CN105573997A - Method and device for determining electric larceny suspect user - Google Patents
Method and device for determining electric larceny suspect user Download PDFInfo
- Publication number
- CN105573997A CN105573997A CN201410527637.6A CN201410527637A CN105573997A CN 105573997 A CN105573997 A CN 105573997A CN 201410527637 A CN201410527637 A CN 201410527637A CN 105573997 A CN105573997 A CN 105573997A
- Authority
- CN
- China
- Prior art keywords
- user
- neural network
- stealing suspicion
- stealing
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses a method and device for determining an electric larceny suspect user. The method comprises the following steps of 1, building an expert sample library according to the historical electricity use data of a user, wherein sample data included in the expert sample library includes historical electricity use data of the user and an electric larceny suspect coefficient; 2, optimizing a weight sequence of a BP (Back Propagation) neural network model by using a genetic algorithm, and obtaining the optimized BP neural network model; 3, training the BP neural network model by using the sample data included in the expert sample library; 4, analyzing the electricity use data to be analyzed of the user according to the trained BP neural network model, and determining the electric larceny suspect coefficient of the user according to the analysis result; and 5, determining the electric larceny suspect user according to the electric larceny suspect coefficient. The electric larceny suspect user can be efficiently, conveniently and fast recognized.
Description
Technical field
The embodiment of the present invention relates to power domain, particularly relates to a kind of method and the device of determining stealing suspicion user.
Background technology
At power domain, electricity filching behavior is allow the problem of power supply enterprise's headache always.Various electricity filching behavior constantly renovates, power supply enterprise is made to have to immediately following the paces of electricity filching person, constantly improving Prevention Stealing Electricity Technology always, but, the progress of Prevention Stealing Electricity Technology lags behind the development of electricity filching behavior all the time, always after new stealing electricity method occurs, just propose solution in the mode of mending the fold after the sheep is lost, power supply enterprise is in passive status all the time.
Analyze from the technology of electric energy metrical, electric energy meter is divided into several important component parts such as potential winding, current coil, disk, magnet steel, register.Want stealing, if change the input voltage of electric energy meter, electric current, phase place and rotating speed etc. any one, the ultimate principle of stealing that Here it is.Current stealing electricity method realizes mainly for above factor, specifically has several as follows:
1) under-voltage method stealing.
So-called under-voltage method stealing refers to that electricity filching person adopts and deliberately causes metered voltage loop to open a way or loose contact, or change the normal wiring in metered voltage loop, or at potential winding circuit in series resistance etc., make metered voltage loop obstacle, thus make the potential winding decompression of electric energy meter or rated voltage reduce the method finally causing electric energy meter to be disregarded or lack quantity calculation.Gimmick is commonly used in under-voltage method stealing to be had: (1) uses voltage backflow open circuit; (2) voltage circuit loose contact fault is caused; (3) resistance step-down is sealed in; (4) circuit connecting is changed.
2) undercurrent method stealing.
The stealing of so-called undercurrent method, refer to that electricity filching person adopts the mode of connection or manufacture current return fault changing current return someway, thus reach and hinder electric current by the current coil in electric energy meter or only make a small amount of electric current by its current coil, and the method that the galvanometer amount on electric energy meter that finally realizes diminishes.Gimmick is commonly used in the stealing of undercurrent method to be had: (1) makes current return open a way; (2) short circuit current loop; (3) no-load voltage ratio of TA is changed; (4) circuit connecting is changed.
3) phase-shifting method stealing.
So-called phase-shifting method stealing, refer to that electricity filching person adopts various gimmick deliberately to change the normal wiring of electric energy meter or access and electric energy meter coil without voltage, the electric current of electrical communication, the specific connection that then can utilize inductance, electric capacity also had, thus the normal phase relation changed in electric energy meter coil between voltage, electric current, finally cause the stealing electricity method that electric energy meter slow-speed is even reversed.Gimmick is commonly used in phase-shifting method stealing to be had: (1) changes the wiring of current return; (2) wiring of voltage circuit is changed: (3) are with current transformer or supplementary transformer electric current; (4) with external power source, ammeter is reversed; (5) after not having the step-up transformer of electrical communication certain phase voltage to be raised with first and second side, anti-phase adding shows tail zero line; (6) with inductance or electric capacity phase shift.
4) stealing of difference method is expanded.
The stealing of so-called expansion difference method refers to, ammeter is torn in electricity filching person private open, by the inner structure performance adopting various gimmick to change electric energy meter, causes the Enlarging-Errors of ammeter itself; Or utilize mechanical force or circuit damage ammeter, change the mounting condition of ammeter, make the method that reometer is counted less.The gimmick expanding the stealing of difference method conventional has: ammeter is torn in (1) private open, changes the structural behaviour of ammeter inside; (2) ammeter is damaged by big current or mechanical force; (3) mounting condition of ammeter is changed.
5) without the stealing of table method.
The stealing of so-called nothing table method refers to, end through applying to install just wiring electricity consumption on the circuit of power supply department privately of registering one's residence, or has table user privately to get rid of the stealing electricity method showing electricity consumption.This kind of stealing electricity method and aforementioned four classes are being distinguished in nature to some extent, front four class gimmicks are belong to catlike electricity filching behavior substantially, without the electricity filching behavior that the stealing of table method is then brazenly with plundering character, and its harmfulness is also larger, the electricity of power supply department is not only caused to damage husband, upset, destroy supply order, and easily cause personal injury and cause fire etc.Meanwhile, without table method stealing, society is made or negative effect also larger, also may play the effect of adding fuel to the flames to other electricity filching behavior.
Corresponding with above-mentioned stealing electricity method, the technical measures of opposing electricity-stealing at present mainly contain below that these are several:
1) Special metering cabinet (case) is adopted to add the mode of lead sealing.This is major way anti-electricity-theft traditionally.As sealed up common lead sealing on table cover, terminal box, metering cabinet (case) door; High-low pressure metering cabinet, electric energy metering box.The shortcoming of this mode is that common lead sealing is easily opened rear recovery by electricity filching person, also easily counterfeit.
2) false proof and anti-electricity-theft mode that is anti-picking lead sealing is adopted.Difference in this anti-electricity-theft mode is mainly enclosed in false proof, pick-proof ability for common lead and design.Can being printed on the lead sealing cap sleeve of printed words of power supply enterprise in lead sealing, lead sealing numbering indicates obviously, and during installation, installation personnel and numbering are put on record, in order to increase the counterfeit difficulty of electricity filching person.Advantage is: because lead sealing cap is coarctate with lead sealing, opens lead sealing and is certain to damage lead sealing cap, proof electricity filching behavior that can be favourable.Shortcoming is: accurately can not prove power-steeling quantity and stealing time.
3) high-order installation electric energy meter.After electric energy meter is arranged on eminence, stealing people wants stealing just must climb up on the electric pole of several meters high, is easily found.But this mode brings larger trouble to checking meter.
4) high-voltage electric energy meter is adopted.Advantage is: only otherwise power failure people is difficult to close to high-voltage electric energy meter.Shortcoming is: to check meter and periodic inspection make troubles.
5) anti-electricity-theft electric energy meter is adopted.The shortcoming of this mode is that anti-stealing electricity function is single, is mainly used on single-phase electric energy meter.
6) network monitoring remote meter reading is adopted.The electric energy meter with remote meter-reading function is arranged on electricity consumption side and the mains side of every bar distribution line, check meter, the power supply of same time period and power consumption are by statistic computation simultaneously, then compare with theory wire loss, when occurring abnormal, prove to there is measurement problem, then investigate pointedly.The advantage of this mode is: be conducive to the management level improving Controlling line loss, spatial load forecasting and distribution.Shortcoming is: because user on each distribution line is many, therefore will find concrete stealing point workload larger.
7) electronics seal is adopted.The advantage of this method is: if illegally open Special metering cabinet (case), controller can disconnect power supply automatically, records trip time simultaneously, this adds increased stealing difficulty.And if electricity filching person is attempted to destroy note amount device and just can be left stealing time evidence.Shortcoming is: can reduce power supply reliability if be interfered.
8) installing measuring apparatus fault note, to record instrument anti-electricity-theft.The advantage of this mode is: when electricity filching person attempt by change secondary circuit make the voltage of access electric energy meter, electric current, phasing degree change time, it can automatically record stealing occur time and leak meter electricity.If only change electric energy meter, the electricity that can record with registering instrument is inconsistent, thus pinpoints the problems.Shortcoming is: as changed the no-load voltage ratio of current transformer, just can not identify.
Known by analyzing above, the measures of anti-stealing electricity generally adopted at present, all more or less there is defect and deficiency.First, the measures such as the seal of metering cabinet (case) are not perfectly safe, cannot thorough pick-proof or ensure power supply reliability; In addition, first find suspicious stealing user by the mode of manually patrolling, and then hardware unit of opposing electricity-stealing accordingly is installed monitors, this original pattern of manually opposing electricity-stealing, a large amount of electricity filching persons must be caused to be called fish that has escape the net, and what be found is probably minority; But also expensive hardware cost of opposing electricity-stealing will be paid.
Therefore, in the urgent need to a kind of technology that efficiently can identify stealing suspicion user easily.
Summary of the invention
The invention provides a kind of method and the device of determining stealing suspicion user, to realize efficiently identifying easily stealing suspicion user.
First aspect, embodiments provides a kind of method determining stealing suspicion user, comprising:
S1, history electricity consumption data construct expert sample bank according to user, the sample data that described expert sample bank comprises comprises history electricity consumption data and the stealing suspicion coefficient of user;
The weights sequence of S2, employing genetic algorithm optimization BP neural network model, the BP neural network model be optimized;
S3, the sample data comprised in described expert sample bank is used to train described BP neural network model;
S4, according to training after BP neural network model to the electricity consumption data analysis to be analyzed of user, determine the stealing suspicion coefficient of user according to analysis result;
S5, according to described stealing suspicion coefficient determination stealing suspicion user.
Second aspect, the embodiment of the present invention additionally provides a kind of device determining stealing suspicion user, comprising:
Sample Storehouse construction unit, for the history electricity consumption data construct expert sample bank according to user, the sample data that described expert sample bank comprises comprises history electricity consumption data and the stealing suspicion coefficient of user;
Model optimization unit, for adopting the weights sequence of genetic algorithm optimization BP neural network model, the BP neural network model be optimized;
Training unit, trains described BP neural network model for using the sample data comprised in described expert sample bank;
Stealing suspicion factor determination unit, for according to training after BP neural network model to the electricity consumption data analysis to be analyzed of user, determine the stealing suspicion coefficient of user according to analysis result;
Stealing suspicion user determining unit, for according to described stealing suspicion coefficient determination stealing suspicion user.
The technical scheme of the embodiment of the present invention is by implying excavation and the study of rule to magnanimity electricity consumption historical data, dope the stealing suspicion coefficient of user, navigate to the user of stealing suspicion fast and accurately, greatly can improve existing efficiency of opposing electricity-stealing, improve the accuracy of opposing electricity-stealing, in the marketing inspection that can be widely used in power supply enterprise and work of electricity anti-stealing; In addition, by improved Back Propagation, the method adopting genetic algorithm to combine with BP neural network algorithm, improves the generalization ability of traditional BP neural network, improves time span and the precision of prediction.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of the method for determination stealing suspicion user described in the embodiment of the present invention one.
Fig. 2 is the process flow diagram of the method for determination stealing suspicion user described in the embodiment of the present invention two;
Fig. 3 is the process flow diagram of the method for determination stealing suspicion user described in the embodiment of the present invention three;
Fig. 4 is the process flow diagram of the method for determination stealing suspicion user described in the embodiment of the present invention four;
Fig. 5 is the structured flowchart of the device of determination stealing suspicion user described in the embodiment of the present invention five.
Embodiment
Below in conjunction with drawings and Examples, the present invention is described in further detail.Be understandable that, specific embodiment described herein is only for explaining the present invention, but not limitation of the invention.It also should be noted that, for convenience of description, illustrate only part related to the present invention in accompanying drawing but not entire infrastructure.
Embodiment one
Fig. 1 is the process flow diagram of the method for the determination stealing suspicion user described in the embodiment of the present invention one, and the method can be performed by the device of the determination stealing suspicion user in computing machine, specifically comprises the steps:
S1, history electricity consumption data construct expert sample bank according to user, the sample data that described expert sample bank comprises comprises history electricity consumption data and the stealing suspicion coefficient of user.
The present invention is based on the large data analysis to a large amount of history electricity consumption data, therefrom excavate the related information between electricity consumption data and stealing.Therefore, first obtain the history electricity consumption data of user, build expert sample bank according to history electricity consumption data, as the basis of above-mentioned large data analysis.
Wherein, described electricity consumption data are the data that can reflect user's stealing feature.By studying the concrete service conditions of power domain, sum up the influence factor that can reflect electricity consumption behavioural characteristic, these type of data are called stealing characterization factor by the present invention.Specifically, stealing characterization factor can comprise following kind:
1) unit consumption of product
For continuous stealing family, just effect is lost to the fluction analysis of its power consumption longitudinal direction.Can by the unit consumption of product of user (unit product power consumption) for this problem, the standard of promulgating with country carries out across comparison.When consumer products unit consumption declines obvious, namely show there is exception, now should examine: whether enterprise have employed advanced equipment or technique, and causes unit consumption of product to decline, otherwise can think that it has great stealing suspicion.
Formula: unit product power consumption=user is for the production of the total electricity consumption/product population of management.
2) the convergent rate of industry
By the electricity consumption data analysis to this area every profession and trade, draw the average electricity consumption level data of industry, then the electricity consumption data of electricity consumer and industry average level data are contrasted, the convergent rate of industry is lower more at least for identical or close part.The convergent rate of industry is lower, shows multiplexing electric abnormality, there is the possibility of stealing.
3) a situation arises for alarm event
When electricity consumer carries out stealing, often along with the generation of following alarm event, below event frequency more, then stealing suspicion is larger.
A. indication declines
B. electric energy meter flies away event
C. electric energy meter stops walking event
D. voltage unbalance factor out-of-limit event
E. current unbalance factor out-of-limit event
F. voltage phase shortage event
G. electric sampling open-phase event
H. electric current reversed polarity event
4) phasing degree
Electricity filching person adopts abnormal wiring, connect people's voltage not corresponding with electric energy meter coil, electric current, or connect people's inductance or electric capacity in the line, change the normal phase relation between electric current and voltage in electric energy meter coil, cause that electric energy meter rotating speed is slack-off even to reverse, the method for this stealing is called phase angle-style stealing method.Concrete as: electric current line exchanges method, current potential height low side exchanges method, phase voltage exchanges method, line voltage exchanges method, phase current exchanges method, in-phase voltage method, in-phase current method, reactive stealing electricity method etc.
Phasing degree obtains by the arc cosine of the power factor calculating A, B, C three-phase.Angle corresponding relation is as follows:
0 < φ < 90---rotate forward;
φ=90---do not turn;
90 < φ < 270---reversion;
φ=270---do not turn;
270 < φ < 360---rotate forward.
5) power consumption
The fluctuation of power consumption judges a key index of user's stealing when changing, the steep increasing of electricity is suddenly fallen and all may be shown multiplexing electric abnormality.If the moon, electricity uprushed 50%, and the moon electricity divided by 30 days again divided by 12 hours, divided by being greater than its attaching capacity after power factor.Problem with regard to very possible private increase-volume amount exists.
6) subscribers feeder loss rate
Current period will add up line loss per unit, and and add up line loss per unit the same period last year and compare, if line loss per unit amplification is more than 10%, then be classified as stealing suspicion family.
7) imbalance of three-phase voltage rate
The fluctuation change of imbalance of three-phase voltage rate also can characterize stealing electricity phenomenon, if imbalance of three-phase voltage rate > 0.3, then illustrates and occurs extremely.
Formula: imbalance of three-phase voltage rate=(max (u) _ min (u))/max (u)
8) power factor
Power factor, for normal electricity consumer, should be the value of a relative constancy, and except non-increasing reactive-load compensation equipment, otherwise power factor should not increase.Usual standard value is 0.9, and power factor change is monthly the amplitude range of upper and lower 0.1 to 0.2.
9) contract capacity ratio
There is corresponding relation numerically the moon of the contract capacity that electricity consumer is applied for when business is applied to install and user between power consumption: if ((contract capacity × 360)/moon power consumption) > 2, then likely this user exists stealing electricity phenomenon.
Collect the history electricity consumption data of corresponding kind according to above-mentioned stealing characterization factor, collected data reflect the stealing feature of user power utilization behavior.That is, described electricity consumption data at least can comprise one or more in following data: the convergent rate of unit consumption of product, industry, a situation arises for alarm event, phasing degree, power consumption, subscribers feeder loss rate, imbalance of three-phase voltage rate, power factor, contract capacity ratio.But be not limited to above-mentioned data, other any data can reacting user's stealing feature equally also can be used as history electricity consumption data for the present invention.
In addition, in order to reflect the electricity consumption situation of user comprehensively, described electricity consumption data should contain all users, namely comprise the electricity consumption data of normal users and stealing user.
After getting the history electricity consumption data of user, build expert sample bank according to these history electricity consumption data, each sample data wherein comprised comprises input quantity, output quantity two parts.Using the input quantity of described history electricity consumption data as sample data, then, corresponding stealing suspicion coefficient is determined, in this, as the output quantity of sample data according to this input quantity.Specifically, with reference to above to the defining method of stealing characterization factor, determine corresponding stealing suspicion coefficient according to the history electricity consumption data as input quantity in this step, the output quantity of sample data can be obtained thus.Some namely sample data constitutes expert sample bank.
The weights sequence of S2, employing genetic algorithm optimization BP neural network model, the BP neural network model be optimized.
The learning process of traditional BP neural network is divided into the forward-propagating process of information and two stages of back-propagation process of error, if the signal of outside input successively processes forward direction through the neuron of input layer, hidden layer and provides result to output layer. can not get desired output at output layer, then proceed to reverse communication process, between actual value and network being exported, error returns along the path originally connect, by revising the neuronic contact weights of each layer, error is reduced, and then proceed to forward-propagating process, iterate, until error is less than specified value.Because this algorithm adopts error derivative guidance learning process, be essentially belong to local optimal searching method.Easily be absorbed in local minimum point when there is more local minimum point, and inevitably there is the contradiction between pace of learning and precision.When pace of learning is very fast, learning process easily produces vibration and is difficult to obtain accurate result, although and when pace of learning is slower result can obtain higher precision, learning cycle is oversize also impracticable.
In order to these defects of improved Back Propagation, adopt the method that genetic algorithm combines with BP neural network algorithm, improve the generalization ability of traditional BP neural network, improve time span and the precision of prediction, specifically improve one's methods as follows:
Utilize the advantage of overall importance of Genetic Algorithms (GeneticAlgorithm) to overcome the easy local convergence of error back propagation BP (BackPropagation) algorithm and to restrain slow defect.Meanwhile, the combination of GA algorithm and BP algorithm also solves this problem of approximate solution utilizing separately GA algorithm can only search out optimum solution at short notice, and the gradient descent algorithm introducing BP algorithm will avoid this phenomenon.Both combine in the mode of genetic algorithm optimization BP neural network by this method: the weighed combination first using GA algorithm optimization neural network, until the average error of fitness function reaches certain accuracy value, carry out local optimum with BP algorithm more on this basis.That is, first by the weights sequence adopting genetic algorithm optimization BP neural network model, the BP neural network model be optimized, then do further optimization with BP algorithm.
S3, the sample data comprised in described expert sample bank is used to train described BP neural network model.
The BP neural network model adopted in the present invention is a kind of machine learning having supervision, and this model adopts three-decker: input layer, hidden layer and output layer, and its action function selects non-linear S type function usually, such as, select Sigmoid function as its action function.The learning process of neural network is namely according to the connection weights of sample determination network and error and the process repeatedly revised.Through the training of a large amount of historical sample data, BP neural network model is by arbitrary correction, and the model finally obtained can reflect the rule contained in these historical sample data.That is, by the BP neural network model after training, the internal association relation between input value (history electricity consumption data) in current a large amount of historical sample data and output valve (stealing suspicion coefficient) can be described.
S4, according to training after BP neural network model to the electricity consumption data analysis to be analyzed of user, determine the stealing suspicion coefficient of user according to analysis result;
S5, according to described stealing suspicion coefficient determination stealing suspicion user.
After obtaining trained neural network model, the BP neural network model trained can be utilized electricity consumption data analysis to be analyzed, calculate the stealing suspicion coefficient of each user, and determine stealing suspicion user accordingly.Specifically, a lot of mode can be adopted realize according to stealing suspicion coefficient determination stealing suspicion user, such as, the stealing suspicion coefficient of each user can be sorted according to numerical values recited, filter out the user of the some of sequence forward (or rearward), as stealing suspicion user; Also the user corresponding to these group electricity consumption data the stealing suspicion coefficient obtained and the threshold value preset can be compared, if can be classified as stealing suspicion user by the threshold value reaching (or not reaching) default.
The technical scheme of the present embodiment, the historical data of above stealing characterization factor is obtained from power business system, by excavating scientific law between this group index and electricity consumer stealing suspicion coefficient, generate rational expert sample bank, BP neural network model is utilized to excavate non-linear rule complicated between its factor and electricity consumer stealing suspicion coefficient and learn, neural network is just become black box that one is infinitely approached this complicated Special Mapping, finally reaches the effect of prediction stealing suspicion user; In addition, be also optimized by the weights sequence of genetic algorithm to traditional BP neural network model, improve the generalization ability of traditional BP neural network model, improve time span and the precision of prediction.
Embodiment two
Fig. 2 is the process flow diagram of the method for the determination stealing suspicion user described in the embodiment of the present invention two, and the present embodiment, on the basis of above-described embodiment one, further discloses the preferred embodiment of step S2 described in embodiment one.
Specifically, comprise the following steps:
S21, the initial weight sequence of BP neural network model is generated initial population as chromosome.
Random generation one component cloth is as initial weight sequence, then real coding scheme is adopted to encode to each weights in this group, and then construct several chromosomes (each chromosome represents a kind of weights distribution of neural network), form the initial population of genetic evolution.Under network structure and the fixed prerequisite of learning rules, each chromosome just corresponding weights gets the neural network of particular value.
S22, build BP neural network according to the chromosome in described population, use the sample data in expert sample bank to train described BP neural network, calculate the error between actual Output rusults and expectation value, determine this chromosomal fitness according to error.
Chromosome is decoded, corresponding neural network is constructed according to decoded numerical value, sample data in expert sample bank is inputted this neural network, the actual Output rusults value of corresponding institute input amendment data is obtained by this neural network, then the expection calculated in this actual Output rusults value and sample data exports the error between data, determines this chromosomal fitness value according to this error.Typically, error is less, then fitness is larger, namely represents that the neural network model weights sequence representated by this chromosome is more suitable for current sample data.
S23, judge whether all chromosomal fitness all reach predetermined threshold value, if then perform step S25, otherwise perform step S24.
S24, fitness is reached to the chromosome of predetermined threshold value, by this chromosome replication to population of future generation;
For the chromosome not reaching predetermined threshold value, adopt genetic operator process current chromosome, produce new chromosome to population of future generation, re-execute step S22 to S24 for this population of future generation;
If all chromosomal fitness values all reach default requirement (such as reaching default accuracy requirement) in current population, expression can process all sample datas in expert sample bank preferably by the BP neural network model with current weight sequence, now can stop the continuation optimization of genetic algorithm to weights sequence.Otherwise, fitness is reached to the chromosome of predetermined threshold value, represent that the weights sequence that this chromosome is corresponding meets the demands, therefore this chromosome is directly copied to population of future generation (individuality specified number that fitness value is maximum can also be selected herein, directly copy to population of future generation); And for the chromosome that fitness does not reach predetermined threshold value or do not satisfy specified requirement, then adopt genetic operator process current chromosome, produce new chromosome and be saved to population of future generation.Described genetic operator can adopt following at least one: selection opertor, crossover operator, mutation operator.The specific implementation of these operators, with reference to existing implementation, does not repeat them here.
Namely this population of future generation is by the of future generation chromosome population of genetic algorithm optimization process through evolution, there occurs change, may be better than the chromosome of previous generation compared to its chromosome of previous generation population through the process of genetic operator.Next, continue to perform step S22-S24, till in current population, all chromosomal fitness values all meet the requirement preset to the population of future generation through genetic evolution.
S25, using the weights sequence of the chromosome of current population as described BP neural network, according to described weights sequence pair, BP neural network model is optimized.
Chromosome after step S22-S24 optimizes represents that the BP neural network model with current weight sequence can process all sample datas in expert sample bank preferably, therefore, using the weights sequence of the chromosome of current population as BP neural network, thus obtain the BP neural network model through genetic algorithm optimization.
Be optimized by the weights sequence of genetic algorithm to traditional BP neural network model, effectively overcome the problem that traditional BP neural network model is easily absorbed in local minimum point, taken into account overall calculation speed and the computational accuracy of algorithm simultaneously.
Embodiment three
Fig. 3 is the process flow diagram of the method for determination stealing suspicion user described in the embodiment of the present invention three, and the present embodiment, on the basis of above-described embodiment one or two, increased data prediction step Sa before step S1.
As shown in Figure 3, step Sa comprises: carry out the described history electricity consumption data of user.Such as, can perform in following operation one or more: missing values process, outlier processing, normalized.
In view of the original electricity consumption data gathered from various power business system may exist partial data disappearance, exceed the phenomenons such as normal zone of reasonableness, form be lack of standardization and inconsistent, for the ease of the process of follow-up flow process, pretreatment operation can be carried out to the original electricity consumption data collected, may carry out correcting and processing by Problems existing in raw data.Such as, for the problem of partial data disappearance, the part of completion disappearance can be carried out according to information such as the attribute information of user, history electricity consumption data record, averages of the same trade, make data relatively reasonable and complete; For the data not in normal range, abnormal data is corrected according to its upper limit, lower limit or intermediate value according to normal data area; Lack of standardization for form, inconsistent data, according to the unified standard preset, data are standardized and normalized, such as, stealing suspicion factor data value pointed in embodiment one is all transformed into [0,1], in interval, its concrete conversion regime can adopt following formula:
In formula, the maximal value of Xmax representative data variation range, the minimum value of Xmin representative data variation range, Xi is data to be converted.
In addition, similar data prediction step Sb can also be increased for electricity consumption data to be analyzed before step S 4, namely one or more in following operation be performed to described electricity consumption data to be analyzed: missing values process, outlier processing, normalized.
It is pointed out that kind of the pretreatment mode of three described in the present embodiment is only exemplary, according to the needs of actual conditions, other pretreatment modes of any necessity all can adopt, within the protection domain being all included in the present embodiment.In addition, pre-treatment step Sa and Sb can individualism, also can exist simultaneously, can determine according to actual conditions.Such as, if provide the in-let dimple specification of himself image data of power business system of electricity consumption data strict, or, although do not control especially data acquisition entrance, but after data enter system, carry out follow-up Optimat operation, so in this case without the need to the pre-treatment step described in the present embodiment; Otherwise, if the data in power business system do not carry out specification all the time, so just need to be unified data by the pretreatment operation of the present embodiment and standardize.
The technical scheme of the present embodiment, by performing pretreatment operation to electricity consumption data, can obtain electricity consumption data that are unified, specification, the continuation process for subsequent step provides the Data Source of high-quality.
Embodiment four
Fig. 4 is the process flow diagram of the method for the determination stealing suspicion user described in the embodiment of the present invention four, and the present embodiment, on the basis of above-described embodiment one, further increases model Optimization Steps S6 more after step s 5.
As shown in Figure 4, step S6 comprises: add in expert sample bank using the electricity consumption data of determined stealing suspicion user as sample data, and the model training then using new data of adding again to perform described in step S3 operates.
BP neural network model is a learning model can optimized along with the renewal of sample constantly circulation evolution, previous model prediction result is proceeded training as new sample to model, circulates and so forth and just can obtain the neural network model of unlimited approaching to reality situation.In the present embodiment, after previous step S5 utilizes neural network model to obtain preliminary predicting the outcome, using electricity consumption data to be analyzed and the stealing suspicion coefficient that obtains as the input quantity of training sample and output quantity, thus obtain a new training sample, then this training sample is introduced expert sample bank, new samples is utilized again to carry out training optimization to model, the incidence relation between input quantity and output quantity new model after training being reflected comprise in new samples, thus more close to reality.Along with continuous use and the evolution of neural network model, its prediction effect is more and more accurate, and the confidence level of its result is more and more higher.
The technical scheme of the present embodiment, introduces BP neural network model evolutionary mechanism, and reached the effect in the unlimited approaching to reality world by self-recision and study, the identification for stealing suspicion user provides strong instrument.
Embodiment five
Fig. 5 is the structured flowchart of the device of determination stealing suspicion user described in the embodiment of the present invention five, and as shown in Figure 5, the device of the determination stealing suspicion user described in the present embodiment specifically comprises:
Sample Storehouse construction unit 501, for the history electricity consumption data construct expert sample bank according to user, the sample data that described expert sample bank comprises comprises history electricity consumption data and the stealing suspicion coefficient of user;
Model optimization unit 502, for adopting the weights sequence of genetic algorithm optimization BP neural network model, the BP neural network model be optimized;
Training unit 503, trains described BP neural network model for using the sample data comprised in described expert sample bank;
Stealing suspicion factor determination unit 504, for according to training after BP neural network model to the electricity consumption data analysis to be analyzed of user, determine the stealing suspicion coefficient of user according to analysis result;
Stealing suspicion user determining unit 505, for according to described stealing suspicion coefficient determination stealing suspicion user.
Further, described model optimization unit 502 specifically for:
The initial weight sequence of BP neural network model is generated initial population as chromosome;
Build BP neural network according to each chromosome in described population, use the sample data in expert sample bank to train this BP neural network described, calculate the error between actual Output rusults and expectation value, determine this chromosomal fitness according to error;
Judge whether that all chromosomal fitness all reach predetermined threshold value, if then perform the last operation be optimized, otherwise: chromosome fitness being reached to predetermined threshold value, by this chromosome replication to population of future generation; For the chromosome not reaching predetermined threshold value, adopt genetic operator process current chromosome, produce new chromosome to population of future generation;
Re-execute for this population of future generation and above-mentionedly determine the operation of fitness and the operation of judgement;
Using the weights sequence of the chromosome of current population as described BP neural network, what be optimized according to described weights sequence is optimized described BP neural network model.
Further, the genetic operator that described model optimization unit 502 adopts comprises following at least one: selection opertor, crossover operator and mutation operator.
Further, described stealing suspicion factor determination unit 504 comprises according to described stealing suspicion coefficient determination stealing suspicion user:
Clooating sequence according to described stealing suspicion coefficient determines that corresponding user is stealing suspicion user; Or
Determine that corresponding user is stealing suspicion user according to described stealing suspicion coefficient to the comparison of predetermined threshold value.
Further, described device also comprises historical data pretreatment unit, for carrying out missing values process, outlier processing and/or normalized to history electricity consumption data.
Further, described device also comprises electricity consumption data pre-processing unit to be analyzed, for carrying out missing values process, outlier processing and/or normalized to described electricity consumption data to be analyzed.
Further, described device also comprises model and optimizes unit again, for adding in described expert sample bank using stealing suspicion factor determination unit determined stealing suspicion coefficient as sample data, new data of adding then are used again to perform described training and operation by training unit.
Further, described electricity consumption data are the data that can reflect user's stealing feature, comprise one or more in following data: the convergent rate of unit consumption of product, industry, a situation arises for alarm event, phasing degree, power consumption, subscribers feeder loss rate, imbalance of three-phase voltage rate, power factor, contract capacity ratio.
The device of the determination stealing suspicion user that the present embodiment provides can perform the method for the determination stealing suspicion user that the embodiment of the present invention one, embodiment two, embodiment three and embodiment four provide, and possesses the corresponding functional module of manner of execution and beneficial effect.
Note, above are only preferred embodiment of the present invention and institute's application technology principle.Skilled person in the art will appreciate that and the invention is not restricted to specific embodiment described here, various obvious change can be carried out for a person skilled in the art, readjust and substitute and can not protection scope of the present invention be departed from.Therefore, although be described in further detail invention has been by above embodiment, the present invention is not limited only to above embodiment, when not departing from the present invention's design, can also comprise other Equivalent embodiments more, and scope of the present invention is determined by appended right.
Claims (10)
1. determine a stealing suspicion user's method, it is characterized in that, comprising:
S1, history electricity consumption data construct expert sample bank according to user, the sample data that described expert sample bank comprises comprises history electricity consumption data and the stealing suspicion coefficient of user;
The weights sequence of S2, employing genetic algorithm optimization BP neural network model, the BP neural network model be optimized;
S3, the sample data comprised in described expert sample bank is used to train described BP neural network model;
S4, according to training after BP neural network model to the electricity consumption data analysis to be analyzed of user, determine the stealing suspicion coefficient of user according to analysis result;
S5, according to described stealing suspicion coefficient determination stealing suspicion user.
2. the method determining stealing suspicion user according to claim 1, is characterized in that, described step S2 adopts the weights sequence of genetic algorithm optimization BP neural network model, and the BP neural network model be optimized comprises:
S21, the initial weight sequence of BP neural network model is generated initial population as chromosome;
S22, build BP neural network according to the chromosome in described population, use the sample data in expert sample bank to train described BP neural network, calculate the error between actual Output rusults and expectation value, determine this chromosomal fitness according to error;
S23, judge whether that all chromosomal fitness all reach predetermined threshold value, if then perform step S25, otherwise: chromosome fitness being reached to predetermined threshold value, by this chromosome replication to population of future generation; For the chromosome not reaching predetermined threshold value, adopt genetic operator process current chromosome, produce new chromosome to population of future generation;
S24, re-execute step S22 to S24 for this population of future generation;
S25, using the weights sequence of the chromosome of current population as described BP neural network, according to described weights sequence pair, BP neural network model is optimized.
3. the method determining stealing suspicion user according to claim 2, is characterized in that, the genetic operator adopted in described step S23 comprises following at least one: selection opertor, crossover operator and mutation operator.
4. the method for the determination stealing suspicion user according to claim 1-3, is characterized in that, described step S5 comprises according to described stealing suspicion coefficient determination stealing suspicion user:
Clooating sequence according to described stealing suspicion coefficient determines that corresponding user is stealing suspicion user; Or
Determine that corresponding user is stealing suspicion user according to described stealing suspicion coefficient to the comparison of predetermined threshold value.
5. the method for the determination stealing suspicion user according to claim 1-3, is characterized in that, also comprise before described step S1: carry out the described history electricity consumption data of user
Missing values process, outlier processing and/or normalized.
6. the method for the determination stealing suspicion user according to claim 1-3, is characterized in that, also comprise before described step S4: carry out missing values process, outlier processing and/or normalized to electricity consumption data to be analyzed.
7. the method for the determination stealing suspicion user according to any one of claim 1-3, is characterized in that, after step s 5, also comprise:
The stealing suspicion coefficient determined by step S4 adds in the expert sample bank described in step S1 as sample data, and the model training then using new data of adding again to perform described in step S3 operates.
8. the method determining stealing suspicion user according to claim 1, it is characterized in that, described electricity consumption data are the data that can reflect user's stealing feature, comprise one or more in following data: the convergent rate of unit consumption of product, industry, a situation arises for alarm event, phasing degree, power consumption, subscribers feeder loss rate, imbalance of three-phase voltage rate, power factor, contract capacity ratio.
9. determine a stealing suspicion user's device, it is characterized in that, comprising:
Sample Storehouse construction unit, for the history electricity consumption data construct expert sample bank according to user, the sample data that described expert sample bank comprises comprises history electricity consumption data and the stealing suspicion coefficient of user;
Model optimization unit, for adopting the weights sequence of genetic algorithm optimization BP neural network model, the BP neural network model be optimized;
Training unit, trains described BP neural network model for using the sample data comprised in described expert sample bank;
Stealing suspicion factor determination unit, for according to training after BP neural network model to the electricity consumption data analysis to be analyzed of user, determine the stealing suspicion coefficient of user according to analysis result;
Stealing suspicion user determining unit, for according to described stealing suspicion coefficient determination stealing suspicion user.
10. the device determining stealing suspicion user according to claim 9, is characterized in that, described model optimization unit specifically for:
The initial weight sequence of BP neural network model is generated initial population as chromosome;
Build BP neural network according to each chromosome in described population, use the sample data in expert sample bank to train this BP neural network described, calculate the error between actual Output rusults and expectation value, determine this chromosomal fitness according to error;
Judge whether that all chromosomal fitness all reach predetermined threshold value, if then perform the last operation be optimized, otherwise: chromosome fitness being reached to predetermined threshold value, by this chromosome replication to population of future generation; For the chromosome not reaching predetermined threshold value, adopt genetic operator process current chromosome, produce new chromosome to population of future generation;
Re-execute for this population of future generation and above-mentionedly determine the operation of fitness and the operation of judgement;
Using the weights sequence of the chromosome of current population as described BP neural network, what be optimized according to described weights sequence is optimized described BP neural network model;
The genetic operator that described model optimization unit adopts comprises following at least one: selection opertor, crossover operator and mutation operator;
Described stealing suspicion factor determination unit comprises according to described stealing suspicion coefficient determination stealing suspicion user:
Clooating sequence according to described stealing suspicion coefficient determines that corresponding user is stealing suspicion user; Or
Determine that corresponding user is stealing suspicion user according to described stealing suspicion coefficient to the comparison of predetermined threshold value;
Described device also comprises historical data pretreatment unit, for carrying out missing values process, outlier processing and/or normalized to history electricity consumption data.
Described device also comprises electricity consumption data pre-processing unit to be analyzed, for carrying out missing values process, outlier processing and/or normalized to described electricity consumption data to be analyzed;
Described device also comprises model and optimizes unit again, for adding in described expert sample bank using stealing suspicion factor determination unit determined stealing suspicion coefficient as sample data, new data of adding then are used again to perform described training and operation by training unit;
Described electricity consumption data are the data that can reflect user's stealing feature, comprise one or more in following data: the convergent rate of unit consumption of product, industry, a situation arises for alarm event, phasing degree, power consumption, subscribers feeder loss rate, imbalance of three-phase voltage rate, power factor, contract capacity ratio.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410527637.6A CN105573997A (en) | 2014-10-09 | 2014-10-09 | Method and device for determining electric larceny suspect user |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410527637.6A CN105573997A (en) | 2014-10-09 | 2014-10-09 | Method and device for determining electric larceny suspect user |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105573997A true CN105573997A (en) | 2016-05-11 |
Family
ID=55884147
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410527637.6A Pending CN105573997A (en) | 2014-10-09 | 2014-10-09 | Method and device for determining electric larceny suspect user |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105573997A (en) |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106373025A (en) * | 2016-08-22 | 2017-02-01 | 重庆邮电大学 | Outlier detection-based real-time anti-power-theft monitoring method for power utilization information acquisition system |
| CN106680557A (en) * | 2017-01-05 | 2017-05-17 | 云南电网有限责任公司电力科学研究院 | Electricity theft prevention method based on user behavior analysis |
| CN107145966A (en) * | 2017-04-12 | 2017-09-08 | 山大地纬软件股份有限公司 | Logic-based returns the analysis and early warning method of opposing electricity-stealing of probability analysis Optimized model |
| CN107862347A (en) * | 2017-12-04 | 2018-03-30 | 国网山东省电力公司济南供电公司 | A kind of discovery method of the electricity stealing based on random forest |
| CN108490288A (en) * | 2018-03-09 | 2018-09-04 | 华南师范大学 | A kind of stealing detection method and system |
| CN108765004A (en) * | 2018-05-28 | 2018-11-06 | 贵州黔驰信息股份有限公司 | A method of user's electricity stealing is identified based on data mining |
| CN109063929A (en) * | 2018-08-29 | 2018-12-21 | 广东电网有限责任公司 | It opposes electricity-stealing analysis and early warning method, apparatus and computer readable storage medium |
| CN109213787A (en) * | 2018-11-07 | 2019-01-15 | 闫福录 | A kind of anti-electricity-theft algorithm chip and electricity anti-theft method in integration characteristic library |
| CN109214464A (en) * | 2018-09-28 | 2019-01-15 | 国网江苏省电力有限公司常州供电分公司 | A kind of doubtful stealing customer identification device and recognition methods based on big data |
| CN109307811A (en) * | 2018-08-06 | 2019-02-05 | 国网浙江省电力有限公司宁波供电公司 | A kind of user's dedicated transformer electricity consumption monitoring method excavated based on big data |
| 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 |
| CN109885559A (en) * | 2019-01-23 | 2019-06-14 | 长春工程学院 | A kind of stealing user discovery method based on the analysis of user's sample data difference characteristic |
| CN110045165A (en) * | 2018-01-15 | 2019-07-23 | 国网江苏省电力公司常州供电公司 | It is anti-specially to become user's continuous type stealing electricity method |
| CN111144540A (en) * | 2019-12-05 | 2020-05-12 | 国网山东省电力公司电力科学研究院 | Generation method of anti-electricity-stealing simulation data set |
| CN111667144A (en) * | 2020-04-30 | 2020-09-15 | 北京中电普华信息技术有限公司 | User identification method and device |
| CN108123920B (en) * | 2016-11-30 | 2020-12-29 | 中国科学院沈阳自动化研究所 | Method for detecting malicious users in neighborhood network of smart power grid based on suspected electricity stealing degree |
| CN112308124A (en) * | 2020-10-21 | 2021-02-02 | 国家电网有限公司 | Intelligent electricity larceny prevention method for electricity consumption information acquisition system |
| CN112733456A (en) * | 2021-03-17 | 2021-04-30 | 国网河南省电力公司营销服务中心 | Electricity stealing prevention behavior identification method and system |
| CN113393103A (en) * | 2021-06-03 | 2021-09-14 | 西南科技大学 | Anti-electricity-stealing system based on genetic algorithm optimization BP neural network |
| 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 |
| CN113687176A (en) * | 2021-10-25 | 2021-11-23 | 广东电网有限责任公司湛江供电局 | Deep neural network-based power consumption abnormity detection method and system |
| CN113744081A (en) * | 2021-08-23 | 2021-12-03 | 国网青海省电力公司信息通信公司 | Electricity stealing behavior analysis method |
| CN116486590A (en) * | 2023-05-10 | 2023-07-25 | 漆燕 | Ammeter data analysis system based on remote meter reading mode |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1866033A (en) * | 2005-05-20 | 2006-11-22 | 湖南泰通电力科技有限公司 | Real-time monitoring system for preventing electricity theft for power network |
| CN102866321A (en) * | 2012-08-13 | 2013-01-09 | 广东电网公司电力科学研究院 | Self-adaptive stealing-leakage prevention diagnosis method |
| CN103729746A (en) * | 2014-01-17 | 2014-04-16 | 深圳供电局有限公司 | Line loss abnormity location method and system |
| CN104036357A (en) * | 2014-06-12 | 2014-09-10 | 国家电网公司 | Analysis method for electricity stealing behavioral mode of electricity utilization of user |
-
2014
- 2014-10-09 CN CN201410527637.6A patent/CN105573997A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1866033A (en) * | 2005-05-20 | 2006-11-22 | 湖南泰通电力科技有限公司 | Real-time monitoring system for preventing electricity theft for power network |
| CN102866321A (en) * | 2012-08-13 | 2013-01-09 | 广东电网公司电力科学研究院 | Self-adaptive stealing-leakage prevention diagnosis method |
| CN103729746A (en) * | 2014-01-17 | 2014-04-16 | 深圳供电局有限公司 | Line loss abnormity location method and system |
| CN104036357A (en) * | 2014-06-12 | 2014-09-10 | 国家电网公司 | Analysis method for electricity stealing behavioral mode of electricity utilization of user |
Non-Patent Citations (4)
| Title |
|---|
| GORDON S. LINOFF: "《数据挖掘技术》", 31 March 2013, 清华大学出版社 * |
| 姚明海: ""改进的遗传算法在优化BP 网络权值中的应用"", 《计算机工程与应用》 * |
| 曹峥: ""反窃电系统的研究与应用"", 《中国优秀硕士学位论文全文数据库，工程科技II辑》 * |
| 颜声远 等，: "《人因工程与设计》", 31 January 2012, 哈尔滨工业大学出版社 * |
Cited By (32)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106373025A (en) * | 2016-08-22 | 2017-02-01 | 重庆邮电大学 | Outlier detection-based real-time anti-power-theft monitoring method for power utilization information acquisition system |
| CN106373025B (en) * | 2016-08-22 | 2019-07-19 | 重庆邮电大学 | Power information acquisition system based on outlier detection anti-electricity-theft monitoring method in real time |
| CN108123920B (en) * | 2016-11-30 | 2020-12-29 | 中国科学院沈阳自动化研究所 | Method for detecting malicious users in neighborhood network of smart power grid based on suspected electricity stealing degree |
| CN106680557A (en) * | 2017-01-05 | 2017-05-17 | 云南电网有限责任公司电力科学研究院 | Electricity theft prevention method based on user behavior analysis |
| CN107145966A (en) * | 2017-04-12 | 2017-09-08 | 山大地纬软件股份有限公司 | Logic-based returns the analysis and early warning method of opposing electricity-stealing of probability analysis Optimized model |
| CN107862347A (en) * | 2017-12-04 | 2018-03-30 | 国网山东省电力公司济南供电公司 | A kind of discovery method of the electricity stealing based on random forest |
| CN110045165B (en) * | 2018-01-15 | 2021-03-30 | 国网江苏省电力公司常州供电公司 | Anti-private transformer user continuous electricity stealing method |
| CN110045165A (en) * | 2018-01-15 | 2019-07-23 | 国网江苏省电力公司常州供电公司 | It is anti-specially to become user's continuous type stealing electricity method |
| CN108490288B (en) * | 2018-03-09 | 2019-04-16 | 华南师范大学 | A kind of stealing detection method and system |
| CN108490288A (en) * | 2018-03-09 | 2018-09-04 | 华南师范大学 | A kind of stealing detection method and system |
| CN108765004A (en) * | 2018-05-28 | 2018-11-06 | 贵州黔驰信息股份有限公司 | A method of user's electricity stealing is identified based on data mining |
| CN109307811A (en) * | 2018-08-06 | 2019-02-05 | 国网浙江省电力有限公司宁波供电公司 | A kind of user's dedicated transformer electricity consumption monitoring method excavated based on big data |
| CN109063929A (en) * | 2018-08-29 | 2018-12-21 | 广东电网有限责任公司 | It opposes electricity-stealing analysis and early warning method, apparatus and computer readable storage medium |
| CN109214464A (en) * | 2018-09-28 | 2019-01-15 | 国网江苏省电力有限公司常州供电分公司 | A kind of doubtful stealing customer identification device and recognition methods based on big data |
| CN109213787A (en) * | 2018-11-07 | 2019-01-15 | 闫福录 | A kind of anti-electricity-theft algorithm chip and electricity anti-theft method in integration characteristic library |
| CN109213787B (en) * | 2018-11-07 | 2022-03-08 | 闫福录 | Electricity larceny prevention algorithm chip integrated with feature library and electricity larceny prevention method |
| 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 |
| CN109885559A (en) * | 2019-01-23 | 2019-06-14 | 长春工程学院 | A kind of stealing user discovery method based on the analysis of user's sample data difference characteristic |
| CN109885559B (en) * | 2019-01-23 | 2022-11-18 | 长春工程学院 | Electricity stealing user discovery method based on user sample data difference characteristic analysis |
| CN111144540A (en) * | 2019-12-05 | 2020-05-12 | 国网山东省电力公司电力科学研究院 | Generation method of anti-electricity-stealing simulation data set |
| CN111667144A (en) * | 2020-04-30 | 2020-09-15 | 北京中电普华信息技术有限公司 | User identification method and device |
| CN111667144B (en) * | 2020-04-30 | 2023-04-28 | 北京中电普华信息技术有限公司 | User identification method and device |
| CN112308124A (en) * | 2020-10-21 | 2021-02-02 | 国家电网有限公司 | Intelligent electricity larceny prevention method for electricity consumption information acquisition system |
| CN112733456A (en) * | 2021-03-17 | 2021-04-30 | 国网河南省电力公司营销服务中心 | Electricity stealing prevention behavior identification method and system |
| CN113393103A (en) * | 2021-06-03 | 2021-09-14 | 西南科技大学 | Anti-electricity-stealing system based on genetic algorithm optimization BP neural network |
| 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 |
| CN113744081A (en) * | 2021-08-23 | 2021-12-03 | 国网青海省电力公司信息通信公司 | Electricity stealing behavior analysis method |
| CN113744081B (en) * | 2021-08-23 | 2024-05-28 | 国网青海省电力公司信息通信公司 | Analysis method for electricity stealing behavior |
| CN113687176A (en) * | 2021-10-25 | 2021-11-23 | 广东电网有限责任公司湛江供电局 | Deep neural network-based power consumption abnormity detection method and system |
| CN113687176B (en) * | 2021-10-25 | 2022-02-15 | 广东电网有限责任公司湛江供电局 | Deep neural network-based power consumption abnormity detection method and system |
| CN116486590A (en) * | 2023-05-10 | 2023-07-25 | 漆燕 | Ammeter data analysis system based on remote meter reading mode |
| CN116486590B (en) * | 2023-05-10 | 2024-03-22 | 江阴众和电力仪表有限公司 | Ammeter data analysis system based on remote meter reading mode |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105573997A (en) | Method and device for determining electric larceny suspect user | |
| CN105205531A (en) | Anti-electric-larceny prediction method based on machine learning and apparatus thereof | |
| Yan et al. | Performance analysis of electricity theft detection for the smart grid: An overview | |
| CN102866321B (en) | Self-adaptive stealing-leakage prevention diagnosis method | |
| CN103793859B (en) | A kind of wind power plant operation monitoring and event integrated evaluating method | |
| Goyal et al. | Asset health management using predictive and prescriptive analytics for the electric power grid | |
| CN105608842B (en) | A kind of damaged online monitoring alarm device of nuclear reactor fuel | |
| CN105356461B (en) | A kind of accounting method of the load unbalanced administration project carbon emission reduction amount of low voltage electric network | |
| CN104391202A (en) | Abnormal electricity consumption judging method based on analysis of abnormal electric quantity | |
| CN111861211A (en) | System with double-layer anti-electricity-stealing model | |
| Bin-Halabi et al. | Remote detection and identification of illegal consumers in power grids | |
| US11740266B2 (en) | Systems and methods for monitoring energy-related data in an electrical system | |
| CN115528817A (en) | Intelligent power distribution and utilization system, method, medium, equipment and terminal for user side | |
| CN114881808B (en) | Big data-based accurate identification method for electric power larceny and electric power larceny prevention system | |
| Botev et al. | Detecting non-technical energy losses through structural periodic patterns in AMI data | |
| CN110806518A (en) | Transformer area line loss abnormal motion analysis module and operation method thereof | |
| CN113393103A (en) | Anti-electricity-stealing system based on genetic algorithm optimization BP neural network | |
| Stracqualursi et al. | Systematic review of energy theft practices and autonomous detection through artificial intelligence methods | |
| CN105005575A (en) | Quick developing interface method for enterprise intelligent prediction | |
| Saeed et al. | Electricity theft detection in power utilities using bagged CHAID-based classification trees | |
| Zhang et al. | Research on comprehensive diagnosis model of anti-stealing electricity based on big data technology | |
| Wu et al. | Survey on negative line loss rate of transformer region: rectification measures and challenges | |
| CN116522746A (en) | Power distribution hosting method for high-energy-consumption enterprises | |
| Altamimi et al. | Energy theft detection using the wasserstein distance on residuals | |
| Madani et al. | Strategies and applications to meet grid challenges and enhance power system performance |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160511 |
|
| RJ01 | Rejection of invention patent application after publication |