Virtual power plant abnormal operation data flow identification method and related equipment

Abstract

The present application provides a method for identifying abnormal operation data streams of virtual power plants and related equipment. The method includes: obtaining a first virtual power plant operation data stream; the first virtual power plant operation data stream is a virtual power plant operation data stream to be identified; cleaning the first virtual power plant operation data stream to obtain a second virtual power plant operation data stream; wherein the cleaning includes missing value filling processing and noise reduction processing; the second virtual power plant operation data stream is the virtual power plant operation data stream to be identified after cleaning; analyzing the first time series characteristics of the second virtual power plant operation data stream, and extracting the data features of the second virtual power plant operation data stream based on the first time series characteristics; calculating the similarity between the data features of the second virtual power plant operation data stream and the abnormal data features of the preset virtual power plant operation data stream; in response to determining that the similarity is greater than the first threshold, determining that the first virtual power plant operation data stream is an abnormal virtual power plant operation data stream. It has a high identification accuracy.

Description

Technical Field

[0001] The present application relates to the technical field of virtual power plant data processing, and in particular to a method for identifying abnormal operation data flow of a virtual power plant and related equipment. Background Art

[0002] A virtual power plant (VPP) is a virtual energy system that integrates distributed energy resources (such as solar panels, wind turbines, energy storage equipment, etc.) and flexible loads (such as electric vehicles, energy storage equipment, etc.) and is centrally controlled and coordinated through a smart grid management system. Due to the volatility and uncertainty of distributed energy resources, there is a large deviation between the predicted data and the actual data of virtual power plants, resulting in a high proportion of abnormal operation data. This affects the operating efficiency of the virtual power plant itself and poses a threat to the overall safety and stability of the power system. Therefore, it is of great significance to detect abnormal data flows in virtual power plants.

[0003] In the related art, the identification method of abnormal data flow in virtual power plants has problems such as poor identification accuracy. Summary of the invention

[0004] In view of this, the purpose of this application is to propose a method for identifying abnormal operation data flow of a virtual power plant and related equipment.

[0005] Based on the above objectives, the present application provides a method for identifying abnormal operation data flow of a virtual power plant, including:

[0006] Acquire a first virtual power plant operation data stream; the first virtual power plant operation data stream is a virtual power plant operation data stream to be identified;

[0007] Cleaning the first virtual power plant operation data stream to obtain a second virtual power plant operation data stream; wherein the cleaning includes missing value filling processing and noise reduction processing; the second virtual power plant operation data stream is the virtual power plant operation data stream to be identified after cleaning;

[0008] Analyzing a first time series characteristic of the second virtual power plant operation data stream, and extracting data features of the second virtual power plant operation data stream based on the first time series characteristic;

[0009] Calculating the similarity between the data features of the second virtual power plant operation data stream and the abnormal data features of the preset virtual power plant operation data stream;

[0010] In response to determining that the similarity is greater than a first threshold, determining that the first virtual power plant operation data flow is an abnormal virtual power plant operation data flow.

[0011] In some embodiments, the missing value filling process includes:

[0012] Pass-through Calculate missing values; where, K(y) is a missing value; α m and β m are respectively spline parameters of the first virtual power plant operation data stream; y a and y b are the values ​​of any two different data points in the first virtual power plant operation data stream, y is the mean value of the first virtual power plant operation data stream, k b+1 To run the calibration parameters of the data stream, p b is the distribution deviation value of the current data stream;

[0013] Based on the missing values, the operation data flow to be identified is filled.

[0014] In some embodiments, the noise reduction process is performed by Conduct, among which, L v For the designed data filter, Z k The property value of the first virtual power plant operation data flow, Z m is the mean value of the first virtual power plant operation data stream, P c are random parameters of the filter, N is the number of filter iterations, y x This is the first virtual power plant operation data stream after noise reduction. x This is the first virtual power plant operation data stream before noise reduction processing. t is the sampling time of the first virtual power plant operation data stream, m c Noise parameter values ​​for the first virtual power plant operation data stream.

[0015] In some embodiments, the cleaning further includes performing a first deduplication process before the missing value filling process; and performing a second deduplication process after the missing value filling process and before the noise reduction process.

[0016] In some embodiments, the first time series characteristics of the second virtual power plant operation data stream are analyzed by formula Conduct, among which, P(x,y) A time series function for the second virtual power plant operation data stream, d(xg ,[y x1 -y x2 ]) Distance between data streams for different second virtual power plant operations x g The time series value of the second virtual power plant operation data stream, y x1 , y x2 are the data values ​​of different second virtual power plant operation data streams, γ 1 and γ 2 are the time series parameters corresponding to different second virtual power plant operation data streams;

[0017] The data feature of the second virtual power plant operation data stream is extracted based on the first time series characteristics by formula Conduct, among which, f I The current imbalance characteristics of the extracted second virtual power plant operation data flow are I a , I b and I c are the three-phase currents of the power plant, is the mean current of the power plant, f U The voltage imbalance characteristics of the extracted second virtual power plant operation data stream are U a , U b and U c are the three-phase voltages of the power plant, is the mean voltage of the power plant, T C To extract the time characteristics of the second virtual power plant operation data flow, t c is the length of time for the extracted second virtual power plant operation data stream, V P and V h They are the operating data values ​​of the power plant at different times; P(x,y) Run the time series function of the data stream for the second virtual power plant.

[0018] In some embodiments, the similarity between the data feature of the second virtual power plant operation data stream and the abnormal data feature of the preset virtual power plant operation data stream is calculated by formula: Conduct, among which, is a similarity factor between the data feature of the second virtual power plant operation data stream and the abnormal data feature of the preset virtual power plant operation data stream, Q α （p i ） Clustering function for the data stream running for the second virtual power plant, Q β （p j ） The clustering function for the abnormal data characteristics of the preset virtual power plant operation data stream, u ab is the similarity between the data characteristics of the second virtual power plant operation data stream and the abnormal data characteristics of the preset virtual power plant operation data stream, E a is the separation of the features, is the characteristic contrast factor, S ab is the feature comparison function.

[0019] In some embodiments, the method further comprises determining abnormal data features of a preset virtual power plant operation data stream by:

[0020] In response to determining that the characteristic entropy value of the virtual power plant operation data stream is greater than a second threshold, determining that the characteristic of the virtual power plant operation data stream is the abnormal data characteristic of the preset virtual power plant operation data stream;

[0021] Among them, the characteristic entropy value of the virtual power plant operation data flow is expressed by the formula Conduct; among them, H s is the characteristic entropy value of the virtual power plant operation data stream, P s is the uncertainty of any feature in the current virtual power plant operation data stream, Current unbalance characteristic f I The weight coefficient of Voltage unbalance characteristic f U The weight coefficient of Time characteristic T C The weight coefficient of .

[0022] An embodiment of the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the methods described above when executing the program.

[0023] An embodiment of the present application also provides a non-transitory computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable a computer to execute any of the methods described above.

[0024] An embodiment of the present application further provides a computer program product, comprising computer program instructions, which, when executed on a computer, enable the computer to execute any of the methods described above.

[0025] As can be seen from the above, the method and related equipment for identifying abnormal operation data streams of virtual power plants provided in the present application are obtained by obtaining a first virtual power plant operation data stream; the first virtual power plant operation data stream is the virtual power plant operation data stream to be identified; the first virtual power plant operation data stream is cleaned to obtain a second virtual power plant operation data stream; wherein the cleaning includes missing value filling processing and noise reduction processing; the second virtual power plant operation data stream is the virtual power plant operation data stream to be identified after cleaning; the first time series characteristics of the second virtual power plant operation data stream are analyzed, and the data features of the second virtual power plant operation data stream are extracted based on the first time series characteristics; the similarity between the data features of the second virtual power plant operation data stream and the abnormal data features of the preset virtual power plant operation data stream is calculated; in response to determining that the similarity is greater than the first threshold, the first virtual power plant operation data stream is determined to be an abnormal virtual power plant operation data stream, which can have a high identification accuracy in practical applications. It can help power companies quickly and accurately discover and handle abnormal power consumption behaviors and improve the operating efficiency and economic benefits of power companies. It is of great significance to improve the operating efficiency and stability of virtual power plants and reduce their high proportion of abnormal operating data flow. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the present application or related technologies, the drawings required for use in the embodiments or related technical descriptions are briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0027] Figure 1 This is a schematic diagram of a method for identifying abnormal operation data streams of a virtual power plant according to an embodiment of the present application;

[0028] Figure 2 A schematic diagram of a data cleaning process for a virtual power plant operation data stream according to an embodiment of the present application;

[0029] Figure 3 A schematic diagram of the data cleaning process of the training set in an embodiment of the present application;

[0030] Figure 4A schematic diagram of data feature entropy values ​​of a training set according to an embodiment of the present application;

[0031] Figure 5 This is a schematic diagram of the false detection rate in the application example of this application;

[0032] Figure 6 This is a schematic diagram of a device for identifying abnormal operation data flow of a virtual power plant according to an embodiment of the present application;

[0033] Figure 7 A schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0034] In order to make the objectives, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.

[0035] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present application should be understood by people with ordinary skills in the field to which the present application belongs. The "first", "second" and similar words used in the embodiments of the present application do not represent any order, quantity or importance, but are only used to distinguish different components. "Including" or "comprising" and similar words mean that the elements or objects appearing in front of the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect.

[0036] In the related art, based on PMU event data and abnormal data model, the BIRCH algorithm is used to perform preliminary classification and abnormal detection on PMU data, calculate information entropy, adjust classification results, and thus identify abnormal data. However, the algorithm is relatively complex, resulting in low recognition efficiency of the algorithm. The method for identifying abnormal data in the master-substation channel of the dispatching automation system preprocesses the master-substation channel data, uses parameter estimation algorithm, mines periodic laws, and reorganizes data to identify abnormal data. However, due to the complexity of power system data, this method is prone to misjudgment and missed judgment, affecting the recognition accuracy. Another method is to improve the random forest algorithm, calculate the information gain rate, and select features with higher correlation to realize the recognition of abnormal data. However, due to the high noise of the data in the virtual power plant, the identification result will be overfitted, resulting in poor recognition accuracy. Another method is to collect real-time data generated by the electric energy metering device, calculate the singular value features of different data points, and verify the abnormal data. However, the algorithm has a large amount of calculation and the recognition process takes a long time.

[0037] Therefore, when the abnormal operation data identification method in the related art is applied to the abnormal identification of distributed energy resources in virtual power plants with a high proportion of abnormal operation data, there are problems such as insufficient identification accuracy, large amount of calculation or long identification time.

[0038] Based on this, the embodiments of the present application provide a method, system, and device for identifying a high proportion of abnormal operation data streams of virtual power plants, by cleaning the collected virtual power plant operation data to remove data noise. The corresponding data features are extracted from the cleaning results, the corresponding feature entropy values ​​are calculated, the abnormal features in the data stream are detected, and the anomalies in the data stream are discovered in a timely manner. By calculating the similarity between the input data features and the abnormal features, the recognition accuracy of the abnormal operation data stream is improved, and the recognition of the virtual power plant operation data stream is achieved, with high recognition accuracy in practical applications. It can help power companies quickly and accurately discover and handle abnormal electricity consumption behaviors, and improve the operating efficiency and economic benefits of power companies. Therefore, it can solve the problems of insufficient recognition accuracy, large calculation amount, or long recognition time to a certain extent.

[0039] like Figure 1 As shown, the embodiment of the present application provides a method for identifying abnormal operation data flow of a virtual power plant, including:

[0040] S100, obtaining a first virtual power plant operation data stream; the first virtual power plant operation data stream is a virtual power plant operation data stream to be identified;

[0041] S200, cleaning the first virtual power plant operation data stream to obtain a second virtual power plant operation data stream; wherein the cleaning includes missing value filling processing and noise reduction processing; the second virtual power plant operation data stream is the virtual power plant operation data stream to be identified after cleaning;

[0042] S300, analyzing a first time series characteristic of the second virtual power plant operation data stream, and extracting data features of the second virtual power plant operation data stream based on the first time series characteristic;

[0043] S400, calculating the similarity between the data features of the second virtual power plant operation data stream and the abnormal data features of the preset virtual power plant operation data stream;

[0044] S500: In response to determining that the similarity is greater than a first threshold, determining that the first virtual power plant operation data flow is an abnormal virtual power plant operation data flow.

[0045] The method for identifying abnormal operation data streams of virtual power plants provided in the embodiment of the present application is as follows: obtaining a first virtual power plant operation data stream; the first virtual power plant operation data stream is the virtual power plant operation data stream to be identified; cleaning the first virtual power plant operation data stream to obtain a second virtual power plant operation data stream; wherein the cleaning includes missing value filling processing and noise reduction processing; the second virtual power plant operation data stream is the virtual power plant operation data stream to be identified after cleaning; analyzing the first time series characteristics of the second virtual power plant operation data stream, extracting the data features of the second virtual power plant operation data stream based on the first time series characteristics; calculating the similarity between the data features of the second virtual power plant operation data stream and the abnormal data features of the preset virtual power plant operation data stream; in response to determining that the similarity is greater than the first threshold, determining that the first virtual power plant operation data stream is an abnormal virtual power plant operation data stream, which can have a high identification accuracy in practical applications. It can help power companies quickly and accurately discover and handle abnormal electricity consumption behaviors and improve the operating efficiency and economic benefits of power companies. It is of great significance to improve the operating efficiency and stability of virtual power plants and reduce their high proportion of abnormal operation data streams.

[0046] In some of the embodiments, in step S100, the first virtual power plant operation data stream can be obtained by installing various sensors and monitoring equipment inside the virtual power plant, collecting data such as the power generation of distributed energy equipment and transmitting it to a data center, converting it into a digital signal and storing it.

[0047] In some embodiments, in step S200, cleaning the first virtual power plant operation data stream may include a first deduplication process: removing duplicate values ​​in the first virtual power plant operation data stream; a missing value filling process: filling the missing values ​​in the first virtual power plant operation data stream; a second deduplication process: removing duplicate values ​​in the first virtual power plant operation data stream after the missing value filling. That is, the cleaning includes a missing value filling process and a noise reduction process; the cleaning also includes a first deduplication process before the missing value filling process; and a second deduplication process after the missing value filling process and before the noise reduction process.

[0048] In some embodiments, the schematic diagram of the first deduplication process can be as follows: Figure 2 Wherein, the missing value filling process may include:

[0049] Pass-through (1) Calculate missing values; where: K(y) is a missing value; α m and β m are respectively spline parameters of the first virtual power plant operation data stream;y a and y b are the values ​​of any two different data points in the first virtual power plant operation data stream, y is the average value of the data flow of the entire first virtual power plant operation, k b+1 To run the calibration parameters of the data stream, p b is the distribution deviation value of the current data stream; it should be understood that y a and b are the values ​​of any two different data points selected from the same first virtual power plant operation data stream.

[0050] Based on the missing values, the operation data flow to be identified is filled.

[0051] In this way, missing values ​​of the virtual power plant operation data stream (such as the first virtual power plant operation data stream or the virtual power plant operation data stream used to determine the abnormal data characteristics) can be filled, and the integrity of the virtual power plant operation data stream (such as the first virtual power plant operation data stream or the virtual power plant operation data stream used to determine the abnormal data characteristics) can be ensured. Through the second deduplication process, the filled duplicate virtual power plant operation data stream can be screened out and deleted, further improving the quality of the virtual power plant operation data stream.

[0052] In some embodiments, the noise reduction process can be performed by the formula (2) Conduct, among which, L v For the designed data filter, Z k The property value of the first virtual power plant operation data flow, Z m is the mean value of the first virtual power plant operation data stream, P c are random parameters of the filter, N is the number of filter iterations, y x This is the first virtual power plant operation data stream after noise reduction. x This is the first virtual power plant operation data stream before noise reduction processing. t is the sampling time of the first virtual power plant operation data stream, m c Noise parameter values ​​for the first virtual power plant operation data stream.

[0053] In this way, after the above-mentioned first deduplication processing, missing value filling processing, second deduplication processing and denoising processing, the data cleaning of the virtual power plant operation data stream (such as the first virtual power plant operation data stream or the virtual power plant operation data stream used to determine the characteristics of abnormal data) can be completed, the quality of the virtual power plant operation data stream (such as the first virtual power plant operation data stream or the virtual power plant operation data stream used to determine the characteristics of abnormal data) can be effectively improved, and the accuracy and consistency of the data in the virtual power plant operation data stream (such as the first virtual power plant operation data stream or the virtual power plant operation data stream used to determine the characteristics of abnormal data) can be improved, laying the foundation for the subsequent feature extraction of the virtual power plant operation data stream (such as the second virtual power plant operation data stream or the virtual power plant operation data stream used to determine the characteristics of abnormal data), and improving the reliability of the data analysis results.

[0054] In some embodiments, in step S300, the first time series characteristics of the second virtual power plant operation data stream are analyzed by the formula: (3) Conduct, among which, P (x,y) A time series function for the second virtual power plant operation data stream, d(x g ,[y x1 -y x2 ]) Distance between data streams for different second virtual power plant operations x g The time series value of the second virtual power plant operation data stream, y x1 , y x2 are the data values ​​of different second virtual power plant operation data streams, γ 1 and γ 2 are time series parameters corresponding to different second virtual power plant operation data flows. In this way, the time series characteristics of the virtual power plant high-proportion operation data flow can be analyzed through the above formula (3), and multiple features of the virtual power plant operation data flow can be extracted based on this formula.

[0055] The data features of the second virtual power plant operation data stream extracted based on the first time series characteristics can be obtained by the formula (4) Conduct, among which, The current imbalance characteristics of the extracted second virtual power plant operation data flow are I a , I b and I c are the three-phase currents of the power plant, is the mean current of the power plant, f U The voltage imbalance characteristics of the extracted second virtual power plant operation data stream are U a , U b and U c are the three-phase voltages of the power plant, is the mean voltage of the power plant, T C To extract the time characteristics of the second virtual power plant operation data flow, t c is the length of time for the extracted second virtual power plant operation data stream, V P and V h They are the operating data values ​​of the power plant at different times; P(x,y) Run the time series function of the data stream for the second virtual power plant.

[0056] In this way, multiple features of the virtual power plant operation data stream (such as the second virtual power plant operation data stream or the virtual power plant operation data stream used to determine the abnormal data features) can be extracted through formula (5). It is convenient to detect the abnormal features of the virtual power plant operation data stream (such as the second virtual power plant operation data stream or the virtual power plant operation data stream used to determine the abnormal data features) through subsequent steps, and the abnormalities in the data stream can be discovered in time.

[0057] In step S400, in some embodiments, the method may further include determining abnormal data features of a preset virtual power plant operation data stream by:

[0058] Acquire a third virtual power plant operation data stream; the third virtual power plant operation data stream is a virtual power plant operation data stream used to determine abnormal data characteristics;

[0059] Cleaning the third virtual power plant operation data stream to obtain a fourth virtual power plant operation data stream; wherein the cleaning includes missing value filling processing and noise reduction processing; the fourth virtual power plant operation data stream is a cleaned virtual power plant operation data stream used to determine abnormal data characteristics;

[0060] Analyzing a second time series characteristic of the fourth virtual power plant operation data stream, and extracting data features of the fourth virtual power plant operation data stream based on the second time series characteristic;

[0061] Calculating a characteristic entropy value of the fourth virtual power plant operation data stream;

[0062] In response to determining that the characteristic entropy value of the fourth virtual power plant operation data flow (ie, the fourth virtual power plant operation data flow) is greater than a second threshold, determining that the characteristic of the virtual power plant operation data flow is the abnormal data characteristic of the preset virtual power plant operation data flow.

[0063] It can be understood that in the method for determining the abnormal data characteristics of the preset virtual power plant operation data stream, the specific content of each step can be the same as the specific content of each step in the aforementioned virtual power plant abnormal operation data stream identification method. Specifically, the missing value can be calculated by formula (1), where the meaning of the parameter can be changed to the corresponding parameter of the third virtual power plant operation data stream. The noise reduction processing can be calculated by formula (2), where the meaning of the parameter can be changed to the corresponding parameter of the third virtual power plant operation data stream. The second time series characteristics can be calculated by formula (3), where the meaning of the parameter can be changed to the corresponding parameter of the fourth virtual power plant operation data stream. The data feature can be calculated by formula (4), where the meaning of the parameter can be changed to the corresponding parameter of the fourth virtual power plant operation data stream.

[0064] In some embodiments, the characteristic entropy value of the virtual power plant operation data stream (that is, the fourth virtual power plant operation data stream) is expressed by the formula: Conduct; among them, H s is the characteristic entropy value of the virtual power plant operation data stream, P s is the uncertainty of any feature in the current virtual power plant operation data stream, , , are the weight coefficients of the corresponding features. Specifically, Current imbalance characteristics of the data flow for the fourth virtual power plant operation f I The weight coefficient of . Voltage imbalance characteristics for the fourth virtual power plant operation data flow f U The weight coefficient of . Temporal characteristics of data flows for the fourth virtual power plant operation T C The weight coefficient of .

[0065] In this way, when the characteristic entropy value of the virtual power plant operation data stream is greater than the second threshold, the current feature is determined as an abnormal feature, so that the preset abnormal data feature of the virtual power plant operation data stream is obtained. On the contrary, when the characteristic entropy value of the virtual power plant operation data stream is less than or equal to the second threshold, the current feature is determined as a normal feature. Afterwards, the identification result of the operation data stream (such as the second virtual power plant operation data stream) of the virtual power plant during operation can be obtained according to the similarity between the preset abnormal data feature and the data feature of the subsequent virtual power plant operation data stream to be identified (such as the second virtual power plant operation data stream). The abnormal data feature is determined by the characteristic entropy value of the virtual power plant operation data stream (such as the fourth virtual power plant operation data stream). Subsequently, only the data feature needs to be compared with the abnormal data feature to obtain the identification result, which can improve the efficiency of the identification result recognition to a certain extent. And because the determination of the abnormal feature data is to comprehensively calculate the characteristic entropy values ​​of different data streams, the more representative data features of the abnormal operation data stream of the virtual power plant in the data features screened out are data features, so it has a higher accuracy.

[0066] In some embodiments, the calculation of the similarity between the data features of the second virtual power plant operation data stream and the abnormal data features of the preset virtual power plant operation data stream can be performed by the formula: (6) Conduct, among which, is a similarity factor between the data feature of the second virtual power plant operation data stream and the abnormal data feature of the preset virtual power plant operation data stream, Q α （p i ） Clustering function for the data stream running for the second virtual power plant, Q β （p j ） The clustering function for the abnormal data characteristics of the preset virtual power plant operation data stream, u ab is the similarity between the data characteristics of the second virtual power plant operation data stream and the abnormal data characteristics of the preset virtual power plant operation data stream, E a is the separation of the features, is the characteristic contrast factor, S ab is the feature comparison function.

[0067] In this way, the similarity between the data features of the virtual power plant operation data stream (eg, the second virtual power plant operation data stream) and the abnormal data features of the preset virtual power plant operation data stream can be calculated.

[0068] In some of the embodiments, step S500 further includes, in response to determining that the similarity is not greater than (ie, less than or equal to) a first threshold, determining that the first virtual power plant operation data flow / the second virtual power plant operation data flow is a normal data flow.

[0069] In this way, by detecting the abnormal characteristics of a high proportion of virtual power plant abnormal operation data streams (such as the first virtual power plant operation data stream or the second virtual power plant operation data stream), abnormal patterns or behaviors in the virtual power plant operation data streams can be accurately identified, which helps to improve the accuracy of identifying abnormal operation data streams.

[0070] The method for identifying abnormal operation data streams of virtual power plants in the embodiments of the present application can effectively monitor and identify potential operational anomalies in virtual power plants, and timely and accurately extract fault information, which helps operation and maintenance personnel to quickly take corresponding measures to avoid the expansion of faults. At the same time, through in-depth analysis of abnormal data streams, it can also reveal weak links and potential risks in the operation of the power grid, providing strong support for the improvement and optimization of the power grid. In addition, the method for identifying abnormal operation data streams of virtual power plants in the embodiments of the present application can also enhance the resilience and risk resistance of the power grid, and help promote the efficient use of energy and green development.

[0071] Verification Example

[0072] In order to verify the effectiveness of the virtual power plant abnormal operation data stream identification method of the present application in practical applications, experimental tests were carried out.

[0073] 1.1 Experimental data: In the experiment, a large number of virtual power plant operation data streams are obtained through the real-time monitoring system of a real power plant, and these virtual power plant operation data streams are divided into a training set (that is, the third virtual power plant operation data stream) and a test set (for example, the first virtual power plant operation data stream). Among them, the data volume of the training set (that is, the third virtual power plant operation data stream) can be 2405 virtual power plant operation data streams, which are used to extract abnormal data features of the virtual power plant operation data stream. The test set can be divided into 8 sets, and each virtual power plant operation data stream sample can contain multiple features. The specific situation of the experimental test set is shown in Table 1.

[0074] Table 1 Experimental test set

[0075]

[0076] The experimental test set is used to conduct experimental tests.

[0077] 1.2 Experimental environment: The specific environment settings are as follows: Python 3.x is used as the programming language, Pandas is used as the data processing tool, Ubuntu 20.04 LTS is used as the operating system, TensorFlow is used as the machine learning system, VisualStudio Code is used as the development tool, and Matplotlib is used as the visualization tool. This provides a stable operating environment for the various algorithms in the embodiments of this application.

[0078] In the above environment, corresponding experimental parameters are set. The specific experimental parameters can be shown in Table 2.

[0079] Table 2 Experimental parameters

[0080]

[0081] It should be understood that these parameters need to be set and adjusted according to specific experimental conditions.

[0082] 1.3 Experimental Methods The abnormal operation data flow identification method of the virtual power plant (algorithm 1), the PMU abnormal data identification algorithm based on flow clustering (algorithm 2) and the abnormal data identification of the master-substation channel of the dispatching automation system (algorithm 3) of the embodiment of the present application are respectively used to identify the abnormal operation data flow of the virtual power plant.

[0083] Among them, the abnormal data characteristics of the preset virtual power plant operation data flow in Algorithm 1 are determined: In the experiment, the cleaning method in the virtual power plant abnormal operation data flow identification method of the embodiment of the present application is used to clean the training set (that is, the third virtual power plant operation data flow). The data cleaning process can be as follows: Figure 3 shown.

[0084] like Figure 3 As shown, there are a lot of interference factors in the original virtual power plant operation data stream, which leads to large data deviation and large amplitude fluctuation. The cleaning method in the virtual power plant abnormal operation data stream identification method of the embodiment of the present application is used to clean the data, thereby improving the quality of the data in the virtual power plant operation data stream.

[0085] On the basis of the above, the data features of the training set (i.e., the third virtual power plant operation data stream) are extracted by using the (data feature extraction and feature entropy value calculation method) in the virtual power plant abnormal operation data stream identification method of the embodiment of the present application, and the corresponding feature entropy value is calculated. The data features and feature entropy values ​​of the training set (i.e., the third virtual power plant operation data stream) calculated by the calculation can be shown as follows: Figure 4 shown.

[0086] like Figure 4As shown, the threshold value of the feature entropy value can be 0.75. There are 6 data feature entropy values ​​of the above training set (that is, the third virtual power plant operation data flow) that exceed the set threshold. The 6 features are set as abnormal features of the virtual power plant operation data flow, and the preset abnormal data features of the virtual power plant operation data flow are obtained. The above 8 test sets (for example, the first virtual power plant operation data flow) are used for abnormal identification.

[0087] Among them, for Algorithm 2, that is, the parameter settings and specific methods in the PMU abnormal data identification algorithm based on flow clustering can directly adopt the existing methods, and this application does not involve the improvement of the existing PMU abnormal data identification algorithm based on flow clustering. For Algorithm 3, that is, the parameter settings and specific methods in the abnormal data identification algorithm of the master-substation channel of the dispatching automation system can directly adopt the existing methods, and this application does not involve the improvement of the existing related methods.

[0088] 1.4 Experimental Results

[0089] Algorithm 1, Algorithm 2 and Algorithm 3 are used to identify anomalies in the data of 8 test sets respectively. The experimental results can be shown in Table 3 and Figure 5 Table 3 shows the number of abnormal data flows detected by Algorithm 1, Algorithm 2 and Algorithm 3. To further verify the effects of the above three algorithms in practical applications, the false detection rate of the algorithm is used as the evaluation index to compare the recognition accuracy of the three algorithms. Figure 5 The comparison chart of the false detection rate of the recognition results of Algorithm 1, Algorithm 2 and Algorithm 3. The false detection rate of each test set can be calculated as follows: False detection rate = FP / (FP+TN). Among them, FP is the amount of data that is actually abnormal but judged to be normal; TN is the amount of data that is actually abnormal but also judged to be abnormal. The false detection rate of each algorithm can be the average of the false detection rates of the 8 test sets.

[0090] Table 3 Identification results of three algorithms

[0091]

[0092] 1.5 Results Analysis

[0093] According to Table 3, for different test sets, the method of the embodiment of the present application can basically identify all abnormal operation data in the test set, and the recognition accuracy is good. Algorithm 2 has some abnormal operation data that cannot be identified, and in the identification process of Algorithm 3, there is a situation where normal data is identified as abnormal data, and the recognition accuracy is poor. Therefore, the virtual power plant abnormal operation data flow identification method of the embodiment of the present application has a high recognition accuracy in practical applications.

[0094] according to Figure 5It can be seen that the false detection rate of algorithm 1 is relatively low, all below 5%, while the false detection rates of algorithm 2 and algorithm 3 are relatively high, up to more than 40%, and the recognition accuracy is relatively poor. Therefore, the virtual power plant abnormal operation data flow identification method of the embodiment of the present application has a high recognition accuracy in practical applications.

[0095] It is understandable that before using the technical solutions of each embodiment of the present disclosure, the type, scope of use, usage scenarios, etc. of the personal information involved will be informed to the user in an appropriate manner, and the user's authorization will be obtained.

[0096] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly remind the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can independently choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0097] As an optional but non-limiting implementation, in response to receiving the user's active request, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0098] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0099] It should be noted that the method of the embodiment of the present application can be performed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only perform one or more steps in the method of the embodiment of the present application, and the multiple devices will interact with each other to complete the described method.

[0100] It should be noted that the above describes some embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0101] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a device for identifying abnormal operation data flow of a virtual power plant.

[0102] refer to Figure 6 The virtual power plant abnormal operation data flow identification device 800 comprises:

[0103] The acquisition module 810 is used to acquire a first virtual power plant operation data stream; the first virtual power plant operation data stream is a virtual power plant operation data stream to be identified;

[0104] A cleaning module 820 is used to clean the first virtual power plant operation data stream to obtain a second virtual power plant operation data stream; wherein the cleaning includes missing value filling processing and noise reduction processing; the second virtual power plant operation data stream is the virtual power plant operation data stream to be identified after cleaning;

[0105] An analysis module 830 is configured to analyze a first time series characteristic of the second virtual power plant operation data stream, and extract data features of the second virtual power plant operation data stream based on the first time series characteristic;

[0106] A calculation module 840, configured to calculate a similarity between a data feature of the second virtual power plant operation data stream and an abnormal data feature of a preset virtual power plant operation data stream;

[0107] The judgment module 850 is used to determine that the first virtual power plant operation data flow is an abnormal virtual power plant operation data flow in response to determining that the similarity is greater than a first threshold.

[0108] In some embodiments, the missing value filling process includes:

[0109] Pass-through Calculate missing values; where, K(y) is a missing value; α m and β m are respectively spline parameters of the first virtual power plant operation data stream; y a and y b are the values ​​of any two different data points in the first virtual power plant operation data stream, y is the average value of the data flow of the entire first virtual power plant operation, k b+1 To run the calibration parameters of the data stream, p b is the distribution deviation value of the current data stream;

[0110] Based on the missing values, the operation data flow to be identified is filled.

[0111] In some embodiments, the noise reduction process is performed by Conduct, among which, L v For the designed data filter, Z k The property value of the first virtual power plant operation data flow, Z m is the mean value of the first virtual power plant operation data stream, P c are random parameters of the filter, N is the number of filter iterations, y x This is the first virtual power plant operation data stream after noise reduction. x This is the first virtual power plant operation data stream before noise reduction processing. t is the sampling time of the first virtual power plant operation data stream, m c Noise parameter values ​​for the first virtual power plant operation data stream.

[0112] In some embodiments, the cleaning module also includes a first deduplication submodule and a second deduplication submodule, wherein the first deduplication submodule is used to perform a first deduplication process before the missing value filling process; the second deduplication submodule is used to perform a second deduplication process after the missing value filling process and before the noise reduction process.

[0113] In some embodiments, the first time series characteristics of the second virtual power plant operation data stream are analyzed by formula Conduct, among which, P(x,y) A time series function for the second virtual power plant operation data stream, d(x g ,[y x1 -y x2 ]) Distance between data streams for different second virtual power plant operations x g The time series value of the second virtual power plant operation data stream, y x1 , y x2 are the data values ​​of different second virtual power plant operation data streams, γ 1 and γ 2 are the time series parameters corresponding to different second virtual power plant operation data streams;

[0114] The data feature of the second virtual power plant operation data stream is extracted based on the first time series characteristics by formula Conduct, among which, f I The current imbalance characteristics of the extracted second virtual power plant operation data flow are I a , I b and I c are the three-phase currents of the power plant, is the mean current of the power plant, f U The voltage imbalance characteristics of the extracted second virtual power plant operation data stream are U a , U b and U c are the three-phase voltages of the power plant, is the mean voltage of the power plant, T C To extract the time characteristics of the second virtual power plant operation data flow, t c is the length of time for the extracted second virtual power plant operation data stream, V P and V h They are the operating data values ​​of the power plant at different times; P(x,y) Run the time series function of the data stream for the second virtual power plant.

[0115] In some embodiments, the similarity between the data feature of the second virtual power plant operation data stream and the abnormal data feature of the preset virtual power plant operation data stream is calculated by formula: Conduct, among which, is a similarity factor between the data feature of the second virtual power plant operation data stream and the abnormal data feature of the preset virtual power plant operation data stream, Q α （p i ） Clustering function for the data stream running for the second virtual power plant, Q β （p j ） The clustering function for the abnormal data characteristics of the preset virtual power plant operation data stream, u ab is the similarity between the data characteristics of the second virtual power plant operation data stream and the abnormal data characteristics of the preset virtual power plant operation data stream, E a is the separation of the features, is the characteristic contrast factor,S ab is the feature comparison function.

[0116] In some embodiments, the device for identifying abnormal operation data flow of a virtual power plant further includes an abnormal data feature determination module, and the abnormal data feature determination module is used to determine the abnormal data feature of the preset virtual power plant operation data flow by the following method:

[0117] In response to determining that the characteristic entropy value of the virtual power plant operation data stream is greater than a second threshold, determining that the characteristic of the virtual power plant operation data stream is the abnormal data characteristic of the preset virtual power plant operation data stream;

[0118] Among them, the characteristic entropy value of the virtual power plant operation data flow is expressed by the formula Conduct; among them, H s is the characteristic entropy value of the virtual power plant operation data stream, P s is the uncertainty of any feature in the current virtual power plant operation data stream, Current unbalance characteristic f I The weight coefficient of Voltage unbalance characteristic f U The weight coefficient of Time characteristic T C The weight coefficient of .

[0119] For the convenience of description, the above device is described in terms of functions divided into various modules. Of course, when implementing the present application, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0120] The device of the above-mentioned embodiment is used to implement the corresponding virtual power plant abnormal operation data flow identification method in any of the above-mentioned embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0121] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for identifying abnormal operation data flow of a virtual power plant as described in any of the above embodiments is implemented.

[0122] Figure 7A more specific schematic diagram of the hardware structure of an electronic device provided in this embodiment is shown, and the device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are connected to each other through the bus 1050 in the device.

[0123] The processor 1010 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0124] The memory 1020 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 may store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program codes are stored in the memory 1020 and are called and executed by the processor 1010.

[0125] The input / output interface 1030 is used to connect the input / output module to realize information input and output. The input / output module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0126] The communication interface 1040 is used to connect a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0127] The bus 1050 includes a path that transmits information between the various components of the device (eg, the processor 1010 , the memory 1020 , the input / output interface 1030 , and the communication interface 1040 ).

[0128] It should be noted that, although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040 and the bus 1050, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include the components necessary for implementing the embodiments of the present specification, and does not necessarily include all the components shown in the figure.

[0129] The electronic device of the above-mentioned embodiment is used to implement the corresponding virtual power plant abnormal operation data flow identification method in any of the above-mentioned embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0130] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the method for identifying abnormal operation data flow of a virtual power plant as described in any of the above embodiments.

[0131] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0132] The computer instructions stored in the storage medium of the above embodiment are used to enable the computer to execute the method for identifying abnormal operation data flow of a virtual power plant as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0133] Based on the same inventive concept, corresponding to the method for identifying abnormal operation data flow of a virtual power plant described in any of the above embodiments, the present disclosure also provides a computer program product, which includes computer program instructions. In some embodiments, the computer program instructions can be executed by one or more processors of a computer so that the computer and / or the processor execute the method for identifying abnormal operation data flow of a virtual power plant. Corresponding to the execution subject corresponding to each step in each embodiment of the method for identifying abnormal operation data flow of a virtual power plant, the processor that executes the corresponding step may belong to the corresponding execution subject.

[0134] The computer program product of the above embodiment is used to enable the computer and / or the processor to execute the method for identifying abnormal operation data flow of a virtual power plant as described in any of the above embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0135] A person skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present application (including the claims) is limited to these examples. In line with the concept of the present application, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of simplicity.

[0136] In addition, to simplify the description and discussion, and in order not to make the embodiments of the present application difficult to understand, the known power / ground connections to the integrated circuit (IC) chip and other components may or may not be shown in the provided drawings. In addition, the device may be shown in the form of a block diagram to avoid making the embodiments of the present application difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform on which the embodiments of the present application are to be implemented (that is, these details should be fully within the scope of understanding of those skilled in the art). Where specific details (e.g., circuits) are set forth to describe exemplary embodiments of the present application, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details or with changes in these specific details. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0137] Although the present application has been described in conjunction with specific embodiments of the present application, many alternatives, modifications and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the discussed embodiments.

[0138] The embodiments of the present application are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present application should be included in the scope of protection of the present application.

Claims

1. A method for identifying abnormal operation data flow of a virtual power plant, characterized in that: include: Acquire a first virtual power plant operation data stream; The first virtual power plant operation data flow is a virtual power plant operation data flow to be identified; Cleaning the first virtual power plant operation data stream to obtain a second virtual power plant operation data stream; wherein the cleaning includes missing value filling processing and noise reduction processing; the second virtual power plant operation data stream is the virtual power plant operation data stream to be identified after cleaning; Analyzing a first time series characteristic of the second virtual power plant operation data stream, and extracting data features of the second virtual power plant operation data stream based on the first time series characteristic; Calculating the similarity between the data features of the second virtual power plant operation data stream and the abnormal data features of the preset virtual power plant operation data stream; In response to determining that the similarity is greater than a first threshold, determining that the first virtual power plant operation data flow is an abnormal virtual power plant operation data flow; The method further includes determining abnormal data features of a preset virtual power plant operation data stream by: In response to determining that the characteristic entropy value of the virtual power plant operation data stream is greater than a second threshold, determining that the characteristic of the virtual power plant operation data stream is the abnormal data characteristic of the preset virtual power plant operation data stream; Among them, the characteristic entropy value of the virtual power plant operation data flow is expressed by the formula Conduct; among them, H s is the characteristic entropy value of the virtual power plant operation data stream, P s is the uncertainty of any feature in the current virtual power plant operation data stream, Current unbalance characteristic f I The weight coefficient of Voltage unbalance characteristic f U The weight coefficient of Time characteristic T C The weight coefficient of The data feature of the second virtual power plant operation data stream is extracted based on the first time series characteristics by formula Conduct, among which, f I The current imbalance characteristics of the extracted second virtual power plant operation data flow are I a , I b and I c are the three-phase currents of the power plant, is the mean current of the power plant, f U The voltage imbalance characteristics of the extracted second virtual power plant operation data stream are U a , U b and U c are the three-phase voltages of the power plant, is the mean voltage of the power plant, T C To extract the time characteristics of the second virtual power plant operation data flow, t c is the length of time for the extracted second virtual power plant operation data stream, V P and V h They are the operating data values ​​of the power plant at different times; P(x,y) Run the time series function of the data stream for the second virtual power plant.

2. The method for identifying abnormal operation data flow of a virtual power plant according to claim 1, characterized in that: The missing value filling process includes: Pass-through Calculate missing values; where, K(y) is a missing value; α m and β m are respectively spline parameters of the first virtual power plant operation data stream; y a and y b are the values ​​of any two different data points in the first virtual power plant operation data stream, y is the mean value of the first virtual power plant operation data stream, k b+1 To run the calibration parameters of the data stream, p b is the distribution deviation value of the current data stream; Based on the missing values, the running data flow to be identified is filled.

3. The method for identifying abnormal operation data flow of a virtual power plant according to claim 1, characterized in that: The noise reduction process is performed by Conduct, among which, L v For the designed data filter, Z k The property value of the first virtual power plant operation data flow, Z m is the mean value of the first virtual power plant operation data stream, P c are random parameters of the filter, N is the number of filter iterations, y x This is the first virtual power plant operation data stream after noise reduction. x This is the first virtual power plant operation data stream before noise reduction processing. t is the sampling time of the first virtual power plant operation data stream, m c Noise parameter values ​​for the first virtual power plant operation data stream.

4. The method for identifying abnormal operation data flow of a virtual power plant according to claim 2, characterized in that: The cleaning further includes performing a first deduplication process before the missing value filling process; and performing a second deduplication process after the missing value filling process and before the noise reduction process.

5. The method for identifying abnormal operation data flow of a virtual power plant according to claim 1, characterized in that: The first time series characteristics of the second virtual power plant operation data stream are analyzed by formula Conduct, among which, P(x,y) A time series function for the second virtual power plant operation data stream, d(x g ,[y x1 -y x2 ]) Distance between data streams for different second virtual power plant operations x g The time series value of the second virtual power plant operation data stream, y x1 , y x2 are the data values ​​of different second virtual power plant operation data streams, γ 1 and γ 2 are the time series parameters corresponding to different second virtual power plant operation data streams.

6. The method for identifying abnormal operation data flow of a virtual power plant according to claim 1, characterized in that: The similarity between the data characteristics of the second virtual power plant operation data stream and the abnormal data characteristics of the preset virtual power plant operation data stream is calculated by the formula Conduct, among which, is a similarity factor between the data feature of the second virtual power plant operation data stream and the abnormal data feature of the preset virtual power plant operation data stream, Q α （p i ） Clustering function for the data stream running for the second virtual power plant, Q β （p j ） The clustering function for the abnormal data characteristics of the preset virtual power plant operation data stream, u ab is the similarity between the data characteristics of the second virtual power plant operation data stream and the abnormal data characteristics of the preset virtual power plant operation data stream, E a is the separation of the features, is the characteristic contrast factor, S ab is the feature comparison function.

7. A device for identifying abnormal operation data flow of a virtual power plant, characterized in that: include: An acquisition module, used for acquiring a first virtual power plant operation data stream; The first virtual power plant operation data flow is a virtual power plant operation data flow to be identified; A cleaning module, used for cleaning the first virtual power plant operation data stream to obtain a second virtual power plant operation data stream; wherein the cleaning includes missing value filling processing and noise reduction processing; the second virtual power plant operation data stream is the virtual power plant operation data stream to be identified after cleaning; an analysis module, configured to analyze a first time series characteristic of the second virtual power plant operation data stream, and extract data features of the second virtual power plant operation data stream based on the first time series characteristic; A calculation module, used for calculating the similarity between the data characteristics of the second virtual power plant operation data flow and the abnormal data characteristics of the preset virtual power plant operation data flow; a judgment module, configured to determine, in response to determining that the similarity is greater than a first threshold, that the first virtual power plant operation data flow is an abnormal virtual power plant operation data flow; The abnormal data feature determination module is used to determine the abnormal data features of the preset virtual power plant operation data flow by the following method: In response to determining that the characteristic entropy value of the virtual power plant operation data stream is greater than a second threshold, determining that the characteristic of the virtual power plant operation data stream is the abnormal data characteristic of the preset virtual power plant operation data stream; Among them, the characteristic entropy value of the virtual power plant operation data flow is expressed by the formula Conduct; among them, H s is the characteristic entropy value of the virtual power plant operation data stream, P s is the uncertainty of any feature in the current virtual power plant operation data stream, Current unbalance characteristic f I The weight coefficient of Voltage unbalance characteristic f U The weight coefficient of Time characteristic T C The weight coefficient of Wherein, the data features of the second virtual power plant operation data stream extracted based on the first time series characteristics are expressed as follows: Conduct, among which, f I The current imbalance characteristics of the extracted second virtual power plant operation data flow are I a , I b and I c are the three-phase currents of the power plant, is the mean current of the power plant, f U The voltage imbalance characteristics of the extracted second virtual power plant operation data stream are U a , U b and U c are the three-phase voltages of the power plant, is the mean voltage of the power plant, T C To extract the time characteristics of the second virtual power plant operation data flow, t c is the length of time for the extracted second virtual power plant operation data stream, V P and V h They are the operating data values ​​of the power plant at different times; P(x,y) Run the time series function of the data stream for the second virtual power plant.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any one of claims 1 to 6 when executing the program.

9. A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute the method according to any one of claims 1 to 6.

Images