CN116047223A - Electricity larceny distinguishing method based on real-time electricity consumption and big data analysis - Google Patents
Electricity larceny distinguishing method based on real-time electricity consumption and big data analysis Download PDFInfo
- Publication number
- CN116047223A CN116047223A CN202211698772.8A CN202211698772A CN116047223A CN 116047223 A CN116047223 A CN 116047223A CN 202211698772 A CN202211698772 A CN 202211698772A CN 116047223 A CN116047223 A CN 116047223A
- Authority
- CN
- China
- Prior art keywords
- user
- line loss
- electricity
- potential
- identified
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000005611 electricity Effects 0.000 title claims abstract description 119
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000007405 data analysis Methods 0.000 title claims abstract description 16
- 230000002159 abnormal effect Effects 0.000 claims abstract description 55
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 30
- 230000005540 biological transmission Effects 0.000 claims abstract description 13
- 230000005856 abnormality Effects 0.000 claims abstract description 5
- 230000006399 behavior Effects 0.000 claims description 28
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000010801 machine learning Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 230000001419 dependent effect Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/088—Aspects of digital computing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Economics (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method for judging electricity larceny based on real-time electricity information and big data analysis, which belongs to the technical field of power systems and specifically comprises the following steps: acquiring a line loss threshold value of a user based on a line loss prediction model of the LA-GSA-GRU algorithm based on real-time electricity utilization data, weather temperature and resistivity of a power transmission line material of the user; when the line loss rate of the user is larger than the line loss threshold value of the user, the user is identified as a potential abnormal client, and the ratio of the line loss rate to the line loss threshold value is used as the line loss ratio; when the number of times that the user is identified as the potential line loss user in the next month is larger than the first threshold value, determining the line loss abnormality degree of the potential line loss user based on the number of times that the user is identified as the potential abnormal line loss user, the average value of the line loss ratios when all the users are identified as the potential abnormal line loss users and the maximum value of the line loss ratios when the users are identified as the potential abnormal line loss users, and judging the electricity stealing behavior based on the line loss abnormality degree, so that the efficiency and the accuracy of electricity stealing judgment are further improved.
Description
Technical Field
The invention belongs to the technical field of power systems, and particularly relates to a method for judging fraudulent use of electricity based on real-time electricity information and big data analysis.
Background
In order to realize accurate identification of electricity larceny by adopting big data, the invention patent publication No. CN111521868B (a method and a device for screening electricity larceny users based on metering big data) obtains metering big data, wherein the metering big data comprises electricity consumption, electric quantity lost in a station area and line loss rate; determining the electricity stealing behavior characteristics according to the metering big data; calculating a related parameter threshold value of the electricity larceny by using a preset algorithm according to the characteristics of the electricity larceny; calculating relevant parameters of electricity stealing behaviors of users in the target platform region by using a preset algorithm according to the metering big data of the target platform region; comparing the electricity larceny related parameter with an electricity larceny related parameter threshold; according to the comparison result, the suspected electricity larceny users in the target platform area are screened, the working efficiency of screening the electricity larceny users is improved, but the following technical problems exist:
1. the influence of the temperature, the electricity consumption and the resistivity of the power transmission line material on the threshold value is ignored, the core of the line loss is generated by the impedance value of the line, and the impedance value of the line can be influenced by different temperatures, the electricity consumption and the resistivity of the power transmission line material, so that a fixed impedance value mode is adopted, the accuracy is not high, and the false identification of a power stealing user can be possibly caused.
2. The error probability of the identification result adopted only once is high, and the error identification of the electricity stealing behavior of the electricity consumer is caused due to the occurrence of abnormal conditions such as replacement of the electric equipment or short circuit, so that the error identification of the electricity stealing consumer is possibly caused if the identification is not carried out for a plurality of times within a certain time threshold.
Aiming at the technical problems, the invention provides a method for judging electricity larceny based on real-time electricity consumption information and big data analysis.
Disclosure of Invention
In order to achieve the purpose of the invention, the invention adopts the following technical scheme:
according to one aspect of the invention, a method for discriminating electricity theft based on real-time electricity information and big data analysis is provided.
A method for discriminating electricity larceny based on real-time electricity consumption and big data analysis is characterized by comprising the following steps:
s11, determining an abnormal threshold value of the power consumption data of the user based on the historical power consumption data of the user, judging whether the real-time power consumption data of the user is larger than the abnormal threshold value of the power consumption data or not based on the real-time power consumption data of the user, if so, entering a step S12, and if not, judging that the user does not have the power stealing behavior;
s12, acquiring a line loss threshold value of the user by adopting a line loss prediction model based on an LA-GSA-GRU algorithm based on real-time power consumption data, weather temperature and resistivity of a power transmission line material of the user;
s13, judging whether the line loss rate of the user is larger than the line loss threshold of the user, if so, identifying the user as a potential abnormal client, taking the ratio of the line loss rate of the user to the line loss threshold as a line loss ratio, and entering a step S14, if not, judging that the user does not have electricity stealing behavior;
and S14, when the number of times that the user is identified as the potential line loss user is larger than a first threshold value in the last month, determining the line loss anomaly degree of the potential line loss user by adopting a prediction model based on a machine learning algorithm based on the number of times that the user is identified as the potential abnormal line loss user, the average value of the line loss ratios when all the users are identified as the potential abnormal line loss users and the maximum value of the line loss ratios when the users are identified as the potential abnormal line loss users, and judging the electricity stealing behavior based on the line loss anomaly degree of the potential line loss user.
The line loss threshold value of the user is obtained based on the real-time power consumption data, the weather temperature and the resistivity of the power transmission line material of the user, so that the determination of the line loss threshold value is combined with the real-time power consumption data, the weather temperature and the resistivity of the power transmission line material of the user, the original technical problems of inaccuracy and poor flexibility of adopting the fixed line loss threshold value are avoided, and the reliability and the accuracy of judgment are further promoted.
By adopting a line loss prediction model based on the LA-GSA-GRU algorithm and automatically adjusting initial gravitation in the GSA based on a learning automaton, the GSA algorithm has better optimizing performance and faster convergence rate, and simultaneously, in order to avoid the problems that the GRU algorithm cannot automatically select in structure, random initial parameters directly influence the calculation process of the GRU algorithm, the convergence rate is slow and the like, the network layer number of an implicit layer of the GRU algorithm and the optimizing of node numbers of each layer are realized by adopting the LA-GSA algorithm, so that the convergence rate and the convergence precision are further improved.
Through the judgment of potential abnormal clients and the setting of the first threshold value, the judgment of the electricity stealing behavior of the user is not only dependent on single data or single potential abnormal conditions, but also the judgment of the line loss anomaly degree is realized by combining a prediction model adopting a machine learning algorithm, so that the accuracy and the reliability of the judgment are obviously improved, and the reliability of the line loss judgment is further ensured.
The further technical scheme is that the abnormal threshold value of the electricity consumption data of the user is determined according to the maximum value of the electricity consumption data of the user in the last year.
The further technical scheme is that the specific steps of line loss threshold construction are as follows:
s21, judging whether the real-time electricity consumption data of the user is larger than the maximum value of the historical electricity consumption data of the user at the same moment in the last week, if so, entering a step S22; if not, the user does not have the abnormal line loss condition, and the judgment of the line loss threshold value is not needed;
s22, obtaining a real-time electricity utilization ratio based on the ratio of the real-time electricity utilization data of the user to the average value of the historical electricity utilization data of the user at the same moment in the last week;
s23, acquiring a basic line loss threshold value of the user by adopting a line loss prediction model based on an LA-GSA-GRU algorithm based on the real-time power utilization ratio, the weather temperature and the resistivity of the power transmission line material;
and S24, correcting the basic line loss threshold value of the user based on the number of times that the user is identified as the potential line loss user in the last month to obtain the line loss threshold value of the user.
By judging the historical electricity consumption data, unnecessary calculation and establishment of a prediction model are avoided, the efficiency of the system is further improved, and the basic line loss threshold value of the user is further corrected by combining the number of times that the user is identified as a potential line loss user in the last month, so that the accuracy and reliability of the judgment of the final line loss threshold value are obviously improved.
Through the judgment of the real-time electricity utilization ratio, not only is the real-time electricity utilization data combined, but also the real-time electricity utilization data is combined with the electricity utilization data in the near week, so that the reliability and consistency of the finally judged data are further improved.
The further technical scheme is that the calculation formula of the line loss threshold value of the user is as follows:
wherein T is limit For the threshold number of times, T is generally taken between 3 and 5 times 1 D, for the number of times the user is identified as potential line loss user in the last month 1 As the basic line loss threshold, K 1 Is constant and has a value ranging from 0 to 0.05.
The further technical scheme is that the first threshold is determined according to the historical electricity fee arrearages of the potential line loss users and the historical electricity fee arrearages, wherein the more the historical electricity fee arrearages of the potential line loss users are, the more the historical electricity fee arrearages are, and the smaller the first threshold is.
The further technical scheme is that when the number of times of the user identified as the potential line loss user in the last month is larger than a second threshold value and the maximum value of the line loss ratio values of the users identified as the potential abnormal line loss users in the last month is larger than a first ratio value threshold value, the user is identified to have electricity stealing behavior, wherein the second threshold value is larger than the first threshold value.
The further technical proposal is that the specific steps of line loss abnormality degree construction are as follows:
s31, judging whether the number of times that the user is identified as a potential line loss user in the last month is larger than a third threshold value, if so, identifying that the user has electricity stealing behavior, and if not, entering step S32;
s32, judging whether the average value of line loss ratios of all users identified as potential abnormal line loss users is larger than a first average value threshold value and the number of times of identifying the users as potential line loss users in the last month is larger than a second threshold value, if so, identifying that the users have electricity stealing behaviors, and if not, entering step S33;
s33, determining the line loss anomaly degree of the potential line loss user by adopting a prediction model based on a BP neural network algorithm based on the number of times the user is identified as the potential abnormal line loss user, the average value of the line loss ratio when the user is identified as the potential abnormal line loss user and the maximum value of the line loss ratio when the user is identified as the potential abnormal line loss user.
By further combining the third threshold value, the second threshold value and the first average threshold value, abnormal users can be accurately identified, excessive computing resources occupied by partial users with larger abnormal degrees are avoided, judging efficiency is improved, and judging accuracy is improved for users with smaller abnormal degrees.
When the line loss anomaly degree of the potential line loss user is larger than a first anomaly degree threshold value, determining that the user has electricity stealing behavior; and when the line loss anomaly degree of the potential line loss user is larger than a second anomaly degree threshold value and the number of times that the user is identified as the potential line loss user is larger than a second threshold value, identifying that the user has electricity stealing behavior.
On the other hand, the invention provides a terminal device, which comprises a memory, a processor and a program stored on the memory and capable of running on the processor, wherein when the processor executes the program, the method for judging electricity theft based on real-time electricity information and big data analysis is realized.
In another aspect, the present invention provides a computer storage medium having a computer program stored thereon, which when executed in a computer causes the computer to perform the above-described electricity theft judging method based on real-time electricity consumption and big data analysis.
Additional features and advantages will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and drawings.
In order to make the above objects, features and advantages of the present invention more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
The above and other features and advantages of the present invention will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings.
Fig. 1 is a flowchart of a method for discriminating electricity theft based on real-time electricity consumption and big data analysis according to embodiment 1.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments can be embodied in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. The same reference numerals in the drawings denote the same or similar structures, and thus detailed descriptions thereof will be omitted.
The terms "a," "an," "the," and "said" are used to indicate the presence of one or more elements/components/etc.; the terms "comprising" and "having" are intended to be inclusive and mean that there may be additional elements/components/etc. in addition to the listed elements/components/etc.
Example 1
In order to solve the above problems, according to one aspect of the present invention, as shown in fig. 1, there is provided a method for determining fraudulent use of electricity based on real-time electricity consumption and big data analysis, comprising:
s11, determining an abnormal threshold value of the power consumption data of the user based on the historical power consumption data of the user, judging whether the real-time power consumption data of the user is larger than the abnormal threshold value of the power consumption data or not based on the real-time power consumption data of the user, if so, entering a step S12, and if not, judging that the user does not have the power stealing behavior;
it should be noted that the electricity consumption data abnormality threshold is determined according to the maximum value of the electricity consumption data of the user in the last year.
S12, acquiring a line loss threshold value of the user by adopting a line loss prediction model based on an LA-GSA-GRU algorithm based on real-time power consumption data, weather temperature and resistivity of a power transmission line material of the user;
it should be further noted that, the formula of calculating the gravitational constant of the GSA algorithm is:
wherein G is 0 For initial attraction, T is the maximum iteration number, T is the current iteration number, rand (0, 1) is a random number with a value ranging from 0 to 1, K2 is a constant, the value is between 0.9 and 1, α is the attenuation coefficient.
S13, judging whether the line loss rate of the user is larger than the line loss threshold of the user, if so, identifying the user as a potential abnormal client, taking the ratio of the line loss rate of the user to the line loss threshold as a line loss ratio, and entering a step S14, if not, judging that the user does not have electricity stealing behavior;
and S14, when the number of times that the user is identified as the potential line loss user is larger than a first threshold value in the last month, determining the line loss anomaly degree of the potential line loss user by adopting a prediction model based on a machine learning algorithm based on the number of times that the user is identified as the potential abnormal line loss user, the average value of the line loss ratios when all the users are identified as the potential abnormal line loss users and the maximum value of the line loss ratios when the users are identified as the potential abnormal line loss users, and judging the electricity stealing behavior based on the line loss anomaly degree of the potential line loss user.
For example, if the number of times the user is identified as a potential abnormal line loss user is 4, the line loss ratio values when the user is identified as a potential abnormal line loss user are 1.2,1.3,1.5,2.0, respectively, the average value is 1.5, and the maximum value of the line loss ratio values when the user is identified as a potential abnormal line loss user is 2.0.
The line loss threshold value of the user is obtained based on the real-time power consumption data, the weather temperature and the resistivity of the power transmission line material of the user, so that the determination of the line loss threshold value is combined with the real-time power consumption data, the weather temperature and the resistivity of the power transmission line material of the user, the original technical problems of inaccuracy and poor flexibility of adopting the fixed line loss threshold value are avoided, and the reliability and the accuracy of judgment are further promoted.
By adopting a line loss prediction model based on the LA-GSA-GRU algorithm and automatically adjusting initial gravitation in the GSA based on a learning automaton, the GSA algorithm has better optimizing performance and faster convergence rate, and simultaneously, in order to avoid the problems that the GRU algorithm cannot automatically select in structure, random initial parameters directly influence the calculation process of the GRU algorithm, the convergence rate is slow and the like, the network layer number of an implicit layer of the GRU algorithm and the optimizing of node numbers of each layer are realized by adopting the LA-GSA algorithm, so that the convergence rate and the convergence precision are further improved.
Through the judgment of potential abnormal clients and the setting of the first threshold value, the judgment of the electricity stealing behavior of the user is not only dependent on single data or single potential abnormal conditions, but also the judgment of the line loss anomaly degree is realized by combining a prediction model adopting a machine learning algorithm, so that the accuracy and the reliability of the judgment are obviously improved, and the reliability of the line loss judgment is further ensured.
In another possible embodiment, the user's electricity consumption data anomaly threshold is determined from a maximum value of electricity consumption data of the user over a recent year.
In another possible embodiment, the specific steps of constructing the line loss threshold value are as follows:
s21, judging whether the real-time electricity consumption data of the user is larger than the maximum value of the historical electricity consumption data of the user at the same moment in the last week, if so, entering a step S22; if not, the user does not have the abnormal line loss condition, and the judgment of the line loss threshold value is not needed;
s22, obtaining a real-time electricity utilization ratio based on the ratio of the real-time electricity utilization data of the user to the average value of the historical electricity utilization data of the user at the same moment in the last week;
s23, acquiring a basic line loss threshold value of the user by adopting a line loss prediction model based on an LA-GSA-GRU algorithm based on the real-time power utilization ratio, the weather temperature and the resistivity of the power transmission line material;
and S24, correcting the basic line loss threshold value of the user based on the number of times that the user is identified as the potential line loss user in the last month to obtain the line loss threshold value of the user.
By judging the historical electricity consumption data, unnecessary calculation and establishment of a prediction model are avoided, the efficiency of the system is further improved, and the basic line loss threshold value of the user is further corrected by combining the number of times that the user is identified as a potential line loss user in the last month, so that the accuracy and reliability of the judgment of the final line loss threshold value are obviously improved.
Through the judgment of the real-time electricity utilization ratio, not only is the real-time electricity utilization data combined, but also the real-time electricity utilization data is combined with the electricity utilization data in the near week, so that the reliability and consistency of the finally judged data are further improved.
In another possible embodiment, the calculation formula of the line loss threshold value of the user is:
wherein T is limit For the threshold number of times, T is generally taken between 3 and 5 times 1 D, for the number of times the user is identified as potential line loss user in the last month 1 As the basic line loss threshold, K 1 Is constant and has a value ranging from 0 to 0.05.
In another possible embodiment, the first threshold is determined according to the historical electricity fee owed times and the historical electricity fee owed amount of the potential line loss user, wherein the more the historical electricity fee owed times and the more the historical electricity fee owed amount of the potential line loss user are, the smaller the first threshold is.
In another possible embodiment, when the number of times the user is identified as a potential line loss user in the last month is greater than a second threshold and the maximum value of the line loss ratio values when the user is identified as a potential abnormal line loss user in the last month is greater than a first threshold, the user is identified as having electricity theft behavior, wherein the second threshold is greater than the first threshold.
In another possible embodiment, the specific steps of line loss anomaly construction are as follows:
s31, judging whether the number of times that the user is identified as a potential line loss user in the last month is larger than a third threshold value, if so, identifying that the user has electricity stealing behavior, and if not, entering step S32;
s32, judging whether the average value of line loss ratios of all users identified as potential abnormal line loss users is larger than a first average value threshold value and the number of times of identifying the users as potential line loss users in the last month is larger than a second threshold value, if so, identifying that the users have electricity stealing behaviors, and if not, entering step S33;
s33, determining the line loss anomaly degree of the potential line loss user by adopting a prediction model based on a BP neural network algorithm based on the number of times the user is identified as the potential abnormal line loss user, the average value of the line loss ratio when the user is identified as the potential abnormal line loss user and the maximum value of the line loss ratio when the user is identified as the potential abnormal line loss user.
By further combining the third threshold value, the second threshold value and the first average threshold value, abnormal users can be accurately identified, excessive computing resources occupied by partial users with larger abnormal degrees are avoided, judging efficiency is improved, and judging accuracy is improved for users with smaller abnormal degrees.
In another possible embodiment, when the line loss anomaly degree of the potential line loss user is greater than a first anomaly degree threshold value, determining that the user has electricity stealing behavior; and when the line loss anomaly degree of the potential line loss user is larger than a second anomaly degree threshold value and the number of times that the user is identified as the potential line loss user is larger than a second threshold value, identifying that the user has electricity stealing behavior.
Example 2
The invention provides a terminal device, which comprises a memory, a processor and a program stored on the memory and capable of running on the processor, wherein the processor realizes the electricity larceny judging method based on real-time electricity information and big data analysis when executing the program.
Example 3
The invention provides a computer storage medium, on which a computer program is stored, which when executed in a computer, causes the computer to execute the above-mentioned electricity stealing judging method based on real-time electricity consumption and big data analysis.
In the several embodiments provided in this application, it should be understood that the disclosed systems and methods may be implemented in other ways as well. The system embodiments described above are merely illustrative, for example, of the flowcharts and block diagrams in the figures that illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present invention may be integrated together to form a single part, or each module may exist alone, or two or more modules may be integrated to form a single part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored on a computer readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method of the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
With the above-described preferred embodiments according to the present invention as an illustration, the above-described descriptions can be used by persons skilled in the relevant art to make various changes and modifications without departing from the scope of the technical idea of the present invention. The technical scope of the present invention is not limited to the description, but must be determined according to the scope of claims.
Claims (10)
1. A method for discriminating electricity larceny based on real-time electricity consumption and big data analysis is characterized by comprising the following steps:
s11, determining an abnormal threshold value of the power consumption data of the user based on the historical power consumption data of the user, judging whether the real-time power consumption data of the user is larger than the abnormal threshold value of the power consumption data or not based on the real-time power consumption data of the user, if so, entering a step S12, and if not, judging that the user does not have the power stealing behavior;
s12, acquiring a line loss threshold value of the user by adopting a line loss prediction model based on an LA-GSA-GRU algorithm based on real-time power consumption data, weather temperature and resistivity of a power transmission line material of the user;
s13, judging whether the line loss rate of the user is larger than the line loss threshold of the user, if so, identifying the user as a potential abnormal client, taking the ratio of the line loss rate of the user to the line loss threshold as a line loss ratio, and entering a step S14, if not, judging that the user does not have electricity stealing behavior;
and S14, when the number of times that the user is identified as the potential line loss user is larger than a first threshold value in the last month, determining the line loss anomaly degree of the potential line loss user by adopting a prediction model based on a machine learning algorithm based on the number of times that the user is identified as the potential abnormal line loss user, the average value of the line loss ratios when all the users are identified as the potential abnormal line loss users and the maximum value of the line loss ratios when the users are identified as the potential abnormal line loss users, and judging the electricity stealing behavior based on the line loss anomaly degree of the potential line loss user.
2. The electricity theft judging method according to claim 1, wherein the electricity consumption data abnormality threshold of the user is determined based on a maximum value of electricity consumption data of the user in the last year.
3. The method for distinguishing the electricity theft according to claim 1, wherein the specific steps of constructing the line loss threshold value are as follows:
s21, judging whether the real-time electricity consumption data of the user is larger than the maximum value of the historical electricity consumption data of the user at the same moment in the last week, if so, entering a step S22; if not, the user does not have the abnormal line loss condition, and the judgment of the line loss threshold value is not needed;
s22, obtaining a real-time electricity utilization ratio based on the ratio of the real-time electricity utilization data of the user to the average value of the historical electricity utilization data of the user at the same moment in the last week;
s23, acquiring a basic line loss threshold value of the user by adopting a line loss prediction model based on an LA-GSA-GRU algorithm based on the real-time power utilization ratio, the weather temperature and the resistivity of the power transmission line material;
and S24, correcting the basic line loss threshold value of the user based on the number of times that the user is identified as the potential line loss user in the last month to obtain the line loss threshold value of the user.
4. The electricity theft judging method according to claim 3, wherein the calculation formula of the line loss threshold value of the user is:
wherein T is limit For the threshold number of times, T is generally taken between 3 and 5 times 1 D, for the number of times the user is identified as potential line loss user in the last month 1 As the basic line loss threshold, K 1 Is constant and has a value ranging from 0 to 0.05.
5. The method for determining the electricity theft according to claim 1, wherein the first threshold is determined according to the number of times of arrearages of the historical electric charges and the amount of arrearages of the historical electric charges of the potential line loss user, and wherein the larger the number of times of arrearages of the historical electric charges and the larger the amount of arrearages of the historical electric charges of the potential line loss user, the smaller the first threshold.
6. The method of claim 1, wherein the user is deemed to have fraudulent activity when the number of times the user was identified as a potential line loss user in the last month is greater than a second threshold and the maximum value of the line loss ratio values when the user was identified as a potential abnormal line loss user in the last month is greater than a first threshold, wherein the second threshold is greater than the first threshold.
7. The method for distinguishing electricity theft according to claim 1, wherein the specific steps of constructing the line loss anomaly are:
s31, judging whether the number of times that the user is identified as a potential line loss user in the last month is larger than a third threshold value, if so, identifying that the user has electricity stealing behavior, and if not, entering step S32;
s32, judging whether the average value of line loss ratios of all users identified as potential abnormal line loss users is larger than a first average value threshold value and the number of times of identifying the users as potential line loss users in the last month is larger than a second threshold value, if so, identifying that the users have electricity stealing behaviors, and if not, entering step S33;
s33, determining the line loss anomaly degree of the potential line loss user by adopting a prediction model based on a BP neural network algorithm based on the number of times the user is identified as the potential abnormal line loss user, the average value of the line loss ratio when the user is identified as the potential abnormal line loss user and the maximum value of the line loss ratio when the user is identified as the potential abnormal line loss user.
8. The method of claim 7, wherein when the line loss anomaly of the potential line loss user is greater than a first anomaly threshold, then recognizing that the user has electricity theft behavior; and when the line loss anomaly degree of the potential line loss user is larger than a second anomaly degree threshold value and the number of times that the user is identified as the potential line loss user is larger than a second threshold value, identifying that the user has electricity stealing behavior.
9. A terminal device comprising a memory, a processor and a program stored on the memory and executable on the processor, wherein the processor implements a method for determining theft of electricity based on real-time electricity information and big data analysis as claimed in any one of claims 1 to 8 when executing the program.
10. A computer storage medium having stored thereon a computer program which, when executed in a computer, causes the computer to perform a method of determining theft of electricity based on real-time electricity usage information and big data analysis as claimed in any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211698772.8A CN116047223A (en) | 2022-12-28 | 2022-12-28 | Electricity larceny distinguishing method based on real-time electricity consumption and big data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211698772.8A CN116047223A (en) | 2022-12-28 | 2022-12-28 | Electricity larceny distinguishing method based on real-time electricity consumption and big data analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116047223A true CN116047223A (en) | 2023-05-02 |
Family
ID=86129071
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211698772.8A Pending CN116047223A (en) | 2022-12-28 | 2022-12-28 | Electricity larceny distinguishing method based on real-time electricity consumption and big data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116047223A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117147958A (en) * | 2023-08-23 | 2023-12-01 | 广东电网有限责任公司佛山供电局 | Method and device for discriminating electricity larceny based on real-time electricity utilization monitoring |
-
2022
- 2022-12-28 CN CN202211698772.8A patent/CN116047223A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117147958A (en) * | 2023-08-23 | 2023-12-01 | 广东电网有限责任公司佛山供电局 | Method and device for discriminating electricity larceny based on real-time electricity utilization monitoring |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111652496B (en) | Running risk assessment method and device based on network security situation awareness system | |
| CN106933650A (en) | load management method and system of cloud application system | |
| CN110166344B (en) | Identity identification method, device and related equipment | |
| CN109377218B (en) | Method, server and mobile terminal for suppressing false sensing attack | |
| CN113342474B (en) | Method, equipment and storage medium for predicting customer flow and training model | |
| CN110874381A (en) | User side load data abnormal value identification method based on space density clustering | |
| CN111181923A (en) | Flow detection method and device, electronic equipment and storage medium | |
| CN117078048A (en) | Digital twinning-based intelligent city resource management method and system | |
| CN116047223A (en) | Electricity larceny distinguishing method based on real-time electricity consumption and big data analysis | |
| CN111784173B (en) | AB experiment data processing method, device, server and medium | |
| CN112529432B (en) | Voltage sag severity assessment method and device and electronic equipment | |
| CN117150508B (en) | Cloud platform-based risk assessment method and system for terminal of Internet of things | |
| CN113487326A (en) | Transaction limiting parameter setting method and device based on intelligent contract | |
| CN109800085A (en) | Detection method, device, storage medium and the electronic equipment of resource distribution | |
| CN108197498A (en) | Obtain the method and device of data | |
| CN117010483A (en) | Federal learning security aggregation method and system for distributed load prediction | |
| CN116861312A (en) | Residual error network-based fault diagnosis method for electric power metering equipment | |
| CN111783487A (en) | Fault early warning method and device for card reader equipment | |
| CN109547236A (en) | Electronic data uploads storage method, readable storage medium storing program for executing and terminal | |
| CN115393100A (en) | Resource recommendation method and device | |
| CN113609990A (en) | Method and device for determining construction progress of target building and server | |
| Irissappane et al. | A case-based reasoning framework to choose trust models for different E-marketplace environments | |
| CN111598390A (en) | Server high availability evaluation method, device, equipment and readable storage medium | |
| CN114189381B (en) | Method for identifying malicious exit relay node of Tor anonymous communication network | |
| CN113934616B (en) | Method for judging abnormal user based on user operation time sequence |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |