An abnormal user detection method and system based on algorithm and big data

Abstract

The present invention discloses an abnormal user detection method and system based on algorithms and big data, the method comprising: obtaining first photovoltaic power generation data of all user power generation equipment to be detected; obtaining second photovoltaic power generation data of each user power generation equipment that meets a certain preset condition according to the first photovoltaic power generation data; obtaining power generation efficiency data of each user power generation equipment that meets the preset condition in a set time period according to the second photovoltaic power generation data; clustering analysis is performed on the power generation efficiency data to obtain user power generation equipment with high power generation efficiency, and users associated with the user power generation equipment with high power generation efficiency are regarded as abnormal users. The present invention can accurately monitor abnormal power generation users, and users associated with the user power generation equipment with high power generation efficiency are regarded as abnormal users, without the need to use conversion algorithms to achieve cross-county, cross-city, etc. power generation efficiency prediction and monitoring.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic power generation, and in particular to an abnormal user detection method and system based on algorithms and big data. Background Art

[0002] How to maximize the development of solar energy will be an important issue in achieving the goal of "carbon neutrality". Photovoltaic power generation is a common means of solar energy development, but because the relationship between power generation equipment manufacturers, power grid companies and power generation companies (i.e. users) is not so close, there are problems such as photovoltaic panel equipment manufacturers not knowing the equipment operation status of power generation companies (users), power grid companies not being able to properly supervise the online power generation of power generation companies (users), affecting the stability of power grid transmission, and power generation companies (users) not knowing how to maintain the operation of power generation equipment, thus affecting the power generation efficiency of the equipment.

[0003] The traditional photovoltaic equipment power generation supervision system is to install power generation metering devices to record the power generation of photovoltaic panels, and install meteorological collection equipment to collect weather and other related information for studying the power generation efficiency and operation of power generation equipment. However, since the light intensity and optimal tilt angle provided by NASA and MeteoNorm systems are regional averages, which have certain differences from the actual installation environment of power generation equipment, it is impossible to accurately achieve cross-county and cross-city power generation efficiency prediction and monitoring through conversion algorithms, and thus it is impossible to accurately monitor abnormalities of power generation equipment of users in a large range. Summary of the invention

[0004] In view of the above technical problems, the purpose of the present invention is to provide an abnormal user detection method and system based on algorithms and big data to solve the problem that the traditional photovoltaic equipment power generation supervision system cannot accurately monitor the abnormalities of power generation equipment of a large range of users.

[0005] The present invention adopts the following technical solutions:

[0006] An abnormal user detection method based on algorithm and big data includes the following steps:

[0007] Acquire first photovoltaic power generation data of all user power generation equipment to be detected;

[0008] According to the first photovoltaic power generation data, second photovoltaic power generation data of each user's power generation equipment that meets a certain preset condition is obtained;

[0009] According to the second photovoltaic power generation data, power generation efficiency data of each user's power generation equipment that meets the preset condition in a set time period is obtained; the power generation efficiency data includes the power generation efficiency value of each user's power generation equipment that meets the preset condition in the set time period;

[0010] Cluster analysis is performed on the power generation efficiency data to obtain user power generation equipment with high power generation efficiency, and users associated with the user power generation equipment with high power generation efficiency are regarded as abnormal users.

[0011] Optionally, performing cluster analysis on the power generation efficiency data to obtain user power generation equipment with high power generation efficiency includes:

[0012] The power generation efficiency values ​​of each user's power generation equipment are sorted to obtain an array of sorted power generation efficiency values; the difference between two adjacent power generation efficiency values ​​in the array is calculated to obtain a plurality of differential values, and the plurality of differential values ​​are V1, V2, ... V k ,V k+1 ,…V n ; Where 1≤k≤n, k and n are both natural numbers;

[0013] For equation V k ≥V k+1 *m to solve and obtain the equation V k ≥V k+1 *k value of m; where m is a constant;

[0014] The user power generation equipment associated with the k power generation efficiency values ​​in the array is regarded as the user power generation equipment with high power generation efficiency.

[0015] Optionally, the user power generation equipment associated with the k power generation efficiency values ​​in the array is used as the user power generation equipment with high power generation efficiency, including:

[0016] If the power generation efficiency values ​​of each user's power generation equipment are arranged in ascending order, the first k power generation efficiency values ​​in the array are obtained in sequence from high power generation efficiency value to low power generation efficiency value, and the user power generation equipment associated with the first k power generation efficiency values ​​is regarded as the user power generation equipment with high power generation efficiency.

[0017] Optionally, after the step of obtaining the power generation efficiency data of each user's power generation equipment that meets the preset condition in a set time period, the step further includes:

[0018] The equipment life cycle of each user's power generation equipment is determined according to the second photovoltaic power generation data, and users associated with user power generation equipment whose equipment life cycle has expired are regarded as users who need to replace power generation equipment.

[0019] Optionally, judging the equipment life cycle of the user's power generation equipment according to the photovoltaic power generation data includes:

[0020] Screening and clustering the power generation efficiency data to obtain user power generation equipment whose power generation efficiency value is lower than a power generation threshold;

[0021] The user power generation equipment with power generation efficiency lower than the power generation threshold is regarded as the power generation equipment with the life cycle of the equipment exhausted.

[0022] Optionally, the obtaining of first photovoltaic power generation data of all user power generation devices to be detected includes:

[0023] The first photovoltaic power generation data is obtained from the photovoltaic power generation data storage database, wherein the first photovoltaic power generation data includes the regional information, equipment attribute information, power generation information, and power generation start time and end time information of each user's power generation equipment.

[0024] Optionally, obtaining second photovoltaic power generation data of each user's power generation equipment that meets a preset condition according to the first photovoltaic power generation data includes:

[0025] The preset condition is that the user's power generation equipment belongs to a certain power supply unit, and the first photovoltaic power generation data is divided according to the different power supply units to which it belongs; wherein, user power generation equipment belonging to the same power supply unit is divided into the same group; user power generation equipment belonging to different power supply units is divided into different groups, thereby obtaining the second photovoltaic power generation data belonging to a certain power supply unit.

[0026] An abnormal user detection system based on algorithms and big data, comprising:

[0027] A data acquisition unit, used for acquiring first photovoltaic power generation data of all user power generation devices to be detected;

[0028] A data screening unit, configured to obtain second photovoltaic power generation data of each user's power generation equipment that meets a preset condition according to the first photovoltaic power generation data;

[0029] A data calculation unit, configured to obtain power generation efficiency data of each user's power generation equipment that meets the preset condition in a set time period according to the second photovoltaic power generation data; the power generation efficiency data includes power generation efficiency values ​​of each user's power generation equipment that meets the preset condition in the set time period;

[0030] The analysis unit is used to perform cluster analysis on the power generation efficiency data to obtain user power generation equipment with high power generation efficiency, and to regard users associated with the user power generation equipment with high power generation efficiency as abnormal users.

[0031] An electronic device, characterized in that it includes: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the abnormal user detection method based on algorithms and big data.

[0032] A computer storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the abnormal user detection method based on an algorithm and big data is implemented.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] The present invention obtains first photovoltaic power generation data of all user power generation equipment to be detected; obtains second photovoltaic power generation data of each user power generation equipment that meets a preset condition based on the first photovoltaic power generation data; obtains power generation efficiency data of each user power generation equipment that meets the preset condition in a set time period based on the second photovoltaic power generation data; cluster analysis is performed on the power generation efficiency data to obtain user power generation equipment with high power generation efficiency, and users associated with the user power generation equipment with high power generation efficiency are regarded as abnormal users. Since the second photovoltaic power generation data uses photovoltaic power generation data of each user power generation equipment that meets a preset condition, for example, the preset condition is a regional condition, when statistics are taken in towns, villages, or a factory, weather conditions can be ignored to perform cluster analysis based on the power generation efficiency data based on an algorithm to obtain user power generation equipment with high power generation efficiency, and further obtain abnormal users. There is no need to use a conversion algorithm to realize cross-county and cross-city power generation efficiency prediction and monitoring, and the user power generation equipment can be accurately monitored for abnormalities. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 A flowchart of an abnormal user detection method based on an algorithm and big data provided by an embodiment of the present invention;

[0036] Figure 2 A flowchart of an abnormal user detection method based on an algorithm and big data is provided for a specific embodiment of the present invention;

[0037] Figure 3 A schematic diagram of an abnormal user detection system based on algorithms and big data provided by a specific embodiment of the present invention;

[0038] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0039] The present invention is further described below in conjunction with the accompanying drawings and specific embodiments. It should be noted that, under the premise of no conflict, the embodiments or technical features described below can be arbitrarily combined to form a new embodiment:

[0040] Embodiment 1:

[0041] Please refer to Figure 1-4 As shown, Figure 1The present invention shows an abnormal user detection method based on an algorithm and big data, comprising the following steps:

[0042] Step S1: Acquire the first photovoltaic power generation data of all user power generation equipment to be detected;

[0043] In this embodiment, all user power generation equipment to be detected avoids only counting photovoltaic power generation data in a small area, and only monitoring abnormal users in a small area.

[0044] Specifically, step S1 includes:

[0045] The first photovoltaic power generation data is obtained from the photovoltaic power generation data storage database, wherein the first photovoltaic power generation data includes the regional information, equipment attribute information, power generation information, and power generation start time and end time information of each user's power generation equipment.

[0046] In this embodiment, the region information refers to the region where the user's power generation equipment is located, and is used to group the user's power generation equipment according to the region information;

[0047] The power generation information, power generation start time and end time information refer to how much electricity the user's power generation equipment has generated in a period of time. According to the power generation information, power generation start time and end time information, the power generation efficiency value of the user's power generation equipment can be obtained by dividing the power generation by the power generation time.

[0048] Step S2: obtaining second photovoltaic power generation data of each user's power generation equipment that meets a certain preset condition according to the first photovoltaic power generation data; specifically, the step S2 includes:

[0049] The preset condition is that the user's power generation equipment belongs to a certain power supply unit, and the first photovoltaic power generation data is divided into multiple groups according to the different power supply units to which it belongs, wherein user power generation equipment belonging to the same power supply unit is divided into the same group; user power generation equipment belonging to different power supply units is divided into different groups.

[0050] The first photovoltaic power generation data is divided according to the different power supply units to which it belongs, to obtain multiple groups of data, and the second photovoltaic power generation data belonging to a certain power supply unit is screened out from the multiple groups of data.

[0051] It should be noted that the second photovoltaic power generation data can be obtained by dividing by power supply unit, and the photovoltaic power generation data of user power generation equipment belonging to the same power supply unit is grouped together; the second photovoltaic power generation data can also be divided not by power supply unit, for example, by region, by township or town, etc. However, it must be satisfied that the light intensity corresponding to the photovoltaic power generation data divided into the same group is close.

[0052] Since the light intensity in the same power supply unit area is similar, the power generation efficiency should be similar. By analyzing the power generation efficiency value, it is possible to detect users of abnormal power generation equipment.

[0053] Step S3: obtaining power generation efficiency data of each user's power generation equipment that meets the preset condition in a set time period according to the second photovoltaic power generation data; the power generation efficiency data includes the power generation efficiency value of each user's power generation equipment that meets the preset condition in the set time period;

[0054] Step S4: performing cluster analysis on the power generation efficiency data to obtain user power generation equipment with high power generation efficiency, and treating users associated with the user power generation equipment with high power generation efficiency as abnormal users.

[0055] In the above implementation process, since the second photovoltaic power generation data uses the photovoltaic power generation data of each user's power generation equipment that meets a certain preset condition, for example, the preset condition is a regional condition, when statistics are made in a town, village, or a factory, the weather conditions can be ignored to perform cluster analysis based on the algorithm through the power generation efficiency data to obtain user power generation equipment with high power generation efficiency, and further obtain abnormal users. There is no need to use a conversion algorithm to realize cross-county, cross-city, etc. power generation efficiency prediction and monitoring, and the user's power generation equipment can be accurately monitored for abnormalities.

[0056] Optionally, performing cluster analysis on the power generation efficiency data to obtain user power generation equipment with high power generation efficiency includes:

[0057] The power generation efficiency values ​​of each user's power generation equipment are sorted to obtain an array of sorted power generation efficiency values; the difference between two adjacent power generation efficiency values ​​in the array is calculated to obtain a plurality of differential values, and the plurality of differential values ​​are V1, V2, ... V k ,V k+1 ,…V n ; Wherein 1≤k≤n, k and n are both natural numbers; n is the number of users corresponding to the first photovoltaic power generation data;

[0058] For equation V k ≥V k+1 *m to solve and obtain the equation V k ≥V k+1 *k value of m; where m is a constant;

[0059] Specifically, the m value is iterated by training the Kmeans model based on the results returned by the on-site inspection of abnormal users, and the m value is adjusted by adjusting the parameter value of Kmean;

[0060] The process of calculating the constant m can be obtained by the following method:

[0061] Through Kmeans clustering, a number of user groups (i.e., a number of groups of power generation efficiency data) are obtained, and the minimum value Vmin of the group with the highest average unit power generation efficiency corresponding to the user group and the maximum value Vmax of the group with the lowest average unit power generation efficiency are obtained;

[0062] Then m=Vmin / Vmax.

[0063] Among them, the Kmeans model clustering algorithm is as follows:

[0064] The provincial photovoltaic user data is clustered based on the K-mean algorithm. Data from 6 to 24 months are taken and classified by region based on the daily average unit power generation efficiency (daily average unit power generation efficiency = monthly power generation / contract capacity / power generation days). Abnormal outlier users are identified by comparing the photovoltaic power generation curve with the data in the same region. Abnormal outlier users are abnormal suspected users.

[0065] For example: The model uses data from March 2021 to August 2021 for fitting, and fits out some suspected users.

[0066] For example, the model selects February 2021 and fits the model based on historical 24-month data, outputting 9 suspected users, of which 6 have breached the contract, and the remaining 2 users are not on site and cannot be verified, as shown in the following table:

[0067] Table: Actual abnormal user table

[0068]

[0069]

[0070]

[0071] In this embodiment, the power generation efficiency values ​​of each time period (i.e., the set time period) are summed, and then the power generation efficiency values ​​are sorted from high to low; the first n power generation efficiency values ​​are taken for differential calculation, that is, the difference between the first value and the second value, the difference between the second value and the third value, and so on, if the kth differential value and the k+1th differential value satisfy: V k >=V k+1 *m, find the minimum k value at this time.

[0072] For example, if n=5, in a certain time period, the efficiency values ​​of the transmitting points are sorted as list1=[10,9.5,8,5,4.5,4,3,2,1];

[0073] Then the difference sequence is list2 = [0.5, 1.5, 3, 0.5, 0.5, 1, 1, 1];

[0074] As a specific embodiment, for example, m is defined as 2.4; when m=2.4,

[0075] When m=2.4, 3>0.5*2.4, then the minimum k value is 3, where 3<=5, that is, the first three points are considered outliers, that is, the user power generation equipment associated with the first three power generation efficiency values ​​is an over-capacity user.

[0076] The user power generation equipment associated with the k power generation efficiency values ​​in the array is regarded as the user power generation equipment with high power generation efficiency.

[0077] Specifically, the user power generation equipment associated with the k power generation efficiency values ​​in the array is used as the user power generation equipment with high power generation efficiency, including:

[0078] If the power generation efficiency values ​​of each user's power generation equipment are arranged in ascending order, the first k power generation efficiency values ​​in the array are obtained in sequence from high power generation efficiency value to low power generation efficiency value, and the user power generation equipment associated with the first k power generation efficiency values ​​is regarded as the user power generation equipment with high power generation efficiency.

[0079] In the above implementation process, since the power generation of fixed-capacity power generation equipment should be within a certain range, after grouping, the outliers with excessively high power generation efficiency are found by combining rule design with clustering, that is, photovoltaic over-capacity users, and then a list of abnormal power generation users is output.

[0080] As another embodiment, after the step of obtaining the power generation efficiency data of each user's power generation equipment that meets the preset condition in the set time period, the method of the present invention further includes:

[0081] Step S41: judging the equipment life cycle of each user's power generation equipment according to the second photovoltaic power generation data, and identifying users associated with user power generation equipment whose equipment life cycle has expired as users who need to replace power generation equipment.

[0082] Optionally, judging the equipment life cycle of the user's power generation equipment according to the photovoltaic power generation data includes:

[0083] Screening and clustering the power generation efficiency data to obtain user power generation equipment whose power generation efficiency value is lower than a power generation threshold;

[0084] The user power generation equipment with power generation efficiency lower than the power generation threshold is regarded as the power generation equipment with the life cycle of the equipment exhausted.

[0085] For specific application examples, please refer to Figure 2 As shown, Figure 2The specific application embodiment of an abnormal user detection method based on an algorithm and big data provided by the method of the present invention is shown. According to the second photovoltaic power generation data, on the one hand, the equipment life cycle of each user's power generation equipment can be determined; on the other hand, according to the second photovoltaic power generation data, abnormal users can be detected.

[0086] 1. Equipment life cycle detection

[0087] In the photovoltaic power generation data storage database (hereinafter referred to as photovoltaic data database), the date, region, weather, equipment information and power generation information are recorded. A small area, such as a town or district, is used as a unit dimension (hereinafter referred to as unit), and a large amount of data in the photovoltaic data database is grouped by unit. Since the light intensity in the same unit is similar, for a period of time, for example, a week of data is obtained, sliced ​​by week, and Kmeans clustering and other analysis methods are performed on the power generation efficiency value to find the category with the lowest efficiency value, that is, the user set that needs to replace the equipment. The efficiency value is lower than the normal value, which can be used to judge that the equipment life has expired, so as to implement the equipment life and power generation efficiency guidance instructions.

[0088] 2. Abnormal user detection: The basic starting point for detecting the list of abnormal power generation users is based on the following assumptions: In a very small unit, factors affecting power generation such as light and equipment aging can be ignored. According to the user's reported capacity recorded by the system, the power generation of fixed-capacity power generation equipment should be within a certain range. After grouping, the combination of rule design and clustering is used to find outliers with excessively high power generation efficiency, that is, photovoltaic over-capacity users, and then output a list of abnormal power generation users.

[0089] It should be noted that overcapacity users are those who arbitrarily introduce or supply power or privately connect backup power and other power sources to the grid without the consent of the power supply company. For example, this user is associated with a photovoltaic power generation user, self-generated and self-used surplus power to the grid, and completed the photovoltaic household registration procedures on July 21, 2020, installed the meter on August 14, and signed the contract on August 21. The installed capacity in the contract is 7.93kw. According to the collection system query, the user had generated 440.41kwh of electricity before signing the contract, which is a breach of contract.

[0090] Embodiment 2:

[0091] As an embodiment, an abnormal user detection system based on algorithms and big data of the present invention includes:

[0092] A data acquisition unit 20 is used to acquire first photovoltaic power generation data of all user power generation devices to be detected;

[0093] A data screening unit 30 is used to obtain second photovoltaic power generation data of each user's power generation equipment that meets a certain preset condition according to the first photovoltaic power generation data;

[0094] The data calculation unit 40 is used to obtain the power generation efficiency data of each user's power generation equipment that meets the preset condition in a set time period according to the second photovoltaic power generation data; the power generation efficiency data includes the power generation efficiency value of each user's power generation equipment that meets the preset condition in the set time period;

[0095] The analysis unit 50 is used to perform cluster analysis on the power generation efficiency data to obtain user power generation equipment with high power generation efficiency, and to regard users associated with the user power generation equipment with high power generation efficiency as abnormal users.

[0096] As another example, please refer to Figure 3 As shown, Figure 3 The present invention shows an abnormal user detection system based on algorithms and big data, including:

[0097] The grouping unit 10 is used for grouping the first photovoltaic power generation data into a plurality of groups according to the different power supply units to which the first photovoltaic power generation data belongs, wherein users belonging to the same power supply unit are divided into the same group; users belonging to different power supply units are divided into different groups;

[0098] A data acquisition unit 20 is used to acquire first photovoltaic power generation data of all user power generation devices to be detected;

[0099] A data screening unit 30 is used to obtain second photovoltaic power generation data of each user's power generation equipment that meets a certain preset condition according to the first photovoltaic power generation data;

[0100] The data calculation unit 40 is used to obtain the power generation efficiency data of each user's power generation equipment that meets the preset condition in a set time period according to the second photovoltaic power generation data; the power generation efficiency data includes the power generation efficiency value of each user's power generation equipment that meets the preset condition in the set time period;

[0101] The analysis unit 50 is used to perform cluster analysis on the power generation efficiency data to obtain user power generation equipment with high power generation efficiency, and to regard users associated with the user power generation equipment with high power generation efficiency as abnormal users.

[0102] Embodiment three:

[0103] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application, which can be used in the present application Figure 4 The schematic diagram shown is used to describe an electronic device 100 for implementing an abnormal user detection method based on algorithms and big data according to an embodiment of the present application.

[0104] like Figure 4The electronic device 100 includes one or more processors 102 and one or more storage devices 104. These components are interconnected via a bus system and / or other forms of connection mechanisms (not shown). It should be noted that Figure 4 The components and structures of the electronic device 100 shown are only exemplary and not restrictive. The electronic device may have Figure 4 Some of the components shown may also have Figure 4 Other components and structures are not shown.

[0105] The processor 102 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 100 to perform desired functions.

[0106] The storage device 104 may include one or more computer program products, and the computer program product may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 102 may run the program instructions to implement the functions (implemented by the processor) in the embodiments of the present application described below and / or other desired functions. Various applications and various data may also be stored in the computer-readable storage medium, such as various data used and / or generated by the application, etc.

[0107] The present invention also provides a computer storage medium on which a computer program is stored. If the method of the present invention is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in the computer storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by a processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer storage medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer storage media does not include electrical carrier signals and telecommunication signals.

[0108] For those skilled in the art, various other corresponding changes and deformations can be made according to the technical solutions and concepts described above, and all of these changes and deformations should fall within the protection scope of the claims of the present invention.

Claims

1. An abnormal user detection method based on algorithm and big data, characterized in that: The following steps are involved: Acquire first photovoltaic power generation data of all user power generation equipment to be detected; According to the first photovoltaic power generation data, second photovoltaic power generation data of each user's power generation equipment that meets a certain preset condition is obtained; the preset condition is that the user's power generation equipment belongs to a certain power supply unit; According to the second photovoltaic power generation data, power generation efficiency data of each user's power generation equipment that meets the preset condition in a set time period is obtained; the power generation efficiency data includes the power generation efficiency value of each user's power generation equipment that meets the preset condition in the set time period; Performing cluster analysis on the power generation efficiency data to obtain user power generation equipment with high power generation efficiency, and treating users associated with the user power generation equipment with high power generation efficiency as abnormal users; The cluster analysis of the power generation efficiency data to obtain user power generation equipment with high power generation efficiency includes: The power generation efficiency values ​​of each user's power generation equipment are sorted to obtain an array of sorted power generation efficiency values; the difference between two adjacent power generation efficiency values ​​in the array is calculated to obtain a plurality of differential values, and the plurality of differential values ​​are V1, V2, ... V k ,V k+1 ,…V n ; Where 1≤k≤n, k and n are both natural numbers; For equation V k ≥V k+1 *m to solve and obtain the equation V k ≥V k+1 *k value of m; where m is a constant; The user power generation equipment associated with the k power generation efficiency values ​​in the array is regarded as the user power generation equipment with high power generation efficiency.

2. The abnormal user detection method based on algorithm and big data according to claim 1 is characterized in that: The user power generation equipment associated with the k power generation efficiency values ​​in the array is used as the user power generation equipment with high power generation efficiency, including: If the power generation efficiency values ​​of each user's power generation equipment are arranged in ascending order, the first k power generation efficiency values ​​in the array are obtained in sequence from high power generation efficiency value to low power generation efficiency value, and the user power generation equipment associated with the first k power generation efficiency values ​​is regarded as the user power generation equipment with high power generation efficiency.

3. The abnormal user detection method based on algorithm and big data according to claim 1 is characterized in that: After the step of obtaining the power generation efficiency data of each user's power generation equipment that meets the preset condition in the set time period, the method further includes: The equipment life cycle of each user's power generation equipment is determined according to the second photovoltaic power generation data, and users associated with user power generation equipment whose equipment life cycle has expired are regarded as users who need to replace power generation equipment.

4. The abnormal user detection method based on algorithm and big data according to claim 3 is characterized in that: The determining, based on the photovoltaic power generation data, the equipment life cycle of the user's power generation equipment includes: Screening and clustering the power generation efficiency data to obtain user power generation equipment whose power generation efficiency value is lower than a power generation threshold; The user power generation equipment with power generation efficiency lower than the power generation threshold is regarded as the power generation equipment with the life cycle of the equipment exhausted.

5. The abnormal user detection method based on algorithm and big data according to claim 1 is characterized in that: The step of obtaining the first photovoltaic power generation data of all user power generation devices to be detected includes: The first photovoltaic power generation data is obtained from the photovoltaic power generation data storage database, wherein the first photovoltaic power generation data includes the regional information, equipment attribute information, power generation information, and power generation start time and end time information of each user's power generation equipment.

6. The abnormal user detection method based on algorithm and big data according to claim 1 is characterized in that: The step of obtaining second photovoltaic power generation data of each user's power generation equipment that meets a preset condition according to the first photovoltaic power generation data includes: The first photovoltaic power generation data is divided according to the different power supply units to which it belongs; wherein, user power generation equipment belonging to the same power supply unit is divided into the same group; user power generation equipment belonging to different power supply units is divided into different groups, thereby obtaining the second photovoltaic power generation data belonging to a certain power supply unit.

7. An abnormal user detection system based on algorithms and big data, characterized in that: include: A data acquisition unit, used for acquiring first photovoltaic power generation data of all user power generation equipment to be detected; A data screening unit, configured to obtain second photovoltaic power generation data of each user's power generation equipment that meets a certain preset condition according to the first photovoltaic power generation data; the preset condition is that the user's power generation equipment belongs to a certain power supply unit; A data calculation unit, configured to obtain power generation efficiency data of each user's power generation equipment that meets the preset condition in a set time period according to the second photovoltaic power generation data; the power generation efficiency data includes power generation efficiency values ​​of each user's power generation equipment that meets the preset condition in the set time period; An analysis unit is used to perform cluster analysis on the power generation efficiency data to obtain user power generation equipment with high power generation efficiency, and to regard users associated with the user power generation equipment with high power generation efficiency as abnormal users; The cluster analysis of the power generation efficiency data to obtain user power generation equipment with high power generation efficiency includes: sorting the power generation efficiency values ​​of each user power generation equipment to obtain an array composed of sorted power generation efficiency values; calculating the difference between two adjacent power generation efficiency values ​​in the array to obtain a plurality of difference values, wherein the plurality of difference values ​​are V1, V2, ... V k ,V k+1 ,…V n ; where 1≤k≤n, k and n are both natural numbers; for equation V k ≥V k+1 *m to solve and obtain the equation V k ≥V k+1 *k value of m; wherein m is a constant; the user power generation equipment associated with the k power generation efficiency values ​​in the array is regarded as the user power generation equipment with high power generation efficiency.

8. An electronic device, characterized in that: include: At least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the abnormal user detection method based on algorithm and big data as described in any one of claims 1-6.

9. A computer storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it implements the abnormal user detection method based on algorithm and big data described in any one of claims 1 to 6.

Images