A method, device, equipment and storage medium for identifying mining users

Abstract

The present invention belongs to the field of electronic information technology, and particularly relates to a method, device, equipment and storage medium for identifying mining users, including the following steps: obtaining power consumption data of a number of high-power-consuming users in a specified area; obtaining green power output data for supplying power to the specified area; preprocessing the obtained green power output data; calculating the power distance between the power consumption sequences of every two high-power-consuming users among the number of high-power-consuming users; establishing a user power community through a community discovery algorithm according to the power distance between the power consumption sequences of every two high-power-consuming users; calculating the Pearson correlation coefficient between the typical power curve and the green power output curve in each user power community; determining mining users according to the magnitude of the Pearson correlation coefficient, and outputting the information of the determined mining users. By analyzing the typical power curve in the automatic community, the present invention has high investigation efficiency, low omission rate and high accuracy.

Description

Technical Field

[0001] The present invention belongs to the field of electronic information technology, and particularly relates to a method, device, equipment and storage medium for identifying mining users. Background Art

[0002] Virtual currencies such as Bitcoin are not officially issued and pose great risks in related speculative activities. At the same time, the mining behavior itself consumes a large amount of electricity but does not actually contribute to the social and economic development, so it also does not conform to the concept of green development in China. However, although larger and more well-known mining farms have been shut down, some small and medium-sized mining farms may still engage in mining activities under the guise of cloud computing centers and data centers. Therefore, it is necessary to invent a method to identify highly suspected mining users based on the electricity consumption characteristics of high-power-consuming users.

[0003] The defects and deficiencies of the prior art are specifically reflected in the following aspects:

[0004] (1) The traditional identification of mining users mainly relies on manual observation and analysis of electricity curves, with low efficiency, high omission rate and high error rate.

[0005] (2) It relies on general machine learning and clustering algorithms, which require a large amount of sample data for training and are often difficult to obtain in practice.

[0006] It has been found through research that the seasonal characteristics of the electricity curves of mining users are obvious. After analysis, the intensity of mining behavior shows a strong positive correlation with the main green power output in the network province where it is located. Since the green power output is high and difficult to consume in a specific season, the price of green power is low, which attracts mining behavior. Therefore, the above characteristics can be used to realize the identification of the electricity consumption of highly suspected mining users based on a small data sample. Summary of the Invention

[0007] The present invention provides a method, device, equipment and storage medium for identifying mining users to solve the technical problems of low efficiency in traditional mining user identification and serious omission and error checking.

[0008] The present invention adopts the following technical solutions to achieve:

[0009] A further improvement of the present invention lies in: including the following steps:

[0010] Obtain the electricity consumption data of several high-power-consuming users in a specified area;

[0011] Obtain the green power output data for supplying power to the specified area;

[0012] Preprocess the obtained green power output data;

[0013] Calculate the electricity distance between the electricity consumption sequences of every two high-power-consuming users among the several high-power-consuming users;

[0014] Based on the electricity quantity distance between the electricity consumption sequences of every two high-power-consuming users, a user electricity quantity community is established through a community discovery algorithm.

[0015] Calculate the Pearson correlation coefficient between the typical electricity quantity curve and the green electricity output curve in each user electricity quantity community.

[0016] Determine the mining users according to the size of the Pearson correlation coefficient, and output the information of the determined mining users.

[0017] A further improvement of the present invention lies in that: the step of obtaining the electricity consumption data of several high-power-consuming users in a specified area specifically includes:

[0018] When obtaining the electricity consumption data of all high-power-consuming users in a specified area, the data time span is greater than or equal to 1 year, and according to the industry label, the electricity consumption data of regular high-power-consuming users is removed to obtain the electricity consumption data of the several high-power-consuming users.

[0019] A further improvement of the present invention lies in that: the data granularity of the green electricity data is greater than or equal to the monthly average power.

[0020] A further improvement of the present invention lies in that: the step of preprocessing the obtained green electricity output data specifically includes: performing interpolation or smoothing processing on the green electricity output data according to time, so that within the same time span, the length of the green electricity output data sequence is equal to the length of the electricity consumption data sequence of each high-power-consuming user.

[0021] A further improvement of the present invention lies in that: when calculating the electricity quantity distance between the electricity consumption sequences of every two high-power-consuming users among the several high-power-consuming users, the following steps are included:

[0022] Calculate the electricity quantity distance between every two high-power-consuming users i and j :

[0023]

[0024] Where pij is the Pearson correlation coefficient between [Qi,t] and [Qj,t]; [Qi,t] and [Qj,t] are the daily electricity consumption sequences of high-power-consuming users i and j, where Q represents the electricity consumption, i and j represent the user numbers, and t represents the date.

[0025] A further improvement of the present invention lies in that: when establishing a user electricity quantity community through a community discovery algorithm based on the electricity quantity distance between the electricity consumption sequences of every two high-power-consuming users, the following steps are included:

[0026] According to the electricity quantity distance between every two high-power-consuming users i and j Compare with a preset threshold dc;

[0027] If is greater than or equal to dc, i and j are not in the same user power community;

[0028] If is less than dc, i and j are in the same user power community;

[0029] dc is 0.8 to 0.9;

[0030] Traverse all high-power-consuming users through the community discovery algorithm to establish several user power communities.

[0031] A further improvement of the present invention lies in: calculating the Pearson correlation coefficient between the typical power curve and the green power output curve in each community, determining the mining users according to the magnitude of the Pearson correlation coefficient, and the specific steps of outputting the determined mining user information include: calculating the Pearson correlation coefficient p between the typical power curve i in each community and the interpolated green power output curve ie and outputting each user power community in several groups according to the magnitude of the Pearson correlation coefficient.

[0032] In a second aspect, a device for identifying mining users includes:

[0033] An electricity consumption data acquisition module for acquiring electricity consumption data of several high-power-consuming users in a specified area;

[0034] A green power output acquisition module for acquiring green power output data for supplying power to the specified area;

[0035] A data preprocessing module for preprocessing the green power output data and the electricity consumption data of high-power-consuming users;

[0036] An electricity distance calculation module for calculating the electricity distance between the electricity consumption sequences of every two users to be measured;

[0037] A user power community establishment module for establishing user power communities through the community discovery algorithm according to the electricity distance between the electricity consumption sequences of every two users to be measured;

[0038] A correlation coefficient calculation module for calculating the Pearson correlation coefficient between the typical power curve and the occurrence of green power output in each community;

[0039] A mining user determination module for determining mining users and outputting the determined mining user information.

[0040] In a third aspect, a computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, it is the above method for identifying mining users.

[0041] Fourth aspect, a computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned method for identifying mining users is implemented.

[0042] Compared with the prior art, the present invention at least includes the following beneficial effects:

[0043] 1. By analyzing the typical power consumption curves in the automatic community, the present invention has high troubleshooting efficiency, low missed inspection rate, and high accuracy.

[0044] 2. The present invention combines the mining behavior with the green power output of the province where it is located to improve the accuracy of identifying mining users.

[0045] 3. By using the Pearson correlation coefficient of the typical power consumption curves and green power output in each community to determine whether a user is mining, the present invention avoids missed inspections and misidentifications. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The accompanying drawings forming a part of the present invention are used to provide a further understanding of the present invention. The schematic embodiments and descriptions thereof of the present invention are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0047] Figure 1 is a flowchart of a method for identifying mining users according to the present invention;

[0048] Figure 2 is a block diagram of a device for identifying mining users according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0049] The present invention will be described in detail below with reference to the accompanying drawings and embodiments. It should be noted that, without conflict, the embodiments and features in the embodiments of the present invention can be combined with each other.

[0050] The following detailed descriptions are all exemplary descriptions, aiming to provide a further detailed description of the present invention. Unless otherwise specified, all technical terms used in the present invention have the same meaning as commonly understood by those of ordinary skill in the art to which the present invention belongs. The terms used in the present invention are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present invention.

[0051] Embodiment 1:

[0052] As Figure 1 shown, a method for identifying mining users includes the following steps:

[0053] Obtain the electricity consumption data of several high-power-consuming users in a specified area;

[0054] Obtain the green power output data for supplying power to the specified area;

[0055] Preprocess the obtained green power output data;

[0056] Calculate the power distance between the power consumption sequences of every two high-power-consuming users among the several high-power-consuming users;

[0057] Establish user power communities through community discovery algorithms based on the power distances between the power consumption sequences of every two high-power-consuming users;

[0058] Calculate the Pearson correlation coefficient between the typical power curve and the green power output curve in each user power community;

[0059] Determine the mining users according to the size of the Pearson correlation coefficient, and output the information of the determined mining users.

[0060] Rank the power consumption of each user from large to small according to the power supply scale of the power company supplying power to the specified area and the tolerance of the users within the same research time period, and select the top 40 - 100 as high-power-consuming users for research.

[0061] For a specified area, collect the daily power consumption data of the high-power-consuming user meters. The data time span is not less than one year, and exclude regular high-power-consuming users such as base stations according to the industry labels in the power marketing system, leaving the data of the remaining users to be detected;

[0062] Collect the dominant and seasonal green power output data of the network province where it is located, including but not limited to power generation forms such as hydropower, wind power, and photovoltaic power stations. The data granularity should be at least the monthly average power;

[0063] Interpolate or smooth the green power output data by time so that within the same time span, the length of the green power output data sequence is equal to the length of the power consumption data sequence of each high-power-consuming user.

[0064] Calculate the power distance between the users to be detected i and j pairwise , where pij is the Pearson correlation coefficient between [Qi,t] and [Qj,t], and [Qi,t] and [Qj,t] are the daily power consumption sequences of i and j. Here, Q represents power consumption, i and j represent user numbers, and t represents the date. The higher this distance value, the weaker the correlation. When the distance exceeds the threshold dc, it is considered that there is no significant correlation between high-power-consuming users.

[0065] According to the power distance between every two high-power-consuming users i and j Compare with the preset threshold dc;

[0066] If is greater than or equal to dc, i and j are not in the same user power community;

[0067] If When it is less than dc, i and j are in the same user power community;

[0068] dc is 0.8 to 0.9.

[0069] Calculate the Pearson correlation coefficient between the typical power curve and the green power output curve in each community. According to the magnitude of the Pearson correlation coefficient, determine the steps of the mining users, and output the determined mining user information, specifically including: calculate the Pearson correlation coefficient p between the typical power curve i in each community and the interpolated green power output curve ie and output each user power community in 4 groups according to the magnitude of the Pearson correlation coefficient.

[0070] Among them, according to p ie judge whether all high-power-consuming users in this community are mining users; if p ie ≥0.8, the user power communities are grouped and output; if, it is highly suspected; if 0.8 > p ie ≥0.6, the user power communities are grouped and output;, it is moderately suspected; if 0.6 > p ie ≥0.4, the user power communities are grouped and output;, it is lowly suspected; if p ie <0, the user power communities are grouped and output, then the users are excluded.

[0071] Embodiment 2:

[0072] As Figure 2 shown, a device for identifying mining users includes:

[0073] An electricity consumption data acquisition module, which acquires the electricity consumption data of several high-power-consuming users in a specified area;

[0074] A green power output acquisition module, which acquires the green power output data for supplying power to the specified area;

[0075] A data preprocessing module, which preprocesses the green power output data and the electricity consumption data of high-power-consuming users;

[0076] A power distance calculation module, which calculates the power distance between the electricity consumption sequences of every two users to be measured;

[0077] A user power community establishment module, which establishes user power communities according to the power distance between the electricity consumption sequences of every two users to be measured through a community discovery algorithm;

[0078] A correlation coefficient calculation module, which calculates the Pearson correlation coefficient between the typical power curve and the appearance of green power output in each community;

[0079] A mining user determination module, which determines the mining users and outputs the determined mining user information.

[0080] When the power consumption data acquisition module obtains the power consumption data of all high-power-consuming users in the specified area, the data time span is greater than or equal to 1 year, and according to the industry label, the power consumption data of regular high-power-consuming users is removed to obtain the power consumption data of the several high-power-consuming users.

[0081] The green power output acquisition module, the data granularity of the green power data collected is greater than or equal to the monthly average power.

[0082] The data preprocessing module interpolates the green power output data according to time to make the length of the green power output data sequence equal to the length of the power consumption data sequence of each high-power-consuming user.

[0083] When the power consumption distance calculation module calculates the power consumption distance between the power consumption sequences of every two high-power-consuming users among several high-power-consuming users, it includes the following steps:

[0084] Calculate the power consumption distance between every two high-power-consuming users i and j :

[0085]

[0086] In the formula, pij is the Pearson correlation coefficient between [Qi,t] and [Qj,t]; [Qi,t] and [Qj,t] are the daily power consumption sequences of high-power-consuming users i and j, where Q represents power consumption, i and j represent user numbers, and t represents the date.

[0087] The user power consumption community establishment module, according to the power consumption distance between every two high-power-consuming users i and j Compare with the preset threshold dc;

[0088] If Greater than or equal to dc, i and j are not in the same user power consumption community;

[0089] If Less than dc, i and j are in the same user power consumption community;

[0090] dc is 0.8 to 0.9;

[0091] Traverse all high-power-consuming users through the community discovery algorithm to establish several user power consumption communities.

[0092] The mining user determination module calculates the Pearson correlation coefficient between the typical power consumption curve and the green power output curve in each community, and determines the mining users according to the size of the Pearson correlation coefficient. The steps for outputting the determined mining user information specifically include: calculating the Pearson correlation coefficient p between the typical power consumption curve i in each community and the interpolated green power output curve ie, and output each user's power consumption community in four groups according to the size of the Pearson correlation coefficient.

[0093] Among them, according to p ie Determine whether all high-power-consuming users in the community are mining users; if p ie ≥0.8 user power consumption communities are grouped and output; if p, then it is highly suspected; if 0.8 > p ie ≥0.6 user power consumption communities are grouped and output;, then it is moderately suspected; if 0.6 > p ie ≥0.4 user power consumption communities are grouped and output;, then it is lowly suspected; if p ie <0 user power consumption communities are grouped and output, then exclude users.

[0094] Example 3:

[0095] A computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, when the processor executes the computer program, it implements the method for identifying mining users described in Example 1.

[0096] Example 4:

[0097] A computer-readable storage medium, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements the method for identifying mining users described in Example 1.

[0098] As is known by technical common sense, the present invention can be implemented by other implementation schemes that do not depart from its spiritual essence or necessary features. Therefore, the above-disclosed implementation schemes are, in all aspects, merely illustrative and not exclusive. All changes within the scope of the present invention or within the scope equivalent to the present invention are encompassed by the present invention.

[0099] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0100] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable data processing devices to generate a machine, such that the instructions executed by the processors of the computer or other programmable data processing devices produce means for implementing the functions specified in one or more flows and / or blocks Figure 1 in one or more flows and / or blocks Figure 1 or in one or more blocks.

[0101] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including instruction means for implementing the functions specified in one or more flows and / or blocks Figure 1 in one or more flows and / or blocks Figure 1 or in one or more blocks.

[0102] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more flows and / or blocks Figure 1 in one or more flows and / or blocks Figure 1 or in one or more blocks.

[0103] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications or equivalent replacements can still be made to the specific embodiments of the present invention. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention shall be covered by the protection scope of the claims of the present invention.

Claims

1. A method for identifying mining users, characterized in that, The following steps are involved: Obtain electricity consumption data of several high-power-consuming users in a specified area; Acquiring green power output data supplied to the designated area; Preprocess the acquired green power output data; Calculating the power consumption distance between power consumption sequences of every two high power consumption users among the plurality of high power consumption users; A user power consumption community is established based on the power consumption distance between every two high-power consumption user power consumption sequences through a community discovery algorithm; Calculate the Pearson correlation coefficient between the typical power curve and the green power output curve in each user power community; According to the size of the Pearson correlation coefficient, the mining user is determined, and the determined mining user information is output; The step of obtaining the power consumption data of several high power consumption users in the specified area specifically includes: When acquiring electricity consumption data of all high-power consumption users in a specified area, the data time span is greater than or equal to 1 year, and according to industry labels, the electricity consumption data of conventional high-power consumption users are removed to obtain the electricity consumption data of the several high-power consumption users.

2. The method for identifying mining users according to claim 1, wherein, The data granularity of green electricity data is greater than or equal to the monthly average power.

3. The method for identifying mining users according to claim 1, wherein The step of preprocessing the acquired green power output data specifically includes: interpolating or smoothing the green power output data according to time, so that within the same time span, the length of the green power output data sequence is equal to the length of the power consumption data sequence of each high power consumption user.

4. The method for identifying mining users according to claim 1, characterized in that, When calculating the power consumption distance between the power consumption sequences of every two high power consumption users among the plurality of high power consumption users, the following steps are included: Calculate the electricity distance between every two high-power-consuming users i and j : Where pij is the Pearson correlation coefficient between [Qi,t] and [Qj,t]; [Qi,t] and [Qj,t] are the daily power consumption sequences of high power consumption users i and j, where Q represents power consumption, i and j represent user serial numbers, and t represents the date.

5. The method for identifying mining users according to claim 4, wherein, When establishing a user power consumption community based on the power consumption distance between every two high-power consumption user power consumption sequences through a community discovery algorithm, the following steps are included: According to the electricity quantity distance between every two high-power-consuming users i and j Compare with a preset threshold value dc; If When it is greater than or equal to dc, i and j are not in the same user power community; If When it is less than dc, i and j are in the same user power community; dc is 0.8~0.9; Through the community discovery algorithm, all high-power consumption users are traversed and several user power consumption communities are established.

6. The method for identifying mining users according to claim 1, wherein The steps of calculating the Pearson correlation coefficient between the typical power consumption curve and the green power output curve in each community, determining the mining users according to the magnitude of the Pearson correlation coefficient, and outputting the determined mining user information specifically include: calculating the Pearson correlation coefficient p between the typical power consumption curve i in each community and the interpolated green power output curve ie , and outputting each user power community in several groups according to the magnitude of the Pearson correlation coefficient.

7. An apparatus for identifying mining users, characterized in that, include: The power consumption data collection module obtains the power consumption data of several high power consumption users in the specified area. When obtaining the power consumption data of all high power consumption users in the specified area, the data time span is greater than or equal to 1 year, and according to the industry label, the power consumption data of conventional high power consumption users is removed to obtain the power consumption data of the several high power consumption users; A green power output collection module is used to obtain green power output data supplied to the designated area; Data preprocessing module, which preprocesses green power output data and power consumption data of high power consumption users; The power distance calculation module calculates the power distance between each two power consumption sequences of the users to be tested; The user power community establishment module establishes a user power community based on the power distance between each two user power consumption sequences to be tested through a community discovery algorithm; The correlation coefficient calculation module calculates the Pearson correlation coefficient of the typical electricity curve and green electricity output in each community; The mining user determination module determines the mining user and outputs the determined mining user information.

8. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for identifying a mining user according to any one of claims 1-6 is implemented.

9. A computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the method for identifying a mining user according to any one of claims 1-6 is implemented.

Images