CN107220906A - Multiple Time Scales multiplexing electric abnormality analysis method based on electricity consumption acquisition system - Google Patents
Multiple Time Scales multiplexing electric abnormality analysis method based on electricity consumption acquisition system Download PDFInfo
- Publication number
- CN107220906A CN107220906A CN201710398830.8A CN201710398830A CN107220906A CN 107220906 A CN107220906 A CN 107220906A CN 201710398830 A CN201710398830 A CN 201710398830A CN 107220906 A CN107220906 A CN 107220906A
- Authority
- CN
- China
- Prior art keywords
- mrow
- data
- user
- electricity consumption
- msub
- 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
Classifications
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
A kind of Multiple Time Scales multiplexing electric abnormality analysis method based on electricity consumption acquisition system, category monitoring field.It is first according to time scale, and the data that power information acquisition system is gathered are classified；The data that electricity consumption acquisition system is obtained have been combed into short-term electricity consumption data and medium-term and long-term electricity consumption data, for short-term electricity consumption data, using electric informations such as Current Voltages, with reference to related limit value decision method, recognize multiplexing electric abnormality user；For medium-term and long-term electricity consumption data, using the electric information such as daily power consumption and moon power consumption, with reference to clustering algorithm and correlation coefficient process, multiplexing electric abnormality situation is searched；The described Multiple Time Scales multiplexing electric abnormality analysis method based on electricity consumption acquisition system, according to time scale, the data that electricity consumption acquisition system is obtained, have been combed into short-term electricity consumption data and medium-term and long-term electricity consumption data, so that from different time scale angle searchings to abnormal electricity consumption suspicion user.It can be widely used for electric company's management of power use and user power utilization abnormal conditions identification field.
Description
Technical field
The invention belongs to monitor field, more particularly to determination side the reason for a kind of exception for power grid user electricity consumption quantity
Method.
Background technology
Platform area line loss per unit is the difference divided by the total deliveries of platform Qu of the total deliveries of platform Qu and the total electricity sales amounts of platform Qu, and it is power supply
One very important performance assessment criteria of company, directly affects the economic benefit of company.
At present, most of Utility companies demand platform area line losses per unit are within 10%.However, due to by personnel, equipment, stealing
Etc. the influence of factor, electricity consumption is caused to occur abnormal, so that platform area line loss per unit is higher, it is necessary to be investigated and defect elimination.In the past
Mostly by live inspection or based on user monthly electricity, monthly line loss situation, electric energy metrical abnormal user is determined by rule of thumb,
These traditional method poor in timeliness, accuracy rate are low.Therefore how effectively to handle multiplexing electric abnormality problem causes live O＆M
The extensive concern of personnel.
Power information acquisition system can carry out monitoring, analyze and handling in real time to power information.It is as electricity consumption is gathered
The popularization and application of system, collection coverage is progressively expanded to resident, general industry and commerce user etc. from special change user, obtains daily
The electricity consumption data amount taken is also more and more comprehensive.Relevance is there is between these electricity consumption datas, electricity consumption behavior etc. is hidden a large amount of
Valuable information, can provide foundation for multiplexing electric abnormality analysis.
Scholar is had at present and is based on electricity consumption acquisition system, it is proposed that related analysis method.For example, " being counted based on peeling off
The research of opposing electricity-stealing of method and power information acquisition system " (《Electric power system protection and control》, Cheng Chao, Zhang Hanjing, scape will is quick etc.,
2015,43 (17)：P69-74. electricity filching means and principle are analyzed in), and then based on the rule of voltage x current value, with reference to peeling off
Point detection method determines stealing decision algorithm." checking method is performed based on Density Clustering and the electricity price of Frechet discriminant analyses "
(《Electric power network technique》, Peng Xiangang, Zheng Weiqin, forest rent is auspicious to wait .2015,39 (11)：P3195-3201.) using data mining technology as base
A kind of plinth, it is proposed that abnormal user discriminating method based on Density Clustering Analysis and Frechet distance discriminations." dug based on data
The design and realization of the metering device on-line monitoring and intelligent diagnosis system of pick " (《Electrical measurement and instrument》, Xiao Jianhong, Yan little Wen, week
It is forever true, wait .2014,51 (14)：P1-5. a set of metering device on-line checking and intelligent diagnosis system, energy are proposed and have developed in)
Situations such as enough analyzing user's stealing and metering device failure.
The studies above achieves certain progress, but these documents are only analyzed a certain method, and these sides
Method has the respective scope of application, and the abnormal conditions that can be handled are also restricted.
Therefore, how on the basis of user's electricity mass data, data and method are sorted out and pre-processed, analyzed
Go out the usable condition of various methods, can popularization and application, ancillary staff carry out electric energy metrical extremely investigation also needs to
Further research.
The content of the invention
It is different that the technical problems to be solved by the invention are to provide a kind of Multiple Time Scales electricity consumption based on electricity consumption acquisition system
Normal analysis method.It is based on power information acquisition system, according to time scale length, the number gathered to power information acquisition system
According to being classified, the data that electricity consumption acquisition system is obtained short-term electricity consumption data and medium-term and long-term electricity consumption data have been combed into；For
Short-term electricity consumption data, using electric informations such as Current Voltages, with reference to related limit value decision method, recognizes multiplexing electric abnormality user；
For medium-term and long-term electricity consumption data, using the electric information such as daily power consumption and moon power consumption, with reference to clustering algorithm and correlation coefficient process,
Multiplexing electric abnormality situation is searched, and then realizes the analysis of Multiple Time Scales multiplexing electric abnormality, can be searched from different time scale angles
Rope is to abnormal electricity consumption suspicion user.
The technical scheme is that：A kind of Multiple Time Scales multiplexing electric abnormality analysis side based on electricity consumption acquisition system is provided
Method, including by the data of power information acquisition system collection user power utilization, it is characterized in that：
Time scale is first according to, the data that power information acquisition system is gathered are classified；
Described time scale is divided into short period yardstick data and medium-term and long-term time scale data；
Described short period yardstick data are included per moment Current Voltage set and daily Current Voltage set in 24 hours；
Described medium-term and long-term time scale data include monthly every daily power consumption set and annual monthly electricity consumption duration set；
To short period yardstick data, user power utilization is carried out using Current Voltage decision algorithm and recognized extremely；
Centering long-term time scales data, carry out user power utilization using clustering algorithm and correlation coefficient process and recognize extremely；
The described Multiple Time Scales multiplexing electric abnormality analysis method based on electricity consumption acquisition system, according to time scale, will be used
The data that electric acquisition system is obtained, have been combed into short-term electricity consumption data and medium-term and long-term electricity consumption data, so that from different time chis
Angle searching is spent to abnormal electricity consumption suspicion user.
Specifically, when carrying out the multiplexing electric abnormality analysis of short period yardstick, described Current Voltage decision algorithm electricity consumption
Press deviation ratio βUWith three-phase current unbalance rate βIIt is used as the judgement element of multiplexing electric abnormality, variation factor betaUAnd three-phase electricity
Flow unbalance factor βISpecific calculation it is as follows：
U is voltage in formula；UeFor rated voltage；ImaxFor phase current maximum in three-phase；IavFor three-phase current average value；
According to variation factor betaUWith three-phase current unbalance rate βICalculate the variation system of user A phases, B phases and C phases
Number βAU、βBU、βCUAnd current imbalance rate βI, and do following judgement：
In formula：WithRespectively variation coefficient and the limit value of current imbalance rate；
When the variation factor beta of each phaseU, three-phase current unbalance rate βIWith the limit value of variation coefficientElectric current
The limit value of unbalance factorBoolean be "true" when, then it represents that there is multiplexing electric abnormality suspicion in the user.
Specifically, during the multiplexing electric abnormality analysis of underway long-term time scales, described clustering algorithm is first by poly-
Alanysis obtains the typical power load curve of the electricity consumption classification, and then will need user and the typical case's power load curve of investigation
It is compared, and then finds out multiplexing electric abnormality suspicion user.
Clustering algorithm described in it is K-means algorithms.
Specifically, during the multiplexing electric abnormality analysis of underway long-term time scales, described correlation coefficient process calculates platform area
Line loss and electric supply meter show the coefficient correlation between electricity, if correlation is high, and the user has abnormal suspicion.
Specifically, when calculating platform area's line loss and electric supply meter shows the coefficient correlation between electricity, for platform area line loss
Δ W and user's electricity WO,i, the correlation coefficient riCalculation formula it is as follows：
In formula：WO,iElectricity, Δ W are shown for electric supply meteriFor error in dipping, Δ W is platform area line loss, and E () is desired value
Function；
If correlation coefficient riMore than its threshold valueThen represent that the user has multiplexing electric abnormality suspicion.
Technical scheme, long term data carries out user power utilization exception in based on the monthly set pair per daily power consumption
During identification, carried out according to the following steps：
Step 1：30 days one month nearest daily power consumption data of the rational user of platform area's line loss are chosen as sample data,
30 days nearest one month daily power consumption data of platform area user to be analyzed are extracted as analyze data；
Step 2：For lack part in sample data and analyze data, cubic spline interpolation combination linear interpolation is utilized
Method supplements missing data, wherein the use cubic spline interpolation of cubic spline interpolation condition is met, when being unsatisfactory for, using linear
Interpolation processing；
Step 3：After all power consumption data of completion, in order to eliminate the influence of different dimensions, preferably embody electricity consumption and become
Law is, it is necessary to initial data be normalized, data compression between interval [0,1].Specific processing formula is such as
Under：
In formula：Data after w, w ' the respectively initial data of user's daily power consumption and conversion；wminAnd wmaxRespectively use
Daily power consumption minimum value and maximum of the family in one month；
Step 4：Sample data after normalization is classified according to load nature of electricity consumed, and use is found out using clustering
Electrical anomaly suspicion user；
Step 5：According to the critical point summary table data and user's daily power consumption data in be analyzed area, calculate and put into effect area day line loss
Amount, and then the Pearson correlation coefficient between platform area day line loss amount and user's daily power consumption is calculated using correlation coefficient process, search
Go out multiplexing electric abnormality suspicion user；
Step 6：On-site verification is carried out to the multiplexing electric abnormality suspicion user found in step 4 and step 5, multiplexing electric abnormality is found out
User.
Technical scheme, long term data carries out user power utilization exception in based on year monthly electricity consumption duration set pair
During identification, the data analyzed become the moon power consumption data in December, 1 from the daily power consumption data of 30 days one month, other
Calculating process is identical with carrying out the step of user power utilization exception identification is based on monthly every daily power consumption set centering long term data.
Compared with the prior art, it is an advantage of the invention that：
1. according to time scale, the data that electricity consumption acquisition system is obtained have been combed into short-term electricity consumption data and medium-term and long-term use
Electric data, and then propose a kind of Multiple Time Scales multiplexing electric abnormality analysis method to recognize multiplexing electric abnormality situation；
2. the Short Term Anomalous electrical energy consumption analysis method based on Current Voltage decision algorithm has higher accuracy, it is adaptable to distinguish
Know special transformer terminals user abnormal conditions；
3. clustering algorithm and correlation coefficient process have the different scope of applications, multiplexing electric abnormality use can be effectively searched
Family；
4. the exception analysis method based on monthly data is good compared with the method real-time based on annual data, but annual data is true
Reality is good, there is certain break-up value.
Brief description of the drawings
Fig. 1 is multiplexing electric abnormality analysis method overall framework schematic diagram of the present invention；
Fig. 2 is the calculation process schematic diagram of K-means algorithms of the present invention；
Fig. 3 is to obtain resident's typical load curve of 30 days based on monthly electricity consumption data；
Fig. 4 is to obtain commercial user's typical load curve of 30 days based on monthly electricity consumption data.
Embodiment
The present invention will be further described with reference to the accompanying drawings and examples.
Technical scheme, based on power information acquisition system, according to time scale length, electricity consumption data is divided
For short-term electricity consumption data and medium-term and long-term electricity consumption data, and then propose Multiple Time Scales multiplexing electric abnormality analysis method.This method pin
To short period yardstick, using electric informations such as Current Voltages, with reference to related limit value decision method, identification multiplexing electric abnormality is used
Family；For medium-term and long-term time scale, using the electric information such as daily power consumption and moon power consumption, with reference to clustering algorithm and coefficient correlation
Method, searches multiplexing electric abnormality situation.
The data volume obtained in view of power information acquisition system is larger, comprising information content it is more, therefore according to the time
Yardstick is classified to data, and then proposes the analysis method of correlation to recognize the suspicion user of user's exception.Based on electricity consumption
The Multiple Time Scales multiplexing electric abnormality analysis method overall framework of information acquisition system is as shown in Figure 1.
Detailed process is as follows：Time scale is first according to, the data to system acquisition are classified, short-term data can be divided into
Per moment Current Voltage set and daily Current Voltage set in 24 hours, medium-term and long-term data can be divided into monthly per daily power consumption set
With annual monthly electricity consumption duration set, abnormal identification can be carried out using Current Voltage decision algorithm for short-term data, for middle length
Issue using clustering algorithm and correlation coefficient process according to can carry out abnormal identification, so that from different time scale angle searchings to different
Conventional electricity suspicion user.
Method of the present invention is directed to different user, and concrete operations have certain difference.It is used for gathering electricity consumption at present
The device of information mainly has two kinds, and one kind is special transformer terminals, and another is concentrator.Its special secondary school transformer terminals can obtain user's
The information such as Current Voltage and power consumption, for this certain customers, can be divided using the abnormal electricity consumption of short-term and medium-term and long-term time scale
Analysis method carries out comprehensive descision；And the typically no passage for opening acquisition current-voltage information of concentrator, user's use can only be obtained
Information about power, the abnormal electrical energy consumption analysis method of long-term time scale carries out abnormal identification in being used for this certain customers.
1st, the multiplexing electric abnormality analysis method of short period yardstick
1.1st, voltage x current decision algorithm
Special transformer terminals mainly gather information to three-phase user, and under normal circumstances, for three-phase user, voltage can be tieed up
Hold near rated value, while current imbalance rate is also smaller.When there is obvious variation or there is larger imbalance
During electric current, show the possible multiplexing electric abnormality of this user, it is necessary to investigate.Therefore variation factor beta is selected hereinUWith three-phase current not
Balanced ratio βIAs the judgement element of multiplexing electric abnormality, specific formula for calculation is as follows：
In formula：U is voltage；UeFor rated voltage；ImaxFor phase current maximum in three-phase；IavFor three-phase current average value.
1.2 analysis methods based on real-time electricity consumption data
Special transformer terminals can with the voltage of user in real, current data, and then based on these data, according to formula (1) and
Formula (2) calculates the variation factor beta of user A phases, B phases and C phasesAU、βBU、βCUAnd current imbalance rate βI, and do and following sentence
It is disconnected：
In formula：WithRespectively variation coefficient and the limit value of current imbalance rate.When formula (3) result is cloth
During value of TRUE, then it represents that the user has multiplexing electric abnormality suspicion.
1.3 analysis methods based on day electricity consumption data
Special transformer terminals can according to 15min time interval, the voltage and current data to user sample, drafting day
Pressure and current curve.More than several hours would generally be maintained in view of abnormal electricity consumption, therefore therefrom choose the electricity at each integral point moment
Pressure, current data can be described the problem as the foundation of analysis.The three-phase maximum voltage deviation ratio of daily 24 hours it is European away from
From dUWith three-phase current unbalance rate Euclidean distance dICalculation formula difference is as follows：
If dUValue exceedes its limit valueOr dIValue exceedes its limit valueThen represent that the user has multiplexing electric abnormality suspicion.
2nd, the abnormal electrical energy consumption analysis method of medium-term and long-term time scale
2.1 clustering algorithm
For the user of identical electricity consumption classification, electricity consumption behavioural characteristic each other has certain similitude.Based on this
One feature, can obtain the typical power load curve of the electricity consumption classification, and then will need what is investigated by clustering first
User is compared with typical power load curve, finds out multiplexing electric abnormality suspicion user.
In various clustering methods, K-means clustering algorithms have the advantages that fast convergence rate, are easily achieved, extensive
Applied in analysis of power consumption load, therefore the technical program selects this method.
The specific calculation process of K-means algorithms is as shown in Figure 2.
Cluster centre set can be obtained based on K-means algorithms, i.e. typical case power load set Q={ q1, q2,…,
qK}.And then the power load data W and Q investigated will be needed to contrast, calculate minimum euclidean distance dW：
dW=min [dist (W, q1),dist(W,q2),...,dist(W,qK)] (6)
In formula：Dist () is Euclidean distance function.If dWValue exceedes its limit valueThen represent that the user has electricity consumption
Abnormal suspicion.
2.2 correlation coefficient process
The calculation formula of meter error in dipping is as follows：
In formula：For the actual power consumption of user；WO,iElectricity is shown for meter.It is wrong for same meter circuit connection
By mistake, usual electric supply meter shows that electricity and true electricity are linear relationships, as follows：
Therefore formula (7) can be changed into：
As can be seen from the above equation, when electric supply meter shows electricity WO,iIt is bigger, error in dipping Δ WiIt is bigger, platform area line loss
Δ W is also bigger, WO,iThere is obvious correlation between platform area line loss.Therefore platform area can be calculated using correlation coefficient process
Line loss and electric supply meter show the coefficient correlation between electricity, if correlation is high, and the user has abnormal suspicion.What is commonly used
In coefficient correlation, Pearson correlation coefficient can effectively weigh linear correlation degree between two variables, therefore can select this
Method carries out multiplexing electric abnormality analysis.For platform area line loss Δ W and user's electricity WO,i, Pearson correlation coefficient calculation formula is as follows：
In formula：E () is expectation value function.If ri is more than its threshold valueThen represent that the user has multiplexing electric abnormality suspicion
Doubt.
2.3 analysis methods based on monthly electricity consumption data
Analysis method calculating process based on monthly electricity consumption data is as follows：
Step 1：30 days one month nearest daily power consumption data of the rational user of platform area's line loss are chosen as sample data,
30 days nearest one month daily power consumption data of platform area user to be analyzed are extracted as analyze data；
Step 2：For lack part in sample data and analyze data, cubic spline interpolation is utilized[11]Inserted with reference to linear
The method supplement missing data of value, wherein meeting the use cubic spline interpolation of cubic spline interpolation condition, when being unsatisfactory for, is used
Linear interpolation processing；
Step 3：After all power consumption data of completion, in order to eliminate the influence of different dimensions, preferably embody electricity consumption and become
Law is, it is necessary to initial data be normalized, data compression between interval [0,1].Specific processing formula is such as
Under：
In formula：Data after w, w ' the respectively initial data of user's daily power consumption and conversion；wminAnd wmaxRespectively use
Daily power consumption minimum value and maximum of the family in one month.
Step 4：Sample data after normalization is classified according to load nature of electricity consumed, and use is found out using clustering
Electrical anomaly suspicion user；
Step 5：According to the critical point summary table data and user's daily power consumption data in be analyzed area, calculate and put into effect area day line loss
Amount, and then the Pearson correlation coefficient between platform area day line loss amount and user's daily power consumption is calculated using correlation coefficient process, search
Go out multiplexing electric abnormality suspicion user；
Step 6：On-site verification is carried out to the multiplexing electric abnormality suspicion user found in step 4 and step 5, multiplexing electric abnormality is found out
User.
2.4 analysis methods based on annual electricity consumption data
Analysis method based on annual electricity consumption data is similar with the analysis method based on monthly electricity consumption data, will simply divide
The data of analysis become the moon power consumption data in December, 1 from the daily power consumption data of 30 days one month, other steps and calculate
Cheng Xiangtong.
Embodiment：
The abnormal electricity consumption instance analysis of 3.1 short period yardsticks
Using the higher special transformer terminals user in 139,5 Ge Tai areas of somewhere line loss as analysis object, short period yardstick is verified
Abnormal electrical energy consumption analysis method validity.
IfIt may determine that abnormal suspicion number of users is 6 according to real time data, specifically
Table number (last 8) and anomaly it is as shown in table 1.Find that 6 meters are all in the presence of abnormal through scene investigation.
Analysis result of the table 1 based on real time data
IfIt may determine that the user of abnormal electricity consumption is 9 according to day electricity consumption data, except
6 in table 1 have abnormal electricity consumption suspicion with open air, also 2 users, as shown in table 2, through scene investigation, are implicitly present in meter
Amount problem.
As can be seen here, the Short Term Anomalous electrical energy consumption analysis method based on Current Voltage decision algorithm has higher accuracy.
Analysis result of the table 2 based on day electricity consumption data
The abnormal electricity consumption instance analysis of long-term time scale in 3.2
In order to verify the validity of clustering algorithm, the platform rational 5789 family resident of area's line loss and 1951 families are chosen first
Commercial user carries out clustering as sample data, draws typical load curve, and some then is included into 62 family residents
Platform area with 7 family commercial users is contrasted with typical load curve as analysis object, judges suspicion user.
In clustering, the cluster numbers of resident and commercial user are respectively set to 15 and 10, based on monthly
Electricity consumption data obtains the typical load curve of 30 days as shown in Figure 3 and Figure 4.
Analysis object is contrasted with typical load curve, Distance l imit1.1 are taken, 7 family residents of precipitation are divided into
There is abnormal suspicion, scene investigation finds that wherein 5 family meters are implicitly present in exception, and accuracy rate is 71.43%, concrete condition such as table 3
It is shown, it can be seen that clustering algorithm can effectively screen out suspicion user.
Analysis result of the table 3 based on clustering algorithm
In order to verify the validity of correlation coefficient process, 62 family residents and 7 family commercial users and platform area line loss are calculated
Coefficient correlation, and choose coefficient correlation more than 0.9 as suspicion user, specific result of calculation as shown in table 4, altogether comprising 4 families
Resident and 1 family commercial user, have found that 2 family residents and 1 family commercial user have multiplexing electric abnormality, accuracy rate through scene investigation
For 60%.
Contrast clustering algorithm and correlation coefficient process are can be found that：Resident's abnormal quantity and standard that clustering algorithm is found
True rate is all higher than correlation coefficient process, and correlation coefficient process has found family commercial user's multiplexing electric abnormality more than clustering algorithm, thus
It can be seen that two kinds of algorithms have different applicabilities.
Analysis result of the table 4 based on correlation coefficient process
Based on annual data, the family of multiplexing electric abnormality suspicion user 7 is found using cluster algorithm, 4 families are checked and verify, accuracy rate is
57.14%；The family of multiplexing electric abnormality suspicion user 6 is found using correlation coefficient process, 3 families are checked and verify, accuracy rate is 50%.
Compared to monthly data, the multiplexing electric abnormality investigation method accuracy rate based on annual data will be more lower slightly, through dividing
Analysis, mainly including following two reasons：(1) monthly data includes 30 periods, and annual data includes 12 periods, the moon number of degrees
It is big according to sample size, it is capable of the rule of more preferable reflection Electrical change；(2) the monthly data sampling period is short, and annual data is sampled
Cycle is long, and monthly data is capable of the real-time of more preferable reflection Electrical change.But it is due to acquisition channel problem, daily power consumption number
Lacked to a certain degree according to that can exist, made up even with interpolation method, can also there is partial distortion phenomenon, and for moon power consumption
Data, due to there is artificial mend to copy link, so data are more complete, the information of embodiment is more true, therefore based on annual data
Multiplexing electric abnormality investigation method also have certain value.
The abnormal electricity consumption instance analysis of 3.3 Multiple Time Scales
Proposed Multiple Time Scales multiplexing electric abnormality analysis method is utilized, 2079,21 Ge Tai areas user is analyzed,
The family of investigation multiplexing electric abnormality suspicion user 97, checks and verify the family of user 62 altogether, and the average moon line loss per unit in this 21 Ge Tai area have dropped 8.23%, by
This visible institute's extracting method can effectively aid in monitoring personnel to screen the abnormal electricity consumption situation of user in time.
Because technical scheme is according to time scale, the data that electricity consumption acquisition system is obtained have been combed into short term
Electricity consumption data and medium-term and long-term electricity consumption data, and then it is different to recognize electricity consumption to propose a kind of Multiple Time Scales multiplexing electric abnormality analysis method
Reason condition, can draw to draw a conclusion by instance analysis：
(1) the Short Term Anomalous electrical energy consumption analysis method based on Current Voltage decision algorithm has higher accuracy, it is adaptable to
Recognize special transformer terminals user abnormal conditions.
(2) clustering algorithm and correlation coefficient process have the different scope of applications, can effectively search multiplexing electric abnormality use
Family.
(3) exception analysis method based on monthly data is good compared with the method real-time based on annual data, but annual data
Authenticity is good, there is certain break-up value.
It the method can be widely used in electric company's management of power use and user power utilization abnormal conditions identification field.
Claims (8)
1. a kind of Multiple Time Scales multiplexing electric abnormality analysis method based on electricity consumption acquisition system, including system is gathered by power information
The data of system collection user power utilization, it is characterized in that：
Time scale is first according to, the data that power information acquisition system is gathered are classified；
Described time scale is divided into short period yardstick data and medium-term and long-term time scale data；
Described short period yardstick data are included per moment Current Voltage set and daily Current Voltage set in 24 hours；
Described medium-term and long-term time scale data include monthly every daily power consumption set and annual monthly electricity consumption duration set；
To short period yardstick data, user power utilization is carried out using Current Voltage decision algorithm and recognized extremely；
Centering long-term time scales data, carry out user power utilization using clustering algorithm and correlation coefficient process and recognize extremely.
The described Multiple Time Scales multiplexing electric abnormality analysis method based on electricity consumption acquisition system, according to time scale, electricity consumption is adopted
The data that collecting system is obtained, have been combed into short-term electricity consumption data and medium-term and long-term electricity consumption data, so that from different time scale angles
Degree searches abnormal electricity consumption suspicion user.
2. according to the Multiple Time Scales multiplexing electric abnormality analysis method based on electricity consumption acquisition system described in claim 1, its feature
It is the described Current Voltage decision algorithm voltage deviation ratio β when carrying out the multiplexing electric abnormality analysis of short period yardstickUWith
Three-phase current unbalance rate βIIt is used as the judgement element of multiplexing electric abnormality, variation factor betaUWith three-phase current unbalance rate βI's
Specific calculation is as follows：
<mrow>
<msub>
<mi>&beta;</mi>
<mi>U</mi>
</msub>
<mo>=</mo>
<mfrac>
<mrow>
<mo>|</mo>
<mi>U</mi>
<mo>-</mo>
<msub>
<mi>U</mi>
<mi>e</mi>
</msub>
<mo>|</mo>
</mrow>
<msub>
<mi>U</mi>
<mi>e</mi>
</msub>
</mfrac>
</mrow>
<mrow>
<msub>
<mi>&beta;</mi>
<mi>I</mi>
</msub>
<mo>=</mo>
<mfrac>
<mrow>
<mo>|</mo>
<msup>
<mi>I</mi>
<mrow>
<mi>m</mi>
<mi>a</mi>
<mi>x</mi>
</mrow>
</msup>
<mo>-</mo>
<msup>
<mi>I</mi>
<mrow>
<mi>m</mi>
<mi>i</mi>
<mi>n</mi>
</mrow>
</msup>
<mo>|</mo>
</mrow>
<msup>
<mi>I</mi>
<mrow>
<mi>m</mi>
<mi>a</mi>
<mi>x</mi>
</mrow>
</msup>
</mfrac>
</mrow>
U is voltage in formula；UeFor rated voltage；ImaxFor phase current maximum in three-phase；IavFor three-phase current average value；
According to variation factor betaUWith three-phase current unbalance rate βICalculate the variation coefficient of user A phases, B phases and C phases
βAU、βBU、βCUAnd current imbalance rate βI, and do following judgement：
<mrow>
<mo>(</mo>
<msub>
<mi>&beta;</mi>
<mrow>
<mi>A</mi>
<mi>U</mi>
</mrow>
</msub>
<mo>&GreaterEqual;</mo>
<msubsup>
<mi>&beta;</mi>
<mi>U</mi>
<mrow>
<mi>m</mi>
<mi>a</mi>
<mi>x</mi>
</mrow>
</msubsup>
<mo>)</mo>
<mo>|</mo>
<mo>|</mo>
<mo>(</mo>
<msub>
<mi>&beta;</mi>
<mrow>
<mi>B</mi>
<mi>U</mi>
</mrow>
</msub>
<mo>&GreaterEqual;</mo>
<msubsup>
<mi>&beta;</mi>
<mi>U</mi>
<mi>max</mi>
</msubsup>
<mo>)</mo>
</mrow>
<mrow>
<mo>|</mo>
<mo>|</mo>
<mrow>
<mo>(</mo>
<msub>
<mi>&beta;</mi>
<mrow>
<mi>C</mi>
<mi>U</mi>
</mrow>
</msub>
<mo>&GreaterEqual;</mo>
<msubsup>
<mi>&beta;</mi>
<mi>U</mi>
<mrow>
<mi>m</mi>
<mi>a</mi>
<mi>x</mi>
</mrow>
</msubsup>
<mo>)</mo>
</mrow>
<mo>|</mo>
<mo>|</mo>
<mrow>
<mo>(</mo>
<msub>
<mi>&beta;</mi>
<mi>I</mi>
</msub>
<mo>&GreaterEqual;</mo>
<msubsup>
<mi>&beta;</mi>
<mi>I</mi>
<mi>max</mi>
</msubsup>
<mo>)</mo>
</mrow>
</mrow>
In formula：WithRespectively variation coefficient and the limit value of current imbalance rate；
When the variation factor beta of each phaseU, three-phase current unbalance rate βIWith the limit value of variation coefficientElectric current is uneven
The limit value of weighing apparatus rateBoolean be "true" when, then it represents that there is multiplexing electric abnormality suspicion in the user.
3. according to the Multiple Time Scales multiplexing electric abnormality analysis method based on electricity consumption acquisition system described in claim 1, its feature
When being the multiplexing electric abnormality analysis of underway long-term time scales, described clustering algorithm obtains the use by clustering first
The typical power load curve of electric classification, and then the user investigated will be needed to be compared with typical power load curve, and then
Find out multiplexing electric abnormality suspicion user.
4. according to the Multiple Time Scales multiplexing electric abnormality analysis method based on electricity consumption acquisition system described in claim 3, its feature
It is that described clustering algorithm is K-means algorithms.
5. according to the Multiple Time Scales multiplexing electric abnormality analysis method based on electricity consumption acquisition system described in claim 1, its feature
When being the multiplexing electric abnormality analysis of underway long-term time scales, described correlation coefficient process calculates platform area's line loss and electric supply meter
The coefficient correlation between electricity is shown, if correlation is high, the user has abnormal suspicion.
6. according to the Multiple Time Scales multiplexing electric abnormality analysis method based on electricity consumption acquisition system described in claim 5, its feature
It is when calculating platform area's line loss and electric supply meter shows the coefficient correlation between electricity, for platform area line loss Δ W and user's electricity
WO,i, the correlation coefficient riCalculation formula it is as follows：
<mrow>
<msub>
<mi>r</mi>
<mi>i</mi>
</msub>
<mo>=</mo>
<mfrac>
<mrow>
<mi>E</mi>
<mrow>
<mo>(</mo>
<mi>&Delta;</mi>
<mi>W</mi>
<mo>&CenterDot;</mo>
<msub>
<mi>W</mi>
<mrow>
<mi>O</mi>
<mo>,</mo>
<mi>i</mi>
</mrow>
</msub>
<mo>)</mo>
</mrow>
<mo>-</mo>
<mi>E</mi>
<mrow>
<mo>(</mo>
<mi>&Delta;</mi>
<mi>W</mi>
<mo>)</mo>
</mrow>
<mi>E</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>W</mi>
<mrow>
<mi>O</mi>
<mo>,</mo>
<mi>i</mi>
</mrow>
</msub>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<msqrt>
<mrow>
<mi>E</mi>
<mrow>
<mo>(</mo>
<msup>
<mi>&Delta;W</mi>
<mn>2</mn>
</msup>
<mo>)</mo>
</mrow>
<mo>-</mo>
<msup>
<mi>E</mi>
<mn>2</mn>
</msup>
<mrow>
<mo>(</mo>
<mi>&Delta;</mi>
<mi>W</mi>
<mo>)</mo>
</mrow>
</mrow>
</msqrt>
<msqrt>
<mrow>
<mi>E</mi>
<mrow>
<mo>(</mo>
<msubsup>
<mi>W</mi>
<mrow>
<mi>O</mi>
<mo>,</mo>
<mi>i</mi>
</mrow>
<mn>2</mn>
</msubsup>
<mo>)</mo>
</mrow>
<mo>-</mo>
<msup>
<mi>E</mi>
<mn>2</mn>
</msup>
<mrow>
<mo>(</mo>
<msub>
<mi>W</mi>
<mrow>
<mi>O</mi>
<mo>,</mo>
<mi>i</mi>
</mrow>
</msub>
<mo>)</mo>
</mrow>
</mrow>
</msqrt>
</mrow>
</mfrac>
</mrow>
In formula：WO,iElectricity, Δ W are shown for electric supply meteriFor error in dipping, Δ W is platform area line loss, and E () is expectation value function；
If correlation coefficient riMore than its threshold valueThen represent that the user has multiplexing electric abnormality suspicion.
7. according to the Multiple Time Scales multiplexing electric abnormality analysis method based on electricity consumption acquisition system described in claim 1, its feature
It is, when long term data carries out user power utilization identification extremely in based on the monthly set pair per daily power consumption, to enter according to the following steps
OK：
Step 1：30 days one month nearest daily power consumption data of the rational user of platform area's line loss are chosen as sample data, are extracted
30 days nearest one month daily power consumption data of platform area user to be analyzed are as analyze data；
Step 2：For lack part in sample data and analyze data, the method for cubic spline interpolation combination linear interpolation is utilized
Missing data is supplemented, wherein the use cubic spline interpolation of cubic spline interpolation condition is met, when being unsatisfactory for, using linear interpolation
Processing；
Step 3：After all power consumption data of completion, in order to eliminate the influence of different dimensions, more preferable embodiment is advised with Electrical change
Rule is, it is necessary to initial data be normalized, data compression between interval [0,1].Specific processing formula is as follows：
<mrow>
<msup>
<mi>w</mi>
<mo>&prime;</mo>
</msup>
<mo>=</mo>
<mfrac>
<mrow>
<mi>w</mi>
<mo>-</mo>
<msub>
<mi>w</mi>
<mi>min</mi>
</msub>
</mrow>
<mrow>
<msub>
<mi>w</mi>
<mi>max</mi>
</msub>
<mo>-</mo>
<msub>
<mi>w</mi>
<mi>min</mi>
</msub>
</mrow>
</mfrac>
</mrow>
In formula：Data after w, w ' the respectively initial data of user's daily power consumption and conversion；wminAnd wmaxRespectively user exists
Daily power consumption minimum value and maximum in one month；
Step 4：Sample data after normalization is classified according to load nature of electricity consumed, and it is different using clustering to find out electricity consumption
Normal suspicion user；
Step 5：According to the critical point summary table data and user's daily power consumption data in be analyzed area, calculate and put into effect area day line loss amount,
And then the Pearson correlation coefficient between platform area day line loss amount and user's daily power consumption is calculated using correlation coefficient process, find out use
Electrical anomaly suspicion user；
Step 6：On-site verification is carried out to the multiplexing electric abnormality suspicion user found in step 4 and step 5, multiplexing electric abnormality use is found out
Family.
8. according to the Multiple Time Scales multiplexing electric abnormality analysis method based on electricity consumption acquisition system described in claim 1, its feature
It is that, when based on year, monthly long term data carries out user power utilization and recognized extremely in electricity consumption duration set pair, the data analyzed are from one
The daily power consumption data of 30 days individual month become the moon power consumption data in December, 1, other calculating process with based on monthly per daily
It is identical the step of identification is extremely that electricity set centering long term data carries out user power utilization.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710398830.8A CN107220906B (en) | 2017-05-31 | 2017-05-31 | Multiple Time Scales multiplexing electric abnormality analysis method based on electricity consumption acquisition system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710398830.8A CN107220906B (en) | 2017-05-31 | 2017-05-31 | Multiple Time Scales multiplexing electric abnormality analysis method based on electricity consumption acquisition system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107220906A true CN107220906A (en) | 2017-09-29 |
| CN107220906B CN107220906B (en) | 2019-10-11 |
Family
ID=59947125
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710398830.8A Active CN107220906B (en) | 2017-05-31 | 2017-05-31 | Multiple Time Scales multiplexing electric abnormality analysis method based on electricity consumption acquisition system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107220906B (en) |
Cited By (36)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108020752A (en) * | 2017-11-10 | 2018-05-11 | 国网浙江省电力公司电力科学研究院 | A kind of distribution line loss diagnostic method and system based on multi-source perforation correlation |
| CN108062616A (en) * | 2017-11-20 | 2018-05-22 | 国网福建省电力有限公司 | A kind of multiplexing electric abnormality detection model with constraints |
| CN108256752A (en) * | 2018-01-02 | 2018-07-06 | 北京市燃气集团有限责任公司 | A kind of analysis method of gas user gas behavior |
| CN108535599A (en) * | 2018-04-16 | 2018-09-14 | 国网河南省电力公司电力科学研究院 | Low-voltage platform area user's phase recognition methods based on voltage curve clustering |
| CN108776276A (en) * | 2018-06-29 | 2018-11-09 | 合肥工业大学 | Multiplexing electric abnormality detection method and system |
| CN108828375A (en) * | 2018-08-17 | 2018-11-16 | 国网江苏省电力有限公司电力科学研究院 | Air conditioning electricity monitoring system and monitoring method based on two-loop intelligent electric energy meter |
| CN109446193A (en) * | 2018-11-13 | 2019-03-08 | 国网宁夏电力有限公司电力科学研究院 | It opposes electricity-stealing model generating method and device |
| CN109493249A (en) * | 2018-11-05 | 2019-03-19 | 北京邮电大学 | A kind of analysis method of electricity consumption data on Multiple Time Scales |
| CN109634944A (en) * | 2018-12-05 | 2019-04-16 | 贵州电网有限责任公司凯里供电局 | A kind of network loss data cleaning method based on various dimensions space-time analysis |
| CN109636667A (en) * | 2018-12-07 | 2019-04-16 | 国网江苏省电力有限公司扬州供电分公司 | A kind of low-voltage customer multiplexing electric abnormality detection method based on user's week electrical feature |
| CN109655664A (en) * | 2018-12-11 | 2019-04-19 | 全球能源互联网研究院有限公司 | A kind of stealing intelligent diagnosing method and equipment based on load characteristic model library |
| CN109725219A (en) * | 2018-12-29 | 2019-05-07 | 重庆邮电大学 | A kind of electric energy meter platform area automatic identifying method |
| CN109738723A (en) * | 2018-12-29 | 2019-05-10 | 重庆邮电大学 | A kind of electric energy meter three-phase automatic identification method |
| CN109918365A (en) * | 2019-03-01 | 2019-06-21 | 河海大学常州校区 | A kind of data cleaning method suitable for photovoltaic data |
| CN110070256A (en) * | 2019-02-28 | 2019-07-30 | 国网浙江省电力有限公司 | Zero power user based on CRITIC method checks priority weighing computation method |
| CN110276511A (en) * | 2019-04-16 | 2019-09-24 | 国网浙江海盐县供电有限公司 | A kind of line change relationship anomalous discrimination method based on electricity and line loss relevance |
| CN110311709A (en) * | 2019-06-10 | 2019-10-08 | 国网浙江省电力有限公司嘉兴供电公司 | Power information acquisition system fault distinguishing method |
| CN110321934A (en) * | 2019-06-12 | 2019-10-11 | 深圳供电局有限公司 | A kind of method and system detecting user power utilization abnormal data |
| CN110503111A (en) * | 2019-08-23 | 2019-11-26 | 江苏方天电力技术有限公司 | A kind of multiplexing electric abnormality behavior method for visually monitoring based on rgb color mode |
| CN110930034A (en) * | 2019-11-22 | 2020-03-27 | 广东电力交易中心有限责任公司 | Electric power spot market settlement metering data verification method, device and medium |
| CN111007337A (en) * | 2019-12-04 | 2020-04-14 | 河南昊晟电子科技有限公司 | Intelligent power consumption monitoring and information transmission system for safety production |
| CN111444241A (en) * | 2020-03-26 | 2020-07-24 | 南京工程学院 | Data mining-based accurate positioning method for line loss abnormity associated users of distribution room |
| CN111443237A (en) * | 2020-04-20 | 2020-07-24 | 北京中电普华信息技术有限公司 | Method and system for determining compensation electric quantity |
| CN111521868A (en) * | 2020-04-28 | 2020-08-11 | 广东电网有限责任公司梅州供电局 | Method and device for screening electricity stealing users based on big metering data |
| CN111652761A (en) * | 2020-07-28 | 2020-09-11 | 国网江西省电力有限公司供电服务管理中心 | Multi-source feature fusion electricity stealing behavior detection method based on evidence theory |
| CN111797143A (en) * | 2020-07-07 | 2020-10-20 | 长沙理工大学 | Aquaculture industry electricity stealing detection method based on electricity consumption statistical distribution skewness coefficient |
| CN112183634A (en) * | 2020-09-29 | 2021-01-05 | 国网山东省电力公司冠县供电公司 | User demand response method, device, terminal and storage medium |
| CN112650785A (en) * | 2020-12-18 | 2021-04-13 | 云南电网有限责任公司 | Metering abnormal data identification method and system |
| CN113449795A (en) * | 2021-06-29 | 2021-09-28 | 国网北京市电力公司 | Power utilization data processing method and device and electronic equipment |
| CN113552528A (en) * | 2021-06-29 | 2021-10-26 | 国网上海市电力公司 | Transformer substation bus unbalance rate abnormity analysis method based on improved genetic algorithm |
| CN113884734A (en) * | 2021-10-27 | 2022-01-04 | 广东电网有限责任公司 | Non-invasive electricity utilization abnormity diagnosis method and device |
| CN114330583A (en) * | 2021-12-31 | 2022-04-12 | 四川大学 | Abnormal electricity utilization identification method and abnormal electricity utilization identification system |
| CN114325555A (en) * | 2022-01-04 | 2022-04-12 | 国网上海市电力公司 | Metering equipment abnormity on-line monitoring model and error calculation method |
| CN114935697A (en) * | 2022-07-25 | 2022-08-23 | 广东电网有限责任公司佛山供电局 | Three-phase load unbalance identification method, system, equipment and medium |
| CN116304537B (en) * | 2023-04-27 | 2023-08-22 | 青岛鼎信通讯股份有限公司 | Electricity larceny user checking method based on intelligent measuring terminal |
| CN113884734B (en) * | 2021-10-27 | 2024-04-19 | 广东电网有限责任公司 | Non-invasive electricity consumption abnormality diagnosis method and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103914558A (en) * | 2014-04-16 | 2014-07-09 | 中南大学 | Method for mining space-time aggregation patterns of meteorological elements on basis of space-time statistics |
| CN104574202A (en) * | 2014-12-09 | 2015-04-29 | 国网青海省电力公司经济技术研究院 | Analysis method of output characteristic of wind power plant |
| CN106250927A (en) * | 2016-07-29 | 2016-12-21 | 国网河南省电力公司电力科学研究院 | Power distribution network topological structure method of calibration based on k arest neighbors sorting algorithm |
| CN106327356A (en) * | 2016-08-01 | 2017-01-11 | 国家电网公司 | Data mining-based power distribution network fault precise localization method |
| EP3118645A1 (en) * | 2015-07-16 | 2017-01-18 | LSIS Co., Ltd. | System for correcting error |
| CN106409091A (en) * | 2016-12-05 | 2017-02-15 | 浙江舟山海洋输电研究院有限公司 | Method and system for realizing troubleshooting simulation of secondary circuit simulated fault in electric power system |
-
2017
- 2017-05-31 CN CN201710398830.8A patent/CN107220906B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103914558A (en) * | 2014-04-16 | 2014-07-09 | 中南大学 | Method for mining space-time aggregation patterns of meteorological elements on basis of space-time statistics |
| CN104574202A (en) * | 2014-12-09 | 2015-04-29 | 国网青海省电力公司经济技术研究院 | Analysis method of output characteristic of wind power plant |
| EP3118645A1 (en) * | 2015-07-16 | 2017-01-18 | LSIS Co., Ltd. | System for correcting error |
| CN106250927A (en) * | 2016-07-29 | 2016-12-21 | 国网河南省电力公司电力科学研究院 | Power distribution network topological structure method of calibration based on k arest neighbors sorting algorithm |
| CN106327356A (en) * | 2016-08-01 | 2017-01-11 | 国家电网公司 | Data mining-based power distribution network fault precise localization method |
| CN106409091A (en) * | 2016-12-05 | 2017-02-15 | 浙江舟山海洋输电研究院有限公司 | Method and system for realizing troubleshooting simulation of secondary circuit simulated fault in electric power system |
Cited By (50)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108020752B (en) * | 2017-11-10 | 2020-03-27 | 国网浙江省电力公司电力科学研究院 | Distribution line loss diagnosis method and system based on multi-source through correlation |
| CN108020752A (en) * | 2017-11-10 | 2018-05-11 | 国网浙江省电力公司电力科学研究院 | A kind of distribution line loss diagnostic method and system based on multi-source perforation correlation |
| CN108062616A (en) * | 2017-11-20 | 2018-05-22 | 国网福建省电力有限公司 | A kind of multiplexing electric abnormality detection model with constraints |
| CN108062616B (en) * | 2017-11-20 | 2024-01-23 | 国网福建省电力有限公司 | Electricity consumption anomaly detection system with constraint conditions |
| CN108256752A (en) * | 2018-01-02 | 2018-07-06 | 北京市燃气集团有限责任公司 | A kind of analysis method of gas user gas behavior |
| CN108535599A (en) * | 2018-04-16 | 2018-09-14 | 国网河南省电力公司电力科学研究院 | Low-voltage platform area user's phase recognition methods based on voltage curve clustering |
| CN108776276B (en) * | 2018-06-29 | 2020-11-13 | 合肥工业大学 | Power consumption abnormity detection method and system |
| CN108776276A (en) * | 2018-06-29 | 2018-11-09 | 合肥工业大学 | Multiplexing electric abnormality detection method and system |
| CN108828375B (en) * | 2018-08-17 | 2020-08-14 | 国网江苏省电力有限公司电力科学研究院 | Air conditioner electric monitoring system and method based on double-loop intelligent electric energy meter |
| CN108828375A (en) * | 2018-08-17 | 2018-11-16 | 国网江苏省电力有限公司电力科学研究院 | Air conditioning electricity monitoring system and monitoring method based on two-loop intelligent electric energy meter |
| CN109493249A (en) * | 2018-11-05 | 2019-03-19 | 北京邮电大学 | A kind of analysis method of electricity consumption data on Multiple Time Scales |
| CN109493249B (en) * | 2018-11-05 | 2021-11-12 | 北京邮电大学 | Analysis method of electricity consumption data on multiple time scales |
| CN109446193A (en) * | 2018-11-13 | 2019-03-08 | 国网宁夏电力有限公司电力科学研究院 | It opposes electricity-stealing model generating method and device |
| CN109634944A (en) * | 2018-12-05 | 2019-04-16 | 贵州电网有限责任公司凯里供电局 | A kind of network loss data cleaning method based on various dimensions space-time analysis |
| CN109634944B (en) * | 2018-12-05 | 2022-11-04 | 贵州电网有限责任公司 | Network loss data cleaning method based on multi-dimensional space-time analysis |
| CN109636667A (en) * | 2018-12-07 | 2019-04-16 | 国网江苏省电力有限公司扬州供电分公司 | A kind of low-voltage customer multiplexing electric abnormality detection method based on user's week electrical feature |
| CN109655664A (en) * | 2018-12-11 | 2019-04-19 | 全球能源互联网研究院有限公司 | A kind of stealing intelligent diagnosing method and equipment based on load characteristic model library |
| CN109725219A (en) * | 2018-12-29 | 2019-05-07 | 重庆邮电大学 | A kind of electric energy meter platform area automatic identifying method |
| CN109738723A (en) * | 2018-12-29 | 2019-05-10 | 重庆邮电大学 | A kind of electric energy meter three-phase automatic identification method |
| CN110070256B (en) * | 2019-02-28 | 2023-12-08 | 国网浙江省电力有限公司 | Zero-power user investigation priority weight calculation method based on CRITIC method |
| CN110070256A (en) * | 2019-02-28 | 2019-07-30 | 国网浙江省电力有限公司 | Zero power user based on CRITIC method checks priority weighing computation method |
| CN109918365A (en) * | 2019-03-01 | 2019-06-21 | 河海大学常州校区 | A kind of data cleaning method suitable for photovoltaic data |
| CN110276511A (en) * | 2019-04-16 | 2019-09-24 | 国网浙江海盐县供电有限公司 | A kind of line change relationship anomalous discrimination method based on electricity and line loss relevance |
| CN110311709A (en) * | 2019-06-10 | 2019-10-08 | 国网浙江省电力有限公司嘉兴供电公司 | Power information acquisition system fault distinguishing method |
| CN110321934A (en) * | 2019-06-12 | 2019-10-11 | 深圳供电局有限公司 | A kind of method and system detecting user power utilization abnormal data |
| CN110503111B (en) * | 2019-08-23 | 2022-04-15 | 江苏方天电力技术有限公司 | Power utilization abnormal behavior visual monitoring method based on RGB color mode |
| CN110503111A (en) * | 2019-08-23 | 2019-11-26 | 江苏方天电力技术有限公司 | A kind of multiplexing electric abnormality behavior method for visually monitoring based on rgb color mode |
| CN110930034B (en) * | 2019-11-22 | 2022-12-02 | 广东电力交易中心有限责任公司 | Electric power spot market settlement metering data verification method, device and medium |
| CN110930034A (en) * | 2019-11-22 | 2020-03-27 | 广东电力交易中心有限责任公司 | Electric power spot market settlement metering data verification method, device and medium |
| CN111007337B (en) * | 2019-12-04 | 2023-12-19 | 河南昊晟电子科技有限公司 | Intelligent monitoring and information transmission system for safe production electricity consumption |
| CN111007337A (en) * | 2019-12-04 | 2020-04-14 | 河南昊晟电子科技有限公司 | Intelligent power consumption monitoring and information transmission system for safety production |
| CN111444241A (en) * | 2020-03-26 | 2020-07-24 | 南京工程学院 | Data mining-based accurate positioning method for line loss abnormity associated users of distribution room |
| CN111443237A (en) * | 2020-04-20 | 2020-07-24 | 北京中电普华信息技术有限公司 | Method and system for determining compensation electric quantity |
| CN111521868A (en) * | 2020-04-28 | 2020-08-11 | 广东电网有限责任公司梅州供电局 | Method and device for screening electricity stealing users based on big metering data |
| CN111797143A (en) * | 2020-07-07 | 2020-10-20 | 长沙理工大学 | Aquaculture industry electricity stealing detection method based on electricity consumption statistical distribution skewness coefficient |
| CN111797143B (en) * | 2020-07-07 | 2023-12-15 | 长沙理工大学 | Aquaculture electricity larceny detection method based on electricity consumption statistical distribution skewness coefficient |
| CN111652761A (en) * | 2020-07-28 | 2020-09-11 | 国网江西省电力有限公司供电服务管理中心 | Multi-source feature fusion electricity stealing behavior detection method based on evidence theory |
| CN112183634A (en) * | 2020-09-29 | 2021-01-05 | 国网山东省电力公司冠县供电公司 | User demand response method, device, terminal and storage medium |
| CN112650785A (en) * | 2020-12-18 | 2021-04-13 | 云南电网有限责任公司 | Metering abnormal data identification method and system |
| CN112650785B (en) * | 2020-12-18 | 2023-05-26 | 云南电网有限责任公司 | Metering abnormal data identification method and system |
| CN113552528A (en) * | 2021-06-29 | 2021-10-26 | 国网上海市电力公司 | Transformer substation bus unbalance rate abnormity analysis method based on improved genetic algorithm |
| CN113449795A (en) * | 2021-06-29 | 2021-09-28 | 国网北京市电力公司 | Power utilization data processing method and device and electronic equipment |
| CN113884734A (en) * | 2021-10-27 | 2022-01-04 | 广东电网有限责任公司 | Non-invasive electricity utilization abnormity diagnosis method and device |
| CN113884734B (en) * | 2021-10-27 | 2024-04-19 | 广东电网有限责任公司 | Non-invasive electricity consumption abnormality diagnosis method and device |
| CN114330583B (en) * | 2021-12-31 | 2022-11-08 | 四川大学 | Abnormal electricity utilization identification method and abnormal electricity utilization identification system |
| CN114330583A (en) * | 2021-12-31 | 2022-04-12 | 四川大学 | Abnormal electricity utilization identification method and abnormal electricity utilization identification system |
| CN114325555B (en) * | 2022-01-04 | 2023-11-14 | 国网上海市电力公司 | Metering equipment abnormality online monitoring model and error calculation method |
| CN114325555A (en) * | 2022-01-04 | 2022-04-12 | 国网上海市电力公司 | Metering equipment abnormity on-line monitoring model and error calculation method |
| CN114935697A (en) * | 2022-07-25 | 2022-08-23 | 广东电网有限责任公司佛山供电局 | Three-phase load unbalance identification method, system, equipment and medium |
| CN116304537B (en) * | 2023-04-27 | 2023-08-22 | 青岛鼎信通讯股份有限公司 | Electricity larceny user checking method based on intelligent measuring terminal |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107220906B (en) | 2019-10-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107220906B (en) | Multiple Time Scales multiplexing electric abnormality analysis method based on electricity consumption acquisition system | |
| CN107340492B (en) | Electric energy metering device fault analysis method based on big data mining and scene pre-judgment | |
| CN111505433B (en) | Low-voltage transformer area indoor variable relation error correction and phase identification method | |
| CN106338706A (en) | Electric energy metering device overall error detecting method, device and system | |
| CN110634080A (en) | Abnormal electricity utilization detection method, device, equipment and computer readable storage medium | |
| CN106338705A (en) | Error verifying method and device for three-phase electric energy metering device | |
| CN107328974B (en) | Electricity stealing identification method and device | |
| CN108734602B (en) | User electricity stealing behavior identification system based on high-dimensional random matrix | |
| CN113435610B (en) | Method for determining classified line loss based on low-voltage internet of things sensing terminal | |
| CN107589391A (en) | A kind of methods, devices and systems for detecting electric power meter global error | |
| CN111177208A (en) | Power consumption abnormity detection method based on big data analysis | |
| Jiao et al. | Data-driven evaluation for error states of standard electricity meters on automatic verification assembly line | |
| CN109142830A (en) | Stealing detection method based on power information acquisition system big data | |
| CN114240041A (en) | Lean line loss analysis method and system for distribution network distribution area | |
| CN106709623B (en) | Power grid marketing inspection risk control method based on risk calculation model | |
| CN112418687A (en) | User electricity utilization abnormity identification method and device based on electricity utilization characteristics and storage medium | |
| CN112182499A (en) | Low-voltage distribution network topological structure identification method based on time sequence electric quantity data | |
| CN111366889A (en) | Abnormal electricity utilization detection method for intelligent electric meter | |
| CN109784777B (en) | Power grid equipment state evaluation method based on time sequence information fragment cloud similarity measurement | |
| CN107328994A (en) | Insulation Resistance of Transformer experimental rig and method | |
| CN112015724A (en) | Method for analyzing metering abnormality of electric power operation data | |
| CN114066219A (en) | Electricity stealing analysis method for intelligently identifying electricity utilization abnormal points under incidence matrix | |
| CN114065129A (en) | Line-variable relation detection method and detection system based on spectral clustering method | |
| Li | Abnormal energy consumption analysis based on big data mining technology | |
| CN114024308A (en) | Power distribution network platform relationship identification method and system |
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 |