CN112649641A - Electricity stealing user judgment method based on electricity stealing characteristics - Google Patents
Electricity stealing user judgment method based on electricity stealing characteristics Download PDFInfo
- Publication number
- CN112649641A CN112649641A CN202011464556.8A CN202011464556A CN112649641A CN 112649641 A CN112649641 A CN 112649641A CN 202011464556 A CN202011464556 A CN 202011464556A CN 112649641 A CN112649641 A CN 112649641A
- Authority
- CN
- China
- Prior art keywords
- user
- stealing
- electricity
- power
- time sequence
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R11/00—Electromechanical arrangements for measuring time integral of electric power or current, e.g. of consumption
- G01R11/02—Constructional details
- G01R11/24—Arrangements for avoiding or indicating fraudulent use
-
- 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
Abstract
The invention discloses an electricity stealing user judging method based on electricity stealing characteristics, which realizes electricity stealing judgment by using historical data by acquiring an electricity using time sequence of a user to be diagnosed and an electricity using time sequence of a typical electricity stealing user in historical data, performing similarity calculation according to electricity stealing indexes, primarily judging the user to be diagnosed, and performing similarity calculation of a latest electricity using time sequence and an initial electricity using time sequence on a suspected user which is primarily judged to be electricity stealing.
Description
Technical Field
The invention relates to a power stealing user judgment method based on power stealing characteristics, and belongs to the field of power industry power stealing user judgment.
Background
For a long time, phenomena such as electricity stealing and fraud are often prohibited in the society, and the behaviors bring serious threats to the development of national economy, enterprise operation management and standardization of power supply order, and even harm the life and property safety of other users.
With the rapid development of economy and the rapid increase of power consumption, a few power consumers are driven by economic benefits, and the power stealing is carried out by adopting illegal means and is forbidden frequently. Although the power supply enterprises increase the research input of the anti-electricity-stealing technology, the electricity-stealing technology is greatly improved at the same time, more and more high-tech electricity-stealing modes appear, and the characteristics of high concealment and high complexity are presented. In the actual work of anti-electricity-stealing of power company, because of the hysteresis quality of on-the-spot investigation, still have the difficult problem of collecting evidence, how can predetermine in advance which kind of mode electricity-stealing that the user adopts is the key that the accurate collection of evidence of on-the-spot ability was confirmed.
At present, an electric power company relies on an electricity utilization information acquisition system, so that 'full acquisition and full coverage' of electricity utilization of users is basically realized, electricity utilization data and information of a large number of electric power users can be mastered timely, completely and accurately, the electricity utilization information acquisition system is operated for many years, a large amount of historical data are acquired and deposited, and at present, no electricity stealing user judgment method utilizing the historical data exists.
Disclosure of Invention
The invention provides a method for judging a power stealing user based on a power stealing characteristic, which solves the problem.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows:
a method for judging a power stealing user based on a power stealing characteristic comprises the following steps,
acquiring a power utilization time sequence of a user to be diagnosed, and calculating a power stealing index of the user to be diagnosed;
acquiring a power utilization time sequence of a typical power stealing user in historical data, and calculating a power stealing index of the typical power stealing user;
calculating the similarity A of the power utilization time sequence of the user to be diagnosed and the power utilization time sequence of the typical power-stealing user according to the power-stealing index of the user to be diagnosed and the power-stealing index of the typical power-stealing user;
responding to the similarity A meeting the preset condition C, and calculating the similarity B of the latest power utilization time sequence and the initial power utilization time sequence of the user to be diagnosed;
and responding to the condition that the similarity B meets the preset condition D, and judging the user to be diagnosed as the electricity stealing suspected user.
The power utilization time sequence of the user to be diagnosed comprises an initial power utilization time sequence of a period of time and a latest power utilization time sequence of a period of time.
The user types comprise large-scale special transformer users, medium-small-scale special transformer users, three-phase general industrial and commercial users, single-phase general industrial and commercial users and residential users; the electricity stealing indexes of the large-scale special transformer users and the medium-scale and small-scale special transformer users are consistent, and comprise electric quantity, current unbalance rate, voltage unbalance rate and active power; the electricity stealing indexes of three-phase general industrial and commercial users, single-phase general industrial and commercial users and residential users are consistent and are electric quantity.
The typical electricity stealing users adopt a neighbor propagation clustering method for obtaining, and the specific process is,
analyzing electricity stealing characteristics of different electricity stealing modes of a user according to the electricity stealing indexes, and analyzing a relevant electricity stealing method from an electricity stealing work order text of the user;
and obtaining a typical electricity stealing user by utilizing a neighbor propagation clustering method according to the electricity stealing characteristic analysis result and a related electricity stealing method.
The electricity utilization time sequence of a typical electricity stealing user comprises an electricity utilization time sequence of a normal electricity utilization time and an electricity utilization time sequence of an electricity stealing time.
And according to the electricity stealing indexes of the user to be diagnosed and the electricity stealing indexes of the typical electricity stealing users, calculating the similarity A of the electricity utilization time sequence of the user to be diagnosed and the electricity utilization time sequence of the typical electricity stealing users by adopting a dynamic time warping method.
And responding to the similarity A meeting the preset condition C, and calculating the similarity B of the latest power utilization time sequence and the initial power utilization time sequence of the user to be diagnosed by using a cosine function.
A system for judging electricity stealing users based on electricity stealing characteristics comprises,
a to-be-diagnosed user calculation module: acquiring a power utilization time sequence of a user to be diagnosed, and calculating a power stealing index of the user to be diagnosed;
typical electricity stealing user calculation module: acquiring a power utilization time sequence of a typical power stealing user in historical data, and calculating a power stealing index of the typical power stealing user;
a first similarity module: calculating the similarity A of the power utilization time sequence of the user to be diagnosed and the power utilization time sequence of the typical power-stealing user according to the power-stealing index of the user to be diagnosed and the power-stealing index of the typical power-stealing user;
a second similarity module: responding to the similarity A meeting the preset condition C, and calculating the similarity B of the latest power utilization time sequence and the initial power utilization time sequence of the user to be diagnosed;
and a result judging module: and responding to the condition that the similarity B meets the preset condition D, and judging the user to be diagnosed as the electricity stealing suspected user.
A computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by a computing device, cause the computing device to perform a power stealing user determination method based on a power stealing characteristic.
A computing device comprising one or more processors, one or more memories, and one or more programs stored in the one or more memories and configured to be executed by the one or more processors, the one or more programs including instructions for performing a power stealing user determination method based on a power stealing characteristic.
The invention achieves the following beneficial effects: 1. according to the method, the power utilization time sequence of the user to be diagnosed and the power utilization time sequence of a typical power stealing user in historical data are obtained, similarity calculation is carried out according to the power stealing indexes, the user to be diagnosed is preliminarily judged, and the similarity calculation of the latest power utilization time sequence and the initial power utilization time sequence is carried out on the user which is preliminarily judged to be a suspected of power stealing, so that the power stealing judgment by utilizing the historical data is realized; 2. the invention utilizes the mode of combining the initial power utilization time sequence and the latest power utilization time sequence, can effectively eliminate normal power utilization fluctuation caused by production and life changes of users in the aspect of power stealing diagnosis, and more accurately positions the power stealing users; 3. according to the invention, the electricity stealing indexes of different types of users are constructed, and the original electricity utilization data is converted into the data reflecting the electricity stealing behavior of the users, so that the data quality is effectively improved, the data dimension is reduced, and a new direction and a solution are provided for identifying the electricity stealing users; 4. compared with the conventional electricity stealing user judging method, the method can determine whether the user steals electricity, and also can determine the electricity stealing means adopted by the user, so that the method has great significance for field electricity stealing investigation.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
As shown in fig. 1, a method for determining a power stealing user based on a power stealing characteristic includes the following steps:
step 1, acquiring a power utilization time sequence of a user to be diagnosed, and calculating a power stealing index of the user to be diagnosed; and acquiring the electricity utilization time sequence of the typical electricity stealing user in the historical data, and calculating the electricity stealing index of the typical electricity stealing user.
The user types comprise large-scale special transformer users, medium-small-scale special transformer users, three-phase general industrial and commercial users, single-phase general industrial and commercial users and residential users.
The large-scale special transformer users and the medium-small-scale special transformer users are high-voltage users, the large-scale special transformer users (A type) refer to users with the electricity consumption of 100kVA or above, and the medium-small-scale special transformer users (B type) refer to users with the electricity consumption of 100kVA or below; the special transformer of the special transformer user refers to a transformer special for a certain customer, the property right of the special transformer is owned by the customer, and the special transformer user refers to a power user equipped with the special transformer in comparison with a public transformer (a public transformer).
Three-phase general industrial and commercial users, single-phase general industrial and commercial users and residential users are low-voltage users, three-phase general industrial and commercial users (class C) refer to non-residential three-phase electricity users with electricity consumption properties of business, small power, office and the like, and single-phase general industrial and commercial users (class D) refer to non-residential single-phase electricity users with electricity consumption properties of low-voltage 220V business, small power, office and the like.
The power utilization time sequence of the user to be diagnosed comprises an initial power utilization time sequence of a period of time and a latest power utilization time sequence of a period of time; typically, the customer metering point is started with an initial 6 month continuous power time series (daily) and a last 3 month continuous power time series (daily).
Suppose the user U installs the meter and connects with electricity date D0The month is M0(ii) a Current statistical analysis date is DcThe month is McThen, as shown in table 1, the user U power consumption time sequence is constructed in 4 ways:
when D is present0Before month 20 (inclusive), value M is taken0～(M0+5) 6 consecutive natural months, extending over the years;
when D is present0After month number 21 (inclusive), the value (M) is taken0+1)～(M0+6) 6 consecutive natural months, extending across years.
When D is presentcBefore month 10 (inclusive), the value (M) is takenc-3)～(Mc-1) 3 consecutive natural months;
when D is presentcAfter month No. 11 (inclusive), the value (M) is takenc-2)～(Mc) 3 continuous natural months;
TABLE 1 user U Power consumption time series construction
The electricity stealing indexes of different user categories are different, wherein the electricity stealing indexes of the large-scale special transformer users and the medium-sized and small-scale special transformer users are consistent, and comprise electric quantity, current unbalance rate, voltage unbalance rate and active power; the electricity stealing indexes of three-phase general industrial and commercial users, single-phase general industrial and commercial users and residential users are consistent and are electric quantity.
The current unbalance rate is (maximum phase current-minimum phase current)/maximum phase current, and reflects the phenomenon of current undercurrent, namely the difference between three-phase currents, the three-phase currents are kept stable during normal power utilization, and the higher the current unbalance rate is, the higher the represented current abnormal probability is; the voltage unbalance rate (maximum phase voltage-minimum phase voltage)/maximum phase voltage reflects a voltage undervoltage phenomenon, that is, a difference between three-phase voltages, the three-phase voltages are kept stable during normal power consumption, and the higher the voltage unbalance rate, the higher the representative voltage abnormality probability, which is specifically shown in table 2.
TABLE 2 indicator of electricity stealing
The typical electricity stealing user obtains from historical data, specifically obtains from an electricity stealing survey work order by adopting a neighbor propagation clustering method, and specifically comprises the following steps:
1) analyzing electricity stealing characteristics of different electricity stealing modes of a user according to the electricity stealing indexes, and analyzing a relevant electricity stealing method from an electricity stealing work order text of the user;
2) and obtaining a typical electricity stealing user by utilizing a neighbor propagation clustering method according to the electricity stealing characteristic analysis result and a related electricity stealing method.
Meanwhile, the typical electricity stealing user selection also needs to meet the following requirements: 1) the user electricity utilization time sequence data are complete; 2) the electricity stealing check time of the user is definite; 3) the time period of electricity stealing of the user is clear, and the data characteristics are matched; 4) the electricity stealing investigation time is within 5 years, and the electricity stealing state is currently in an electricity utilization state; 5) the electricity stealing means adopted by the user when stealing electricity is definite.
The electricity utilization time sequence of the typical electricity stealing user comprises an electricity utilization time sequence of a normal electricity utilization time and an electricity utilization time sequence of an electricity stealing time; generally, electricity data of 3 months of continuous electricity stealing period are selected before on the basis of electricity stealing finding and location finding time, and then 3 months of continuous normal electricity data after electricity stealing location finding or 3 months of continuous normal electricity data before electricity stealing begins are selected.
The electricity-stealing date of the user is set as D0The month is M0The date of examination and treatment is DEThe month is METhe starting time of electricity stealing is DBThe month is MBThen, the time series data of the user U is constructed in 4 ways:
the first method is as follows: when M isB-M0>3 and DE-DB>When the month is 3, taking MB-3～MB+2 continuous 6 natural month data, cross-year sequential;
the second method comprises the following steps: when M isB-M0>3 and DE-DB<Taking M at 3 monthsB-3～DEData of a plurality of continuous natural months, and the data are spread across years;
the third method comprises the following steps: when M isB-M0<3 and DE-DB>When the month is 3, taking ME-3～ME+2 continuous 6 natural month data, cross-year sequential;
the method is as follows: when M isB-M0<3 and DE-DB<At 3 months, get DB～ME+2 consecutive months of data, extending across years.
The calculation of the electricity stealing index is similar to the calculation of the electricity stealing index of the user to be diagnosed.
And 2, calculating the similarity A of the power utilization Time sequence of the user to be diagnosed and the power utilization Time sequence of the typical power-stealing user by adopting a Dynamic Time Warping (DTW) method according to the power-stealing index of the user to be diagnosed and the power-stealing index of the typical power-stealing user.
Firstly, calculating the daily electric quantity time sequence DTW distance between a typical electricity stealing user and a user to be diagnosed, and if the daily electric quantity time sequence DTW distance is a special transformer user, calculating the total active power DTW distance between the typical electricity stealing user and the user to be diagnosed, the three-phase voltage unbalance time sequence DTW distance between the typical electricity stealing user and the user to be diagnosed, and the three-phase current unbalance time sequence DTW distance between the typical electricity stealing user and the user to be diagnosed; and then calculating the total distance of the users to be diagnosed, namely the similarity A.
For the specific transformer user, the total distance S is calculated as:
Sspecial transformerThe total distance is 0.5 × a daily electric quantity time series DTW distance +0.3 × an active power time series DTW distance +0.1 × a three-phase voltage unbalance time series DTW distance +0.1 × a three-phase current unbalance time series DTW distance.
For the non-specific variation users, the total distance S is calculated as:
Snon-specific transformerThe distance is the daily electricity time series DTW.
When the same user has a plurality of typical electricity stealing users, the total distance S between the user to be diagnosed and each typical electricity stealing user i is calculated one by oneiSelecting S with the smallest distancei *As the user distance value to be diagnosed.
Step 3, if the similarity A is less than or equal to a threshold value K, preliminarily judging that the user to be diagnosed is a suspected electricity stealing user; otherwise, ending.
After all the checked electricity stealing users are grouped according to the user categories, an ith group G is setiThe number of electricity stealing users is Ci. If Ci>1000, then Gi0From GiSelecting 1/10 proportion electricity stealing users randomly; if 500<Ci<1000, then Gi0From GiSelecting 1/5 proportion electricity stealing users randomly; if 100<Ci<500, then Gi0From GiSelecting 1/2 proportion electricity stealing users randomly; if Ci<When the value is 100, Gi0＝Gi. For Gi0The distance S between every two users (k, j) is calculated by all the electricity stealing users according to the DTW methodkj，K＝∑Skj/Ci1，k、j∈Gi0，Ci1Is Gi0The number of users.
Large-scale special transformer users and medium-small-scale special transformer users: and when the similarity between the daily electric quantity time sequence of the user to be diagnosed and the daily electric quantity time sequence of the typical electricity stealing user is smaller than or equal to a threshold value, and the similarity between the power curve time sequence of the user to be diagnosed and the power curve time sequence of the typical electricity stealing user is smaller than or equal to the threshold value, preliminarily judging that the user to be diagnosed is a suspected electricity stealing user.
Three-phase general industrial and commercial users, single-phase general industrial and commercial users and residential users: and when the similarity between the daily electric quantity time sequence of the user to be diagnosed and the daily electric quantity time sequence of the typical electricity stealing user is less than or equal to a threshold value, preliminarily judging that the user to be diagnosed is a suspected electricity stealing user.
Step 4, calculating the similarity B of the latest power utilization time sequence and the initial power utilization time sequence of the user to be diagnosed by using a cosine function, and if the similarity B is less than or equal to a threshold k, judging the user to be diagnosed as a suspected electricity stealing user; wherein k takes a value of 80% according to the correlation empirical value.
And calculating the similarity B of the electricity utilization time sequence of the latest 1 month of the user to be diagnosed (judged according to the current statistical date) and the electricity utilization time sequence of the initial 6 months (consistent with the step 1) (daily electricity utilization time sequence) by using a cosine function.
Last 1 month record PcCurrent statistical diary DcThe month is McRecord PcLast day 1 is DEDay, Pc＝[1,DE]。
PcThe value taking mode is as follows:
when D is presentc<When No. 10, Pc＝Mc-1, i.e. the month preceding the month of the statistical day, DE＝(Mc-1) the last 1 day of the month;
when D is presentc>When number 10, Pc＝McNamely, statistics of the month D of the dayE＝Dc-1。
Calculating the initial electricity consumption of the user for 6 months and the latest 1 month PcThe similarity of the daily electric quantity time series; suppose MkE { initial 6 months } for a month, EDay (M)k) Represents MkLast 1 day of the month.
Firstly, the similarity is calculated as: mkMonth [1, min (D)E,EDay(Mk))]Vector a, and P formed by daily electric quantitycIs [1, min (D)E,EDay(Mk))]Calculating cosine included angle values of the vector a and the vector b formed by daily electric quantity;
if the user is a special change user, the following distances are calculated continuously:
calculate the initial 6 months and the last 1 month P of the usercTotal active power time series similarity;
calculating the three-phase voltage unbalance time sequence similarity of the initial 6 months and the latest 45 days of the user;
and calculating the similarity of the three-phase current unbalanced time sequence of the initial 6 months and the latest 45 days of the user.
And calculating the total time series similarity of the users.
For the special transformer user, calculating the total similarity S as:
Sspecial transformerThe total number of the three-phase current unbalance time series is 0.5 (sigma time series similarity of three-phase current unbalance time series per month/total number of months) +0.3 (sigma time series similarity of active power per month/total number of months) +0.1 (sigma time series similarity of three-phase voltage per month/total number of months) +0.1 (sigma time series similarity of three-phase current unbalance per month/total number of months).
For the non-specific variation users, calculating the total similarity S as follows:
Snon-specific transformerThe similarity of the electric quantity time series every month/total month number is sigma.
According to the method, the electricity stealing judgment by using the historical data is realized by acquiring the electricity utilization time sequence of the user to be diagnosed and the electricity utilization time sequence of a typical electricity stealing user in the historical data, performing similarity calculation according to the electricity stealing indexes, primarily judging the user to be diagnosed, and performing similarity calculation of the latest electricity utilization time sequence and the initial electricity utilization time sequence on the user which is primarily judged to be suspected of electricity stealing.
The method utilizes the mode of combining the initial power utilization time sequence with the latest power utilization time sequence, can effectively eliminate normal power utilization fluctuation caused by production and life changes of users in the aspect of power stealing diagnosis, and can more accurately position power stealing users.
The method constructs electricity stealing indexes of different types of users, converts original electricity utilization data into data reflecting electricity stealing behaviors of the users, effectively improves the quality of the data, reduces data dimensionality, and provides a new direction and solution for identifying the electricity stealing users.
Compared with the conventional electricity stealing user judging method, the method can determine whether the user steals electricity and simultaneously determine the electricity stealing means adopted by the user, and has great significance for on-site electricity stealing investigation and treatment.
A system for judging electricity stealing users based on electricity stealing characteristics comprises,
a to-be-diagnosed user calculation module: acquiring a power utilization time sequence of a user to be diagnosed, and calculating a power stealing index of the user to be diagnosed;
typical electricity stealing user calculation module: acquiring a power utilization time sequence of a typical power stealing user in historical data, and calculating a power stealing index of the typical power stealing user;
a first similarity module: calculating the similarity A of the power utilization time sequence of the user to be diagnosed and the power utilization time sequence of the typical power-stealing user according to the power-stealing index of the user to be diagnosed and the power-stealing index of the typical power-stealing user;
a second similarity module: responding to the similarity A meeting the preset condition C, and calculating the similarity B of the latest power utilization time sequence and the initial power utilization time sequence of the user to be diagnosed;
and a result judging module: and responding to the condition that the similarity B meets the preset condition D, and judging the user to be diagnosed as the electricity stealing suspected user.
A computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by a computing device, cause the computing device to perform a power stealing user determination method based on a power stealing characteristic.
A computing device comprising one or more processors, one or more memories, and one or more programs stored in the one or more memories and configured to be executed by the one or more processors, the one or more programs including instructions for performing a power stealing user determination method based on a power stealing characteristic.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The present invention is not limited to the above embodiments, and any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention are included in the scope of the claims of the present invention which are filed as the application.
Claims (10)
1. A power stealing user judgment method based on power stealing characteristics is characterized in that: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
acquiring a power utilization time sequence of a user to be diagnosed, and calculating a power stealing index of the user to be diagnosed;
acquiring a power utilization time sequence of a typical power stealing user in historical data, and calculating a power stealing index of the typical power stealing user;
calculating the similarity A of the power utilization time sequence of the user to be diagnosed and the power utilization time sequence of the typical power-stealing user according to the power-stealing index of the user to be diagnosed and the power-stealing index of the typical power-stealing user;
responding to the similarity A meeting the preset condition C, and calculating the similarity B of the latest power utilization time sequence and the initial power utilization time sequence of the user to be diagnosed;
and responding to the condition that the similarity B meets the preset condition D, and judging the user to be diagnosed as the electricity stealing suspected user.
2. The electricity stealing user judgment method based on the electricity stealing characteristic as claimed in claim 1, wherein: the power utilization time sequence of the user to be diagnosed comprises an initial power utilization time sequence of a period of time and a latest power utilization time sequence of a period of time.
3. The electricity stealing user judgment method based on the electricity stealing characteristic as claimed in claim 1, wherein: the user types comprise large-scale special transformer users, medium-small-scale special transformer users, three-phase general industrial and commercial users, single-phase general industrial and commercial users and residential users; the electricity stealing indexes of the large-scale special transformer users and the medium-scale and small-scale special transformer users are consistent, and comprise electric quantity, current unbalance rate, voltage unbalance rate and active power; the electricity stealing indexes of three-phase general industrial and commercial users, single-phase general industrial and commercial users and residential users are consistent and are electric quantity.
4. The electricity stealing user judgment method based on the electricity stealing characteristic as claimed in claim 1, wherein: the typical electricity stealing users adopt a neighbor propagation clustering method for obtaining, and the specific process is,
analyzing electricity stealing characteristics of different electricity stealing modes of a user according to the electricity stealing indexes, and analyzing a relevant electricity stealing method from an electricity stealing work order text of the user;
and obtaining a typical electricity stealing user by utilizing a neighbor propagation clustering method according to the electricity stealing characteristic analysis result and a related electricity stealing method.
5. The electricity stealing user judgment method based on the electricity stealing characteristic as claimed in claim 1, wherein: the electricity utilization time sequence of a typical electricity stealing user comprises an electricity utilization time sequence of a normal electricity utilization time and an electricity utilization time sequence of an electricity stealing time.
6. The electricity stealing user judgment method based on the electricity stealing characteristic as claimed in claim 1, wherein: and according to the electricity stealing indexes of the user to be diagnosed and the electricity stealing indexes of the typical electricity stealing users, calculating the similarity A of the electricity utilization time sequence of the user to be diagnosed and the electricity utilization time sequence of the typical electricity stealing users by adopting a dynamic time warping method.
7. The electricity stealing user judgment method based on the electricity stealing characteristic as claimed in claim 1, wherein: and responding to the similarity A meeting the preset condition C, and calculating the similarity B of the latest power utilization time sequence and the initial power utilization time sequence of the user to be diagnosed by using a cosine function.
8. The utility model provides a steal electric user judgement system based on steal electric characteristic which characterized in that: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
a to-be-diagnosed user calculation module: acquiring a power utilization time sequence of a user to be diagnosed, and calculating a power stealing index of the user to be diagnosed;
typical electricity stealing user calculation module: acquiring a power utilization time sequence of a typical power stealing user in historical data, and calculating a power stealing index of the typical power stealing user;
a first similarity module: calculating the similarity A of the power utilization time sequence of the user to be diagnosed and the power utilization time sequence of the typical power-stealing user according to the power-stealing index of the user to be diagnosed and the power-stealing index of the typical power-stealing user;
a second similarity module: responding to the similarity A meeting the preset condition C, and calculating the similarity B of the latest power utilization time sequence and the initial power utilization time sequence of the user to be diagnosed;
and a result judging module: and responding to the condition that the similarity B meets the preset condition D, and judging the user to be diagnosed as the electricity stealing suspected user.
9. A computer readable storage medium storing one or more programs, characterized in that: the one or more programs include instructions that, when executed by a computing device, cause the computing device to perform any of the methods of claims 1-7.
10. A computing device, characterized by: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
one or more processors, one or more memories, and one or more programs stored in the one or more memories and configured to be executed by the one or more processors, the one or more programs including instructions for performing any of the methods of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011464556.8A CN112649641B (en) | 2020-12-14 | 2020-12-14 | Electricity stealing user judging method based on electricity stealing characteristics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011464556.8A CN112649641B (en) | 2020-12-14 | 2020-12-14 | Electricity stealing user judging method based on electricity stealing characteristics |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112649641A true CN112649641A (en) | 2021-04-13 |
| CN112649641B CN112649641B (en) | 2023-05-02 |
Family
ID=75353874
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011464556.8A Active CN112649641B (en) | 2020-12-14 | 2020-12-14 | Electricity stealing user judging method based on electricity stealing characteristics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112649641B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116862116A (en) * | 2023-09-05 | 2023-10-10 | 国网天津市电力公司营销服务中心 | Intelligent early warning method and system for preventing electricity larceny, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105203924A (en) * | 2015-10-10 | 2015-12-30 | 上海博英信息科技有限公司 | Electricity usage trend abnormity suspicion analysis method and anti-electric-larceny monitoring system |
| CN107328974A (en) * | 2017-08-03 | 2017-11-07 | 北京中电普华信息技术有限公司 | A kind of stealing recognition methods and device |
| CN109146705A (en) * | 2018-07-02 | 2019-01-04 | 昆明理工大学 | A kind of method of electricity consumption characteristic index dimensionality reduction and the progress stealing detection of extreme learning machine algorithm |
| CN109583679A (en) * | 2018-09-30 | 2019-04-05 | 国网浙江长兴县供电有限公司 | A kind of stealing Suspected Degree analysis method of more algorithm fusions |
| CN109784388A (en) * | 2018-12-29 | 2019-05-21 | 北京中电普华信息技术有限公司 | Stealing user identification method and device |
| AU2019101183A4 (en) * | 2019-10-02 | 2020-01-16 | Han, Yining MISS | Feature Extraction and Fusion for Industrial Data |
-
2020
- 2020-12-14 CN CN202011464556.8A patent/CN112649641B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105203924A (en) * | 2015-10-10 | 2015-12-30 | 上海博英信息科技有限公司 | Electricity usage trend abnormity suspicion analysis method and anti-electric-larceny monitoring system |
| CN107328974A (en) * | 2017-08-03 | 2017-11-07 | 北京中电普华信息技术有限公司 | A kind of stealing recognition methods and device |
| CN109146705A (en) * | 2018-07-02 | 2019-01-04 | 昆明理工大学 | A kind of method of electricity consumption characteristic index dimensionality reduction and the progress stealing detection of extreme learning machine algorithm |
| CN109583679A (en) * | 2018-09-30 | 2019-04-05 | 国网浙江长兴县供电有限公司 | A kind of stealing Suspected Degree analysis method of more algorithm fusions |
| CN109784388A (en) * | 2018-12-29 | 2019-05-21 | 北京中电普华信息技术有限公司 | Stealing user identification method and device |
| AU2019101183A4 (en) * | 2019-10-02 | 2020-01-16 | Han, Yining MISS | Feature Extraction and Fusion for Industrial Data |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116862116A (en) * | 2023-09-05 | 2023-10-10 | 国网天津市电力公司营销服务中心 | Intelligent early warning method and system for preventing electricity larceny, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112649641B (en) | 2023-05-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110231528B (en) | Transformer household variation common knowledge identification method and device based on load characteristic model library | |
| Calikus et al. | A data-driven approach for discovering heat load patterns in district heating | |
| WO2020252785A1 (en) | Abnormal electricity use recognition method and device, and computer readable storage medium | |
| CN106909676A (en) | The analysis method and device of user power utilization behavior | |
| CN112730938B (en) | Electricity larceny user judging method based on electricity utilization acquisition big data | |
| CN108198408B (en) | Self-adaptive anti-electricity-stealing monitoring method and system based on electricity information acquisition system | |
| CN111008193B (en) | Data cleaning and quality evaluation method and system | |
| CN111291076A (en) | Abnormal water use monitoring and alarming system based on big data and construction method thereof | |
| CN110244099A (en) | Stealing detection method based on user's voltage | |
| CN111310854A (en) | Low false alarm rate electricity stealing detection secondary screening method based on electricity load fingerprint | |
| CN114511181A (en) | Water pollution environment-friendly calibration method and device based on power grid and tax data fusion | |
| CN113516336A (en) | Method and system for determining electricity stealing suspected user | |
| CN106685086B (en) | Remote power utilization management system | |
| CN112649641A (en) | Electricity stealing user judgment method based on electricity stealing characteristics | |
| CN106022640B (en) | Electric quantity index checking system and method | |
| CN106651093A (en) | Smart re-check management and control method used for low voltage set copy system | |
| CN111650432A (en) | Line loss-based electricity stealing determination method and device | |
| CN115166625A (en) | Intelligent ammeter error estimation method and device | |
| CN110717244B (en) | Data trust analysis computer simulation method based on average deviation algorithm | |
| CN112511503A (en) | Method, system, equipment and storage medium for improving safety of intelligent electric meter | |
| CN112685461A (en) | Electricity stealing user judgment method based on pre-judgment model | |
| CN112116216A (en) | New energy consumption evaluation method and system based on multiple objects and multiple dimensions | |
| CN115859331B (en) | Smart city information security guarantee system | |
| Peiyi et al. | Analysis and research on enterprise resumption of work and production based on K-means clustering | |
| Yu et al. | Research on risk identification of power theft in low-voltage distribution network based on machine learning hybrid algorithm |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |