Method for fast location of abnormal values ​​in basic operation data of new energy power grid

Abstract

The present application discloses a method for fast positioning of abnormal values ​​of basic operation data of new energy power grid, the method comprising: obtaining data samples; standardizing the data samples to obtain standard samples; calculating multiple mathematical expectations of operation data corresponding to multiple evaluation indicators in the standard samples; calculating the absolute value of the difference between the average value of multiple mathematical expectations and each mathematical expectation, obtaining multiple first judgment values, and determining the evaluation indicator corresponding to the first judgment value greater than the preset value as the evaluation indicator where the abnormal value is located; calculating the difference between the operation data corresponding to the evaluation indicator where the abnormal value is located and the corresponding mathematical expectation, obtaining multiple second judgment values, and determining the original data corresponding to the maximum value among the multiple second judgment values ​​as the abnormal value. When using this method to locate abnormal values, there is no need to compare one by one, and the abnormal value can be found through rapid calculation by a computer.

Description

Technical Field

[0001] The present application relates to the technical field of data anomaly processing, and in particular to a method for quickly locating abnormal values ​​in basic operation data of a new energy power grid. Background Art

[0002] In the evaluation process of new energy power grids, a large amount of high-quality raw data is the basis for calculating samples. However, in the actual data collection and statistical process, individual data anomalies often occur. The existence of these outliers may have a serious impact on the evaluation of the stability and security of the new energy power grid, and thus cause the evaluation results to deviate from reality. Such inaccurate evaluation may not only cause huge economic losses, but also endanger the safe and stable operation of the new energy power grid.

[0003] At present, the common method of abnormal data screening usually relies on comparing data one by one to determine the outliers. However, this method faces significant challenges: on the one hand, one-by-one comparison requires a lot of manpower and time; on the other hand, this method is inefficient and unfeasible when faced with massive amounts of raw data. Therefore, the existing outlier screening methods are difficult to meet the actual needs of rapid and accurate evaluation after a high proportion of new energy is connected to the power grid. Summary of the invention

[0004] The embodiments of the present application provide a method for quickly locating outliers in basic operating data of a new energy power grid, thereby solving the technical problem that existing outlier screening methods are difficult to meet the actual needs of rapid and accurate evaluation after a high proportion of new energy is connected to the power grid.

[0005] In a first aspect, an embodiment of the present application provides a method for quickly locating abnormal values ​​in basic operating data of a new energy power grid, the method comprising: obtaining a data sample; wherein the data sample comprises operating data of multiple operating schemes of the new energy power grid; standardizing the data sample to obtain a standard sample; calculating multiple mathematical expectations of operating data corresponding to multiple evaluation indicators in the standard sample; calculating the absolute value of the difference between an average value of the multiple mathematical expectations and each of the mathematical expectations to obtain multiple first judgment values, and determining the evaluation indicator corresponding to the first judgment value that is greater than a preset value as the evaluation indicator where the abnormal value is located; calculating the difference between the operating data corresponding to the evaluation indicator where the abnormal value is located and the corresponding mathematical expectation to obtain multiple second judgment values, and determining that the original data corresponding to the maximum value among the multiple second judgment values ​​is the abnormal value.

[0006] In combination with the first aspect, in a possible implementation method, before determining the evaluation indicator corresponding to the first judgment value greater than a preset value as the evaluation indicator where the abnormal value is located, the method also includes: calculating the standard deviation based on the multiple mathematical expectations and the average value of the multiple mathematical expectations; wherein the preset value is the standard deviation of a preset multiple.

[0007] In combination with the first aspect, in a possible implementation manner, the standardizing the data sample to obtain a standard sample includes: standardizing the operating data corresponding to the evaluation indicator belonging to the positive indicator by the following formula: ; The operating data corresponding to the evaluation index belonging to the negative index is standardized by the following formula: ;in, data representing the jth evaluation index of the i-th operation scheme, express After standardization, represents the maximum value of the jth evaluation index, Represents the minimum value of the j-th evaluation index.

[0008] In combination with the first aspect, in a possible implementation manner, the data samples and the standard samples are both in matrix form.

[0009] In a second aspect, an embodiment of the present application provides a device for quickly locating abnormal values ​​of basic operating data of a new energy power grid, the device comprising: an acquisition module for acquiring data samples; wherein the data samples include operating data of multiple operating schemes of the new energy power grid; a standardization module for standardizing the data samples to obtain standard samples; a first calculation module for calculating multiple mathematical expectations of operating data corresponding to multiple evaluation indicators in the standard samples; a second calculation module for calculating the absolute value of the difference between the average value of the multiple mathematical expectations and each of the mathematical expectations to obtain multiple first judgment values; a first determination module for determining the evaluation indicator corresponding to the first judgment value greater than the preset value as the evaluation indicator where the abnormal value is located; a third calculation module for calculating the difference between the operating data corresponding to the evaluation indicator where the abnormal value is located and the corresponding mathematical expectation to obtain multiple second judgment values; a second determination module for determining that the original data corresponding to the maximum value of the multiple second judgment values ​​is an abnormal value.

[0010] In a third aspect, an embodiment of the present application provides an electronic device, comprising: one or more processors; and a memory storing computer executable instructions, wherein the computer executable instructions, when executed by the one or more processors, enable the one or more processors to perform the above-mentioned method.

[0011] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions implement the above method when executed by a computer.

[0012] The technical solution provided in the embodiments of the present application has at least the following technical effects: The embodiment of the present application provides a method for quickly locating abnormal values ​​of basic operation data of a new energy power grid. The method obtains a standard sample by standardizing the data sample, calculates multiple first judgment values ​​according to the standard sample, determines the evaluation index where the abnormal value is located by comparing the multiple first judgment values ​​with the preset values, and calculates multiple second judgment values ​​according to the standard sample, and determines the abnormal value by comparing the multiple second judgment values. Therefore, when using this method to locate abnormal values, there is no need to compare one by one, and the abnormal value can be found through the rapid calculation of the computer, thereby meeting the actual needs of rapid and accurate evaluation after a high proportion of new energy is connected to the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments of the present application will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0014] Figure 1 A flow chart of a method for quickly locating abnormal values ​​in basic operation data of a new energy power grid provided in an embodiment of the present application; Figure 2 A schematic diagram of a device for quickly locating abnormal values ​​in basic operating data of a new energy power grid provided in an embodiment of the present application. DETAILED DESCRIPTION

[0015] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0016] The terms "first", "second", and "third" are used for descriptive purposes only and should not be understood as indicating or implying relative importance. The term "plurality" refers to two or more. For those of ordinary skill in the art, the specific meanings of the above terms in the embodiments of the present application can be understood according to specific circumstances.

[0017] like Figure 1 As shown, an embodiment of the present application provides a method for quickly locating abnormal values ​​of basic operation data of a new energy power grid, and the method includes steps S101 to S107.

[0018] S101. Obtain data samples; wherein the data samples include operation data of multiple operation plans of the new energy power grid.

[0019] S102. Standardize the data samples to obtain standard samples.

[0020] S103. Calculate multiple mathematical expectations of operating data corresponding to multiple evaluation indicators in the standard sample.

[0021] S104, calculating the absolute value of the difference between an average value of multiple mathematical expectations and each mathematical expectation to obtain multiple first judgment values.

[0022] S105: Determine the evaluation index corresponding to the first judgment value that is greater than the preset value as the evaluation index where the abnormal value is located.

[0023] S106. Calculate the difference between the operating data corresponding to the evaluation index where the abnormal value is located and the corresponding mathematical expectation to obtain multiple second judgment values.

[0024] S107: Determine that the original data corresponding to the maximum value among the plurality of second judgment values ​​is an abnormal value.

[0025] The method obtains a standard sample by standardizing the data sample, calculates multiple first judgment values ​​based on the standard sample, determines the evaluation index where the abnormal value is located by comparing the multiple first judgment values ​​with the preset values, and calculates multiple second judgment values ​​based on the standard sample, and determines the abnormal value by comparing the multiple second judgment values. Therefore, when using this method to locate the abnormal value, there is no need to compare one by one, and the abnormal value can be found through the rapid calculation of the computer, thereby meeting the actual needs of rapid and accurate evaluation after a high proportion of new energy is connected to the power grid.

[0026] In the embodiment of the present application, before step S105, the method further includes: calculating a standard deviation according to a plurality of mathematical expectations and an average value of the plurality of mathematical expectations, wherein the preset value is a preset multiple of the standard deviation. For example, the preset multiple is 2 times.

[0027] Specifically, step S102 includes step S201 and step S202.

[0028] S201. The operation data corresponding to the evaluation index belonging to the positive index is standardized by the following formula: .

[0029] S202, the operation data corresponding to the evaluation index belonging to the negative index is standardized by the following formula: .

[0030] in, represents the data of the jth evaluation index of the i-th operation scheme, After standardization, represents the maximum value of the jth evaluation index, Represents the minimum value of the jth evaluation index.

[0031] Specifically, in the embodiment of the present application, the data samples and standard samples are in matrix form. The data samples and standard samples in matrix form can be calculated more conveniently, and some computing software has functions for calculating the mathematical expectation, standard deviation, average value, etc. of the matrix, which can be realized by simply calling.

[0032] A specific example is provided below to illustrate the above method in detail.

[0033] Step 1: obtain the original data of multiple operation schemes of the new energy grid shown in Table 1, and construct the original data shown in Table 1 into an original data matrix , the original data matrix As data samples, Table 1 shows 20 operation schemes and 12 evaluation indicators.

[0034] Table 1

[0035] Original data matrix as follows: .

[0036] Step 2: Standardize the data sample to obtain the standard matrix , The standard matrix As a standard sample. Standard matrix as follows: .

[0037] Step 3: Multiple mathematical expectations of the operating data corresponding to multiple evaluation indicators in the standard sample, that is, the standard matrix Find the mathematical expectation of each column in the formula as follows: ;in, is the standard matrix The mathematical expectation of the jth column, It is the standardized data of the jth evaluation index of the i-th operation scheme.

[0038] Specifically, the mathematical expectation solution results are shown in Table 2.

[0039] Table 2

[0040] Step 4: Calculate the expected average value A of multiple data. The calculation formula is as follows: The calculation result is .

[0041] Step 5: Calculate the standard deviation of multiple mathematical expectations , the calculation formula is as follows: The calculation result is .

[0042] Step 6: Calculate the absolute value of the difference between the average value of multiple mathematical expectations and each mathematical expectation to obtain multiple first judgment values. , the calculation formula is as follows: , the calculation results of step six are shown in Table 3.

[0043] Table 3

[0044] Step 7: Determine the evaluation index where the outlier is located. If value, then the jth evaluation index is the evaluation index where the outlier value is located. ,From Table 3, we can see that the second evaluation index “frequency response time” is the ,evaluation index where the outliers are located.

[0045] Step 8: Calculate the difference between the original data of each operation scheme in the jth evaluation index determined in step 7 and the jth mathematical expectation to obtain multiple second judgment values. , multiple second judgment values ​​are shown in Table 4.

[0046] Table 4

[0047] Step 9: Determine that the raw data corresponding to the maximum value among the multiple second judgment values ​​is an abnormal value. From Table 4, it can be seen that the second judgment value corresponding to the third operation scheme is the largest, so the raw data of the "frequency response time" of the third operation scheme is an abnormal value, and from Table 1, it can be seen that the abnormal value is "8.084".

[0048] like Figure 2 As shown, an embodiment of the present application also provides a device 200 for quickly locating abnormal values ​​of basic operation data of a new energy power grid, wherein the device 200 includes an acquisition module 201, a standardization module 202, a first calculation module 203, a second calculation module 204, a first determination module 205, a third calculation module 206 and a second determination module 207.

[0049] The acquisition module 201 is used to acquire data samples; wherein the data samples include operating data of multiple operating schemes of the new energy power grid. The standardization module 202 is used to standardize the data samples to obtain standard samples. The first calculation module 203 is used to calculate multiple mathematical expectations of operating data corresponding to multiple evaluation indicators in the standard sample. The second calculation module 204 is used to calculate the absolute value of the difference between the average value of multiple mathematical expectations and each mathematical expectation to obtain multiple first judgment values. The first determination module 205 is used to determine the evaluation indicator corresponding to the first judgment value greater than the preset value as the evaluation indicator where the abnormal value is located. The third calculation module 206 is used to calculate the difference between the operating data corresponding to the evaluation indicator where the abnormal value is located and the corresponding mathematical expectation, and obtain multiple second judgment values. The second determination module 207 is used to determine that the original data corresponding to the maximum value among the multiple second judgment values ​​is an abnormal value.

[0050] The device 200 for quickly locating abnormal values ​​of basic operation data of a new energy power grid also includes a fourth calculation module. Before the first determination module 205 determines the evaluation index corresponding to the first judgment value greater than the preset value as the evaluation index where the abnormal value is located, the fourth calculation module is used to calculate the standard deviation based on multiple mathematical expectations and the average value of the multiple mathematical expectations; wherein the preset value is a preset multiple of the standard deviation.

[0051] The standardization module 202 is specifically used to standardize the operation data corresponding to the evaluation index belonging to the positive index by the following formula: , the operating data corresponding to the evaluation indicators belonging to the positive indicators are standardized by the following formula: ,in, represents the data of the jth rating indicator of the i-th running scheme, After standardization, represents the maximum value of the jth evaluation index, Represents the minimum value of the jth evaluation index.

[0052] Furthermore, both the data samples and the standard samples are in matrix form.

[0053] The system or module described in the above embodiment can be implemented by a computer chip or entity, or by a product with a certain function. For the convenience of description, the above system is described by dividing it into various modules according to its function. When implementing the embodiment of the present application, the functions of each module can be implemented in the same or more software and / or hardware. Of course, the module that implements a certain function can also be implemented by combining multiple sub-modules or sub-units.

[0054] An embodiment of the present application also provides an electronic device, which includes: one or more processors; and a memory storing computer-executable instructions, wherein the computer-executable instructions, when executed by the one or more processors, enable the one or more processors to perform the above-mentioned method.

[0055] An embodiment of the present application provides a computer-readable storage medium, which stores computer-readable instructions. When the computer-readable instructions are executed by a computer, the above method is implemented.

[0056] The above-mentioned storage media include but are not limited to random access memory (RAM), read-only memory (ROM), cache, hard disk drive (HDD) or memory card (Memory Card).

[0057] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other. Each embodiment focuses on the differences from other embodiments.

[0058] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit the present application. Although the present application has been described in detail with reference to the aforementioned embodiments, a person of ordinary skill in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some or all of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the present application.

Claims

1. A method for quickly locating abnormal values ​​of new energy power grid basic operation data, characterized in that: include: Acquire data samples; wherein the data samples include operation data of multiple operation schemes of the new energy power grid; Standardizing the data sample to obtain a standard sample; Calculating multiple mathematical expectations of operating data corresponding to multiple evaluation indicators in the standard sample; Calculate the absolute value of the difference between the average value of the multiple mathematical expectations and each of the mathematical expectations to obtain multiple first judgment values, and determine the evaluation index corresponding to the first judgment value greater than a preset value as the evaluation index where the abnormal value is located; The difference between the operating data corresponding to the evaluation index where the abnormal value is located and the corresponding mathematical expectation is calculated to obtain multiple second judgment values, and the original data corresponding to the maximum value among the multiple second judgment values ​​is determined to be the abnormal value.

2. The method according to claim 1, characterized in that Before determining the evaluation index corresponding to the first judgment value greater than a preset value as the evaluation index where the abnormal value is located, the method further includes: Calculating a standard deviation according to the multiple mathematical expectations and an average of the multiple mathematical expectations; The preset value is a preset multiple of the standard deviation.

3. The method according to claim 1, characterized in that The step of standardizing the data sample to obtain a standard sample includes: The operating data corresponding to the evaluation index belonging to the positive index is standardized by the following formula: ; The operating data corresponding to the evaluation index belonging to the negative index is standardized by the following formula: ; in, data representing the jth evaluation index of the i-th operation scheme, express After standardization, represents the maximum value of the jth evaluation index, Represents the minimum value of the j-th evaluation index.

4. The method according to claim 1, characterized in that The data samples and the standard samples are both in matrix form.

5. A device for quickly locating abnormal values ​​of basic operation data of new energy power grid, characterized in that: include: An acquisition module, used to acquire data samples; wherein the data samples include operation data of multiple operation schemes of the new energy power grid; A standardization module, used to standardize the data sample to obtain a standard sample; A first calculation module, used to calculate multiple mathematical expectations of operating data corresponding to multiple evaluation indicators in the standard sample; A second calculation module, used for calculating the absolute value of the difference between the average value of the multiple mathematical expectations and each of the mathematical expectations, to obtain multiple first judgment values; A first determining module, configured to determine the evaluation index corresponding to the first judgment value greater than the preset value as the evaluation index where the abnormal value is located; A third calculation module is used to calculate the difference between the operation data corresponding to the evaluation index where the abnormal value is located and the corresponding mathematical expectation to obtain multiple second judgment values; The second determination module is used to determine that the original data corresponding to the maximum value among the plurality of second judgment values ​​is an abnormal value.

6. An electronic device, characterized in that: include: one or more processors; as well as A memory storing computer executable instructions which, when executed by the one or more processors, cause the one or more processors to perform the method of any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a computer, the method according to any one of claims 1 to 4 is implemented.

Images