Power grid information cleaning method and device, nonvolatile storage medium and electronic equipment

Abstract

The invention discloses a power grid information cleaning method and device, a nonvolatile storage medium and electronic equipment. The method comprises the following steps: acquiring a plurality of power grid information subgroups in one-to-one correspondence with a plurality of power grid points; dividing the plurality of power grid information subgroups into a plurality of initial groups; according to the similarity between any two starting groups, combining the plurality of starting groups and forming a plurality of spaces; clustering the power grid information of the same data type for multiple times in the plurality of spaces by adopting different compatibility degrees to obtain a plurality of clustering results; determining respective selection amplitude of the power grid information according to the plurality of clustering results; finally grouping the power grid information in the plurality of spaces according to the respective selection amplitude of the power grid information, and determining the respective error amplitude of the power grid information; and according to the respective error amplitude of the power grid information, eliminating the error power grid information. The technical problem that error information of a plurality of types of power grid information cannot be accurately distinguished is solved.

Description

Technical Field

[0001] The present invention relates to the field of power system information processing, and in particular to a power grid information cleaning method, device, non-volatile storage medium and electronic equipment. Background Art

[0002] With the continuous improvement of the informatization and intelligence of the power grid, it is necessary to store the power grid information. Specifically, the processor module transmits the collected power grid information to the big data platform for storage. The power grid information includes several types of electrical parameters such as voltage, current, power, frequency, harmonics, etc. In order to correctly store several types of power grid information, it is necessary to correctly clean out the error information in several types of power grid information.

[0003] The current error information cleaning method for several types of power grid information is to obtain an error detection model by performing grouping processing on several types of power grid information in the past. In this model, the error amplitude of the power grid information is determined by calculating the interval between each power grid information and the corresponding group midpoint. However, for several types of power grid information, during the iterative grouping, the error information in some information will be rigidly classified into the group with the lowest interval, so that when the number of information in the group is compared with the pre-set minimum number of group information, some error information is also totaled, so that an incorrect error detection model is constructed, thereby causing incorrect error information detection of several types of power grid information, which is not conducive to the storage of power grid information.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present invention provide a power grid information cleaning method, device, non-volatile storage medium and electronic device to at least solve the technical problem that erroneous information of several types of power grid information cannot be accurately distinguished.

[0006] According to one aspect of an embodiment of the present invention, a power grid information cleaning method is provided, including: acquiring different types of power grid information of each of a plurality of power grid points to obtain a plurality of power grid information subgroups corresponding one-to-one to the plurality of power grid points; dividing the plurality of power grid information subgroups into a plurality of starting groups according to data types of the plurality of power grid information subgroups; merging the plurality of starting groups into a plurality of spaces according to the similarity between any two of the plurality of starting groups; clustering the power grid information of the same data type multiple times in the plurality of spaces using different compatibilities to obtain a plurality of clustering results, wherein the plurality of clustering results correspond one-to-one to the plurality of compatibilities; determining the respective selection ranges of the power grid information according to the plurality of clustering results; finally grouping the power grid information in the plurality of spaces according to the respective selection ranges of the power grid information to determine the respective error ranges of the power grid information; and removing the erroneous power grid information according to the respective error ranges of the power grid information.

[0007] Optionally, according to the data types of the multiple power grid information subgroups, the multiple power grid information subgroups are divided into a plurality of starting groups, including: classifying the power grid information included in the multiple power grid information subgroups according to the data type, determining a reference quantity one for each of the multiple types of power grid information, wherein the reference quantity one characterizes the smoothness of the change of the corresponding type of power grid information; determining an average of the reference quantity one for each of the multiple types of power grid information, and obtaining a reference quantity two for each of the multiple types of power grid information; selecting the data type with the largest reference quantity two as the reference type; and dividing the multiple power grid information subgroups into a plurality of starting groups according to the reference type.

[0008] Optionally, according to the reference type, multiple power grid information subgroups are divided into multiple starting groups, including: determining the average of the information values ​​of the reference type in the multiple power grid information subgroups respectively to obtain the reference characterization quantity of each of the multiple power grid information subgroups; based on the reference characterization quantities of each of the multiple power grid information subgroups, using a clustering algorithm to cluster the multiple power grid information subgroups to obtain multiple starting groups.

[0009] Optionally, according to the similarity between any two of the multiple starting groups, merging the multiple starting groups to form multiple spaces includes: determining the similarity between any two of the multiple starting groups; merging two starting groups whose similarity is greater than a predetermined similarity threshold value to obtain multiple spaces.

[0010] Optionally, determining the similarity between any two of the multiple starting groups includes: using the following method to determine the similarity between a reference group and a target group to determine the similarity between any two of the multiple starting groups: determining a change ratio one of the target type of data within the reference group, and a change ratio two of the target type of data within the target group; determining the difference between the change ratio one and the change ratio two as a distinguishing amount of the target type; determining the distinguishing amounts of each of the multiple types of data according to the above-mentioned method of determining the distinguishing amount of the target type, wherein the multiple types are data types of power grid information; determining the similarity between the reference group and the target group based on the distinguishing amounts of each of the multiple types of data.

[0011] Optionally, based on multiple clustering results, the selection range of each power grid information is determined, including: based on multiple clustering results, determining the compatibility of each power grid information, wherein the compatibility is used to describe the stability of the clustering results of the corresponding power grid information under different compatibilities; based on the compatibility, determining the selection range of each power grid information.

[0012] According to another aspect of an embodiment of the present invention, a power grid information cleaning device is provided, comprising: an acquisition module for acquiring different types of power grid information of each of a plurality of power grid points, and obtaining a plurality of power grid information subgroups corresponding one-to-one to the plurality of power grid points; a first grouping module for dividing the plurality of power grid information subgroups into a plurality of starting groups according to the data types of the plurality of power grid information subgroups; a merging module for merging the plurality of starting groups into a plurality of spaces according to the similarity between any two of the plurality of starting groups; a clustering module for clustering the power grid information of the same data type multiple times in the plurality of spaces using different compatibilities, and obtaining a plurality of clustering results, wherein the plurality of clustering results correspond one-to-one to the plurality of compatibilities; a determination module for determining the respective selection ranges of the power grid information according to the plurality of clustering results; a second grouping module for finally grouping the power grid information in the plurality of spaces according to the respective selection ranges of the power grid information, and determining the respective error ranges of the power grid information; and a clearing module for clearing the erroneous power grid information according to the respective error ranges of the power grid information.

[0013] According to another aspect of an embodiment of the present invention, a non-volatile storage medium is provided. The non-volatile storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing any one of the power grid information cleaning methods.

[0014] According to another aspect of an embodiment of the present invention, there is provided an electronic device, comprising: one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by one or more processors, the one or more processors implement any one of the power grid information cleaning methods.

[0015] According to another aspect of the embodiments of the present invention, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, any one of the above-mentioned power grid information cleaning methods is implemented.

[0016] In an embodiment of the present invention, by acquiring different types of grid information of each of the multiple grid points, a plurality of grid information subgroups corresponding to the multiple grid points are obtained; according to the data types of the multiple grid information subgroups, the multiple grid information subgroups are divided into a plurality of starting groups; according to the similarity between any two starting groups in the plurality of starting groups, the plurality of starting groups are merged to form a plurality of spaces; in the plurality of spaces, different compatibilities are used to perform multiple clustering on the grid information of the same data type to obtain a plurality of clustering results, wherein the plurality of clustering results correspond to the plurality of compatibilities one-to-one; according to the plurality of clustering results, the respective selection ranges of the grid information are determined; according to the respective selection ranges of the grid information, the grid information is finally grouped in the plurality of spaces to determine the respective error ranges of the grid information; according to the respective error ranges of the grid information, the erroneous grid information is cleared, thereby solving the technical problem that the erroneous information of several types of grid information cannot be accurately distinguished, achieving the purpose of accurately distinguishing the erroneous information in several types of grid information, and further realizing the technical effect of improving the accuracy of grid information storage. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0018] Figure 1 is a flow chart of a power grid information cleaning method provided according to an embodiment of the present invention;

[0019] Figure 2 is a schematic diagram of a power grid information cleaning device provided according to an embodiment of the present invention;

[0020] Figure 3 is a schematic diagram of an electronic device provided according to an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0022] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0023] According to an embodiment of the present invention, a method embodiment of power grid information cleaning is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0024] Figure 1 is a flow chart of a method for cleaning power grid information according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0025] Step S102, acquiring different types of grid information of each of the plurality of grid points, and obtaining a plurality of grid information subgroups corresponding one-to-one to the plurality of grid points;

[0026] In this step, the collection of power grid information is synchronously performed on several pre-set power grid locations within the power grids. Several types of power grid information collected and digitized at the same power grid location form a power grid information subgroup at the power grid location, and the power grid information subgroups at each power grid location are obtained in turn.

[0027] Step S104, dividing the plurality of power grid information subgroups into a plurality of starting groups according to data types of the plurality of power grid information subgroups;

[0028] In this step, according to the information value changes of adjacent elements in different power grid information subgroups, the reference amount of each category is determined and the reference category is selected. Then, the reference category in each power grid information subgroup is grouped according to the average information value of the reference category to obtain several starting groups.

[0029] In an optional embodiment, the multiple power grid information subgroups are divided into multiple starting groups according to their data types, including: classifying the power grid information included in the multiple power grid information subgroups according to the data type, determining a reference quantity one for each of the multiple types of power grid information, wherein the reference quantity one characterizes the smoothness of the change of the corresponding type of power grid information; determining an average of the reference quantity one for each of the multiple types of power grid information, and obtaining a reference quantity two for each of the multiple types of power grid information; selecting the data type with the largest reference quantity two as the reference type; and dividing the multiple power grid information subgroups into multiple starting groups according to the reference type.

[0030] Optionally, for any type of category in any power grid information subgroup, the least squares method is used to construct a type time-series change regression line for several power grid information of this type in the power grid information subgroup; the slope measure is calculated for each element in the type time-series change regression line, and the slope measure calculation is performed on the current element and its adjacent previous element, and the obtained slope measure is used as the slope measure of the current element. The slope measure calculation is not performed on the first element. The method for obtaining the slope measure is to obtain the tangent value of the angle between the line connecting the current element and its adjacent previous element on the type time-series change regression line and the X-axis, and the tangent value is the slope measure of the current element.

[0031] After obtaining a number of slope quantities, obtain the modulus of the quantity obtained by subtracting the slope quantities of two adjacent elements, and use the average of all such moduli as the starting reference quantity of the type in the power grid information subgroup; perform anti-correlation normalization on the starting reference quantity, and define the obtained value as the reference quantity one of the type in the power grid information subgroup; calculate the reference quantity one of each type in each power grid information subgroup in accordance with the above method, and use the average of all reference quantities one as the reference quantity two of the type; obtain the reference quantity one of each type in each power grid information subgroup, obtain the reference quantity two of each type, use the type with the highest reference quantity two as the reference type, and divide the multiple power grid information subgroups into multiple starting groups according to the reference type.

[0032] In an optional embodiment, multiple power grid information subgroups are divided into multiple starting groups according to the reference type, including: determining the average of the information values ​​of the reference type in the multiple power grid information subgroups respectively to obtain the reference characterization quantity of each of the multiple power grid information subgroups; based on the reference characterization quantities of each of the multiple power grid information subgroups, clustering the multiple power grid information subgroups using a clustering algorithm to obtain multiple starting groups.

[0033] Optionally, for any power grid information subgroup, obtain the average of the information values ​​of the reference type of all power grid information in the power grid information subgroup, and define it as the reference characterization value of the power grid information subgroup; obtain the reference characterization value of each power grid information subgroup, and use a hierarchical clustering algorithm to group all power grid information subgroups according to the reference characterization value, and obtain a number of groups by grouping, which are defined as a number of starting groups, and each starting group contains a number of power grid information subgroups.

[0034] Step S106, merging the multiple starting groups into multiple spaces according to the similarity between any two starting groups in the multiple starting groups;

[0035] In this step, the similarity between the grid information values ​​of different starting groups is determined based on their changes, and then similar starting groups are grouped together to obtain some grid information subgroups, which contain the spatial information of the corresponding grids. In other words, by comparing the changes in grid information, the connections and similarities between grids can be determined and grouped to better understand the spatial information of their locations.

[0036] In an optional embodiment, based on the similarity between any two of the multiple starting groups, the multiple starting groups are merged to form multiple spaces, including: determining the similarity between any two of the multiple starting groups; merging two starting groups whose similarity is greater than a predetermined similarity threshold value to obtain multiple spaces.

[0037] Optionally, an approximate critical amount is defined in advance. If the approximate amplitude of the target starting group and the reference starting group is higher than the approximate critical amount, a combination is performed on a number of grid locations corresponding to a number of grid information subgroups respectively included in the target starting group and the reference starting group, and the combination is regarded as a space. The approximate amplitude is obtained for an arbitrary pair of starting groups. If the approximate amplitude is higher than the approximate critical amount, a combination is performed on a number of grid locations corresponding to a number of grid information subgroups included in the starting group, and finally a number of spaces can be obtained, each space containing a number of grid locations, and the approximate amplitude of the starting group where the grid information subgroup corresponding to an arbitrary pair of grid locations in the same space is higher than the approximate critical amount.

[0038] In an optional embodiment, according to determining the similarity between any two starting groups among a plurality of starting groups, the method includes: using the following method to determine the similarity between a reference group and a target group to determine the similarity between any two starting groups among a plurality of starting groups: determining a change ratio one of the target type of data within the reference group, and a change ratio two of the target type of data within the target group; determining the difference between the change ratio one and the change ratio two as a distinguishing amount of the target type; determining the distinguishing amounts of each of a plurality of types of data according to the above-mentioned method of determining the distinguishing amount of the target type, wherein the plurality of types are data types of power grid information; determining the similarity between the reference group and the target group according to the distinguishing amounts of each of the plurality of types of data.

[0039] Optionally, facing any type outside the reference type in any pair of starting groups, any one of the starting groups in the pair of starting groups is defined as the target starting group, the other starting group is defined as the reference starting group, any one of the power grid information subgroups in the target starting group is defined as the target power grid information subgroup, and any one of the power grid information subgroups in the reference starting group is defined as the reference power grid information subgroup. A number of power grid information of the type in the target power grid information subgroup is obtained, and the ratio of the adjacent power grid information of the type in the target power grid information subgroup is calculated, and defined as the change ratio of each power grid information of the type in the target power grid information subgroup. Obtain the change ratio of each grid information of the type in the reference grid information subgroup, obtain the modulus of the amount obtained by subtracting the change ratio of the grid information in the target grid information subgroup at a random sampling time under the type from the change ratio of the grid information in the reference grid information subgroup, and define it as the difference amplitude between the target grid information subgroup and the reference grid information subgroup at the sampling time under the type, obtain the difference amplitude between the target grid information subgroup and the reference grid information subgroup at each sampling time under the type, and define the average of all difference amplitudes as the difference amount 1 of the type between the target grid information subgroup and the reference grid information subgroup. Obtain the difference amount 1 of a random pair of grid information subgroups belonging to different starting groups in the target starting group and the reference starting group. In this way, obtain a number of difference amounts 1, and define the average of all difference amounts 1 as the difference amount 2 of the type between the target starting group and the reference starting group. Obtain the difference value 2 of each category other than the reference category in the target starting group and the reference starting group, perform anti-correlation normalization on the mean of all difference values ​​2, and define the obtained value as the approximate amplitude of the target starting group and the reference starting group.

[0040] Step S108, clustering the power grid information of the same data type multiple times in multiple spaces using different compatibilities to obtain multiple clustering results, wherein the multiple clustering results correspond to the multiple compatibilities one by one;

[0041] In this step, in a space, we can select any class as the current category and another class as the target category. There are multiple power grid points in the space, and we can obtain the power grid information subgroup of any power grid point. For each power grid information subgroup, we can calculate the time-series change regression line of the current category and the target category respectively, and calculate the Jaccard index between them to measure their similarity. By calculating the mean of the similarity between the current category and the target category at all power grids, the correlation amplitude between the current category and the target category is obtained. If the correlation amplitude is higher than the set threshold, the target category will be regarded as the reference category of the current category in the space, and other categories will also be associated and identified to obtain several reference categories. Then, we standardize the correlation amplitudes of all reference categories and the current category to obtain the correlation index of each reference category. Next, we perform the K value clustering method on the power grid information of the current category in the power grid information subgroup at each power grid to divide it into different groups. The interval between the power grid information is calculated by taking the absolute value after subtraction, and grouping is performed according to each sub-compatibility status to obtain multiple groups under different sub-compatibility status.

[0042] Step S110, determining the selection range of each power grid information according to the multiple clustering results;

[0043] In this step, based on the changes in groups of power grid information under adjacent secondary compatibility conditions and the changes in groups under corresponding other types, the compatibility of each power grid information in each type of each space under various compatibility conditions is obtained, and the selection range of each element of each power grid information is obtained based on the changes in the compatibility.

[0044] In an optional embodiment, the selection range of each power grid information is determined based on multiple clustering results, including: determining the compatibility of each power grid information based on multiple clustering results, wherein the compatibility is used to describe the stability of the clustering results of the corresponding power grid information under different compatibilities; determining the selection range of each power grid information based on the compatibility.

[0045] Optionally, the calculation equation of the compatibility of the w-th grid information of each spatial current type under the j-th compatibility condition is:

[0046]

[0047] In the equation, μ w (j) represents the grid information compatibility index of the wth grid information of the current type of the space under the jth compatible condition, ξ w (j) the type compatibility index of the wth grid information of the current type of the space under the jth compatible condition, γ1 and γ2 are reference criticality; The average of the adjacent intervals of the group in which the w-th power grid information of the current type of the space belongs under the j-th compatible condition; represents the average of the adjacent interval intervals of the group in which the wth grid information of the current type of the space belongs under the j-1th compatible state; e is the Euler number; P represents the number of reference types of the current type in the space, s p Characterizes the correlation index of the current species with the pth reference species in this space, PNJ w,p (j) represents the group similarity of the wth grid information of the current type of the space under the jth compatible condition to the group of the pth reference type; PNJ w,p (j-1 represents the group similarity of the w-th grid information of the current type of the space in the j-1-th compatible state to the group of the p-th reference type.

[0048] Obtain the compatibility of each compatibility state of the w-th power grid information of each current type in each space except the first compatibility state, use the order of the compatibility state as the value of the X-axis, and the compatibility as the value of the Y-axis, use the least squares method to obtain the compatibility regression line of the w-th power grid information, obtain the compatibility of each compatibility state and the slope of the compatibility of the adjacent previous compatibility state based on the compatibility regression line, thereby obtaining several slopes, and use the standard deviation and mean multiplied by the total slope as the compatibility change index of the w-th power grid information, perform anti-correlation normalization on the compatibility change index, and define the obtained value as the selectivity range of the w-th power grid information, obtain the selectivity range of each power grid information of the current type in the space, and finally obtain the selectivity range of each power grid information in each type in each space.

[0049] Step S112, according to the respective selection ranges of the power grid information, the power grid information is finally grouped in a plurality of spaces to determine the respective error ranges of the power grid information;

[0050] In this step, after obtaining the selection range of each power grid information in each category of each space, a selection critical amount is defined in advance, and the grouping period under the K value clustering method is performed on any type of power grid information in several power grid information subgroups in any space. If the selection range of any power grid information is higher than the selection critical amount, the power grid information is taken as the power grid information added to the set group minimum number of power grid information during the grouping period under the K value clustering method, and the final grouping value is obtained through grouping under the K value clustering method; the grouping value is obtained for each category of each space; after obtaining the grouping value, facing any power grid information, the distance between the power grid information and the midpoint of the group with the lowest distance in the corresponding grouping value is obtained, and it is defined as the dispersion distance of the power grid information; the dispersion distance of each power grid information in the corresponding grouping value of the power grid information is obtained, and the overall dispersion distance is standardized using the (standard score method) Z-Score method, and the obtained value is defined as the error range of each power grid information.

[0051] Step S114, clearing the erroneous power grid information according to the error amplitude of each power grid information.

[0052] In this step, the error amplitude of each power grid information in each type of each space is obtained, and an error critical amount is defined in advance. If the error amplitude of the power grid information is higher than the error critical amount, the power grid information is error information. Error identification is performed on each power grid information in several types of power grid information. Finally, the identified error information is cleared and stored after cleaning.

[0053] By acquiring different types of grid information of multiple grid points, a plurality of grid information subgroups corresponding to the multiple grid points are obtained; the multiple grid information subgroups are divided into a plurality of starting groups according to the data types of the multiple grid information subgroups; the multiple starting groups are merged into a plurality of spaces according to the similarity between any two starting groups in the plurality of starting groups; in the plurality of spaces, grid information of the same data type is clustered multiple times using different compatibilities to obtain a plurality of clustering results, wherein the plurality of clustering results correspond to the plurality of compatibilities one-to-one; according to the plurality of clustering results, the respective selection ranges of the grid information are determined; according to the respective selection ranges of the grid information, the grid information is finally grouped in the plurality of spaces to determine the respective error ranges of the grid information; according to the respective error ranges of the grid information, the erroneous grid information is cleared, thereby solving the technical problem that the erroneous information of several types of grid information cannot be accurately distinguished, achieving the purpose of accurately distinguishing the erroneous information in several types of grid information, and further realizing the technical effect of improving the accuracy of grid information storage.

[0054] Based on the above embodiments and optional embodiments, the present invention proposes an optional implementation mode:

[0055] Step S1, acquiring different types of grid information of each of a plurality of grid points, and obtaining a plurality of grid information subgroups corresponding one-to-one to the plurality of grid points;

[0056] Optionally, the collection of power grid information is performed synchronously at pre-set power grid locations within several power grids, and several types of power grid information collected and digitized at the same power grid location form a power grid information subgroup at the power grid location, and the power grid information subgroups at each power grid location are obtained in turn.

[0057] Step S2, dividing the multiple power grid information subgroups into multiple starting groups according to the data types of the multiple power grid information subgroups, including: classifying the power grid information included in the multiple power grid information subgroups according to the data type, determining the reference amount one of each of the multiple types of power grid information, wherein the reference amount one characterizes the smoothness of the change of the corresponding type of power grid information; determining the average of the reference amount one of each of the multiple types of power grid information, and obtaining the reference amount two of each of the multiple types of power grid information; selecting the data type with the largest reference amount two as the reference type; and dividing the multiple power grid information subgroups into multiple starting groups according to the reference type.

[0058] Optionally, for any type of category in any power grid information subgroup, the least squares method is used to construct a type time-series change regression line for several power grid information of this type in the power grid information subgroup; the slope measure is calculated for each element in the type time-series change regression line, and the slope measure calculation is performed on the current element and its adjacent previous element, and the obtained slope measure is used as the slope measure of the current element. The slope measure calculation is not performed on the first element. The method for obtaining the slope measure is to obtain the tangent value of the angle between the line connecting the current element and its adjacent previous element on the type time-series change regression line and the X-axis, and the tangent value is the slope measure of the current element.

[0059] After obtaining a number of slope quantities, obtain the modulus of the quantity obtained by subtracting the slope quantities of two adjacent elements, and use the average of all such moduli as the starting reference quantity of the type in the power grid information subgroup; perform anti-correlation normalization on the starting reference quantity, and define the obtained value as the reference quantity one of the type in the power grid information subgroup; calculate the reference quantity one of each type in each power grid information subgroup in accordance with the above method, and use the average of all reference quantities one as the reference quantity two of the type; obtain the reference quantity one of each type in each power grid information subgroup, obtain the reference quantity two of each type, use the type with the highest reference quantity two as the reference type, and divide the multiple power grid information subgroups into multiple starting groups according to the reference type.

[0060] Step S21, according to the reference type, divides the multiple power grid information subgroups into multiple starting groups, including: determining the average of the information values ​​of the reference type in the multiple power grid information subgroups respectively, to obtain the reference characterization quantity of each of the multiple power grid information subgroups; based on the reference characterization quantity of each of the multiple power grid information subgroups, clustering the multiple power grid information subgroups using a clustering algorithm to obtain multiple starting groups.

[0061] Optionally, for any power grid information subgroup, obtain the average of the information values ​​of the reference type of all power grid information in the power grid information subgroup, and define it as the reference characterization value of the power grid information subgroup; obtain the reference characterization value of each power grid information subgroup, and use a hierarchical clustering algorithm to group all power grid information subgroups according to the reference characterization value, and obtain a number of groups by grouping, which are defined as a number of starting groups, and each starting group contains a number of power grid information subgroups.

[0062] Step S3, merging the multiple starting groups into multiple spaces according to the similarity between any two starting groups in the multiple starting groups, including: determining the similarity between any two starting groups in the multiple starting groups; merging two starting groups whose similarity is greater than a predetermined similarity threshold value to obtain multiple spaces.

[0063] Optionally, an approximate critical amount is defined in advance. If the approximate amplitude of the target starting group and the reference starting group is higher than the approximate critical amount, a combination is performed on a number of grid locations corresponding to a number of grid information subgroups respectively included in the target starting group and the reference starting group, and the combination is regarded as a space. The approximate amplitude is obtained for an arbitrary pair of starting groups. If the approximate amplitude is higher than the approximate critical amount, a combination is performed on a number of grid locations corresponding to a number of grid information subgroups included in the starting group, and finally a number of spaces can be obtained, each space containing a number of grid locations, and the approximate amplitude of the starting group where the grid information subgroup corresponding to an arbitrary pair of grid locations in the same space is higher than the approximate critical amount.

[0064] Step S31, based on determining the similarity between any two of the multiple starting groups, includes: using the following method to determine the similarity between a reference group and a target group to determine the similarity between any two of the multiple starting groups: determining a change ratio one of the target type of data in the reference group, and a change ratio two of the target type of data in the target group; determining the difference between the change ratio one and the change ratio two as a distinguishing amount of the target type; determining the distinguishing amounts of each of the multiple types of data according to the above-mentioned method of determining the distinguishing amount of the target type, wherein the multiple types are data types of power grid information; determining the similarity between the reference group and the target group based on the distinguishing amounts of each of the multiple types of data.

[0065] Optionally, facing any type outside the reference type in any pair of starting groups, any one of the starting groups in the pair of starting groups is defined as the target starting group, the other starting group is defined as the reference starting group, any one of the power grid information subgroups in the target starting group is defined as the target power grid information subgroup, and any one of the power grid information subgroups in the reference starting group is defined as the reference power grid information subgroup. A number of power grid information of the type in the target power grid information subgroup is obtained, and the ratio of the adjacent power grid information of the type in the target power grid information subgroup is calculated, and defined as the change ratio of each power grid information of the type in the target power grid information subgroup. Obtain the change ratio of each grid information of the type in the reference grid information subgroup, obtain the modulus of the amount obtained by subtracting the change ratio of the grid information in the target grid information subgroup at a random sampling time under the type from the change ratio of the grid information in the reference grid information subgroup, and define it as the difference amplitude between the target grid information subgroup and the reference grid information subgroup at the sampling time under the type, obtain the difference amplitude between the target grid information subgroup and the reference grid information subgroup at each sampling time under the type, and define the average of all difference amplitudes as the difference amount 1 of the type between the target grid information subgroup and the reference grid information subgroup. Obtain the difference amount 1 of a random pair of grid information subgroups belonging to different starting groups in the target starting group and the reference starting group. In this way, obtain a number of difference amounts 1, and define the average of all difference amounts 1 as the difference amount 2 of the type between the target starting group and the reference starting group. Obtain the difference value 2 of each category other than the reference category in the target starting group and the reference starting group, perform anti-correlation normalization on the mean of all difference values ​​2, and define the obtained value as the approximate amplitude of the target starting group and the reference starting group.

[0066] Step S4, clustering the power grid information of the same data type multiple times in multiple spaces using different compatibilities to obtain multiple clustering results, wherein the multiple clustering results correspond to the multiple compatibilities one by one;

[0067] Optionally, in a space, we can select any class as the current category and another class as the target category. There are multiple power grids in the space, and we can obtain the power grid information subgroup at any power grid. For each power grid information subgroup, we can calculate the time-series change regression line of the current category and the target category respectively, and calculate the Jaccard index between them to measure their similarity. By calculating the mean of the similarity between the current category and the target category at all power grids, the correlation amplitude between the current category and the target category is obtained. If the correlation amplitude is higher than the set threshold, the target category will be regarded as the reference category of the current category in the space, and other categories will also be associated and identified to obtain several reference categories. Then, we standardize the correlation amplitudes of all reference categories and the current category to obtain the correlation index of each reference category. Next, we perform the K-value clustering method on the power grid information of the current category in the power grid information subgroup at each power grid to divide it into different groups. The interval between the power grid information is calculated by taking the absolute value after subtraction, and grouping is performed according to each sub-compatibility status to obtain multiple groups under different sub-compatibility status.

[0068] Step S5, determining the selection range of each power grid information based on multiple clustering results, including: determining the compatibility of each power grid information based on multiple clustering results, wherein the compatibility is used to describe the stability of the clustering results of the corresponding power grid information under different compatibilities; determining the selection range of each power grid information based on the compatibility.

[0069] Optionally, the calculation equation of the compatibility of the w-th grid information of each spatial current type under the j-th compatibility condition is:

[0070]

[0071] In the equation, μ w (j) represents the grid information compatibility index of the wth grid information of the current type of the space under the jth compatible condition, ξ w (j) the type compatibility index of the wth grid information of the current type of the space under the jth compatible condition, γ1 and γ2 are reference criticality; The average of the adjacent intervals of the group in which the w-th power grid information of the current type of the space belongs under the j-th compatible condition; represents the average of the adjacent interval intervals of the group in which the wth grid information of the current type of the space belongs under the j-1th compatible state; e is the Euler number; P represents the number of reference types of the current type in the space, s p Characterizes the correlation index of the current species with the pth reference species in this space, PNJ w,p(j) represents the group similarity of the wth grid information of the current type of the space under the jth compatible condition to the group of the pth reference type; PNJ w,p (j-1 represents the group similarity of the w-th grid information of the current type of the space in the j-1-th compatible state to the group of the p-th reference type.

[0072] Obtain the compatibility of each compatibility state of the w-th power grid information of each current type in each space except the first compatibility state, use the order of the compatibility state as the value of the X-axis, and the compatibility as the value of the Y-axis, use the least squares method to obtain the compatibility regression line of the w-th power grid information, obtain the compatibility of each compatibility state and the slope of the compatibility of the adjacent previous compatibility state based on the compatibility regression line, thereby obtaining several slopes, and use the standard deviation and mean multiplied by the total slope as the compatibility change index of the w-th power grid information, perform anti-correlation normalization on the compatibility change index, and define the obtained value as the selectivity range of the w-th power grid information, obtain the selectivity range of each power grid information of the current type in the space, and finally obtain the selectivity range of each power grid information in each type in each space.

[0073] Step S6, finally grouping the power grid information in a plurality of spaces according to the respective selection ranges of the power grid information, and determining the respective error ranges of the power grid information;

[0074] In this step, after obtaining the selection range of each power grid information in each category of each space, a selection critical amount is defined in advance, and the grouping period under the K value clustering method is performed on any type of power grid information in several power grid information subgroups in any space. If the selection range of any power grid information is higher than the selection critical amount, the power grid information is taken as the power grid information added to the set group minimum number of power grid information during the grouping period under the K value clustering method, and the final grouping value is obtained through grouping under the K value clustering method; the grouping value is obtained for each category of each space; after obtaining the grouping value, facing any power grid information, the distance between the power grid information and the midpoint of the group with the lowest distance in the corresponding grouping value is obtained, and it is defined as the dispersion distance of the power grid information; the dispersion distance of each power grid information in the corresponding grouping value of the power grid information is obtained, and the overall dispersion distance is standardized using the (standard score method) Z-Score method, and the obtained value is defined as the error range of each power grid information.

[0075] Step S7, clearing the erroneous power grid information according to the error amplitude of each power grid information.

[0076] In this step, the error amplitude of each power grid information in each type of each space is obtained, and an error critical amount is defined in advance. If the error amplitude of the power grid information is higher than the error critical amount, the power grid information is error information. Error identification is performed on each power grid information in several types of power grid information. Finally, the identified error information is cleared and stored after cleaning.

[0077] The above optional implementation achieves at least the following effects: solves the technical problem of being unable to accurately distinguish erroneous information in several types of power grid information, achieves the purpose of accurately distinguishing erroneous information in several types of power grid information, and further achieves the technical effect of improving the accuracy of power grid information storage.

[0078] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0079] In this embodiment, a power grid information cleaning device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the terms "module" and "device" can implement a combination of software and / or hardware for a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0080] According to an embodiment of the present invention, there is also provided an embodiment of a device for implementing power grid information cleaning. Figure 2 is a schematic diagram of a power grid information cleaning device according to an embodiment of the present invention. Figure 2 As shown, the above-mentioned power grid information cleaning device includes an acquisition module 21, a first grouping module 22, a merging module 23, a clustering module 24, a determination module 25, a second grouping module 26, and a clearing module 27. The device is described below.

[0081] An acquisition module 21 is used to acquire different types of grid information of each of the multiple grid points, and obtain multiple grid information subgroups corresponding to the multiple grid points one by one;

[0082] A first grouping module 22, connected to the acquisition module 21, is used to group the plurality of power grid information subgroups into a plurality of starting groups according to data types of the plurality of power grid information subgroups;

[0083] A merging module 23, connected to the first grouping module 22, is used to merge the multiple starting groups into multiple spaces according to the similarity between any two starting groups in the multiple starting groups;

[0084] The clustering module 24 is connected to the merging module 23 and is used to cluster the power grid information of the same data type multiple times in multiple spaces with different compatibilities to obtain multiple clustering results, wherein the multiple clustering results correspond to the multiple compatibilities one by one;

[0085] The determination module 25 is connected to the clustering module 24 and is used to determine the selection range of each power grid information according to the multiple clustering results;

[0086] The second grouping module 26 is connected to the determination module 25 and is used to group the power grid information in a plurality of spaces according to the respective selection ranges of the power grid information and determine the respective error ranges of the power grid information;

[0087] The clearing module 27 is connected to the second grouping module 26 and clears the erroneous power grid information according to the error amplitudes of the respective power grid information.

[0088] In a power grid information cleaning device provided by an embodiment of the present invention, an acquisition module is set to acquire different types of power grid information of each of multiple power grid points to obtain multiple power grid information subgroups corresponding to the multiple power grid points one by one; a first grouping module is used to divide the multiple power grid information subgroups into multiple starting groups according to the data types of the multiple power grid information subgroups; a merging module is used to merge the multiple starting groups into multiple spaces according to the similarity between any two starting groups in the multiple starting groups; a clustering module is used to cluster the power grid information of the same data type multiple times in multiple spaces using different compatibilities to obtain multiple clustering results, wherein the multiple clustering results correspond to the multiple compatibilities one by one; a determination module is used to determine the respective selection ranges of the power grid information according to the multiple clustering results; a second grouping module is used to finally group the power grid information in multiple spaces according to the respective selection ranges of the power grid information to determine the respective error ranges of the power grid information; a clearing module clears the erroneous power grid information according to the respective error ranges of the power grid information, thereby solving the technical problem that the erroneous information of several types of power grid information cannot be accurately distinguished, achieving the purpose of accurately distinguishing the erroneous information in several types of power grid information, and thus achieving the technical effect of improving the accuracy of power grid information storage.

[0089] It should be noted that the above modules can be implemented by software or hardware. For example, for the latter, it can be implemented in the following ways: the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0090] It should be noted that the acquisition module 21, the first grouping module 22, the merging module 23, the clustering module 24, the determination module 25, the second grouping module 26, and the clearing module 27 correspond to steps S102 to S114 in the embodiment, and the examples and application scenarios implemented by the modules and the corresponding steps are the same, but are not limited to the contents disclosed in the above embodiments. It should be noted that the modules as part of the device can be run in a computer terminal.

[0091] It should be noted that the optional or preferred implementation of this embodiment can refer to the relevant description in the embodiment, which will not be repeated here.

[0092] The above-mentioned power grid information cleaning device may also include a processor and a memory. The acquisition module 21, the first grouping module 22, the merging module 23, the clustering module 24, the determination module 25, the second grouping module 26, the clearing module 27, etc. are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize the corresponding functions.

[0093] The processor includes a kernel, which retrieves the corresponding program unit from the memory. There can be one or more kernels. The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one storage chip.

[0094] An embodiment of the present invention provides a non-volatile storage medium on which a program is stored. When the program is executed by a processor, a method for cleaning power grid information is implemented.

[0095] like Figure 3 As shown, an embodiment of the present invention provides an electronic device, the electronic device 10 includes a processor, a memory, and a program stored in the memory and executable on the processor, and the processor implements the following steps when executing the program: the memory is used to store a computer program, wherein, when the computer program is executed by the processor, the processor implements the above-mentioned power grid information cleaning method, the device in this article may be a server, a PC, etc., the device in this article may be a server, a PC, etc.

[0096] The present invention also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program initialized with the following method steps: computer instructions are executed by a processor to perform the above-mentioned power grid information cleaning method.

[0097] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0098] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0099] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0100] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0101] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0102] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0103] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules 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, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape 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. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0104] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0105] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0106] The above are only embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.

Claims

1. A method for cleaning power grid information, characterized in that: include: Acquire different types of grid information of each of the plurality of grid points to obtain a plurality of grid information subgroups corresponding one to one to the plurality of grid points; Dividing the plurality of power grid information subgroups into a plurality of starting groups according to data types of the plurality of power grid information subgroups; According to the similarity between any two starting groups in the multiple starting groups, the multiple starting groups are merged to form multiple spaces; In the multiple spaces, respectively, different compatibilities are used to cluster the power grid information of the same data type multiple times to obtain multiple clustering results, wherein the multiple clustering results correspond to the multiple compatibilities one by one; Determining the selection range of each power grid information according to the plurality of clustering results; According to the respective selection ranges of the power grid information, the power grid information is finally grouped in the plurality of spaces to determine the respective error ranges of the power grid information; According to the error magnitudes of the respective power grid information, the erroneous power grid information is cleared.

2. The method according to claim 1, characterized in that According to the data types of the plurality of power grid information subgroups, the plurality of power grid information subgroups are divided into a plurality of starting groups, including: Classifying the power grid information included in the plurality of power grid information subgroups according to data types, and determining a reference quantity one for each of the plurality of types of power grid information, wherein the reference quantity one represents a smoothness of change of the corresponding type of power grid information; Determine an average of the reference quantities 1 of the plurality of types of power grid information, and obtain the reference quantities 2 of the plurality of types of power grid information; Select the data type with the largest reference quantity 2 as the reference type; The plurality of grid information subgroups are divided into a plurality of starting groups according to the reference type.

3. The method according to claim 2, characterized in that According to the reference type, the plurality of power grid information subgroups are divided into a plurality of starting groups, including: Determining the average of the information values ​​of the reference type in the plurality of power grid information subgroups respectively, to obtain the reference characterization quantities of the plurality of power grid information subgroups respectively; Based on the reference characterizing quantities of the plurality of power grid information subgroups, a clustering algorithm is used to cluster the plurality of power grid information subgroups to obtain the plurality of starting groups.

4. The method according to claim 1, characterized in that: The step of merging the plurality of starting groups into a plurality of spaces according to the similarity between any two starting groups in the plurality of starting groups comprises: Determining the similarity between any two starting groups in the plurality of starting groups; Two initial groups whose similarity is greater than a predetermined similarity threshold are merged to obtain the multiple spaces.

5. The method according to claim 4, characterized in that Determining the similarity between any two starting groups in the plurality of starting groups comprises: The similarity between any two starting groups in the plurality of starting groups is determined by using the following method for determining the similarity between the reference group and the target group: Determine a change ratio 1 of the target type of data in the reference group, and a change ratio 2 of the target type of data in the target group; Determine the difference between the change ratio 1 and the change ratio 2 as the distinguishing amount of the target type; According to the above method of determining the difference amount of the target type, determining the difference amount of each of the multiple types of data, wherein the multiple types are data types of power grid information; The similarity between the reference group and the target group is determined according to the respective difference amounts of the multiple types of data.

6. The method according to claim 1, characterized in that Determining the selection range of each power grid information according to the plurality of clustering results includes: Determining the compatibility of each of the power grid information according to the multiple clustering results, wherein the compatibility is used to describe the stability of the clustering results of the corresponding power grid information under different compatibilities; According to the compatibility amount, the selection range of each of the power grid information is determined.

7. A power grid information cleaning device, characterized in that: include: An acquisition module, used to acquire different types of grid information of each of the plurality of grid points, and obtain a plurality of grid information subgroups corresponding one by one to the plurality of grid points; A first grouping module, configured to group the plurality of power grid information subgroups into a plurality of starting groups according to data types of the plurality of power grid information subgroups; a merging module, configured to merge the plurality of starting groups into a plurality of spaces according to the similarity between any two starting groups in the plurality of starting groups; A clustering module, used to cluster the power grid information of the same data type multiple times in the multiple spaces using different compatibilities to obtain multiple clustering results, wherein the multiple clustering results correspond to the multiple compatibilities one by one; A determination module, used to determine the selection range of each power grid information according to the multiple clustering results; A second grouping module is used to finally group the power grid information in the plurality of spaces according to the respective selection ranges of the power grid information, and determine the respective error ranges of the power grid information; The clearing module clears the erroneous power grid information according to the error magnitude of each of the power grid information.

8. A non-volatile storage medium, characterized in that: The non-volatile storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the power grid information cleaning method described in any one of claims 1 to 6.

9. An electronic device, characterized in that: include: One or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the power grid information cleaning method described in any one of claims 1 to 6.

10. A computer program product comprising computer instructions, characterized in that: The computer instructions are executed by the processor to implement the power grid information cleaning method described in any one of claims 1 to 6.

Images