Method and system for simultaneously identifying line loss abnormal transformer area and transformer area electricity utilization abnormal users

Abstract

The invention provides a method and a system for simultaneously identifying a line loss abnormal transformer area and a transformer area power utilization abnormal user, and aims to overcome the defects that a low-voltage transformer area line loss abnormity identification method based on a k-means clustering algorithm does not consider distributed photovoltaic access and only analyzes the characteristic of the line loss rate so as to have the possibility of misjudgment. The electricity sale quantity, the photovoltaic output and the load are adopted as characteristic indexes of the transformer area line loss abnormity, the local outlier factor of each piece of multi-dimensional characteristic data is calculated through the local reachable density, and when the local outlier factor is larger than a threshold value, it is judged that the transformer area is an abnormal line loss transformer area. And for the abnormal line loss transformer area, calculating the local reachable density of the multi-dimensional feature data of each user in the abnormal line loss transformer area, calculating the local outlier factor of the multi-dimensional feature data of each user, and when the local outlier factor is greater than a threshold value, determining that the user is an abnormal user.

Description

TECHNICAL FIELD

[0001] The application belongs to the field of new energy grid connection management, and particularly relates to a line loss abnormal transformer area and transformer area electricity abnormal user simultaneous identification method and system. BACKGROUND

[0002] After the distributed photovoltaic is accessed to the power distribution network, the power flow direction of the traditional power distribution network is changed, which brings great challenges to line loss management. At present, the line loss rate is qualified or abnormal is still determined by the experience of operation and maintenance personnel. With the access of a large number of distributed photovoltaics, this method is easy to miss many existing line loss abnormalities.

[0003] In the aspect of line loss abnormal transformer area identification, the document "Low-voltage transformer area line loss abnormality identification method based on k-means clustering algorithm" uses k-means clustering to cluster the line loss rate of the transformer area, judges whether the transformer area exists line loss abnormality according to the size of the average line loss rate and the distance between each clustering center, further analyzes the time dispersion degree of the transformer area with higher line loss rate, and judges whether the transformer area truly exists line loss abnormality according to the abnormality coefficient. This method does not consider the access of distributed photovoltaics, and there is a possibility of misjudgment by only analyzing the line loss rate.

[0004] In the aspect of transformer area abnormal user identification, the document "Electric power user electricity data outlier detection method based on improved Gaussian kernel function" classifies users through fuzzy clustering, extracts the electricity behavior characteristic quantity of each type of user, reduces the dimension of the electricity behavior characteristic quantity by using principal component analysis method, and identifies abnormal users by using improved local outlier factor algorithm. This method needs to analyze all low-voltage transformer areas in the regional power grid, and the amount of user data analyzed is extremely large, which requires a lot of manpower and material resources. SUMMARY

[0005] Therefore, the application aims to overcome the defects in the prior art and provides a line loss abnormal transformer area and transformer area electricity abnormal user simultaneous identification method and system. The method first identifies line loss abnormalities for all low-voltage transformer areas in the regional power grid, finds out the transformer areas with line loss abnormalities, and further finds out the abnormal users of the line loss abnormal transformer areas, which can avoid the problem of too large amount of user data analyzed by the "electric power user electricity data outlier detection method based on improved Gaussian kernel function".

[0006] To achieve the above purpose, the technical scheme of the application is as follows:

[0007] In a first aspect, the application is a line loss abnormal transformer area and transformer area electricity abnormal user simultaneous identification method, which comprises the following steps:

[0008] Step S1: Obtain the daily electricity sales, photovoltaic output and load data of each transformer area in the regional power grid as the first data set of the characteristic indexes for line loss abnormality identification of each transformer area;

[0009] Step S2: Calculate the local outlier factor of each area of the regional power grid based on the first data set;

[0010] Step S3: Calculate the number of data points whose local outlier factor is greater than the first threshold value, and determine that the area with less than 20% of the data points as normal line loss area, and the area with 20% or more of the data points as abnormal line loss area, which needs to be further investigated for abnormal power users;

[0011] Step S4: Input the voltage, power consumption and photovoltaic grid-connected power data of each user in the abnormal line loss area per day to obtain the second data set with voltage, power consumption and photovoltaic grid-connected power as the characteristic indicators of each user's power consumption data;

[0012] Step S5: Calculate the local outlier factor of each user in the abnormal line loss area based on the second data set;

[0013] Step S6: Calculate the number of data points whose local outlier factor is greater than the second threshold value, and determine that the user with less than 10% of the data points as normal power user, and the user with 10% or more of the data points as abnormal power user.

[0014] Further, the calculation method of the local outlier factor of step S2 includes the following steps:

[0015] S21: Calculate the kth reachable distance of each data point within the kth distance neighborhood:

[0016] D k (o,p)=max{d k (o),d(o,p)};

[0017] Where D k (o,p) is the kth reachable distance from data point o to data point p, d k (o) is the kth distance of data point o, and d(o,p) is the distance from data point o to data point p;

[0018] S22: Calculate the local kth reachable density of each point:

[0019]

[0020] Where LDD k (p) is the local kth reachable density of data point p, N k (p) is the set of all points within the kth distance of data point p, and contains the point on the kth distance, D k (o,p) is the kth reachable distance from data point o to data point p;

[0021] S23: calculating the kth local outlier factor of each point:

[0022]

[0023] wherein, LOF k (p) is the kth local outlier factor of data point p, LDD k (o) is the kth local reachable density of data point o.

[0024] Further, the first threshold in step S3 is 1.05.

[0025] Further, in step S3, the number of data points with the local outlier factor greater than 1.05 is calculated for each area, and if the number of data points with the local outlier factor greater than 1.05 is less than 20% of the total number of data points, i.e., the number of days with the local outlier factor greater than 1.05 in 30 days is less than 6 days, the area is considered to be a normal line loss area; if the number of data points with the local outlier factor greater than 1.05 is greater than or equal to 20% of the total number of data points, i.e., the number of days with the local outlier factor greater than 1.05 in 30 days is greater than 6 days, the area is considered to be an abnormal line loss area.

[0026] Further, in step S5, the same method as in step S2 is used to calculate the local outlier factor.

[0027] Further, the second threshold in step S6 is 1.10.

[0028] Further, in step S6, the number of data points with the local outlier factor greater than 1.10 is calculated for each area, and if the number of data points with the local outlier factor greater than 1.10 is less than 10% of the total number of data points, i.e., the number of days with the local outlier factor greater than 1.10 in 30 days is less than 3 days, the user is considered to be a normal electricity user; if the number of data points with the local outlier factor greater than 1.10 is greater than or equal to 10% of the total number of data points, i.e., the number of days with the local outlier factor greater than 1.10 in 30 days is greater than 3 days, the user is considered to be an abnormal electricity user.

[0029] Further, the number of data points in the first and second data sets is the number of days, and the data dimension is 3 dimensions.

[0030] In a second aspect, the present application provides a system for simultaneously identifying abnormal line loss areas and abnormal electricity users in an area, comprising the following modules:

[0031] A first acquisition module: used to acquire the daily electricity sales, photovoltaic output and load data of each area of the regional power grid as the first data set of the characteristic index for identifying the abnormal line loss of each area;

[0032] The first computing module is used for calculating the local outlier factor of each area of the regional power grid based on the first data set.

[0033] The first determining module is used for determining that the data points are normal line loss area if the number of data points is less than 20% when the local outlier factor is greater than the first threshold value, and determining that the data points are abnormal line loss area if the number of data points is greater than or equal to 20%.

[0034] The second obtaining module inputs the voltage, power consumption and photovoltaic grid-connected power data of each user in the abnormal line loss area per day to obtain a second data set in which the voltage, power consumption and photovoltaic grid-connected power are used as the characteristic indexes of the power consumption data of each user.

[0035] The second computing module is used for calculating the local outlier factor of each user in the abnormal line loss area based on the second data set.

[0036] The second determining module is used for determining that the user is a normal power consumption user if the number of data points is less than 10% when the local outlier factor is greater than the second threshold value, and determining that the user is an abnormal power consumption user if the number of data points is greater than or equal to 10%.

[0037] In a third aspect, the present application provides a computer terminal device, which comprises a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, and the processor implements the simultaneous identification method of abnormal line loss area and abnormal power consumption user of the area as described in the first aspect of the present application when executing the computer program.

[0038] In a fourth aspect, the present application provides a computer readable storage medium, which comprises a stored computer program, wherein the computer readable storage medium controls the device where the computer readable storage medium is located to execute the simultaneous identification method of abnormal line loss area and abnormal power consumption user of the area as described in the first aspect of the present application when the computer program is running.

[0039] Compared with the prior art, the present application has the following advantages:

[0040] (1) According to the general principle of "finding abnormal area first, then finding abnormal user", the present application avoids the problem of too large data volume when analyzing all user data of the regional power grid;

[0041] (2) In the identification of abnormal line loss area, the present application uses the power consumption, photovoltaic output and load as the characteristic indexes for identifying the abnormal line loss of each area, which is different from using only a single line loss rate as the characteristic index, thereby reducing the probability of misjudgment;

[0042] (3) In the identification of abnormal power consumption user, the present application uses the voltage, power consumption and photovoltaic grid-connected power data as the characteristic indexes, thereby improving the identification accuracy.

[0043] (4) The line loss abnormal transformer area and the abnormal user identification in the application both adopt the density-based outlier detection method. The density-based outlier detection method has the advantage of not being affected by data distribution. Since the distribution characteristics of transformer area and user data are unknown in advance, the density-based outlier detection method has good adaptability. BRIEF DESCRIPTION OF DRAWINGS

[0044] The accompanying drawings, which form a part of the present application, are intended to provide further understanding of the present application, and are incorporated herein for explanation of the present application and are not intended to constitute an improper limitation of the present application. In the drawings:

[0045] Figure 1 The simultaneous identification method and flow chart of the line loss abnormal transformer area and the abnormal user of the application. DETAILED DESCRIPTION

[0046] It should be noted that the embodiments in the application and the features in the embodiments can be combined with each other without conflict.

[0047] The embodiments of the present disclosure are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference signs represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and are intended to explain the present disclosure, and cannot be understood as a limitation of the present disclosure.

[0048] The application provides a simultaneous identification method of line loss abnormal transformer area and abnormal user of transformer area, and the overall process is "finding abnormal transformer area first, and then finding abnormal user". The main technical problems solved are:

[0049] (1) The low-voltage transformer area line loss abnormality identification method based on k-means clustering algorithm does not consider the access of distributed photovoltaic, and only analyzes the line loss rate, which has the disadvantage of misjudgment possibility. The power sales, photovoltaic output and load are used as the feature indexes of transformer area line loss abnormality, the local reachable density of each multi-dimensional feature data {power sales, photovoltaic output, load} in the data set D is calculated, the local outlier factor of each multi-dimensional feature data is calculated through the local reachable density, and when the local outlier factor is greater than the threshold value, it is determined that the transformer area is an abnormal line loss transformer area.

[0050] (2) For the abnormal line loss transformer area, the voltage, power consumption and photovoltaic grid-connected feed-in power are used as the feature indexes of user line loss abnormality, the local reachable density of each user multi-dimensional feature data {voltage, power consumption, photovoltaic grid-connected feed-in power} in the abnormal line loss transformer area is calculated, the local outlier factor of each user multi-dimensional feature data is calculated through the local reachable density, and when the local outlier factor is greater than the threshold value, it is determined that the user is an abnormal user.

[0051] The flow chart of the simultaneous identification method based on line loss abnormality of substation and abnormal user of substation according to the present application is shown in Figure 1 , and specifically comprises:

[0052] Step S1: Collecting the daily power sales, photovoltaic output and load data of each substation of the regional power grid, taking the power sales, photovoltaic output and load as the characteristic indexes for judging the line loss abnormality of each substation, obtaining a first data set with the power sales, photovoltaic output and load as the characteristic indexes, and the data number of the first data set of each substation being the number of days and the data dimension being 3.

[0053] Step S2: Calculating the local outlier factor of each substation of the regional power grid based on the first data set, and the calculation method being:

[0054] Firstly, calculating the kth reachable distance of each point within the kth distance neighborhood of each data point

[0055] D k (o,p)=max{d k (o),d(o,p)} (1)

[0056] Wherein, D k (o,p) is the kth reachable distance from data point o to data point p, d k (o) is the kth distance of data point o, and d(o,p) is the distance from data point o to data point p.

[0057] Then, calculating the local kth reachable density of each point

[0058]

[0059] Wherein, LDD k (p) is the local kth reachable density of data point p, N k (p) is the set of all points within the kth distance of data point p, and contains the point on the kth distance, D k (o,p) is the kth reachable distance from data point o to data point p.

[0060] Finally, calculating the kth local outlier factor of each point

[0061]

[0062] Wherein, LOF k (p) is the kth local outlier factor of data point p, and LDD k (o) is the local kth reachable density of data point o.

[0063] Step S3: Calculating the data number of each substation with the local outlier factor greater than 1.05.

[0064] If the number of data points with local outlier factor greater than 1.05 in the substation is less than 20% of the total number of data points, i.e. the number of days with local outlier factor greater than 1.05 in 30 days is less than 6 days, the substation is considered to be a normal line loss substation; if the number of data points with local outlier factor greater than 1.05 in the substation is greater than or equal to 20% of the total number of data points, i.e. the number of days with local outlier factor greater than 1.05 in 30 days is greater than 6 days, the substation is considered to be an abnormal line loss substation, and the possible electricity stealing user in the substation needs to be investigated.

[0065] Step S4: For the abnormal line loss substation investigated in step S3, further investigate the abnormal user. Input the voltage, power consumption and photovoltaic grid-connected power data of each user in the abnormal line loss substation every day, take the voltage, power consumption and photovoltaic grid-connected power as the characteristic indicators of the power consumption data of each user, and obtain a second data set with voltage, power consumption and photovoltaic grid-connected power as the characteristic indicators of the power consumption data of each user; the number of data points in the second data set of each user is the number of days, and the dimension is 3.

[0066] Step S5: Calculate the k-th local outlier factor of each user every day by the same method as step S2.

[0067] Step S6: Calculate the number of data points with local outlier factor greater than 1.10 for each user.

[0068] If the number of data points with local outlier factor greater than 1.10 for the user is less than 10% of the total number of data points, i.e. the number of days with local outlier factor greater than 1.10 in 30 days is less than 3 days, the user is considered to be a normal power consumption user, and the power metering data needs to be investigated to find other reasons for the abnormal line loss of the substation; if the number of data points with local outlier factor greater than 1.10 for the user is greater than or equal to 10% of the total number of data points, i.e. the number of days with local outlier factor greater than 1.10 in 30 days is greater than 3 days, the user is considered to be an abnormal power consumption user, and the power meter of the user needs to be further investigated to determine whether the user has electricity stealing behavior.

[0069] The present application will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0070] Embodiment 1

[0071] (1) Collect the daily power sales, photovoltaic output and load data of each substation in a certain area power grid, take the power sales, photovoltaic output and load as the characteristic indicators for each substation line loss anomaly discrimination, and the data set D of each substation has a data number of days and a data dimension of 3.

[0072] (2) Calculate the k-th reachable distance of each data point in the k-th distance neighborhood

[0073] D k (o,p) = max{dk (o), d(o, p)} (1)

[0074] where D k (o, p) is the kth reachable distance from data point o to data point p, d k (o) is the kth distance of data point o, d(o, p) is the distance from data point o to data point p.

[0075] Calculate the local kth reachable density of each point:

[0076]

[0077] where LDD k (p) is the local kth reachable density of data point p, N k (p) is the set of all points within the kth distance of data point p, and contains the point at the kth distance, D k (o, p) is the kth reachable distance from data point o to data point p.

[0078] The python code for the local reachable density program is:

[0079]

[0080]

[0081] where data1 is {sales, photovoltaic output, and load} feature samples when identifying abnormal transformer areas.

[0082] Calculate the kth local outlier factor of each point:

[0083]

[0084] where LOF k (p) is the kth local outlier factor of data point p, LDD k (o) is the local kth reachable density of data point o.

[0085] The python code for calculating the kth local outlier factor is:

[0086]

[0087] (3) Calculate the number of data points with a local outlier factor greater than 1.05 for each transformer area.

[0088] (4) If the number of data points with a local outlier factor greater than 1.05 in the substation area is less than 20% of the total number of data points, i.e., the number of days with a local outlier factor greater than 1.05 in 30 days is less than 6 days, the substation area is considered to be a normal line loss substation area; if the number of data points with a local outlier factor greater than 1.05 in the substation area is greater than or equal to 20% of the total number of data points, i.e., the number of days with a local outlier factor greater than 1.05 in 30 days is greater than 6 days, the substation area is considered to be an abnormal line loss substation area, and the possible electricity stealing users in the substation area need to be investigated. The python code for outputting the substation area with a local outlier factor greater than the threshold value is:

[0089] def display(k, data1, **k):

[0090] data3 = data1

[0091] display = []

[0092] for i, data in enumerate(data3):

[0093] data1 = list(data3)

[0094] data1.remove(data)

[0095] l = LOF(data, **k)

[0096] value = l.LOF(k, data)

[0097] if value > 1.05: % Abnormal user detection here is 1.10

[0098] display.append({"LOF": value, "data": data, "index": i})

[0099] display.sort(key=lambda o: o["LOF"], reverse=True)

[0100] return display

[0101] After calculation, the number of days with a local outlier factor greater than 1.05 in 30 days in the substation area A of the regional power grid is greater than 6 days, and the substation area A is determined to be an abnormal line loss substation area; the number of days with a local outlier factor greater than 1.05 in 30 days in the substation area E is 2 days, and the substation area E is determined to be a line loss attention substation area.

[0102] (5) For the line loss abnormal area found in step (4), further investigate the abnormal user. Input the voltage, power consumption and photovoltaic grid-connected power data of each user in the line loss abnormal area every day, and take the voltage, power consumption and photovoltaic grid-connected power as the characteristic indicators of the power consumption data of each user. The number of data in each user data set is the number of days, and the dimension is 3.

[0103] (6) In step S4, the same method as step S2 is used to calculate the k-th local outlier factor of each user every day. When identifying the abnormal user, data1 is the characteristic sample of {voltage, power consumption, photovoltaic grid-connected power}.

[0104] (7) In step S5, the number of data points with local outlier factor greater than 1.10 for each user is calculated.

[0105] (8) If the number of data points with local outlier factor greater than 1.10 for the user is less than 10% of the total number of data, i.e. the number of days with local outlier factor greater than 1.10 in 30 days is less than 3 days, the user is considered to be a normal power consumption user, and the power metering data needs to be investigated to find other reasons for the line loss anomaly of the area; if the number of data points with local outlier factor greater than 1.10 for the user is greater than or equal to 10% of the total number of data, i.e. the number of days with local outlier factor greater than 1.10 in 30 days is greater than 3 days, the user is considered to be an abnormal power consumption user, and the power meter needs to be further investigated to determine whether the user has electricity stealing behavior.

[0106] After calculation, the number of days with local outlier factor greater than 1.10 in 30 days for user S in area A is greater than 3 days, and user S in area A is determined to be an abnormal power consumption user. After on-site investigation, user S replaced the power meter connection, verifying the accuracy of the method.

[0107] Embodiment 2

[0108] A system for simultaneously identifying line loss abnormal areas and abnormal power consumption users in the areas, comprising the following modules:

[0109] A first acquisition module for acquiring a first data set of daily power sales, photovoltaic output and load data of each area in the regional power grid as characteristic indicators for line loss anomaly identification of each area;

[0110] A first calculation module for calculating the local outlier factor of each area in the regional power grid based on the first data set;

[0111] A first determination module for calculating the number of data points with local outlier factor greater than a first threshold value. If the number of data points is less than 20%, it is determined to be a normal line loss area, and if the number of data points is greater than or equal to 20%, it is determined to be an abnormal line loss area;

[0112] The second acquisition module: input the voltage, power consumption and photovoltaic grid-connected power data of each user in the abnormal line loss area per day, to obtain a second data set with voltage, power consumption and photovoltaic grid-connected power as the characteristic indicators of the power consumption data of each user;

[0113] The second calculation module: for calculating the local outlier factor of each user in the abnormal line loss area based on the second data set;

[0114] The second determination module: the user whose local outlier factor is greater than the second threshold value and whose data point number is less than 10% is determined as a normal power consumption user, and the user whose data point number is greater than or equal to 10% is determined as an abnormal power consumption user.

[0115] Embodiment 3

[0116] A computer terminal device, comprising a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the method for simultaneous identification of abnormal line loss area and abnormal power consumption user of the area as described in embodiment 1 when executing the computer program.

[0117] Embodiment 4

[0118] A computer readable storage medium, comprising a stored computer program, wherein the computer readable storage medium controls the device where the computer readable storage medium is located to execute the method for simultaneous identification of abnormal line loss area and abnormal power consumption user of the area as described in embodiment 1 when the computer program is running.

[0119] The collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in the present disclosure comply with relevant laws and regulations and do not violate public order and good customs.

[0120] It should be noted that the personal information from the user should be collected for legal and reasonable purposes, and should not be shared or sold outside these legal uses. In addition, such collection / sharing should be carried out after the user's informed consent is received, including but not limited to informing the user to read the user agreement / user notice before the user uses the function, and signing the agreement / authorization including authorization of relevant user information. In addition, any necessary steps should be taken to protect and ensure access to such personal information data, and to ensure that other people with access to personal information data comply with their privacy policy and processes.

[0121] The present disclosure contemplates that the systems and methods described herein can be deployed in various environments in which privacy of personal information is of concern. For example, the systems and methods described herein can be used in applications where user privacy is a concern, such as healthcare, finance, and / or other industries where privacy of personal information is important. The present disclosure contemplates embodiments in which aliases are used for one or more data processing activities, where the aliases do not include any personally identifiable information. For instance, user identifiers can be replaced by an alias that is not personally identifiable. In instances where personal information is used by the systems and methods described herein, the present disclosure contemplates that appropriate data privacy measures will be employed, such as removing PII, providing notice to users, and / or receiving consent from users prior to deploying the systems and methods described herein.

[0122] The data acquisition, transmission, storage, use, processing, etc. in the technical solutions of the present disclosure comply with the relevant provisions of national laws and regulations.

[0123] It should be noted that in the embodiments of the present disclosure, some industry existing solutions, components, models, etc. may be mentioned, which should be considered as exemplary, and the purpose is only to illustrate the feasibility in the implementation of the technical solutions of the present application, but it does not mean that the applicant has or will necessarily use the solution.

[0124] In the foregoing embodiment description, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present disclosure. In the present specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in any one or more embodiments or examples. In addition, those skilled in the art can combine and combine the different embodiments or examples described in the specification and the features of the different embodiments or examples without contradiction.

[0125] In addition, the terms "first", "second" are only for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include at least one of the features. In the description of the present disclosure, the meaning of "multiple" is at least two, for example, two, three, etc., unless otherwise explicitly specified.

[0126] Any process or method descriptions or any other descriptions in flow charts herein or otherwise described herein, can be understood as representing code modules, segments, or portions of code which include one or more executable instructions for implementing specific logic functions (or steps) in the process, and that the various systems described herein can include one or more circuits, components, or other devices configured to implement the described functions (or steps). The various embodiments and implementations of the present disclosure can be realized using any combination of dedicated circuits, processing elements, or other hardware, software, or firmware, or any combination thereof.

[0127] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0128] It should be understood that various parts of this disclosure can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0129] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware, and the program can be stored in a computer-readable storage medium. When executed, the program includes one or a combination of the steps of the method embodiments.

[0130] Furthermore, the functional units in the various embodiments of this disclosure can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0131] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of the present disclosure have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present disclosure. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present disclosure.

Claims

1. A method for simultaneously identifying transformer substations with abnormal line loss and users with abnormal power consumption within those substations, characterized in that: Includes the following steps: Step S1: Obtain the first dataset of characteristic indicators for line loss anomaly identification for each distribution area, which consists of daily electricity sales, photovoltaic output and load data of each distribution area of ​​the regional power grid. Step S2: Calculate the local outlier factor for each transformer substation in the regional power grid based on the first dataset; Step S3: Calculate the number of data points with local outlier factors greater than the first threshold. If the number of data points is less than 20%, it is determined to be a normal line loss area. If the number of data points is greater than or equal to 20%, it is determined to be an abnormal line loss area, and further investigation of abnormal electricity users is required. Step S4: Input the daily voltage, power consumption and photovoltaic grid-connected power input data of each user in the abnormal line loss area to obtain a second dataset with voltage, power consumption and photovoltaic grid-connected power input as characteristic indicators of each user's power consumption data; Step S5: Calculate the local outlier factor for each user in the abnormal line loss area based on the second dataset; Step S6: Calculate the number of data points with a local outlier factor greater than the second threshold. Users with less than 10% of the data points are judged as normal users, and users with more than or equal to 10% of the data points are judged as abnormal users.

2. The method for simultaneously identifying abnormal line loss distribution areas and abnormal power consumption users within distribution areas according to claim 1, characterized in that: The method for calculating the local outlier factor in step S2 includes the following steps: S21: Calculate the k-th reachable distance of each data point to all points in its k-th distance neighborhood: D k (o,p)=max{d k (o),d(o,p)}; Where D k (o,p) represents the k-th reachable distance from data point o to data point p, and d k (o) is the k-th distance from data point o, and d(o,p) is the distance from data point o to data point p; S22: Calculate the local k-th reachability density at each point: LDD k (p) represents the local k-th reachability density of data point p, N k (p) is the set of all points within the k-th distance of data point p, including points at the k-th distance. k (o,p) represents the k-th reachable distance from data point o to data point p; S23: Calculate the k-th local outlier factor for each point: Among them LOF k (p) is the k-th local outlier of data point p, LDD k (o) represents the local k-th reachable density of data point o.

3. The method for simultaneously identifying abnormal line loss distribution areas and abnormal power consumption users within distribution areas according to claim 1, characterized in that: The first threshold in step S3 is 1.

05.

4. The method for simultaneously identifying abnormal line loss distribution areas and abnormal power consumption users within distribution areas according to claim 3, characterized in that: In step S3, the number of data points with a local outlier factor greater than 1.05 for each transformer area is calculated. If the number of data points with a local outlier factor greater than 1.05 for that transformer area is less than 20% of the total number of data points, that is, the number of days with a local outlier factor greater than 1.05 in 30 days is less than 6 days, then the transformer area is considered to be a transformer area with normal line loss. If the number of data points with a local outlier factor greater than 1.05 for that transformer area is greater than or equal to 20% of the total number of data points, that is, the number of days with a local outlier factor greater than 1.05 in 30 days is greater than 6 days, then the transformer area is considered to be a transformer area with abnormal line loss.

5. The method for simultaneously identifying abnormal line loss distribution areas and abnormal power consumption users within distribution areas according to claim 1, characterized in that: In step S5, the local outlier factor is calculated using the same method as in step S2.

6. The method for simultaneously identifying abnormal line loss distribution areas and abnormal power consumption users within distribution areas according to claim 1, characterized in that: The second threshold in step S6 is 1.

10.

7. The method for simultaneously identifying abnormal line loss distribution areas and abnormal power consumption users within distribution areas according to claim 6, characterized in that: In step S6, the number of data points with a local outlier factor greater than 1.10 for each transformer area is calculated. If the number of data points with a local outlier factor greater than 1.10 for a user is less than 10% of the total number of data points, that is, the number of days with a local outlier factor greater than 1.10 in 30 days is less than 3 days, then the user is considered a user with normal electricity consumption. If the number of data points with a local outlier factor greater than 1.10 for a user is greater than or equal to 10% of the total number of data points, that is, the number of days with a local outlier factor greater than 1.10 in 30 days is greater than 3 days, then the user is considered a user with abnormal electricity consumption.

8. The method for simultaneously identifying abnormal line loss distribution areas and abnormal power consumption users within distribution areas according to claim 1, characterized in that: The first and second datasets contain data in the number of days and have a 3-dimensional data structure.

9. A system for simultaneously identifying transformer substations with abnormal line loss and users with abnormal power consumption within those substations, characterized in that: Includes the following modules: The first acquisition module is used to acquire the first dataset, which uses the daily electricity sales, photovoltaic output and load data of each distribution area of ​​the regional power grid as the feature indicators for judging the line loss anomalies of each distribution area. First calculation module: used to calculate the local outlier factor of each transformer area in the regional power grid based on the first dataset; The first judgment module is used to calculate the number of data points with a local outlier factor greater than the first threshold. If the number of data points is less than 20%, it is judged as a normal line loss area. If the number of data points is greater than or equal to 20%, it is judged as an abnormal line loss area. The second acquisition module: Input the daily voltage, power consumption and photovoltaic grid-connected power input data of each user in the abnormal line loss area, and obtain the second dataset with voltage, power consumption and photovoltaic grid-connected power input as feature indicators of each user's power consumption data; The second calculation module is used to calculate the local outlier factor for each user in the abnormal line loss area based on the second dataset. The second judgment module calculates the number of data points with a local outlier factor greater than the second threshold. Users with less than 10% of the data points are judged as normal users, and users with more than or equal to 10% of the data points are judged as abnormal users.

10. A computer terminal device, characterized in that: It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the method for simultaneously identifying abnormal line loss distribution areas and abnormal power consumption users in the distribution areas as described in any one of embodiments 1-8.

Images