An electric power use anomaly monitoring method and device, electronic equipment and storage medium

Abstract

The application discloses a kind of power consumption anomaly monitoring method, device, electronic equipment and storage medium.The method comprises: obtaining the historical power consumption data of each user in the transformer area, and determining the monitoring vector corresponding to each user according to the historical power consumption data of each user;According to the monitoring vector corresponding to each user, the monitoring matrix of the transformer area is constructed, and the local density and relative distance of each user in each user are determined according to the monitoring matrix, wherein the local density of each user is determined according to the relative density of each user in the local range determined by the monitoring matrix in the local range;According to the local density and relative distance of each user, the power consumption anomaly user is determined from each user, and the power consumption anomaly user is marked.Embodiments of the present application, the power consumption anomaly user in the transformer area is judged by using the local density and relative distance of each user, the probability of power consumption anomaly user judgment error when the local density in the range changes greatly is reduced, and the monitoring accuracy is improved.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to computer technology, and particularly relate to a power consumption anomaly monitoring method and device, electronic equipment and storage medium. BACKGROUND

[0002] In the power system, the power consumption of users is finely managed by taking a transformer area as a management unit. The transformer area with low-voltage distribution generally has the characteristics of high loss, and the power consumption anomaly in the transformer area with low-voltage distribution is the main reason for the high loss of the transformer area. The power consumption anomaly includes electricity stealing, metering failure and special load, etc. The existing power consumption monitoring method is based on the monthly meter reading power and the alarm events of the electric energy meter for analysis and judgment. However, the power consumption anomaly is usually caused by the superposition of multiple abnormal reasons, and only using the monthly meter reading power and the alarm events of the electric energy meter to determine the power consumption anomaly reduces the accuracy of positioning the power consumption anomaly user because the judgment basis is relatively single. SUMMARY

[0003] The present application provides a power consumption anomaly monitoring method, device, electronic equipment and storage medium to realize accurate judgment of power consumption anomaly users in a transformer area.

[0004] In a first aspect, the embodiments of the present application provide a power consumption anomaly monitoring method, which comprises:

[0005] obtaining historical power consumption data of each user in a transformer area, and determining a monitoring vector corresponding to each user according to the historical power consumption data of each user;

[0006] constructing a monitoring matrix of the transformer area according to the monitoring vector corresponding to each user, and determining the local density and relative distance of each user in the monitoring matrix, wherein the local density of each user is the relative density of each user with other users in a local range determined according to the monitoring matrix corresponding to the local range;

[0007] determining a power consumption anomaly user from each user according to the local density and relative distance of each user, and marking the power consumption anomaly user.

[0008] Further, determining the monitoring vector corresponding to each user according to the historical power consumption data of each user comprises:

[0009] calculating the value of each user in multiple dimension features according to the historical power consumption data of each user in the multiple dimension features to obtain the multi-dimensional feature value of each user;

[0010] determining the monitoring vector corresponding to each user according to the multi-dimensional feature value of each user.

[0011] Further, determining the local density of each user in the users according to the monitoring matrix comprises:

[0012] Calculating the average potential energy of the multiple dimensional features corresponding to each user according to the multiple dimensional eigenvalues of each user in the monitoring matrix;

[0013] Determining the distance between each pair of users in the users according to the average potential energy of the multiple dimensional features corresponding to each user and the monitoring matrix;

[0014] Determining the local density of each user in the users according to the distance between each pair of users in the users and the adjustable parameter set.

[0015] Further, determining the distance between each pair of users in the users according to the average potential energy of the multiple dimensional features corresponding to each user and the monitoring matrix comprises:

[0016] Determining the distance weight of the multiple dimensional features corresponding to each user according to the average potential energy of the multiple dimensional features corresponding to each user;

[0017] Determining the distance between each pair of users in the users according to the distance weight of the multiple dimensional features corresponding to each user and the multiple dimensional eigenvalues of each user in the monitoring matrix.

[0018] Further, determining the relative distance of each user in the users according to the monitoring matrix comprises:

[0019] Calculating the average potential energy of the multiple dimensional features corresponding to each user according to the multiple dimensional eigenvalues of each user in the monitoring matrix;

[0020] Determining the distance between each pair of users in the users according to the average potential energy of the multiple dimensional features corresponding to each user and the monitoring matrix;

[0021] Determining the local density of each user in the users according to the distance between each pair of users in the users and the adjustable parameter set.

[0022] Determining the relative distance of each user in the users according to the distance between each pair of users in the users and the local density of each user in the users.

[0023] Further, determining the relative distance of each user in the users according to the distance between each pair of users in the users and the local density of each user in the users comprises:

[0024] Selecting a local user with a local density less than the local density of each user in the users from the users;

[0025] determine a distance between each of the users and the local user corresponding to the each of the users, and take a square root of a minimum distance between each of the users and the local user corresponding to the each of the users to obtain a relative distance value of each of the users.

[0026] Further, the abnormal user is determined from the users according to the local density and the relative distance of each of the users, and the abnormal user is marked.

[0027] An abnormal factor corresponding to each of the users is determined according to the local density and the adjustable parameter set of each of the users.

[0028] The user whose abnormal factor exceeds a preset abnormal threshold and whose relative distance is greater than a total relative distance value of the area is determined as the abnormal user.

[0029] In a second aspect, an embodiment of the present application further provides an abnormal power consumption monitoring device, which comprises:

[0030] A vector determination module is configured to acquire historical power consumption data of users in an area, and determine a monitoring vector corresponding to each of the users according to the historical power consumption data of the users.

[0031] A distance determination module is configured to construct a monitoring matrix of the area according to the monitoring vector corresponding to each of the users, and determine a local density and a relative distance of each of the users according to the monitoring matrix, wherein the local density of each of the users is a relative density of each of the users in a local range with other users determined according to a local range corresponding to the monitoring matrix.

[0032] An abnormal marking module is configured to determine an abnormal user from the users according to the local density and the relative distance of each of the users, and mark the abnormal user.

[0033] In a third aspect, an embodiment of the present application further provides an electronic device, which comprises:

[0034] One or more processors;

[0035] A storage device configured to store one or more programs,

[0036] When the one or more programs are executed by the one or more processors, the one or more processors implement the abnormal power consumption monitoring method.

[0037] In a fourth aspect, an embodiment of the present application further provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement the abnormal power consumption monitoring method.

[0038] In the embodiment of the present application, the historical power consumption data of each user in the transformer area is acquired, and the monitoring vector corresponding to each user is determined according to the historical power consumption data of each user; the monitoring matrix of the transformer area is constructed according to the monitoring vector corresponding to each user, and the local density and relative distance of each user in each user are determined according to the monitoring matrix, wherein the local density of each user is the relative density of each user in the local range determined according to the local range of the monitoring matrix; the power consumption abnormal user is determined from each user according to the local density and relative distance of each user, and the power consumption abnormal user is marked. That is, in the embodiment of the present application, the power consumption abnormal user in the transformer area is determined by using the local density and relative distance of each user, which reduces the probability of incorrect determination of the power consumption abnormal user when the local density in the range changes greatly, and improves the accuracy of monitoring. BRIEF DESCRIPTION OF DRAWINGS

[0039] Figure 1 is a flowchart of the power consumption abnormality monitoring method provided in the embodiment of the present application;

[0040] Figure 2 is another flowchart of the power consumption abnormality monitoring method provided in the embodiment of the present application;

[0041] Figure 3 is a principle diagram of the power consumption abnormality monitoring method provided in the embodiment of the present application;

[0042] Figure 4 is a structure diagram of the power consumption abnormality monitoring device provided in the embodiment of the present application;

[0043] Figure 5 is a structure diagram of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0044] The present application will be further described below in conjunction with the drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application. In addition, it should be noted that, for the convenience of description, only the parts related to the present application are shown in the drawings, but not all the structures.

[0045] Figure 1 is a flowchart of the power consumption abnormality monitoring method provided in the embodiment of the present application, which can be executed by the power consumption abnormality monitoring device provided in the embodiment of the present application, and the device can be realized by software and / or hardware. In one specific embodiment, the device can be integrated in an electronic device, such as a server. The following embodiments will be described by taking the device integrated in the electronic device as an example, and the device can be integrated in the electronic device, such as a server. Please refer to Figure 1 , the method can specifically include the following steps:

[0046] S110, acquire historical power consumption data of each user in the transformer area, and determine the monitoring vector corresponding to each user according to the historical power consumption data of each user;

[0047] For example, in the power system, the power supply range or area of a transformer is called a transformer area, and each user in the transformer area can be all users in the power supply range of a transformer. The historical power consumption data of each user in the transformer area can be the electrical data of each user in the transformer area in multiple dimensions in the historical database, wherein the electrical data of each user in multiple dimensions can be electrical data in dimensions such as voltage feature class, current feature class, power factor feature class, compliance power feature class, and power feature class, wherein each dimension of the multiple dimensions of electrical data contains multiple characteristic values corresponding to the user and the total table. Wherein the electrical data can be voltage data, current data, power factor, load power and power data corresponding to the total table and each user in the transformer area. The monitoring vector corresponding to each user can be a vector composed of all characteristic values of each user in multiple dimensions, wherein the monitoring vector corresponding to each user corresponds to the number of users, and the more users, the more monitoring vectors. Wherein the historical power consumption data of each user can be all historical power consumption data of each user, or historical power consumption data in a monitoring time period, and the longer the historical power consumption data, the higher the accuracy of determining the abnormal power consumption user.

[0048] In a specific implementation, the historical power consumption data of each user in the transformer area is acquired from the historical database corresponding to the transformer area, the multi-dimensional characteristic values of each user are calculated in multiple dimensions according to the historical power consumption data of each user, and the monitoring vector of each user is formed according to the multi-dimensional characteristic values of each user. Wherein, according to the actual demand and monitoring focus, part of the characteristics can be selected from the multi-dimensional characteristic values of each user as the constituent elements of the monitoring vector, so as to form the monitoring matrix of the transformer area according to the monitoring vector of each user to determine whether the user is an abnormal power consumption user of the transformer area.

[0049] In the embodiment of the present application, the characteristic value of each dimension in the plurality of dimensions of the electrical data is calculated from two aspects of user data and total table data, the voltage characteristic value can be the voltage mean value of the user calculated according to the historical power consumption of each user, the voltage variance, the voltage mean value corresponding to the total table of the substation when collecting the user data, the voltage difference mean value between the total table and the user data, the voltage variance between the total table and the user data; the current characteristic value can be the current mean value corresponding to the fire line and the zero line of the user respectively calculated according to the historical power consumption data of each user, the power variance, the current mean value corresponding to the total table of the substation when collecting the user data, the current difference mean value between the total table and the user data, the current variance between the total table and the user data; the power factor characteristic value can be the power factor mean value of the user calculated according to the historical power consumption data of each user, the power factor variance, the power factor difference mean value between the total table and the user data, and the power factor variance between the total table and the user data; the load power characteristic value can be the power mean value of the user calculated according to the historical power consumption data of each user, the power variance, the power mean value corresponding to the total table of the substation when collecting the user data, the power difference mean value between the total table and the user data, the power variance between the total table and the user data; the power characteristic value can be the power mean value of the user calculated according to the historical power consumption data of each user, the power variance, the power mean value corresponding to the total table of the substation when collecting the user data, the power difference mean value between the total table and the user data, the power variance between the total table and the user data.

[0050] S120, constructing a monitoring matrix of the substation according to the monitoring vectors corresponding to each user, and determining the local density and the relative distance of each user in each user according to the monitoring matrix, wherein the local density of each user is the relative density of each user with other users in the local range determined according to the local range corresponding to the monitoring matrix.

[0051] For example, the monitoring matrix of the transformer area can be constructed according to the monitoring vectors corresponding to the users in the transformer area, and is used to determine the abnormal user in the transformer area. The local density of each user can be the corresponding multi-dimensional feature value of each user in the monitoring matrix corresponding to the transformer area, and is one of the indicators for determining whether the corresponding multi-dimensional feature value of each user is an outlier of the monitoring matrix corresponding to the transformer area. The local density of each user is determined according to the relative density of each user with other users in the local range of the monitoring matrix. The relative distance of each user can be the minimum distance value of each user relative to other users, which is determined according to the local density of each user and the distance between two users in the users, and is used to measure the outlying degree of the multi-dimensional feature of the user relative to the monitoring matrix corresponding to the transformer area. The minimum distance value of each user relative to other users is determined based on the other users whose local density is lower than that of each user, and can reduce the problem of large local data changes to a certain extent.

[0052] In a specific implementation, the monitoring matrix of the transformer area is constructed according to the monitoring vectors corresponding to the users, and the data cluster of the multi-dimensional feature value corresponding to each user is formed according to the monitoring matrix of the transformer area. The elements in the monitoring matrix of the transformer area can be one data point in the multi-dimensional feature value corresponding to each user, and the multi-dimensional feature value corresponding to each user can be a user point of the monitoring matrix in multiple dimensions. The local density of each user and the minimum distance value of each user relative to other users are determined according to the monitoring matrix, that is, the local density and the relative distance of each user are determined according to the monitoring matrix, so as to determine whether each user point in the monitoring matrix is an outlier according to the local density and the relative distance of each user, and the user corresponding to the outlier user point is determined as an abnormal user.

[0053] In a specific implementation, the monitoring matrix of the transformer area is constructed according to the monitoring vectors corresponding to the users, and the data cluster of the multi-dimensional feature value corresponding to each user is formed according to the monitoring matrix of the transformer area. The elements in the monitoring matrix of the transformer area can be one data point in the multi-dimensional feature value corresponding to each user, and the multi-dimensional feature value corresponding to each user can be a user point of the monitoring matrix in multiple dimensions. The local density of each user and the minimum distance value of each user relative to other users are determined according to the monitoring matrix, that is, the local density and the relative distance of each user are determined according to the monitoring matrix, so as to determine whether each user point in the monitoring matrix is an outlier according to the local density and the relative distance of each user, and the user corresponding to the outlier user point is determined as an abnormal user.

[0054] In a specific implementation, the power consumption abnormal user can be a user with abnormal power consumption in a transformer area, wherein the reasons for abnormal power consumption include electricity stealing, metering failure, and special load, etc. The abnormal factor corresponding to each user is determined according to the local density of each user and the adjustable parameter corresponding to the adjustable range, wherein the abnormal factor corresponding to each user is the ratio of the average density of other users corresponding to each user calculated and the local density of each user, which is used to compare with the preset abnormal threshold to determine the probability that the user is a power consumption abnormal user. When the abnormal factor corresponding to each user is greater than the preset abnormal threshold, it means that the user has a large difference with other users, and can be an abnormal user. In combination with the comparison of the relative distance of the user and the total relative distance value of the transformer area, when the relative distance of the user is greater than the total relative distance value of the transformer area and the abnormal factor corresponding to the user is greater than the preset abnormal threshold, the user is determined to be a power consumption abnormal user, and the power consumption abnormal user is marked.

[0055] In the embodiment of the application, the historical power consumption data of each user in the transformer area is obtained, and the monitoring vector corresponding to each user is determined according to the historical power consumption data of each user. The monitoring matrix of the transformer area is constructed according to the monitoring vector corresponding to each user, and the local density and the relative distance of each user in each user are determined according to the monitoring matrix, wherein the local density of each user is the relative density of each user with other users in the local range determined according to the local range corresponding to the monitoring matrix. The power consumption abnormal user is determined from each user according to the local density and the relative distance of each user, and the power consumption abnormal user is marked. That is, in the embodiment of the application, the power consumption abnormal user in the transformer area is determined by using the local density and the relative distance of each user, which reduces the probability of incorrect determination of the power consumption abnormal user when the local density in the range changes greatly, and improves the accuracy of monitoring.

[0056] The power consumption abnormal monitoring method provided by the embodiment of the application will be further described below, as shown in the following Figure 2 The method can specifically include the following steps:

[0057] S210, the historical power consumption data of each user in the transformer area is obtained, and the value of each user in multiple dimension features is calculated according to the historical power consumption data of each user in each user, to obtain the multi-dimensional feature value of each user;

[0058] In a specific implementation, the multi-dimensional feature value of each user can be a value calculated by averaging, difference averaging, and change variance, etc. from the electrical data and total meter data in the voltage feature class, the current feature class, the power factor feature class, the compliance power feature class, and the electricity quantity feature class, etc. dimensions of the historical power consumption data of each user. Among them, the historical power consumption data of each user can be the electrical data corresponding to the voltage value of the user at each collection time point, the user live line current value, the user zero line current value, the user power factor value, the user power value, the user electricity quantity value, the total meter voltage value, the total meter live line current value, the total meter zero line current value, the total meter power factor value, the total meter power value, and the electricity quantity value, etc. collected when the user data.

[0059] S220, determining the monitoring vector corresponding to each user according to the multi-dimensional feature value of each user, and constructing the monitoring matrix of the transformer area according to the monitoring vector corresponding to each user;

[0060] In a specific implementation, the historical power consumption data of each user in the transformer area is obtained from the historical database corresponding to the transformer area, the multi-dimensional feature value of each user is calculated in multiple dimensions according to the historical power consumption data of each user, the monitoring vector of each user is formed according to the multi-dimensional feature value of each user in each user, and the monitoring matrix of the transformer area is constructed according to the monitoring vector corresponding to each user. The monitoring matrix of the transformer area contains the monitoring vectors corresponding to all users in the transformer area. According to the actual demand and monitoring focus, part of the features can be selected from the multi-dimensional feature values of each user as the constituent elements of the monitoring vector, so as to determine whether the user is an abnormal user of the transformer area according to the monitoring matrix of the transformer area formed by the monitoring vector of each user.

[0061] For example, when there are n users in the transformer area, each user corresponds to 25 multi-dimensional features, and the monitoring vector of the Kth user is (a k，1 , a k，2 , a k，i , …a k，25 ), where i is the i th dimensional feature of each user, and the monitoring matrix composed of 25 variables of n users is as follows:

[0062]

[0063] S230, calculating the average potential energy of each user corresponding to the multi-dimensional feature according to the multi-dimensional feature value of each user in the monitoring matrix, and determining the distance between each user in the monitoring matrix according to the average potential energy of each user corresponding to the multi-dimensional feature and the monitoring matrix;

[0064] In a specific implementation, the average potential energy of each user corresponding to the plurality of dimensional characteristics can be the average potential energy of each user on each dimension corresponding to the characteristic of the plurality of dimensional characteristics, for example, when the multi-dimensional characteristic value of each user has 25, the average potential energy of 25 characteristics of each user needs to be calculated as a gap index for measuring each user corresponding to the plurality of dimensional characteristics. The distance between two users in each user can be the distance value between users in the multi-dimensional space calculated according to the multi-dimensional characteristic value corresponding to the two users in the monitoring matrix. Wherein, according to the comparison between the average potential energy of each user corresponding to the plurality of dimensional characteristics and the potential energy of each user corresponding to the plurality of dimensional characteristics, the distribution gap between different characteristics is eliminated, and the data performance of other dimensional characteristics is avoided. Wherein, the average potential energy of each user corresponding to the plurality of dimensional characteristics is calculated based on the following formula

[0065]

[0066] Wherein, D is the monitoring matrix, D i is a value set corresponding to the i-th characteristic of each user in the monitoring matrix, x p and x q are values corresponding to the i-th characteristic of two users randomly extracted from the value set D i , P(x p ) and P(x q ) are the potential energy of the i-th characteristic of the two users extracted. Wherein, the potential energy P(x i ) of each user corresponding to the plurality of dimensional characteristics is calculated based on the following formula:

[0067]

[0068] Wherein, x i is a value corresponding to the i-th characteristic of any one of the users in the monitoring matrix, y j is a value corresponding to the i-th characteristic of the j-th other user in the monitoring matrix, and n is the number of users.

[0069] Further, the distance between two users in each user is determined according to the average potential energy of each user corresponding to the plurality of dimensional characteristics and the monitoring matrix, including:

[0070] Determine the distance weight of each user corresponding to the plurality of dimensional characteristics according to the average potential energy of each user corresponding to the plurality of dimensional characteristics;

[0071] Determine the distance between two users in each user according to the distance weight of each user corresponding to the plurality of dimensional characteristics and the plurality of dimensional characteristic values of each user in the monitoring matrix.

[0072] In a specific implementation, the distance weight of each user corresponding to the multiple dimension features can be a weight value determined based on the average potential energy of each user corresponding to the multiple dimension features, a difference between the potential energy of each user corresponding to the dimension feature and the potential energy of other users corresponding to the dimension feature, for eliminating the distribution gap between different features, and can avoid the data features being covered. Wherein, the distance weight ω of each user corresponding to the multiple dimension features is calculated based on the following formula i :

[0073]

[0074] Wherein, and is the potential energy corresponding to the i-th feature of the user p and the user q, is the average potential energy corresponding to the i-th feature of each user, ω i is the distance weight corresponding to the i-th feature of each user. Wherein, the distance d(p, q, ω) between two users in each user is calculated based on the following formula:

[0075]

[0076] Wherein, m is the number of multiple dimension feature values, ω i is the distance weight corresponding to the i-th feature of each user, is the i-th feature value of each user and is the i-th feature value of other users in the monitoring matrix, p is the p-th user in the monitoring matrix, and q is the q-th user in the monitoring matrix.

[0077] In the embodiment of the application, the average potential energy of each user corresponding to the multiple dimension features, the potential energy of other users corresponding to the multiple dimension features in the monitoring matrix, and the potential energy of each user corresponding to the multiple dimension features are substituted into formula (3) to determine the distance weight value of each user corresponding to the multiple dimension features, and the distance between two users in each user is determined by substituting the distance weight of each user corresponding to the multiple dimension features and the multiple dimension feature values of each user in the monitoring matrix into formula (4).

[0078] S240, determine the local density of each user in each user according to the distance between two users in each user and the adjustable parameter set, and determine the relative distance of each user in each user according to the distance between two users in each user and the local density of each user in each user.

[0079] In a specific implementation, the adjustable parameter set can be a set of all points in the nearest interval corresponding to the preset distance of the user. The relative distance of each user in the users is obtained by calculating the minimum value between other users with a local density lower than the local density of each user from the distance between each two users in the users, which is used to measure the outlying degree of the user. The relative distance determined based on the potential energy density can more accurately measure the outlying degree of the user, overcoming the problem of large local data changes.

[0080] wherein the local density of each user in the users is determined based on the following formula p :

[0081]

[0082] wherein N k (P) is a set of all points in the nearest interval corresponding to the kth distance of the pth user, k is an adjustable parameter, and |N k (P) | is the total number of samples contained in the adjustable parameter set, and d(p, q, ω) is the distance between the pth user and the qth user in the users.

[0083] Further, the relative distance of each user in the users is determined based on the distance between each two users in the users and the local density of each user in the users, comprising:

[0084] selecting a local user with a local density less than the local density of each user in the users from the users;

[0085] determining the distance between each user and the local user corresponding to each user in the users, and taking the square root of the minimum distance between each user and the local user corresponding to each user in the users to obtain the relative distance value of each user in the users.

[0086] In a specific implementation, the local user with the local density of each user in the users can be a user with a local density lower than the local density of each user in the other users. The local user with a local density less than the local density of each user in the users is selected from the users, which is used to screen out other users with a field distance greater than each user. The distance value between each user and the local user corresponding to each user in the users is determined based on the distance between each two users in the users, and the minimum distance value is selected from the distance value between each user and the local user corresponding to each user in the users to obtain the relative distance value of each user in the users. The relative distance value of each user in the users is calculated based on the following formula p :

[0087]

[0088] wherein d(p, q, ω) is a distance value between the pth user and the qth user in each user, ρ p is the local density of the pth user, ρ q is the local density of the qth user, and ω is a distance weight corresponding to multiple dimension features of each user.

[0089] S250, determining an abnormality factor corresponding to each user in each user according to the local density of each user and the adjustable parameter set;

[0090] In a specific implementation, the abnormality factor corresponding to each user is determined according to the local density of each user and the adjustable parameter corresponding to the adjustable range, wherein the abnormality factor corresponding to each user is a ratio of the average density of other users corresponding to each user calculated and the local density of each user, which is used to compare with a preset abnormality threshold to determine the probability that the user is an electricity abnormality user. The abnormality factor corresponding to each user in each user is calculated based on the following formula k (P):

[0091]

[0092] wherein J k (P) is the abnormality factor corresponding to each user when the adjustable parameter is K for the pth user, ρ p is the local density of the pth user, ρ o is the user closest to the pth user in the adjustable range.

[0093] S260, determining a user whose abnormality factor exceeds a preset abnormality threshold and whose relative distance is greater than the total relative distance value of the transformer area from each user as an electricity abnormality user, and marking the electricity abnormality user.

[0094] In a specific implementation, the electricity abnormality user can be a user with electricity abnormality in the transformer area, wherein the reasons for electricity abnormality include electricity stealing, metering failure, and special load, etc. The abnormality factor corresponding to each user is determined according to the local density of each user and the adjustable parameter corresponding to the adjustable range, wherein the abnormality factor corresponding to each user is a ratio of the average density of other users corresponding to each user calculated and the local density of each user, which is used to compare with a preset abnormality threshold to determine the probability that the user is an electricity abnormality user. When the abnormality factor corresponding to each user in each user is greater than the preset abnormality threshold, it indicates that the user has a large gap with other users, which can be an abnormal user. In combination with the comparison between the relative distance of the user and the total relative distance value of the transformer area, when the relative distance of the user is greater than the total relative distance value of the transformer area and the abnormality factor corresponding to the user is greater than the preset abnormality threshold, it is determined that the user is an electricity abnormality user, and the electricity abnormality user is marked.

[0095] Figure 3 A schematic diagram of one principle of the power consumption anomaly monitoring method provided by the embodiment of the present application is shown in FIG. 1. Figure 3 As shown, the multi-dimensional feature value of each user is substituted into formula (2) for calculation to obtain the potential energy of each user corresponding to the multiple dimensions of features. The potential energy of each user corresponding to the multiple dimensions of features is substituted into formula (1) for calculation to obtain the average potential energy of each user corresponding to the multiple dimensions of features. The average potential energy of each user corresponding to the multiple dimensions of features is substituted into formula (3) for calculation to obtain the distance weight of each user corresponding to the multiple dimensions of features. The distance weight of each user corresponding to the multiple dimensions of features and the multiple dimensions of feature values of each user are substituted into formula (4) for calculation to obtain the distance between each two users in the users. The distance between each two users in the users and the adjustable parameter set are substituted into formula (5) for calculation to obtain the local density of each user in the users. The local density of each user in the users and the distance between each two users in the users are substituted into formula (6) for calculation to obtain the relative distance value of each user in the users, and the local density of each user in the users and the adjustable parameter are substituted into formula (7) for calculation to obtain the anomaly factor corresponding to each user in the users. It is judged whether the relative distance of each user is greater than the total segment distance of the transformer area, and whether the anomaly factor corresponding to each user is greater than the preset anomaly threshold value. When the relative distance of each user is greater than the total segment distance of the transformer area, and the anomaly factor corresponding to each user is greater than the preset anomaly threshold value, it is determined that the user is a power consumption anomaly user in the transformer area.

[0096] In the embodiment of the present application, the historical power consumption data of each user in the transformer area is obtained, and the monitoring vector corresponding to each user is determined according to the historical power consumption data of each user. The monitoring matrix of the transformer area is constructed according to the monitoring vector corresponding to each user, and the local density and the relative distance of each user in the users are determined according to the monitoring matrix. The local density of each user is the relative density of each user with other users in the local range determined according to the local range corresponding to the monitoring matrix. The power consumption anomaly user is determined from the users according to the local density and the relative distance of each user, and the power consumption anomaly user is marked. That is, in the embodiment of the present application, the power consumption anomaly user in the transformer area is determined by using the local density and the relative distance of each user, which reduces the probability of incorrect determination of the power consumption anomaly user when the local density in the range changes greatly, and improves the accuracy of monitoring.

[0097] Figure 4 FIG. 2 is a structural schematic diagram of the power consumption anomaly monitoring device provided by the embodiment of the present application, as shown in FIG. 2, the power consumption anomaly monitoring device comprises: Figure 4

[0098] The vector determination module 410 is configured to obtain the historical power consumption data of each user in the transformer area, and determine the monitoring vector corresponding to each user according to the historical power consumption data of each user.​

[0099] The distance determination module 420 is configured to construct a monitoring matrix of the transformer area according to the monitoring vectors of the users, and determine local density and relative distance of each user in the users according to the monitoring matrix, wherein the local density of each user is determined according to relative density of each user in a local range within the local range according to a corresponding local range of the monitoring matrix.

[0100] The anomaly marking module 430 is configured to determine an electricity consumption anomaly user from the users according to the local density and the relative distance of each user, and mark the electricity consumption anomaly user.

[0101] In an embodiment, the vector determination module 410 determines the monitoring vectors of the users according to historical electricity consumption data of the users, and the method comprises the following steps.

[0102] The method further comprises the following steps.

[0103] The method further comprises the following steps.

[0104] In an embodiment, the distance determination module 420 determines the local density of each user in the users according to the monitoring matrix, and the method comprises the following steps.

[0105] The method further comprises the following steps.

[0106] The method further comprises the following steps.

[0107] The method further comprises the following steps.

[0108] In an embodiment, the distance determination module 420 determines the distance between each two users in the users according to the average potential energy of the multiple dimension features corresponding to each user and the monitoring matrix, and the method comprises the following steps.

[0109] The method further comprises the following steps.

[0110] The method further comprises the following steps.

[0111] In an embodiment, the distance determining module 420 determines the relative distance of each user among the users according to the monitoring matrix, comprising:

[0112] calculating the average potential energy of the multiple dimension features corresponding to each user according to the multiple dimension eigenvalues of each user in the monitoring matrix;

[0113] determining the distance between each two users among the users according to the average potential energy of the multiple dimension features corresponding to each user and the monitoring matrix;

[0114] determining the local density of each user among the users according to the distance between each two users among the users and the adjustable parameter set;

[0115] determining the relative distance of each user among the users according to the distance between each two users among the users and the local density of each user among the users.

[0116] In an embodiment, the distance determining module 420 determines the relative distance of each user among the users according to the distance between each two users among the users and the local density of each user among the users, comprising:

[0117] selecting a local user from the users whose local density is less than the local density of each user among the users;

[0118] determining the distance between each user among the users and the local user corresponding to each user, and taking the square root of the minimum distance between each user among the users and the local user corresponding to each user to obtain the relative distance value of each user among the users.

[0119] In an embodiment, the anomaly marking module 430 determines the electricity anomaly user from the users according to the local density and the relative distance of each user, comprising:

[0120] determining the anomaly factor corresponding to each user among the users according to the local density of each user among the users and the adjustable parameter set;

[0121] determining the user whose anomaly factor exceeds the preset anomaly threshold and whose relative distance is greater than the total relative distance value of the area as the electricity anomaly user.

[0122] In the device of the embodiment of the application, the historical power consumption data of each user in a transformer area is acquired, and the monitoring vector corresponding to each user is determined according to the historical power consumption data of each user; the monitoring matrix of the transformer area is constructed according to the monitoring vector corresponding to each user, and the local density and relative distance of each user in each user are determined according to the monitoring matrix, wherein the local density of each user is the relative density of each user in the local range with other users determined according to the local range corresponding to the monitoring matrix; the power consumption abnormal user is determined from each user according to the local density and relative distance of each user, and the power consumption abnormal user is marked. That is, the power consumption abnormal user in the transformer area is determined by using the local density and relative distance of each user in the embodiment of the application, the probability of power consumption abnormal user determination error when the local density in the range changes greatly is reduced, and the monitoring accuracy is improved.

[0123] Figure 5 A structural schematic diagram of an electronic device is provided for the embodiment of the application. Figure 5 A block diagram of an exemplary electronic device 12 suitable for implementing an embodiment of the application is shown. Figure 5 The electronic device 12 shown is merely an example and should not limit the function and use range of the embodiment of the application.

[0124] As shown in Figure 5 The electronic device 12 is shown in the form of a general computing device. The components of the electronic device 12 can include, but are not limited to, one or more processors or processing units 16, system memory 28, and a bus 18 that connects the various system components including the system memory 28 and the processing unit 16.

[0125] The bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration bus, a processor or local bus using any of a variety of bus architectures including an industry standard architecture (ISA), micro-channel architecture (MAC), enhanced ISA (EISA), Video Electronics Standards Association (VESA) local bus, and a peripheral component interconnect (PCI) bus.

[0126] The electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that is accessible by the electronic device 12 and includes both volatile and non-volatile media, removable and non-removable media.

[0127] System memory 28 can include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. Electronic device 12 can further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 can be provided for reading from and writing to a non-removable, non-volatile magnetic media (not shown and typically called a "hard drive"). Figure 5 Although not shown, a magnetic disk drive can also be utilized in some embodiments for reading from and writing to a removable, non-volatile magnetic media such as a "floppy disk," and an optical disk drive can be used in some embodiments for reading from and writing to a removable, non-volatile optical media such as an optical disc (e.g., CD-ROM, DVD-ROM, etc.). In such instances, each can be connected to bus 18 by one or more data media interfaces. Storage 28 can include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the application. Figure 5

[0128] Program / utility 40, having a set (at least one) of program modules 42, can be stored in, for example, memory 28 by way of example, such as an operating system, one or more application programs, other program modules, and program data, each or some combination thereof, can include implementation of a network environment. Program modules 42 generally carry out the functions and / or methodologies of embodiments of the application as described herein.

[0129] Electronic device 12 can also communicate with one or more external devices 14 such as a keyboard or pointing device, a display 24, etc. One or more devices enabling a user to interact with an electronic device 12 can also be included by electronic device 12, and / or any devices (e.g., a network card, a modem, etc.) that enable electronic device / terminal / server 12 to communicate in some manner with other computing devices. Such communication can occur via input / output (I / O) interface 22. Still yet, electronic device 12 can communicate with one or more networks such as a local area network (LAN), a wide area network (WAN), and / or the Internet through network adapter 20. As depicted, network adapter 20 communicates with the other components of electronic device 12 via bus 18. It should be appreciated that although not shown, other hardware and / or software modules could be utilized in conjunction with electronic device 12. Such as, but not limited to, microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data archival storage systems, etc.

[0130] Processing unit 16 executes various function applications and data processing by running programs stored in system memory 28, such as implementing the power anomaly monitoring method provided by embodiments of the application, which includes:​

[0131] obtain historical power consumption data of each user in the transformer area, and determine a monitoring vector corresponding to each user according to the historical power consumption data of each user;

[0132] construct a monitoring matrix of the transformer area according to the monitoring vector corresponding to each user, and determine a local density and a relative distance of each user in the transformer area according to the monitoring matrix, wherein the local density of each user is a relative density of each user with other users in a local range determined according to a local range corresponding to the monitoring matrix;

[0133] determine a power consumption abnormal user from the users according to the local density and the relative distance of each user, and mark the power consumption abnormal user.

[0134] The embodiment of the present application also provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to realize the power consumption abnormal monitoring method, and the method comprises the following steps:

[0135] obtain historical power consumption data of each user in the transformer area, and determine a monitoring vector corresponding to each user according to the historical power consumption data of each user;

[0136] construct a monitoring matrix of the transformer area according to the monitoring vector corresponding to each user, and determine a local density and a relative distance of each user in the transformer area according to the monitoring matrix, wherein the local density of each user is a relative density of each user with other users in a local range determined according to a local range corresponding to the monitoring matrix;

[0137] determine a power consumption abnormal user from the users according to the local density and the relative distance of each user, and mark the power consumption abnormal user.

[0138] The computer storage medium of the embodiments of the present application can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination thereof. More specific examples (non-exhaustive list) of the computer-readable storage medium include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device.

[0139] The computer-readable signal medium can include a data signal propagated in baseband or propagated as a carrier wave, in which the computer-readable program code is contained. Such propagated data signal can take a variety of forms, including but not limited to electro-magnetic, optical or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium that is not a storage medium and that can be used to carry or propagate program code that is used by or in connection with an instruction execution system, apparatus, or device.

[0140] The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wire line, optical fiber, RF, etc., or any suitable combination of the above.

[0141] The computer program code for carrying out operations of the present application can be written in one or more programming languages or combinations of languages including object oriented programming languages such as Java, Smalltalk, C++ or conventional procedural programming languages such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0142] Note that the above merely describes preferred embodiments of the present application and the principles of the technology applied. Those skilled in the art will understand that the present application is not limited to the specific embodiments described herein, and that various obvious changes, modifications and substitutions can be made to the present application without departing from the scope of the present application. Therefore, although the present application has been described in detail through the above embodiments, the present application is not limited to the above embodiments, and can include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the claims.

Claims

1. An electric power abnormality monitoring method characterized by comprising: The method comprises the following steps: obtaining historical power consumption data of each user in a transformer area, and determining a monitoring vector corresponding to each user according to the historical power consumption data of each user; constructing a monitoring matrix of the transformer area according to the monitoring vector corresponding to each user, and determining a local density and a relative distance of each user in the transformer area according to the monitoring matrix, wherein the local density of each user is the relative density of each user in a local range with other users determined according to a local range corresponding to the monitoring matrix; determining a power consumption abnormal user from the users according to the local density and the relative distance of each user, and marking the power consumption abnormal user; the step of determining a power consumption abnormal user from the users according to the local density and the relative distance of each user comprises: determining an abnormal factor corresponding to each user in the users according to the local density of each user and an adjustable parameter set; determining a user whose abnormal factor exceeds a preset abnormal threshold and whose relative distance is greater than a total relative distance value of the transformer area as a power consumption abnormal user; the step of determining a relative distance of each user in the users according to the monitoring matrix comprises: calculating average potential energy of multiple dimension characteristics corresponding to each user according to the multiple dimension characteristic values of each user in the monitoring matrix; determining a distance between two users in the users according to the average potential energy of multiple dimension characteristics corresponding to each user and the monitoring matrix; determining a local density of each user in the users according to the distance between two users in the users and an adjustable parameter set; determining a relative distance of each user in the users according to the distance between two users in the users and the local density of each user.

2. The method of claim 1, wherein, the step of determining a monitoring vector corresponding to each user according to the historical power consumption data of each user comprises: calculating values of multiple dimension characteristics of each user in the users according to the historical power consumption data of each user, to obtain multiple dimension characteristic values of each user; determining a monitoring vector corresponding to the users according to the multiple dimension characteristic values of each user.

3. The method of claim 2, wherein, the step of determining a local density of each user in the users according to the monitoring matrix comprises: calculating average potential energy of multiple dimension characteristics corresponding to each user according to the multiple dimension characteristic values of each user in the monitoring matrix; determining a distance between two users in the users according to the average potential energy of multiple dimension characteristics corresponding to each user and the monitoring matrix; determining a local density of each user in the users according to the distance between two users in the users and an adjustable parameter set.

4. The method of claim 3, wherein, the step of determining a distance between two users in the users according to the average potential energy of multiple dimension characteristics corresponding to each user and the monitoring matrix comprises: determining distance weights of multiple dimension characteristics corresponding to each user according to the average potential energy of multiple dimension characteristics corresponding to each user; determining a distance between two users in the users according to the distance weights of multiple dimension characteristics corresponding to each user and the multiple dimension characteristic values of each user in the monitoring matrix.

5. The method of claim 1, wherein, The relative distance of each user in the users is determined according to the distance between each two users in the users and the local density of each user in the users, including: selecting a local user with a local density less than the local density of each user in the users from the users; determining the distance between each user in the users and the local user corresponding to the user, and taking the square root of the minimum distance between each user in the users and the local user corresponding to the user to obtain the relative distance value of each user in the users.

6. An electric power abnormality monitoring device characterized by comprising: including: a vector determination module configured to acquire historical power consumption data of each user in a power supply area, and determine a monitoring vector corresponding to each user according to the historical power consumption data of the user; a distance determination module configured to construct a monitoring matrix of the power supply area according to the monitoring vectors corresponding to the users, and determine the local density and the relative distance of each user in the users according to the monitoring matrix, wherein the local density of each user is determined according to the relative density of each user in a local range with other users in the local range; an abnormality marking module configured to determine a power consumption abnormal user from the users according to the local density and the relative distance of each user, and mark the power consumption abnormal user; the abnormality marking module includes: determining an abnormality factor corresponding to each user in the users according to the local density of each user in the users and an adjustable parameter set; determining a user with an abnormality factor exceeding a preset abnormality threshold and a relative distance greater than a total relative distance value of the power supply area as the power consumption abnormal user; the distance determination module determines the relative distance of each user in the users according to the monitoring matrix, including: calculating average potential energy of multiple dimension features corresponding to each user according to the multiple dimension feature values of each user in the monitoring matrix; determining the distance between each two users in the users according to the average potential energy of the multiple dimension features corresponding to each user and the monitoring matrix; determining the local density of each user in the users according to the distance between each two users in the users and the adjustable parameter set; determining the relative distance of each user in the users according to the distance between each two users in the users and the local density of each user in the users.

7. An electronic device, comprising: The electronic device includes: one or more processors; a storage device configured to store one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the power consumption anomaly monitoring method according to any one of claims 1 to 5.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the power consumption anomaly monitoring method according to any one of claims 1 to 5.

Images