring anomalous data. The present invention improves the accuracy of anomaly detection.

Description

Power grid operation risk management and control method and system

[0001] Cross-reference to related applications

[0002] The present application claims priority to the Chinese patent application No. 2024112429435, filed on September 5, 2024, and entitled "Power grid operation risk management and control method and system", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0003] The present application relates to the technical field of data processing, and particularly relates to a power grid operation risk management and control method and system. BACKGROUND

[0004] As a modern social infrastructure, the stable operation of the power grid is of great importance to national security, economic development and people's life. Nowadays, with the continuous growth of residential electricity demand, the carrying pressure of the power grid has significantly increased, and the operation safety is facing severe challenges. Once the power grid fails, it may lead to large-scale power outages or even unsafe accidents, which seriously affects industrial production, commercial operation and residents' life, and causes huge economic losses and social impact. Therefore, effectively managing and reducing the operation risk of the power grid has become an important issue to be solved in the power industry. In the field of power grid operation monitoring, factors such as equipment failure, overload and external interference often lead to abnormal situations such as voltage drop and current surge in different electrical data, which in turn cause abnormal data in electrical data. Therefore, a power grid operation risk management and control method and system are proposed, which collects electrical data, analyzes abnormal data in electrical data, and evaluates the operation risk of the power grid.

[0005] The patent document with the granted announcement No. CN111798312 discloses a financial transaction system anomaly identification method based on the isolated forest algorithm. The method performs consistency check on the original data, removes invalid data and duplicate data, fills in missing values, and converts category variables into numerical variables. The input data is modeled by isolated forest. The path length of the sample point in the isolated forest model is calculated to calculate the abnormal value score. According to experience, a threshold value of abnormal value score is set. The transaction behavior with abnormal value score greater than the threshold value is judged as abnormal behavior, and the abnormal behavior is reported to the verification module.

[0006] When analyzing abnormal data in electrical data using the traditional isolation forest algorithm in the above method, the average path length of each data in all isolation trees is calculated with the same weight to evaluate the abnormality, but this ignores the key role of each electrical parameter with high abnormality degree in abnormality detection, resulting in that these key information cannot fully play a role in the model construction process, and then some isolation trees that perform well in a specific abnormal mode cannot be given due attention in the calculation of the final abnormal score, which may lead to the real abnormal data being misjudged as normal data, posing a potential threat to the safe and stable operation of the power grid. SUMMARY

[0007] In order to solve the technical problem that the traditional isolation forest algorithm uses the same weight to calculate the average path length of each data in all isolation trees to evaluate the abnormality, ignores the key role of the electrical parameter with high abnormality degree in abnormality detection, and then may lead to the real abnormal point being misjudged as normal, the present application provides a power grid operation risk management and control method and system.

[0008] In the first aspect, the present application provides a power grid operation risk management and control method, which adopts the following technical scheme:

[0009] A power grid operation risk management and control method, comprising the steps of:

[0010] Collecting each electrical data and each electrical parameter sequence, wherein the electrical data includes each electrical parameter; obtaining the historical data of each data in each electrical parameter sequence; obtaining the deviation degree of each data in each electrical parameter sequence, wherein the deviation degree represents the prominence of the value of each data in each electrical parameter sequence compared to the value of its historical data; and obtaining the abnormality degree of each electrical parameter: In the formula, θ k represents the abnormality degree of the kth electrical parameter; A k,i represents the deviation degree of the i th data in the k th electrical parameter sequence; n k represents the number of data in the k th electrical parameter sequence; G k represents the kurtosis of the deviation degree of all data in the k th electrical parameter sequence; exp() represents the exponential function with the natural constant as the base;

[0011] Constructing each isolation tree according to each electrical parameter of all electrical data, obtaining the path length of each electrical data in each isolation tree according to each isolation tree, and obtaining the weighted path length of each electrical data in each isolation tree, wherein the weighted path length is obtained by weighting the path length of each electrical data in each isolation tree with the abnormality degree of the corresponding electrical parameter of the layer where the electrical data is located;

[0012] According to the weighted path length of each electrical data in each isolated tree, an abnormal score of each electrical data is obtained, and abnormal data is obtained.

[0013] The innovation of the application is that the path length of each electrical data in each isolated tree is weighted according to the abnormal degree of the electrical parameter corresponding to the layer where the electrical data is located in each isolated tree, the weighted path length of each electrical data in each isolated tree is obtained, the different effects of the abnormal degrees of different electrical parameters in abnormal detection are considered, the abnormal data has a shorter path length in the isolated tree, which is convenient for subsequent identification as abnormal data, reduces the misjudgment, and significantly improves the accuracy of abnormal detection; further, the abnormal degree of each electrical parameter is first evaluated by the direct difference between any data in the electrical parameter sequence and the average level of its historical data, and the change of the dispersion degree of the historical data distribution caused by the addition of the data, and finally the abnormal degree of each electrical parameter is evaluated by using the mean of the deviation degree of all data in each electrical parameter sequence and the kurtosis, so that the abnormal degree of each electrical parameter is more accurate.

[0014] Preferably, the historical data of each data in each electrical parameter sequence is obtained, including:

[0015] The m data of the i th data in the k th electrical parameter sequence before the k th electrical parameter sequence are recorded as the historical data of the i th data in the k th electrical parameter sequence.

[0016] The deviation degree of each data in each electrical parameter sequence is obtained by analyzing the degree of deviation of the value of each data from the value of its historical data.

[0017] Preferably, the deviation degree of each data in each electrical parameter sequence is obtained, including:

[0018] In the formula, A k,i represents the deviation degree of the i th data in the k th electrical parameter sequence; x k,i represents the value of the i th data in the k th electrical parameter sequence; y k,i represents the mean of all historical data of the i th data in the k th electrical parameter sequence; d k,i represents the range of all historical data of the i th data in the k th electrical parameter sequence; h k,i represents the coefficient of variation of the value of the i th data in the k th electrical parameter sequence and all its historical data; k k,i represents the coefficient of variation of the value of all historical data of the i th data in the k th electrical parameter sequence; tanh() represents the hyperbolic tangent function.

[0019] The abnormality degree of each electrical parameter is obtained according to the deviation degree of each data in the sequence of each electrical parameter.

[0020] Preferably, the constructing of each isolated tree according to each electrical parameter of all electrical data comprises:

[0021] The number M of isolated trees and the depth W of each isolated tree are preset, M isolated trees are constructed according to multiple electrical parameters of all electrical data, for any one isolated tree, any one electrical parameter of all electrical data is randomly selected for segmentation at the first layer of the isolated tree, the segmentation value is a random value in the value range of the electrical parameter of all electrical data, any one electrical parameter of all electrical data is randomly selected for segmentation at the second layer of the isolated tree according to the first layer segmentation method of the isolated tree, and the process is sequentially repeated until the depth of the isolated tree is W.

[0022] Preferably, the obtaining of the path length of each electrical data in each isolated tree comprises:

[0023] The number of edges from the root node of each isolated tree to each electrical data in the isolated tree is taken as the path length of each electrical data in the isolated tree.

[0024] Preferably, the obtaining of the weighted path length of each electrical data in each isolated tree comprises: L c,d =exp(-θ c,d )×Q c,d ;

[0025] In the formula, L c,d represents the weighted path length of the dth electrical data in the cth isolated tree; Q c,d represents the path length of the dth electrical data in the cth isolated tree; θ c,d represents the abnormality degree of the electrical parameter corresponding to the layer where the dth electrical data in the cth isolated tree is located; and exp() represents an exponential function with a natural constant as the base number.

[0026] If the abnormality degree of the electrical parameter corresponding to the layer where each electrical data in the isolated tree is located is greater, it indicates that each electrical data is more abnormal, and the path length of each electrical data in the isolated tree is adjusted to be smaller, so as to detect it as abnormal data.

[0027] Preferably, the obtaining of the abnormality score of each electrical data according to the weighted path length of each electrical data in each isolated tree, and the obtaining of abnormal data comprises:

[0028] A preset anomaly threshold T, the average of the weighted path lengths of the dth electrical data in all isolated trees is taken as the weighted average path length of the dth electrical data, and the weighted average path lengths of all electrical data are obtained; using the isolated forest algorithm, the anomaly score of each electrical data is obtained according to the weighted average path length of each electrical data, and if the anomaly score of any electrical data is greater than or equal to the anomaly threshold, the electrical data is an abnormal data.

[0029] The accuracy of the abnormality detection result is improved.

[0030] Preferably, the collection of each electrical data and each electrical parameter sequence comprises:

[0031] A preset sampling time is 1 second / time, current sensors, voltage sensors and temperature sensors are installed at key positions of the power grid bus, current data, voltage data and temperature data are collected each time as an electrical data, and a total of two hours are collected; each electrical data contains three electrical parameters (current data, voltage data and temperature data);

[0032] According to the order of the sampling time from small to large, the electrical parameters of all electrical data are sorted to obtain the electrical parameter sequence.

[0033] In a second aspect, the present application provides a power grid operation risk management and control system, which adopts the following technical scheme:

[0034] A power grid operation risk management and control system comprises a processor and a memory, and the memory stores computer program instructions, when the computer program instructions are executed by the processor, the above-mentioned power grid operation risk management and control method is realized.

[0035] By adopting the above technical scheme, the above-mentioned power grid operation risk management and control method is generated into a computer program and stored in the memory, so as to be loaded and executed by the processor, so as to manufacture a terminal device according to the memory and the processor, and facilitate use.

[0036] The present application has the following technical effects: the present application weights the path length of each electrical data in each isolated tree according to the abnormality degree of the electrical parameter corresponding to the layer where the electrical data is located, obtains the weighted path length of each electrical data in each isolated tree, considers the different effects of the abnormality degrees of different electrical parameters in anomaly detection, finally makes the abnormal data have a shorter path length in the isolated tree, facilitates subsequent identification as abnormal data, reduces the misjudgment, and significantly improves the accuracy of anomaly detection. BRIEF DESCRIPTION OF DRAWINGS

[0037] The above and other objects, features and advantages of the present application will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings in which a number of embodiments of the application are illustrated by way of example and not limitation. Like or corresponding elements in the figures are denoted by like reference numerals.

[0038] Fig. 1 is a flow chart of a power grid operation risk management method according to an embodiment of the present application. DETAILED DESCRIPTION

[0039] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0040] It should be understood that when the claims, the specification, and the drawings of the present application use the terms "first", "second", etc., these terms are only used to distinguish different objects, and are not used to describe a specific sequence. The terms "include" and "contain" used in the specification and claims of the present application indicate the presence of the described features, integers, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or sets thereof.

[0041] The embodiments of the present application disclose a power grid operation risk management method, referring to Fig. 1, comprising steps S1-S3:

[0042] S1: collecting electrical data and sequences of various electrical parameters in the power grid operation process.

[0043] It should be noted that the purpose of the present application is to monitor the electrical data in the power grid operation process in a certain area in real time to determine abnormal conditions in the power grid operation process. The known electrical parameter types in the power grid operation process include current data, voltage data, temperature data, etc.

[0044] In the embodiments of the present application, the preset sampling time is 1 second / time, current sensors, voltage sensors, and temperature sensors are installed at key positions of the power grid bus, current data, voltage data, and temperature data are collected each time, and a total of two hours are collected to obtain each electrical data, wherein the each electrical data contains three electrical parameters (current data, voltage data, and temperature data).

[0045] According to the order from small to large of the sampling time, the various electrical parameters of all the electrical data are sorted to obtain sequences of various electrical parameters.

[0046] S2: Obtain the historical data of each data in each electrical parameter sequence, obtain the deviation degree of each data in each electrical parameter sequence according to the deviation of each data in each electrical parameter sequence in its historical data, and obtain the abnormality degree of each electrical parameter according to the deviation degree of each data in each electrical parameter sequence.

[0047] It should be noted that the electrical data with high abnormality degree can quickly and accurately capture the key information of abnormal features, but the traditional isolation forest algorithm uses the same weight to calculate the average path length of each data in all isolation trees to evaluate its abnormality when analyzing the abnormal data in the electrical data. However, this ignores the key role of the electrical parameters with high abnormality degree in abnormal detection, resulting in that these key information cannot fully play a role in the model construction process, and further makes some isolation trees that perform well in specific abnormal patterns cannot get due attention in the calculation of the final abnormal score, which may lead to the real abnormal points being misjudged as normal, and poses a potential threat to the safe and stable operation of the power grid.

[0048] Step S2 includes steps S20-S21, which are as follows:

[0049] S20: Obtain the historical data of each data in each electrical parameter sequence, obtain the deviation degree of each data in each electrical parameter sequence according to the deviation of each data in each electrical parameter sequence in its historical data.

[0050] It should be noted that timely detection of the abnormality of electrical parameters in the operation of the power grid is crucial to ensure the safe and stable operation of the power grid. Due to the complex and variable actual environment, such as sudden increase of regional load, short circuit on transmission line, transmission line circuit breaking and other situations, the electrical parameters will change significantly. These rapidly changing data represent the occurrence of unsafe events, so it is necessary to analyze whether the data deviates from other data by combining the change characteristics of any data in each electrical parameter sequence. However, the operation state of the power grid will change with time, load, weather conditions and other factors, and directly analyzing all data in each electrical parameter sequence may not accurately reflect the actual state of the data. Therefore, the historical data of the data in a certain period of time in its electrical parameter sequence is selected as the historical data of the data, and the direct difference between the data and the average level of its historical data and the change of the dispersion degree of the historical data distribution caused by the addition of the data are considered to comprehensively evaluate the deviation degree of the data.

[0051] In the embodiment of the present application, the number of preset historical data is m, and m data before the i-th data in the k-th electrical parameter sequence is recorded as the historical data of the i-th data in the k-th electrical parameter sequence; in the embodiment of the present application, the number of preset historical data is m=20, and in other embodiments, the implementer can preset the value of the number of historical data according to the specific implementation.

[0052] The deviation degree of the i-th data in the k-th electrical parameter sequence is obtained:

[0053] In the formula, A k,i represents the deviation degree of the i-th data in the k-th electrical parameter sequence; x k,i represents the value of the i-th data in the k-th electrical parameter sequence; y k,i represents the mean value of all historical data of the i-th data in the k-th electrical parameter sequence; d k,i represents the range of all historical data of the i-th data in the k-th electrical parameter sequence, and it is to be noted that the acquisition of the range of the data set is a prior art, and in the embodiment of the present application, it will not be described in more detail; h k,i represents the coefficient of variation of the value of the i-th data in the k-th electrical parameter sequence and all historical data thereof; k k,i represents the coefficient of variation of the value of all historical data of the i-th data in the k-th electrical parameter sequence; it is to be noted that the acquisition of the coefficient of variation of the value of all data in the data is a known technology, and in the embodiment of the present application, it will not be described in more detail; tanh() represents the hyperbolic tangent function, which is used for normalization processing.

[0054] represents the deviation of the value of the i-th data in the k-th electrical parameter sequence relative to the average level of the value of all historical data thereof, when the range d k,i is small, it indicates that the values of all historical data of the i-th data in the k-th electrical parameter sequence are relatively concentrated, and at this time, if the value of the i-th data is greatly different from the average value of all historical data thereof, the value of is large, at this time, the i-th data in the k-th electrical parameter sequence is significantly higher than the value of all historical data thereof; therefore, the deviation degree of the i-th data in the k-th electrical parameter sequence is large.

[0055] h k,i -k k,iThe greater the difference value between the coefficient of variation of the value of the i-th data in the k-th electrical parameter sequence and all historical data thereof and the coefficient of variation of the value of all historical data of the i-th data in the k-th electrical parameter sequence, the more significantly the addition of the i-th data in the k-th electrical parameter sequence enhances the discrete degree of all historical data thereof, and thus the greater the deviation degree of the i-th data in the k-th electrical parameter sequence.

[0056] S21: Obtain the abnormality degree of each electrical parameter according to the deviation degree of each data in each electrical parameter sequence.

[0057] It should be noted that, since the normal operation range of each electrical parameter (such as voltage, current, temperature, etc.) in the process of power grid operation is crucial to the stability and efficiency of the system, if some electrical parameters deviate from the normal range or appear abnormal fluctuations, it may lead to the decline of the performance of the power grid system, equipment damage, and even safety accidents, therefore, the abnormality degree of each electrical parameter can be obtained according to the deviation degree of all data in each electrical parameter sequence, but the distribution of the deviation degree of all data in each electrical parameter is ignored, for example, there are a small number of data with high deviation degree in all data in each electrical parameter sequence, which means that this electrical parameter is abnormal, and the abnormality degree thereof is high, therefore, when the abnormality degree of the electrical parameter is quantified only according to the mean value of the deviation degree of all data in each electrical parameter sequence, the data with high deviation degree may be averaged to a low or medium value by the data with low deviation degree, which may mislead that the abnormality degree of the electrical parameter is low, therefore, the abnormality degree of each electrical parameter is obtained in combination with the kurtosis of the deviation degree of all data in each electrical parameter sequence and the mean value of the deviation degree of all data in each electrical parameter sequence, if the kurtosis is large and the mean value is large, it means that the abnormality degree of each electrical parameter is high.

[0058] In the embodiment of the present application, the abnormality degree of the k-th electrical parameter is obtained as follows:

[0059] In the formula, θ k represents the abnormality degree of the k-th electrical parameter; A k,i represents the deviation degree of the i-th data in the k-th electrical parameter sequence; n k represents the number of data in the k-th electrical parameter sequence; G k represents the kurtosis of the deviation degree of all data in the k-th electrical parameter sequence; exp() represents the exponential function with the natural constant as the base;

[0060] a mean value of deviation degrees of all data in the kth electrical parameter sequence, the greater the value, the more data in the kth electrical parameter sequence deviates from the average level, that is, the more abnormal data in the kth electrical parameter sequence; G k the greater the value, the higher the sharpness of the distribution of the deviation degrees of all data in the kth electrical parameter sequence, the more pointed the data distribution, the longer the tail, which means that there are more abnormal data in the kth electrical parameter of all electrical data, that is, the greater the abnormality of the kth electrical parameter.

[0061] S3: constructing a plurality of isolated trees according to a plurality of electrical parameters of all electrical data; obtaining a weighted path length of each electrical data in each isolated tree according to an abnormality degree of the electrical parameter corresponding to the layer where the electrical data is located in each isolated tree; and obtaining abnormal data according to the weighted path length of each electrical data in each isolated tree.

[0062] Step S3 includes steps S30-S31, which are as follows:

[0063] S30: constructing a plurality of isolated trees according to a plurality of electrical parameters of all electrical data; and obtaining a weighted path length of each electrical data in each isolated tree according to an abnormality degree of the electrical parameter corresponding to the layer where the electrical data is located in each isolated tree.

[0064] It should be noted that the conventional isolated forest algorithm considers all electrical parameters of electrical data as equally important when detecting abnormality of electrical data, which ignores the different roles of different electrical parameters in power grid stability and abnormality detection. For example, when a voltage drop occurs in the power grid, the abnormality degree of the voltage-related electrical parameter (such as voltage data) can be very high. Therefore, the isolated trees are first constructed according to a plurality of electrical parameters of all electrical data, and then the path length of each electrical data in each isolated tree is adjusted according to the abnormality degree of the electrical parameter corresponding to the layer where the electrical data is located in each isolated tree. When the abnormality degree of the electrical parameter corresponding to the layer where the electrical data is located in each isolated tree is greater, the path length of each electrical data in each isolated tree needs to be adjusted smaller, so that the abnormal data has a shorter path length in the isolated tree, which is convenient for being identified as abnormal data subsequently.

[0065] In the embodiment of the present application, the number of preset isolated trees M and the depth W of each isolated tree are determined, M isolated trees are constructed according to a plurality of electrical parameters of all electrical data, for any one isolated tree, an arbitrary electrical parameter of all electrical data is randomly selected for segmentation at the first layer of the isolated tree, the segmentation value is a random value in the value range of the electrical parameter of all electrical data, an arbitrary electrical parameter of all electrical data is randomly selected for segmentation at the second layer of the isolated tree according to the first layer segmentation method of the isolated tree, and the process is repeated until the depth of the isolated tree is W.

[0066] It should be noted that the root node of the isolated tree is the 0th layer, and the depth of the isolated tree is the sum of the number of layers of the isolated tree.

[0067] In the embodiment of the present application, the preset number of isolated trees M = 20, and the depth W = 8 of each isolated tree. In other embodiments, the implementer can preset the values of M and W according to the specific implementation range.

[0068] The path length of each electrical data in each isolated tree is the number of edges from the root node of each isolated tree to each electrical data in each isolated tree.

[0069] In the embodiment of the present application, the weighted path length of each electrical data in each isolated tree is obtained: c,d = exp(-θ c,d ) × Q c,d ;

[0070] In the formula, L c,d represents the weighted path length of the dth electrical data in the cth isolated tree; Q c,d represents the path length of the dth electrical data in the cth isolated tree; θ c,d represents the abnormality degree of the electrical parameter corresponding to the layer where the dth electrical data in the cth isolated tree is located; exp() represents the exponential function with natural constant as the base; when the abnormality degree of the electrical parameter corresponding to the layer where the dth electrical data in the cth isolated tree is located is higher, the possibility that the dth electrical data in the cth isolated tree is abnormal data is greater, and in the traditional isolated tree, the smaller the path length of the data is, the more abnormal the data is, so it is necessary to make the path length of the more abnormal electrical data smaller.

[0071] S31: Obtain abnormal data according to the weighted path length of each electrical data in each isolated tree.

[0072] It should be noted that since the abnormal data often deviates from the distribution mode of the normal data, the abnormal data has a shorter path length in the isolated tree, therefore, first, the weighted average path length of each electrical data is obtained according to the weighted path length of each electrical data in each isolated tree, the abnormal score of each electrical data is obtained, thereby improving the accuracy of the abnormal detection.

[0073] In the embodiment of the present application, the average of the weighted path lengths of the dth electrical data in all isolated trees is taken as the weighted average path length of the dth electrical data, the weighted average path lengths of all electrical data are obtained, the anomaly score of each electrical data is obtained according to the weighted average path length of each electrical data by using the isolated forest algorithm, a preset anomaly threshold T is used, if the anomaly score of any electrical data is greater than or equal to the anomaly threshold, the electrical data is abnormal data, at this time, the system issues a warning and prompts the corresponding management personnel to control it.

[0074] The embodiment of the present application also discloses a power grid operation risk management and control system, comprising a processor and a memory, the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a power grid operation risk management and control method according to the present application is realized.

[0075] The above system also includes a communication bus and a communication interface and other components well known to those skilled in the art, the settings and functions of which are known in the art, and therefore will not be described here.

[0076] In the present application, the aforementioned memory can be any tangible medium containing or storing a program, which can be used or combined with an instruction execution system, device or instrument. For example, the computer readable storage medium can be any appropriate magnetic storage medium or magneto-optical storage medium, such as resistive memory, dynamic random access memory, static random access memory, enhanced dynamic random access memory, high bandwidth memory, hybrid memory cube, etc., or any other medium that can be used to store the required information and can be accessed by an application program, module or both. Any such computer storage medium can be part of the device or accessible or connectable to the device.

[0077] Although the present application has shown and described several embodiments of the present application, it will be apparent to those skilled in the art that many modifications, changes and substitutions can be made without departing from the spirit and scope of the present application. It should be understood that various alternatives to the embodiments of the present application described herein can be employed in practicing the present application.

[0078] The above are the preferred embodiments of the present application, which do not limit the protection scope of the present application, therefore: any equivalent changes made on the structure, shape, principle of the present application should be covered within the protection scope of the present application.

Claims

1. A power grid operation risk management method, characterized in that, The method comprises the steps of: collecting electrical data and electrical parameter sequences, the electrical data comprising electrical parameters, obtaining historical data of each data in the electrical parameter sequences, and obtaining deviation degrees of each data in the electrical parameter sequences, the deviation degrees representing the prominence of the values of each data in the electrical parameter sequences compared with the values of the historical data; obtaining the abnormality degree of each electrical parameter: where θ k represents the abnormality degree of the kth electrical parameter; A k,i represents the deviation degree of the i th data in the kth electrical parameter sequence; n k represents the number of data in the kth electrical parameter sequence; G k represents the kurtosis of the deviation degree of all data in the kth electrical parameter sequence; exp() represents the exponential function with the natural constant as the base; constructing isolated trees according to the electrical parameters of all the electrical data, obtaining path lengths of each electrical data in each isolated tree according to the isolated trees, and obtaining weighted path lengths of each electrical data in each isolated tree, the weighted path lengths being obtained by weighting the path lengths of each electrical data in each isolated tree by the abnormality degrees of the electrical parameter corresponding to the layer where each electrical data is located in each isolated tree; obtaining abnormal scores of each electrical data according to the weighted path lengths of each electrical data in each isolated tree, and obtaining abnormal data.

2. The power grid operation risk management method of claim 1, wherein, The method comprises the steps of: presetting a historical data number m, and taking m data before the i-th data in the k-th electrical parameter sequence as the historical data of the i-th data in the k-th electrical parameter sequence.

3. The power grid operation risk management method of claim 1, wherein, The acquisition of the deviation degree of each data in each sequence of electrical parameters comprises: wherein A k,i represents the deviation of the i-th data in the k-th electrical parameter sequence; x k,i represents the value of the i-th data in the k-th electrical parameter sequence; y k,i represents the mean of all historical data of the i-th data in the k-th electrical parameter sequence; d k,i represents the range of all historical data of the i-th data in the k-th electrical parameter sequence; h k,i represents the coefficient of variation of the value of the i-th data in the k-th electrical parameter sequence and all its historical data; k k,i represents the coefficient of variation of the value of all historical data of the i-th data in the k-th electrical parameter sequence; tanh() represents the hyperbolic tangent function.

4. The power grid operation risk management method of claim 1, wherein, The method comprises the steps of: presetting an isolated tree number M and a depth W of each isolated tree, constructing M isolated trees according to the electrical parameters of all the electrical data, for any isolated tree, randomly selecting any electrical parameter of all the electrical data for segmentation at the first layer of the isolated tree, the segmentation value being a random value in the value range of the electrical parameter, randomly selecting any electrical parameter of all the electrical data for segmentation at the second layer of the isolated tree according to the first layer segmentation method of the isolated tree, and sequentially selecting electrical parameters for segmentation until the depth of the isolated tree reaches W.

5. The power grid operation risk management method of claim 1, wherein, The method comprises the steps of: taking the number of edges from the root node of each isolated tree to each electrical data in each isolated tree as the path length of each electrical data in each isolated tree.

6. The power grid operation risk management method of claim 1, wherein, The acquiring the weighted path length of each electrical data in each isolated tree comprises: L c,d = exp(-θ c,d ) × Q c,d ; wherein L c,d represents the weighted path length of the dth electrical data in the cth isolated tree; Q c,d represents the path length of the dth electrical data in the cth isolated tree; θ c,d represents the abnormality degree of the item electrical parameter corresponding to the layer where the dth electrical data in the cth isolated tree is located; exp() represents the exponential function with the natural constant as the base number.

7. The power grid operation risk management method of claim 1, wherein, The method comprises the steps of: presetting an abnormal threshold T, taking the average of the weighted path lengths of the d-th electrical data in all the isolated trees as the weighted average path length of the d-th electrical data, obtaining the weighted average path lengths of all the electrical data, obtaining abnormal scores of each electrical data according to the weighted average path lengths of each electrical data using the isolated forest algorithm, and taking any electrical data as abnormal data if the abnormal score of the electrical data is greater than or equal to the abnormal threshold.

8. The power grid operation risk management method of claim 1, wherein, The method comprises the steps of: presetting a sampling time of 1 second / time, installing current sensors, voltage sensors and temperature sensors at key positions of a power grid bus, collecting current data, voltage data and temperature data as an electrical data each time, and collecting electrical data for two hours in total, each electrical data comprising three electrical parameters (current data, voltage data and temperature data). According to the order from small to large of the sampling time, all electrical parameters of the electrical data are sorted to obtain the electrical parameter sequence.

9. A power grid operation risk management system, characterized in that, Comprise: A processor and a memory, the memory stores computer program instructions, when the computer program instructions are executed by the processor, a power grid operation risk management method according to any one of claims 1-8 is realized.

Images