CN104951989A - Electricity theft analyzing method and system - Google Patents

Abstract

The invention discloses an electricity theft analyzing method and system. The method includes calculating industry power consumption amount trend coefficient and judging whether the industry power consumption amount trend is greater than a first statistical threshold value or not; if the industry power consumption amount trend is greater than the first statistical threshold value, calculating the matching coefficient of a single user and the industry characteristic trend and judging whether the matching coefficient of the single user and the industry characteristic trend is greater than a second statistic threshold value or not. If the matching coefficient of the single user and the industry characteristic trend is greater than the second statistic threshold value, no electricity theft occurs; if the matching coefficient of the single user and the industry characteristic trend is not greater than a second statistic threshold value, electricity theft may occur. According to the invention, through studying current information of a power consumption information collecting system and through deep digging and effective use of mass data, industry power consumption trend and power consumption trend of users in the industry can be analyzed and the matching degree can be judged, so that whether electricity theft occurs or not can be judged. Therefore, effectiveness and pointedness of the collection system in aspects of electricity theft prevention and investigation are improved.

Description

A kind of stealing analytical approach and system

Technical field

The present invention relates to multiplexe electric technology field, particularly, relate to a kind of stealing analytical approach and system.

Background technology

Power user power consumption information acquisition system is the system gathering the power information of power consumer, process and monitor in real time, system gathers automatically according to power information, measure exception monitoring, electric energy quality monitoring, electrical energy consumption analysis and management, relevant information are issued, distributed energy monitoring, intelligent power equipment the functional simulation design such as information interaction.

At present, power information acquisition system has been installed by company of great majority net province, in intelligent electric energy meter and electricity management terminal, be integrated with module for anti-fraudulent.Such as, warning to some multiplexing electric abnormalities and record can be realized by intelligent electric energy meter and electricity management terminal, as decompression, disconnected phase, table cover are opened and show meter programmed events etc.But the effect of the anti-stealing electricity function embedded in intelligent electric energy meter and electricity management terminal is limited, although existing power information acquisition system acquires a large amount of electricity consumption related datas, but lack the analyzing and processing function of special effective anti-electricity-theft relevant information, cause important stealing relevant abnormalities information to be submerged in the pending data of magnanimity.

Summary of the invention

The special problem effectively analyzed cannot be carried out to anti-electricity-theft relevant information to solve in prior art, the present invention proposes a kind of stealing analytical approach.

According to stealing analytical approach of the present invention, comprising:

Calculate trade power consumption amount trend coefficient, judge whether trade power consumption amount trend coefficient is greater than the first statistics threshold values;

If trade power consumption amount trend coefficient is greater than the first statistics threshold values, then calculates single household and industrial characteristic trend matching coefficient, judge whether single household and industrial characteristic trend matching coefficient are greater than the second statistics threshold values;

If single household and industrial characteristic trend matching coefficient are greater than the second statistics threshold values, then do not there is stealing, otherwise stealing may occur.

The special problem effectively analyzed cannot be carried out to anti-electricity-theft relevant information to solve in prior art, the present invention proposes a kind of stealing analytic system.

According to stealing analytic system of the present invention, comprising:

First computing module, for calculating trade power consumption amount trend coefficient, judges whether trade power consumption amount trend coefficient is greater than the first statistics threshold values;

Second computing module, if be greater than described first statistics threshold values for trade power consumption amount trend coefficient, then calculate single household and industrial characteristic trend matching coefficient, judges whether single household and industrial characteristic trend matching coefficient are greater than the second statistics threshold values;

, if be greater than the second statistics threshold values for single household and industrial characteristic trend matching coefficient, then do not there is stealing, otherwise stealing may occur in stealing analysis module.

Stealing analytical approach of the present invention and system, excavate and effectively utilization by research power information acquisition system existing information and to the degree of depth of mass data, analyze the electricity consumption trend of user in trade power consumption trend and industry, judge its goodness of fit, thus judge whether to there is stealing.Stealing analytical approach of the present invention and system take full advantage of the information of power information acquisition system, improve acquisition system taking precautions against, investigate and prosecute validity in stealing and specific aim.

Other features and advantages of the present invention will be set forth in the following description, and, partly become apparent from instructions, or understand by implementing the present invention.Object of the present invention and other advantages realize by structure specifically noted in write instructions, claims and accompanying drawing and obtain.

Below by drawings and Examples, technical scheme of the present invention is described in further detail.

Accompanying drawing explanation

Accompanying drawing is used to provide a further understanding of the present invention, and forms a part for instructions, together with embodiments of the present invention for explaining the present invention, is not construed as limiting the invention.In the accompanying drawings:

Fig. 1 is the process flow diagram of the embodiment of the present invention one;

Fig. 2 is the process flow diagram of the embodiment of the present invention two;

Fig. 3 is the process flow diagram of the embodiment of the present invention three;

Fig. 4 is the structural drawing of stealing analytic system of the present invention.

Embodiment

Below in conjunction with accompanying drawing, the specific embodiment of the present invention is described in detail, but is to be understood that protection scope of the present invention not by the restriction of embodiment.

The special problem effectively analyzed cannot be carried out to anti-electricity-theft relevant information to solve in prior art, the present invention proposes a kind of stealing analytical approach.

The present invention passes through k-means cluster algorithm by user of the same trade according to power load feature automatic cluster cluster, with the user in cluster the highest by the similarity in power mode, capacity etc.By respectively to history electricity consumption data and the recent electricity consumption data clusters of user, and feature extraction is carried out to different class bunch, then by the comparison of user's recent electricity consumption characteristic sum same industry electrical feature; Self the history feature comparison of the recent electricity consumption characteristic sum of user, detects the exception of user power utilization behavior, finds the user with stealing possibility.

Embodiment of the method one

According to the embodiment of the present invention, provide a kind of stealing analytical approach, as shown in Figure 1, comprising:

Step 10: the industrial trend coefficient W calculating certain trade power consumption amount, judges whether the sector power consumption has characteristic trend: when W is greater than the first statistics threshold values time, then think that the sector power consumption has characteristic trend, proceed to step 20;

Otherwise the sector is without characteristic trend, process ends;

Step 20: when the power consumption of certain industry in step 10 has characteristic trend, calculates unique user and industrial characteristic trend matching coefficient S in the sector, judges whether this user power utilization amount and industrial characteristic trend have consistance: when S is greater than the second statistics threshold values time, then think that the power consumption of this unique user and trade power consumption measure feature trend have consistance, electricity filching behavior does not occur;

Otherwise, then think that the power consumption of this unique user and trade power consumption measure feature trend do not have consistance, may have occurred electricity filching behavior.

Embodiment of the method two

According to the embodiment of the present invention, provide a kind of stealing analytical approach, as shown in Figure 2, be the idiographic flow of step 10 in embodiment of the method one, comprise:

Step 101: obtain the some electricity consumption data of a large number of users in a measurement period from power information acquisition system, and classify according to the different electricity consumption data to obtaining of industry;

Step 102: the some industries obtained according to step 101, as the electricity consumption data of the user of catering trade, draws the rank of catering trade power consumption of different observation station in certain measurement period, thus obtains the electricity consumption trend of catering trade;

Wherein, user specially becomes user, industry and commerce user, resident etc.Measurement period can choose one longer period, can reflect electricity consumption trend.Such as, measurement period can be year, and now the points of measurement is 12 (in units of the moons); Measurement period also can be the moon, and now the points of measurement is 30 (in units of skies); Measurement period can also be week, and now the points of measurement is 7 (in units of skies), measurement period can also for day, now the points of measurement be 24 (by hour in units of).

Step 103: according to following formulae discovery trade power consumption amount trend coefficient W

$W=\frac{\mathrm{\Σ}{R}_i^2-\frac{{\left(\mathrm{\Σ}{R}_i\right)}^2}{N}}{\frac{1}{12}{K}^2(N^3-N)},$

Wherein, N is the points of measurement, and K is industry sampling amount, R _ifor the ascending order value sum (namely carry out ascending order calculating to each user power consumption rank of each observation station in measurement period, then sue for peace to the value that K family calculates in each observation station ascending order) of each observation station K family power consumption rank;

Step 104: the value and the first statistics threshold values that compare W , when W is greater than the first statistics threshold values time, the sector has characteristic trend, otherwise without characteristic trend;

Wherein the first statistics threshold values size draw based on a large amount of statistics, during as got N=30, first statistics threshold values value be 0.306;

If the sector power consumption has characteristic trend, the mode then getting each observation station rank is the rank of industrial characteristic trend, as when N=30, the K(of the first observation station is assumed to be 4) the power consumption rank of individual user is respectively 2,4,3,2, be then 2 at the industrial trend rank of this observation station.

Embodiment of the method three

According to the embodiment of the present invention, provide a kind of stealing analytical approach, as shown in Figure 3, be the idiographic flow of step 20 in embodiment of the method one, comprise:

Step 201: according to following formulae discovery unique user and industrial characteristic trend matching coefficient S,

$S=1-\frac{6\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{d}_i^2}{N(N^2-1)},$

Wherein, d _ifor the rank of industrial characteristic trend and the difference of single household trend rank, N is the points of measurement;

Step 202: compare S and second statistics threshold values , when S is greater than the second statistics threshold values time, then think that unique user electricity consumption and industrial characteristic trend have consistance, electricity filching behavior does not occur;

Otherwise, think that unique user electricity consumption and industrial characteristic trend do not have consistance, may have occurred electricity filching behavior;

Second statistics threshold values size draw based on a large amount of statistics, when N gets different numerical value, second statistics threshold values value different, as follows,

N=7， =0.893；

N=12， =0.712；

N=23， =0.485;

N=24, =0.465;

N=30, =0.432。

System embodiment

The special problem effectively analyzed cannot be carried out to anti-electricity-theft relevant information to solve in prior art, the present invention proposes a kind of stealing analytic system, as shown in Figure 4, comprising:

First computing module 301, for calculating trade power consumption amount trend coefficient, judges whether trade power consumption amount trend coefficient is greater than the first statistics threshold values;

Second computing module 302, if be greater than the first statistics threshold values for trade power consumption amount trend coefficient, then calculate single household and industrial characteristic trend matching coefficient, judges whether single household and industrial characteristic trend matching coefficient are greater than the second statistics threshold values;

, if be greater than the second statistics threshold values for single household and industrial characteristic trend matching coefficient, then do not there is stealing, otherwise stealing may occur in stealing analysis module 303;

Statistical analysis module 304, for the power consumption of Statistics each observation station in measurement period, and carries out power consumption rank.

Wherein the first computing module 301 is specifically for according to following formulae discovery trade power consumption amount trend coefficient

$W=\frac{\mathrm{\Σ}{R}_i^2-\frac{{\left(\mathrm{\Σ}{R}_i\right)}^2}{N}}{\frac{1}{12}{K}^2(N^3-N)},$

Wherein, N is the points of measurement, and K is industry sampling amount, R _ifor the ascending order value sum of each observation station K family power consumption rank;

Second computing module 302 is specifically for according to following formulae discovery single household and industrial characteristic trend matching coefficient

$S=1-\frac{6\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{d}_i^2}{N(N^2-1)},$

Wherein, d _ifor the rank of industrial characteristic trend and the difference of single household trend rank, N is the points of measurement;

In technique scheme, the rank of industrial characteristic trend is the mode of the sector K family in each observation station power consumption rank.

Stealing analytical approach of the present invention and system, excavate and effectively utilization by research power information acquisition system existing information and to the degree of depth of mass data, analyze the electricity consumption trend of user in trade power consumption trend and industry, judge its goodness of fit, thus judge whether to there is stealing.Stealing analytical approach of the present invention and system take full advantage of the information of power information acquisition system, improve acquisition system taking precautions against, investigate and prosecute validity in stealing and specific aim.

The present invention can have multiple multi-form embodiment; above for Fig. 1-Fig. 4 by reference to the accompanying drawings to technical scheme of the present invention explanation for example; this does not also mean that the instantiation that the present invention applies can only be confined in specific flow process or example structure; those of ordinary skill in the art should understand; specific embodiments provided above is some examples in multiple its preferred usage, and the embodiment of any embodiment the claims in the present invention all should within technical solution of the present invention scope required for protection.

Last it is noted that the foregoing is only the preferred embodiments of the present invention, be not limited to the present invention, although with reference to previous embodiment to invention has been detailed description, for a person skilled in the art, it still can be modified to the technical scheme described in foregoing embodiments, or carries out equivalent replacement to wherein portion of techniques feature.Within the spirit and principles in the present invention all, any amendment done, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.

Claims (10)

1. a stealing analytical approach, is characterized in that, comprising:

Calculate trade power consumption amount trend coefficient, judge whether described trade power consumption amount trend coefficient is greater than the first statistics threshold values;

If described trade power consumption amount trend coefficient is greater than described first statistics threshold values, then calculates single household and industrial characteristic trend matching coefficient, judge whether described single household and industrial characteristic trend matching coefficient are greater than the second statistics threshold values;

If described single household and industrial characteristic trend matching coefficient are greater than described second and add up threshold values, then not there is stealing, otherwise stealing may occur.

2. method according to claim 1, is characterized in that, also comprises before calculating trade power consumption amount trend coefficient:

Add up the power consumption of described industry each observation station in measurement period, and carry out power consumption rank.

3. method according to claim 1, is characterized in that, the step of described calculating trade power consumption amount trend coefficient specifically comprises:

Trade power consumption amount trend coefficient according to following formulae discovery

$W=\frac{\mathrm{\Σ}{R}_i^2-\frac{{\left(\mathrm{\Σ}{R}_i\right)}^2}{N}}{\frac{1}{12}{K}^2(N^3-N)},$

Wherein, N is the points of measurement (i.e. measurement period), and K is industry sampling amount, R _ifor the ascending order value sum of each observation station K family power consumption rank.

4. method according to claim 1, is characterized in that, the step of described calculating single household and industrial characteristic trend matching coefficient specifically comprises:

According to following formulae discovery single household and industrial characteristic trend matching coefficient

$S=1-\frac{6\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{d}_i^2}{N(N^2-1)},$

Wherein, d _ifor the rank of industrial characteristic trend and the difference of single household trend rank, N is the points of measurement.

5. method according to claim 4, is characterized in that, the rank of described industrial characteristic trend is the mode of described industry in each observation station power consumption rank.

6. a stealing analytic system, is characterized in that, comprising:

First computing module, for calculating trade power consumption amount trend coefficient, judges whether described trade power consumption amount trend coefficient is greater than the first statistics threshold values;

Second computing module, if be greater than described first statistics threshold values for described trade power consumption amount trend coefficient, then calculate single household and industrial characteristic trend matching coefficient, judges whether described single household and industrial characteristic trend matching coefficient are greater than the second statistics threshold values;

, if be greater than described second for described single household and industrial characteristic trend matching coefficient to add up threshold values, then do not there is stealing, otherwise stealing may occur in stealing analysis module.

7. system according to claim 6, is characterized in that, also comprises:

Statistical analysis module, for adding up the power consumption of described industry each observation station in measurement period, and carries out power consumption rank.

8. system according to claim 6, is characterized in that, described first computing module is specifically for certain trade power consumption amount trend coefficient according to following formulae discovery

$W=\frac{\mathrm{\Σ}{R}_i^2-\frac{{\left(\mathrm{\Σ}{R}_i\right)}^2}{N}}{\frac{1}{12}{K}^2(N^3-N)},$

Wherein, N is the points of measurement (i.e. measurement period), and K is industry sampling amount, R _ifor the ascending order value sum of each observation station K family power consumption rank.

9. system according to claim 6, is characterized in that, described second computing module is specifically for according to following formulae discovery single household and industrial characteristic trend matching coefficient

$S=1-\frac{6\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{d}_i^2}{N(N^2-1)},$

Wherein, d _ifor the rank of industrial characteristic trend and the difference of single household trend rank, N is the points of measurement.

10. system according to claim 9, is characterized in that, the rank of described industrial characteristic trend is the mode of described industry in each observation station power consumption rank.