CN114066261A  Tampering detection method and device for electric meter, computer equipment and storage medium  Google Patents
Tampering detection method and device for electric meter, computer equipment and storage medium Download PDFInfo
 Publication number
 CN114066261A CN114066261A CN202111367099.5A CN202111367099A CN114066261A CN 114066261 A CN114066261 A CN 114066261A CN 202111367099 A CN202111367099 A CN 202111367099A CN 114066261 A CN114066261 A CN 114066261A
 Authority
 CN
 China
 Prior art keywords
 electricity
 target
 power consumption
 sub
 consumption
 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
 238000001514 detection method Methods 0.000 title claims description 25
 230000005611 electricity Effects 0.000 claims abstract description 241
 238000000034 method Methods 0.000 claims abstract description 27
 239000013598 vector Substances 0.000 claims description 27
 230000006399 behavior Effects 0.000 claims description 24
 238000004364 calculation method Methods 0.000 claims description 19
 238000012545 processing Methods 0.000 claims description 9
 238000004590 computer program Methods 0.000 claims description 7
 238000012549 training Methods 0.000 claims description 5
 238000012216 screening Methods 0.000 claims description 2
 238000012843 least square support vector machine Methods 0.000 description 8
 238000005259 measurement Methods 0.000 description 8
 230000006870 function Effects 0.000 description 7
 238000010586 diagram Methods 0.000 description 6
 230000009977 dual effect Effects 0.000 description 5
 230000003287 optical effect Effects 0.000 description 5
 238000012706 supportvector machine Methods 0.000 description 5
 230000002159 abnormal effect Effects 0.000 description 4
 230000009471 action Effects 0.000 description 4
 230000008569 process Effects 0.000 description 4
 230000007547 defect Effects 0.000 description 3
 230000000694 effects Effects 0.000 description 2
 238000013450 outlier detection Methods 0.000 description 2
 230000002093 peripheral effect Effects 0.000 description 2
 238000013459 approach Methods 0.000 description 1
 238000003491 array Methods 0.000 description 1
 230000009286 beneficial effect Effects 0.000 description 1
 238000004422 calculation algorithm Methods 0.000 description 1
 238000004891 communication Methods 0.000 description 1
 230000007423 decrease Effects 0.000 description 1
 230000003247 decreasing effect Effects 0.000 description 1
 238000013135 deep learning Methods 0.000 description 1
 230000004927 fusion Effects 0.000 description 1
 238000002347 injection Methods 0.000 description 1
 239000007924 injection Substances 0.000 description 1
 238000010801 machine learning Methods 0.000 description 1
 238000013507 mapping Methods 0.000 description 1
 239000011159 matrix material Substances 0.000 description 1
 239000013307 optical fiber Substances 0.000 description 1
 230000008707 rearrangement Effects 0.000 description 1
 230000011218 segmentation Effects 0.000 description 1
 239000004065 semiconductor Substances 0.000 description 1
 238000012163 sequencing technique Methods 0.000 description 1
 239000000243 solution Substances 0.000 description 1
 238000006467 substitution reaction Methods 0.000 description 1
 230000005612 types of electricity Effects 0.000 description 1
Images
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
 G06Q10/00—Administration; Management
 G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
 G06Q10/063—Operations research, analysis or management
 G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations

 G—PHYSICS
 G06—COMPUTING; CALCULATING OR COUNTING
 G06F—ELECTRIC DIGITAL DATA PROCESSING
 G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
 G06F17/10—Complex mathematical operations
 G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis

 G—PHYSICS
 G06—COMPUTING; CALCULATING OR COUNTING
 G06F—ELECTRIC DIGITAL DATA PROCESSING
 G06F18/00—Pattern recognition
 G06F18/20—Analysing
 G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
 G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting

 G—PHYSICS
 G06—COMPUTING; CALCULATING OR COUNTING
 G06F—ELECTRIC DIGITAL DATA PROCESSING
 G06F18/00—Pattern recognition
 G06F18/20—Analysing
 G06F18/24—Classification techniques
 G06F18/241—Classification techniques relating to the classification model, e.g. parametric or nonparametric approaches
 G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or nonparametric approaches based on the proximity to a decision surface, e.g. support vector machines

 G—PHYSICS
 G06—COMPUTING; CALCULATING OR COUNTING
 G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
 G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
 G06Q50/06—Energy or water supply
Landscapes
 Engineering & Computer Science (AREA)
 Physics & Mathematics (AREA)
 Theoretical Computer Science (AREA)
 Business, Economics & Management (AREA)
 Data Mining & Analysis (AREA)
 General Physics & Mathematics (AREA)
 Human Resources & Organizations (AREA)
 Economics (AREA)
 Life Sciences & Earth Sciences (AREA)
 Strategic Management (AREA)
 Bioinformatics & Cheminformatics (AREA)
 Bioinformatics & Computational Biology (AREA)
 Evolutionary Biology (AREA)
 General Engineering & Computer Science (AREA)
 Marketing (AREA)
 Health & Medical Sciences (AREA)
 Entrepreneurship & Innovation (AREA)
 Educational Administration (AREA)
 Development Economics (AREA)
 Evolutionary Computation (AREA)
 Computer Vision & Pattern Recognition (AREA)
 Pure & Applied Mathematics (AREA)
 Artificial Intelligence (AREA)
 Tourism & Hospitality (AREA)
 General Business, Economics & Management (AREA)
 Computational Mathematics (AREA)
 Mathematical Analysis (AREA)
 Mathematical Optimization (AREA)
 Operations Research (AREA)
 Mathematical Physics (AREA)
 Primary Health Care (AREA)
 Algebra (AREA)
 Probability & Statistics with Applications (AREA)
 Databases & Information Systems (AREA)
 Software Systems (AREA)
 General Health & Medical Sciences (AREA)
 Water Supply & Treatment (AREA)
 Public Health (AREA)
 Game Theory and Decision Science (AREA)
 Quality & Reliability (AREA)
Abstract
The invention provides a method and a device for detecting tampering of an electric meter, computer equipment and a storage medium, wherein the method comprises the following steps: respectively reading the electricity consumption from the total electricity meter of the platform area as target total electricity consumption, and reading the electricity consumption from the subelectricity meters of each electricity consumer in the platform area as target subelectricity consumption; calculating the difference between the target total electricity consumption and all the target subelectricity consumptions to serve as the target electricity consumption difference; calculating mutual information between the target electronic electricity consumption and the difference of the target electricity consumption to serve as a first target probability of electricity consumption in a power consumption user tampering subammeter; inputting the target electronic power consumption of the same power consumption into the solitary forest, and outputting a second target probability that the power consumption of the power consumption is tampered in the subelectric meter; calculating a target coefficient of electricity consumption in the electricity consumption tampering submeter of the electricity consumer according to the first target probability and the second target probability; and determining the electricity consumption user for tampering the electricity consumption in the electricity distribution table according to the target coefficient. The accuracy of detecting the behavior of tampering the electricity distribution meter by the electricity consumer is improved, and the applicability is high.
Description
Technical Field
The embodiment of the invention relates to the technical field of power grids, in particular to a method and a device for detecting tampering of an electric meter, computer equipment and a storage medium.
Background
The intelligent electric meter can exert great flexibility in optimizing the use of energy, but has more problems of tampering and electric power theft, and besides some old forms of physical tampering, the intelligent electric meter is also subjected to attacks in more complex forms, and the reading of the electric meter is tampered.
At present, the behavior of detecting the degree of a tampered electric meter mainly depends on a marked data set or additional power system state information, which is difficult to obtain in reality and low in applicability, and the data and an actual value have large errors, so that the detection accuracy is low.
Disclosure of Invention
The embodiment of the invention provides a method and a device for detecting tampering of an ammeter, computer equipment and a storage medium, and aims to solve the problems of low behavior applicability and low accuracy in detecting the degree of a tampered ammeter.
In a first aspect, an embodiment of the present invention provides a method for detecting tampering of an electric meter, including:
respectively reading power consumption from a total electric meter of a platform area as target total power consumption, and reading power consumption from a subelectric meter of each power consumer in the platform area as target subpower consumption;
calculating the difference value between the target total electricity consumption and all the target subelectricity consumption as a target electricity consumption difference;
calculating mutual information between the target subelectricity consumption and the target electricity consumption difference to serve as a first target probability that the electricity consumption user tampers with the electricity consumption in the electricity distribution meter;
inputting the target subpower consumption of the same power consumption into an solitary forest, and outputting a second target probability that the power consumption in the branch electric meter is tampered by the power consumption;
calculating a target coefficient of the electricity consumption amount in the electricity distribution meter tampered by the electricity consumer according to the first target probability and the second target probability;
and determining a power consumption user for tampering the power consumption in the electricity distribution meter according to the target coefficient.
In a second aspect, an embodiment of the present invention further provides a tampering detection device for an electricity meter, including:
the electric meter reading module is used for respectively reading power consumption from a total electric meter of the distribution area as target total power consumption, and reading the power consumption from a subelectric meter of each power consumer in the distribution area as target subpower consumption;
the power consumption difference calculation module is used for calculating the difference value between the target total power consumption and all the target subpower consumption to serve as the target power consumption difference;
the first target probability calculation module is used for calculating mutual information between the target subpower consumption and the target power consumption difference, and the mutual information is used as a first target probability that the power consumption user tampers with the power consumption in the electricity distribution meter;
the second target probability calculation module is used for inputting the target subelectricity consumption of the same electricity consumer into an soliton forest and outputting a second target probability that the electricity consumer tampers the electricity consumption in the electricity distribution meter;
the target coefficient calculation module is used for calculating a target coefficient of the electricity consumption amount in the electricity distribution meter tampered by the electricity consumer according to the first target probability and the second target probability;
and the electricity consumption user detection module is used for determining electricity consumption users tampering with the electricity consumption amount in the electricity distribution meter according to the target coefficient.
In a third aspect, an embodiment of the present invention further provides a computer device, where the computer device includes:
one or more processors;
a memory for storing one or more programs,
when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the method for tamper detection of an electricity meter according to the first aspect.
In a fourth aspect, an embodiment of the present invention further provides a computerreadable storage medium, where a computer program is stored on the computerreadable storage medium, and when the computer program is executed by a processor, the method for detecting tampering of an electric meter according to the first aspect is implemented.
In the embodiment, the electricity consumption is respectively read from the total electricity meter of the platform area as the target total electricity consumption, and the electricity consumption is read from the subelectricity meters of each electricity consumer in the platform area as the target subelectricity consumption; calculating the difference between the target total electricity consumption and all the target subelectricity consumptions to serve as the target electricity consumption difference; calculating mutual information between the target electronic electricity consumption and the difference of the target electricity consumption to serve as a first target probability of electricity consumption in a power consumption user tampering subammeter; inputting the target electronic power consumption of the same power consumption into the solitary forest, and outputting a second target probability that the power consumption of the power consumption is tampered in the subelectric meter; calculating a target coefficient of electricity consumption in the electricity consumption tampering submeter of the electricity consumer according to the first target probability and the second target probability; and determining the electricity consumption user for tampering the electricity consumption in the electricity distribution table according to the target coefficient. The behavior that the branch electric meter is tampered by the power consumer is detected by combining the mutual information and the isolated forest, the defect of a single mode can be overcome, the accuracy of the behavior that the branch electric meter is tampered by the power consumer is improved, the mutual information and the isolated forest are lowdimensional data, the mutual information and the isolated forest are easy to obtain in practice, the applicability is high, and the electricity stealing behaviors of various different types can be detected.
Drawings
Fig. 1 is a flowchart of a tampering detection method for an electricity meter according to an embodiment of the present invention;
FIG. 2 is a diagram illustrating an example of a type of electricity stealing provided by an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a tampering detection device for an electricity meter according to a second embodiment of the present invention;
fig. 4 is a schematic structural diagram of a computer device according to a third embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of a tampering detection method for an electric meter according to an embodiment of the present invention, where the present embodiment is applicable to a situation where a behavior of tampering with an electric meter is detected through mutual information and isolated forest, the method may be executed by a tampering detection device for an electric meter, the tampering detection device for an electric meter may be implemented by software and/or hardware, and may be configured in a computer device, such as a server, a workstation, a personal computer, and the like, and specifically includes the following steps:
The power grid may be divided into a plurality of areas, each of which provides power distribution services for a plurality of power consumers, where an area refers to a power supply range or area of a (single) transformer.
The electric meters are arranged in the distribution area, and each electric user is provided with an electric meter.
When tampering is detected, on the one hand, the electricity consumption is read from the total electricity meter of the station area as the target total electricity consumption, and on the other hand, the electricity consumption is read from the subelectricity meters of each electricity consumer in the station area as the target subelectricity consumption.
The common characteristic of different tampering behaviors is that the measurement data (namely, reading) of the electricity meter is inconsistent with the actual electricity utilization condition, and the influence of the tampering modes on the measurement data of the electricity meter can be abstracted into the injection of false data into the measurement data. Regarding electricity consumers in a platform area as different metering units, these metering units may be affected by spurious data, i.e. tampering occurs. The total electric meter of the transformer area is the sum of the real measurement values of the metering units, so that tampering behaviors are difficult to generate, and the influence of false data is difficult to generate. Each tampering action of the power consumers in the distribution area can affect the correlation between the measurement data (namely the standard total power consumption) of the total power meter and the measurement data (namely the target sub power consumption) of the branch power meters, and the metering units with false data, namely the power consumers with electricity stealing actions, can be detected by analyzing the correlation between the measurement data (namely the standard total power consumption) of the total power meter and the measurement data (namely the target sub power consumption) of the branch power meters.
And 102, calculating the difference value between the target total electricity consumption and all the target sub electricity consumption as the target electricity consumption difference.
The tampering action is to tamper the real value of the electricity consumption to achieve the purpose of little metering or no metering. Therefore, the tampering action causes errors between the metering sums of the district total electric meter and the subelectric meter.
Setting the difference of target electricity consumption caused by tampering behaviors at the tth moment as error_{t}The calculation formula is as follows:
wherein, U represents the set of all power consumers in the platform area, M_{t}A target total power usage amount of the station area is indicated,and the target sub electricity consumption of the ith electricity consumer in the platform area is represented.
Considering that normal power consumers cannot differ from target power consumption error_{t}The effect is then again:
wherein C is the set of power consumers with tampering behaviors, m_{i,t}Is the actual power consumption of the user i.
And 103, calculating mutual information between the target electronic electricity consumption and the target electricity consumption difference to serve as a first target probability of electricity consumption in the electricity consumption meter tampered by the electricity consumer.
Mutual Information (Mutual Information) is a useful Information measure in Information theory, and can be used as a measure for measuring the degree of interdependence between random variables, which can be regarded as the amount of Information contained in one random variable about another random variable, or the uncertainty that one random variable decreases because another random variable is known.
The difference between the target electronic power consumption and the target power consumption is regarded as a vector, mutual information of the two vectors does not make any assumption on the property of the relationship between the characteristic words and the categories, the application range in the aspect of measuring the correlation is wider, the mutual information is not limited to the linear correlation category, the correlation is used for detecting various types of correlation, the correlation is used as a first target probability of the power consumption in the power consumption user tampering electric distribution table, and the stronger the correlation is, the larger the first target probability of the power consumption in the power consumption user tampering electric distribution table is.
In a specific implementation, given two random variables x and y, their mutual information is defined by their probability density functions p (x), p (y).
In this embodiment, mutual information between the target electronic power consumption and the target power consumption difference may be calculated as a first target probability that the power consumption is tampered by the power consumer in the electricity distribution table according to the following formula:
wherein I (x, y) is a first target probability, x is a target subpower consumption, y is a target power consumption difference, p (x) is a probability of occurrence of the target subpower consumption, and p (x) is equivalent top (y) is the probability of the occurrence of the difference of the target electricity consumption, and p (x, y) is the probability of the occurrence of the difference of the target subelectricity consumption and the target electricity consumption at the same time;
n is the number of power consumers, x^{(i)}For the ith target electron power usage, δ is the Parzen window and h is the width of the Parzen window δ.
Further, a proper Parson window delta and a proper width h of the window delta are selected, and when N approaches infinity, an approximate probability density function is obtainedIt is possible to converge to the true probability density function p (x).
The palerson window δ is defined as follows:
wherein z is xx^{(i)}D is the dimension of the target subelectricity consumption, and epsilon is the covariance of z. When d is 1, the palson window δ corresponds to an estimate of the edge density.
I (x, y) falls in the section [0,1], and the larger the value of I (x, y), the stronger the correlation between the target sub power usage and the target power usage difference.
And 104, inputting the target sub power consumption of the same power consumption into the solitary forest, and outputting a second target probability that the power consumption in the power consumption meter is tampered by the power consumption.
Since the type of the tampering behavior of the power consumer is uncertain, the application of the correlation to detect the tampering behavior may result in that the tampering behavior with randomly changing tampering amount cannot be identified. If the electricity consumption of a certain type of user who has a tampering behavior is random, the waveform shape of a curve formed by the electricity consumption of the user is different, that is, if the electricity consumption of n second periods in each first period (such as one day) is regarded as an ndimensional vector, the vectors generated by the random electricity consumption are different in direction and distributed dispersedly; and the vector of normal electricity utilization is more concentrated.
Therefore, in this embodiment, an isolated forest iForest may be trained in advance for the power consumers, where the isolated forest is used to detect the probability that the power consumers tamper the power consumption in the electricity meter, and then, in this embodiment, the isolated forest is used to perform outlier detection on the target subpower consumption of each power consumer, and a part with abnormal line loss is determined.
Further, there are many definitions of an anomaly (anomaly detection), and in an isolated forest, an anomaly is defined as an outlier (more likely to be isolated) that is easily isolated, which can be understood as a point that is sparsely distributed and is far from a population with a high density. In the feature space, the sparsely distributed areas indicate that the probability of the event occurring in the areas is low, and thus the data falling in the areas can be considered as abnormal, and it can be seen that the power consumption conforms to the characteristics.
Isolated forest is an unsupervised anomaly detection method suitable for Continuous data (Continuous numerical data), i.e. marked samples are not needed for training, but features need to be Continuous. For how to find which points are easily isolated (isolated), in an isolated forest, the data set is recursively randomly partitioned until all sample points are isolated. Under this strategy of random segmentation, outliers typically have shorter paths. Intuitively, the clusters with high density need to be cut many times to be isolated, but the points with low density can be easily isolated.
In a specific implementation, a plurality of sub power consumptions read from a power consumption meter of the same power consumer in a plurality of second periods (e.g. 1 hour) within a first period (e.g. 1 day) may be queried, and the plurality of sub power consumptions are input into soliton forest as a plurality of vectors, and a second target probability that the power consumption meter is tampered by the power consumer is calculated according to the following formula:
c(n)＝2H(n1)(2(n1)/n)
H(n1)＝ln(n1)+τ
wherein s (x, n) is a second target probability, x is a leaf node on an isolated tree in the isolated forest, n is the number of second periods, E (H (x)) is an expected value of the height H (x) of the leaf node x on a plurality of isolated trees in the isolated forest, c is an average path length of the plurality of isolated trees in the isolated forest, H is a key sum, and τ is an euler constant (e.g., 0.577).
The basic principle of using the isolated forest for the target subelectricity consumption of each electricity consumer is to cut a data space by a random hyperplane, divide the data space into two subspaces, cut the subspaces until only one data node exists in each subspace, and form an isolated tree in which each leaf node only contains one data node. The data density at the outlier is low, so that the data can be stopped in a subspace quickly, and whether the data x is the outlier is judged according to the height h (x) from the leaf node x to the root node. An isolated forest consists of a plurality of isolated trees. For a data set containing n data points, the height of the constructed isolated tree has a maximum value of n1 and a minimum value of log (n), the maximum possible height of the path h (x) increases linearly with n, and the average possible height increases with log (n). Normalizing h (x) according to the similarity of the isolated tree and the binary search tree: and (4) carrying out outlier detection on the isolated forest, and judging the part with abnormal line loss.
The second probability s (x, n) is a monotone decreasing function of the height h (x), the value range is [0,1], and the closer s is to 1, the higher the possibility that the electricity utilization condition of the power consumer is abnormal is.
And 105, calculating a target coefficient of the electricity consumption in the electricity consumption tampering part meter of the electricity consumption user according to the first target probability and the second target probability.
Mutual information and the isolated forest are mutually independent, the mutual information and the isolated forest have advantages and disadvantages respectively, and if the first target probability or the second target probability is singly sequenced, the sequencing of the power consumers without tampering is meaningless in practice.
In this embodiment, mutually independent mutual information is combined with an isolated forest, so that the first target probability and the second target probability are mapped to a target coefficient of electricity consumption in the electric power consumption tampering part meter of the electric power consumer, and the target coefficient represents the amplitude of electricity consumption in the electric power consumption tampering part meter of the electric power consumer, so that the defects caused by singly using the mutual information or the isolated forest can be overcome.
In one embodiment of the present invention, step 105 may include the steps of:
and 1051, determining a least squares support vector regression machine.
And 1052, inputting the first target probability and the second target probability into a least square support vector regression machine for processing so as to output a target coefficient of the power consumption in the power consumption meter tampered by the user.
A Support Vector Machine (SVM) is an algorithm in the field of machine learning, and the result obtained by using the SVM with kernel is not inferior to that based on the deep learning method. The SVM is proposed for the classification problem, and can also solve the Regression problem, which is called Support Vector Regression (SVR). The Least square Support Vector machine (LSSVR) is a special form of the LSSVR and can convert inequality constraint problem into equality constraint problem.
In this embodiment, a least square support vector regression may be trained in advance, and the combined detection of the fusion of the mutual information and the isolated forest is realized through the least square support vector regression, that is, the first target probability and the second target probability are used as the input of the least square support vector regression, and the least square support vector regression processes the first target probability and the second target probability according to the structure thereof, and outputs the target coefficient of the power consumption in the power consumption falsification submeter by the power consumer.
In this embodiment, the least squares support vector regression machine may be trained as follows:
and S1, acquiring the total power consumption of the sample and the sub power consumption of the sample.
The total sample electricity consumption is the electricity consumption read from the total electricity meter of the platform area, and the sample electronic electricity consumption is the electricity consumption which is read from the subelectricity meters of each electricity consumer in the platform area and is not tampered.
Assuming that j days of electricity consumption data of i users in a certain area are provided, in order to facilitate data processing, the subelectricity consumption of each user sample can be normalized, and an i x j dimensional matrix is obtained and is a data source for subsequent training.
For the trained data, the power consumer does not tamper with the electricity meter, i.e., the sum of the sample subpower consumptions is equal to the sample total power consumption.
And noise can be added to the total power consumption of the sample and the sub power consumption of the sample to realize data enhancement, wherein the total power consumption of the sample and the sub power consumption of the sample are modified according to a certain proportion by adding the noise.
And S2, simulating and tampering the behavior of the power consumption in the electricity distribution meter, and modifying the sample sub power consumption to obtain new sample sub power consumption.
In the concrete implementation, the behavior of tampering the electric meter by an electric user in reality can be summarized to obtain a plurality of electricity stealing types, and the sample subelectricity consumption is modified according to the specifications of part or all electricity stealing behaviors, so that the behavior of tampering the electricity consumption in the electric meter is simulated, and the new sample subelectricity consumption is obtained.
Illustratively, let the real sample subpower usage (i.e., the original sample subpower usage) be m_{i,t}The tampered sample subpower usage (i.e., new sample subpower usage) isThen, the electricity stealing type includes at least one of:
type 1:
the sample subpower usage is multiplied by a first tampering factor as a new sample subpower usage.
In type 1, m_{i,t}Andin a proportional relationship, that is,wherein α is a first tamper factor, α is greater than 0 and less than 1, preferably a randomly selected value of (0.1, 0.8).
Type 2:
and taking the maximum value between the sample subpower consumption and the first cutoff point as new sample subpower consumption.
In the case of the type 2, it is,where γ is the first cutoff point, and γ is less than the maximum value of the raw sample subpower usage, i.e., γ<maxm_{i,t}。
Type 3:
and taking the maximum value between the difference obtained by subtracting the second interception point from the sample subpower consumption and the second interception point as the new sample subpower consumption.
In the case of the type 3, it is,where γ is the second truncation point, and γ is less than the maximum value of the raw sample subpower usage, i.e., γ<maxm_{i,t}。
Type 4:
taking the maximum value between the difference obtained by subtracting the third truncation point from the sample subelectricity consumption and 0 as a candidate value; and taking the minimum value between the candidate value and the fourth truncation point as the new sample subpower consumption.
In the case of the type 4, it is,wherein, γ_{1}Is a third truncation point, γ_{2}Is a fourth truncation point, γ_{1}、γ_{2}Are all smaller than the original sampleMaximum value in the electron consumption, i.e. gamma_{1},γ_{2}<maxm_{i,t}。
Type 5:
and setting and assigning the sample sub power consumption measured in the part of the second period in the first period as new sample sub power consumption, adjusting the sample sub power consumption measured in the part of the second period in the first period to be 0, and assigning as new sample sub power consumption.
In the case of the type 5, it is,in relation to time t, at 0 and m_{i,t}In the form of a wave between, i.e.,wherein if t e (t)_{1},t_{2}) If f (t) is 0, otherwise f (t) is 1, t_{1}t_{2}Are randomly generated second cycles (1 hour) within the first cycle (1 day), the number of which is generally less than 4 second cycles (1 hour).
Type 6:
and setting a second tampering coefficient for each second period in the first period, and multiplying the sample sub power consumption measured in each second period by the second tampering coefficient respectively to obtain new sample sub power consumption.
In type 6, m_{i,t}Andin a proportional relationship and the proportional relationship varies with time t, i.e., wherein alpha is_{t}Is a second tamper factor, α_{t}Greater than 0 and less than 1, preferably (0.1, 0.8).
Type 7:
setting a third tampering coefficient for each second period in the first period; and multiplying the third tampering coefficients by the average value of the sample subelectricity consumptions respectively to obtain new sample subelectricity consumptions.
In type 7, m_{i,t}Andaverage value of (2)In a proportional relationship and the proportional relationship varies with time t, i.e.,wherein alpha is_{t}Is a third tamper factor, α_{t}Greater than 0 and less than 1, preferably (0.1, 0.8).
As shown in fig. 2, in the left coordinate system, the vertical axis 0 represents the actual sample subpower consumption (i.e., the original sample subpower consumption), 17 represents the sample subpower consumption tampered with according to the abovementioned tampering behavior (i.e., the new sample subpower consumption), the horizontal axis represents the sample subpower consumption in a plurality of second periods (0.5 hour) in the first period (1 day), and the sample subpower consumption corresponds to the color blocks on the right side and varies from 0 to 16 kWh.
The difference in color between the actual sample subpower usage (i.e., the original sample subpower usage) and the tampered sample subpower usage (i.e., the new sample subpower usage) may reflect the severity of the tampering.
For example, the 2 nd row represents the tampered sample subpower consumption corresponding to the electricity stealing type 2, and in the interval of the second period 621, because the real sample subpower consumption is already larger than the first cutoff point, the tampered sample subpower consumption is maintained at the size of the first cutoff point in the period of time, and the color of the cutoff block is unchanged.
Of course, the abovementioned electricity stealing types are only examples, and when implementing the embodiment of the present invention, other electricity stealing types may be set according to practical situations, and the embodiment of the present invention is not limited thereto. In addition, besides the abovementioned electricity stealing types, those skilled in the art may also adopt other electricity stealing types according to actual needs, and the embodiment of the present invention is not limited thereto.
And S3, calculating the difference between the total power consumption of the sample and the sub power consumption of all samples to be used as the difference of the sample power consumption.
And S4, calculating mutual information between the power consumption difference and the sample sub power consumption difference to serve as a first sample probability of the power consumption in the power consumption user tampering electric meter.
In a specific implementation, mutual information between the sample sub power consumption and the difference between the sample power consumption can be calculated through the following formula, and the mutual information is used as a first sample probability of the power consumption in the power consumption user tampering subelectric meter:
wherein, I (x, y) is the first sample probability, x is the sample subpower consumption, y is the sample power consumption difference, p (x) is the probability of the sample subpower consumption, and p (x) is equivalent top (y) is the probability of the occurrence of the difference of the sample power consumption, and p (x, y) is the probability of the simultaneous occurrence of the sample subpower consumption and the sample power consumption difference;
n is the number of power consumers, x^{(i)}For the ith sample electron power usage, δ is the Parrson window and h is the width of the Parrson window.
And S5, inputting the sample sub power consumption of the same power consumption into the soliton forest, and outputting the second sample probability of the power consumption in the power consumption tampering part electric meter of the power consumption.
In a specific implementation, a plurality of sub power consumption read from the sub electricity meters of the same power consumer in a plurality of second periods in the first period can be inquired;
and inputting the plurality of electronic electricity consumption quantities into the soliton forest as a plurality of vectors, and calculating a second sample probability s (x, n) of electricity consumption quantity in the electric power consumption user tampering part ammeter through the following formula:
c(n)＝2H(n1)(2(n1)/n)
H(n1)＝ln(n1)+τ
wherein s (x, n) is a second sample probability, x is a leaf node on an isolated tree in the isolated forest, n is the number of the second period, E (H (x)) is an expected value of the height H (x) of the leaf node x on a plurality of isolated trees in the isolated forest, c is an average path length of the plurality of isolated trees in the isolated forest, H is a sum of sums, and τ is an euler constant.
In the present embodiment, since the applications of S3, S4, and S5 are substantially similar to the applications of step 102, step 103, and step 104, the description is relatively simple, and for the relevant points, reference is made to the description of step 102, step 103, and step 104, and the embodiment of the present invention is not described in detail herein.
And S6, taking the ratio of the tamper value to the sample sub power consumption which is not tampered as the sample coefficient of the power consumption in the user tampering part electric meter.
Wherein the tampered value is a difference between the untampered sample sub power usage and the tampered sample sub power usage.
For user i, the process of calculating the sample coefficients is represented as follows:
wherein, let the actual sample subpower consumption (i.e. the original sample subpower consumption) of the user i be xi_{,t}With the sample subpower usage tampered with by customer i (i.e., the new sample subpower usage) as
And S7, training a least square support vector regression machine by taking the first sample probability and the second sample probability as samples and the sample coefficient as a label.
In this embodiment, the first sample probability and the second sample probability are samples, the sample coefficient is a label, and the parameters in the least squares support vector regression are trained under the supervision of the label.
For the trained sample D { (x)_{1},y_{1}),(x_{2},y_{2}),…,(x_{m},y_{m}) The LSSVR can be obtained in a form such asModel of (1), whereinIs a kernel function, and w and b are parameters.
The description of LSSVR is:
gamma is a regularization parameter.
And converting the dual problem into a dual problem by a Lagrange multiplier method, and solving the dual problem to obtain a solution of the original problem. The dual problem is:
and solving the dual problem by using a coordinate rotation method under the KKT condition. Compared with a standard support vector machine, the least square support vector machine converts inequality constraint into equality constraint, and the calculation speed is accelerated.
And 106, determining a power consumption user for tampering the power consumption in the electricity distribution table according to the target coefficient.
In this embodiment, the target coefficient may be referred to screen the power consumption user tampering with the power consumption in the electricity distribution meter, so as to perform an alarm operation on the power consumption user.
In a specific implementation, the power consumers can be sorted in a descending order according to the target coefficient, so that the power consumers with the power consumption falsified in the subelectric meter can be screened according to the configuration order of the power consumers.
Let the first target probability be pro_{1}The second target probability is pro_{2}Applying LSSVR to assign the first target probability pro_{1}With a second target probability pro_{2}Mapping to the target coefficient, the sorting process is denoted as rank (LSSVR (pro)_{1},pro_{2}))
In the descending sort, the higher the order of the power consumers is, the higher the target coefficient is, the more likely to screen the power consumption in the tampered power consumption table, and therefore, some conditions may be set so as to screen the power consumers which meet the conditions as the power consumption in the tampered power consumption table, for example, the power consumer with the highest order k (k is a positive integer) bit or r (r is a positive integer)% tampers the power consumption in the tampered power consumption table, or the power consumer with the highest order k bit or r% and the target coefficient is greater than the threshold value tampers the power consumption in the tampered power consumption table, and so on.
In the embodiment, the electricity consumption is respectively read from the total electricity meter of the platform area as the target total electricity consumption, and the electricity consumption is read from the subelectricity meters of each electricity consumer in the platform area as the target subelectricity consumption; calculating the difference between the target total electricity consumption and all the target subelectricity consumptions to serve as the target electricity consumption difference; calculating mutual information between the target electronic electricity consumption and the difference of the target electricity consumption to serve as a first target probability of electricity consumption in a power consumption user tampering subammeter; inputting the target electronic power consumption of the same power consumption into the solitary forest, and outputting a second target probability that the power consumption of the power consumption is tampered in the subelectric meter; calculating a target coefficient of electricity consumption in the electricity consumption tampering submeter of the electricity consumer according to the first target probability and the second target probability; and determining the electricity consumption user for tampering the electricity consumption in the electricity distribution table according to the target coefficient. The behavior that the branch electric meter is tampered by the power consumer is detected by combining the mutual information and the isolated forest, the defect of a single mode can be overcome, the accuracy of the behavior that the branch electric meter is tampered by the power consumer is improved, the mutual information and the isolated forest are lowdimensional data, the mutual information and the isolated forest are easy to obtain in practice, the applicability is high, and the electricity stealing behaviors of various different types can be detected.
It should be noted that, for simplicity of description, the method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present invention is not limited by the illustrated order of acts, as some steps may occur in other orders or concurrently in accordance with the embodiments of the present invention. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred and that no particular act is required to implement the invention.
Example two
Fig. 3 is a block diagram of a structure of a tampering detection device for an electric meter according to a second embodiment of the present invention, which may specifically include the following modules:
an electric meter reading module 301, configured to read electricity consumption from a total electric meter in a distribution area as target total electricity consumption, and read electricity consumption from a subelectric meter of each electricity consumer in the distribution area as target subelectricity consumption;
a power consumption difference calculating module 302, configured to calculate a difference between the target total power consumption and all the target sub power consumptions as a target power consumption difference;
a first target probability calculation module 303, configured to calculate mutual information between the target sub power consumption and the target power consumption difference, where the mutual information is used as a first target probability that the power consumer tampers with the power consumption in the electricity distribution meter;
a second target probability calculation module 304, configured to input the target subpower consumption of the same power consumer into an soliton forest, and output a second target probability that the power consumer tampers with the power consumption in the electricity distribution meter;
a target coefficient calculation module 305, configured to calculate a target coefficient for tampering the electricity consumption amount in the electricity distribution meter by the electricity consumer according to the first target probability and the second target probability;
and the power consumption detecting module 306 is configured to determine a power consumption which tampers with the power consumption in the electricity distribution meter according to the target coefficient.
In an embodiment of the present invention, the first target probability calculating module 303 is further configured to:
calculating mutual information between the target subelectricity consumption and the target electricity consumption difference through the following formula to serve as a first target probability that the electricity consumption user tampers the electricity consumption in the electricity distribution meter:
wherein I (x, y) is a first target probability, x is the target subpower consumption, y is the target power consumption difference, p (x) is the probability of occurrence of the target subpower consumption, and p (x) is equivalent top (y) is the probability of the target power consumption difference occurring, and p (x, y) is the probability of the target sub power consumption and the target power consumption difference occurring at the same time;
n is the number of electricity consumers, x^{(i)}And delta is the Parson window, and h is the width of the Parson window for the ith target electron power consumption.
In an embodiment of the present invention, the second target probability calculation module 304 is further configured to:
inquiring a plurality of sub electricity consumption amounts read from the electricity distribution meter of the same electricity consumer in a plurality of second periods in the first period;
inputting a plurality of subelectricity consumption quantities into an soliton forest as a plurality of vectors, and calculating a second target probability that the electricity consumption quantity in the electricity distribution meter is tampered by the electricity consumer according to the following formula:
c(n)＝2H(n1)(2(n1)/n)
H(n1)＝ln(n1)+τ
wherein s (x, n) is a second target probability, x is a leaf node on an isolated tree in the isolated forest, n is the number of the second periods, E (H (x)) is an expected value of the height H (x) of the leaf node x on a plurality of isolated trees in the isolated forest, c is an average path length of the plurality of isolated trees in the isolated forest, H is a key sum, and τ is an euler constant.
In an embodiment of the present invention, the target coefficient calculation module 305 is further configured to:
determining a least squares support vector regression machine;
and inputting the first target probability and the second target probability into the least square support vector regression machine for processing so as to output a target coefficient of the power consumption amount in the electricity distribution meter tampered by the power consumption user.
In an embodiment of the present invention, the target coefficient calculation module 305 is further configured to:
acquiring total sample power consumption and sample subpower consumption, wherein the total sample power consumption is the power consumption read from a total ammeter in a station area, and the sample subpower consumption is the power consumption which is read from a subammeter of each power consumer in the station area and is not tampered;
simulating the behavior of tampering the electricity consumption in the electricity distribution meter, and modifying the sample sub electricity consumption to obtain new sample sub electricity consumption;
calculating the difference between the total power consumption of the sample and all the subpower consumptions of the sample to serve as the difference of the power consumptions of the sample;
calculating mutual information between the power consumption difference and the sample subpower consumption difference to serve as a first sample probability of the power consumption in the electricity distribution meter tampered by the power consumer;
inputting the subpower consumption of the sample of the same power consumer into an solitary forest, and outputting a second sample probability that the power consumer tampers with the power consumption in the electricity distribution meter;
calculating a ratio of a tampering value to the sample subelectricity consumption which is not tampered, as a sample coefficient of the electricity consumption in the electricity distribution meter tampered by the user, wherein the tampering value is a difference value between the sample subelectricity consumption which is not tampered and the sample subelectricity consumption which is tampered;
and training a least square support vector regression machine by taking the first sample probability and the second sample probability as samples and the sample coefficient as a label.
In an embodiment of the present invention, the target coefficient calculation module 305 is further configured to:
multiplying the sample subpower consumption by a first tampering coefficient to serve as a new sample subpower consumption;
and/or the presence of a gas in the gas,
taking the maximum value between the sample subpower consumption and the first cutoff point as new sample subpower consumption;
and/or the presence of a gas in the gas,
taking the maximum value between the difference obtained by subtracting the second interception point from the sample subpower consumption and the second interception point as new sample subpower consumption;
and/or the presence of a gas in the gas,
taking the maximum value between the difference obtained by subtracting the third truncation point from the sample subelectricity consumption and 0 as a candidate value;
taking the minimum value between the candidate value and the fourth truncation point as the new sample subpower consumption;
and/or the presence of a gas in the gas,
assigning the sample subpower consumption setting measured in a part of second periods within the first period to be a new sample subpower consumption, adjusting the sample subpower consumption measured in the part of second periods within the first period to be 0, and assigning the sample subpower consumption setting to be a new sample subpower consumption;
and/or the presence of a gas in the gas,
setting a second tampering coefficient for each second period in the first period;
multiplying the sample sub power consumption measured in each second period by the second tampering coefficient respectively to serve as new sample sub power consumption;
and/or the presence of a gas in the gas,
setting a third tampering coefficient for each second period in the first period;
and multiplying the third tampering coefficients by the average value of the sample subelectricity consumptions respectively to obtain new sample subelectricity consumptions.
In an embodiment of the present invention, the target coefficient calculation module 305 is further configured to:
calculating mutual information between the sample subpower consumption and the sample power consumption difference through the following formula, and taking the mutual information as a first sample probability of the power consumption in the electricity distribution meter tampered by the power consumer:
wherein I (x, y) is a first sample probability, x is the sample subpower consumption, y is the sample power consumption difference, p (x) is the probability of the sample subpower consumption, and p (x) is equivalent top (y) is the probability of the occurrence of the sample power consumption difference, and p (x, y) is the probability of the occurrence of the sample subpower consumption and the sample power consumption difference at the same time;
n is the number of electricity consumers, x^{(i)}For the ith sample electron power usage, δ is the Pearson window and h is the width of the Pearson window.
In an embodiment of the present invention, the target coefficient calculation module 305 is further configured to:
inquiring a plurality of sub electricity consumption amounts read from the electricity distribution meter of the same electricity consumer in a plurality of second periods in the first period;
inputting a plurality of the subelectricity consumption quantities into an soliton forest as a plurality of vectors, and calculating a second sample probability of tampering the electricity consumption quantities in the electricity distribution meter by the electricity consumer according to the following formula:
c(n)＝2H(n1)(2(n1)/n)
H(n1)＝ln(n1)+τ
wherein s (x, n) is a second sample probability, x is a leaf node on an isolated tree in the isolated forest, n is the number of the second period, E (H (x)) is an expected value of the height H (x) of the leaf node x on a plurality of isolated trees in the isolated forest, c is an average path length of the plurality of isolated trees in the isolated forest, H is a key sum, and τ is an euler constant.
In an embodiment of the present invention, the power consumption detection module 306 is further configured to:
sorting the power consumers in a descending order according to the target coefficient so as to configure the order of the power consumers;
and screening and tampering the power consumption users of the electricity consumption in the electricity distribution meter according to the sequence.
The tampering detection device for the ammeter provided by the embodiment of the invention can execute the tampering detection method for the ammeter provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
EXAMPLE III
Fig. 4 is a schematic structural diagram of a computer device according to a third embodiment of the present invention. FIG. 4 illustrates a block diagram of an exemplary computer device 12 suitable for use in implementing embodiments of the present invention. The computer device 12 shown in FIG. 4 is only one example and should not bring any limitations to the functionality or scope of use of embodiments of the present invention.
As shown in FIG. 4, computer device 12 is in the form of a general purpose computing device. The components of computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the system memory 28 and the processing unit 16.
The system memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)30 and/or cache memory 32. Computer device 12 may further include other removable/nonremovable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to nonremovable, nonvolatile magnetic media (not shown in FIG. 4, and commonly referred to as a "hard drive"). Although not shown in FIG. 4, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CDROM, DVDROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.
A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 42 generally carry out the functions and/or methodologies of the described embodiments of the invention.
The processing unit 16 executes various functional applications and data processing by executing programs stored in the system memory 28, for example, implementing a tampering detection method for an electric meter provided by an embodiment of the present invention.
Example four
The fourth embodiment of the present invention further provides a computerreadable storage medium, where a computer program is stored on the computerreadable storage medium, and when the computer program is executed by a processor, the computer program implements each process of the tampering detection method for an electric meter, and can achieve the same technical effect, and in order to avoid repetition, details are not repeated here.
A computer readable storage medium may include, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a nonexhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a readonly memory (ROM), an erasable programmable readonly memory (EPROM or flash memory), an optical fiber, a portable compact disc readonly memory (CDROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A method of tampering detection of an electricity meter, comprising:
respectively reading power consumption from a total electric meter of a platform area as target total power consumption, and reading power consumption from a subelectric meter of each power consumer in the platform area as target subpower consumption;
calculating the difference value between the target total electricity consumption and all the target subelectricity consumption as a target electricity consumption difference;
calculating mutual information between the target subelectricity consumption and the target electricity consumption difference to serve as a first target probability that the electricity consumption user tampers with the electricity consumption in the electricity distribution meter;
inputting the target subpower consumption of the same power consumption into an solitary forest, and outputting a second target probability that the power consumption in the branch electric meter is tampered by the power consumption;
calculating a target coefficient of the electricity consumption amount in the electricity distribution meter tampered by the electricity consumer according to the first target probability and the second target probability;
and determining a power consumption user for tampering the power consumption in the electricity distribution meter according to the target coefficient.
2. The method of claim 1, wherein the calculating mutual information between the target subpower usage and the target power usage difference as a first target probability that the power consumer tampers with the power usage in the electricity distribution meter comprises:
calculating mutual information between the target subelectricity consumption and the target electricity consumption difference through the following formula to serve as a first target probability that the electricity consumption user tampers the electricity consumption in the electricity distribution meter:
wherein I (x, y) is a first target probability, x is the target subpower consumption, y is the target power consumption difference, p (x) is the probability of occurrence of the target subpower consumption, and p (x) is equivalent top (y) is the probability of the target power consumption difference occurring, and p (x, y) is the probability of the target sub power consumption and the target power consumption difference occurring at the same time;
n is the number of electricity consumers, x^{(i)}And delta is the Parson window, and h is the width of the Parson window for the ith target electron power consumption.
3. The method of claim 1, wherein the inputting the target subpower usage of the same power consumer into soliton and outputting a second target probability that the power consumer tampers with the power usage in the electricity distribution meter comprises:
inquiring a plurality of sub electricity consumption amounts read from the electricity distribution meter of the same electricity consumer in a plurality of second periods in the first period;
inputting a plurality of subelectricity consumption quantities into an soliton forest as a plurality of vectors, and calculating a second target probability that the electricity consumption quantity in the electricity distribution meter is tampered by the electricity consumer according to the following formula:
c(n)＝2H(n1)(2(n1)/n)
H(n1)＝ln(n1)+τ
wherein s (x, n) is a second target probability, x is a leaf node on an isolated tree in the isolated forest, n is the number of the second periods, E (H (x)) is an expected value of the height H (x) of the leaf node x on a plurality of isolated trees in the isolated forest, c is an average path length of the plurality of isolated trees in the isolated forest, H is a key sum, and τ is an euler constant.
4. The method according to any one of claims 13, wherein the calculating a target coefficient for the power consumer to tamper with the power usage in the electricity distribution meter according to the first target probability and the second target probability comprises:
determining a least squares support vector regression machine;
and inputting the first target probability and the second target probability into the least square support vector regression machine for processing so as to output a target coefficient of the power consumption amount in the electricity distribution meter tampered by the power consumption user.
5. The method of claim 4, wherein determining a least squares support vector regression machine comprises:
acquiring total sample power consumption and sample subpower consumption, wherein the total sample power consumption is the power consumption read from a total ammeter in a station area, and the sample subpower consumption is the power consumption which is read from a subammeter of each power consumer in the station area and is not tampered;
simulating the behavior of tampering the electricity consumption in the electricity distribution meter, and modifying the sample sub electricity consumption to obtain new sample sub electricity consumption;
calculating the difference between the total power consumption of the sample and all the subpower consumptions of the sample to serve as the difference of the power consumptions of the sample;
calculating mutual information between the power consumption difference and the sample subpower consumption difference to serve as a first sample probability of the power consumption in the electricity distribution meter tampered by the power consumer;
inputting the subpower consumption of the sample of the same power consumer into an solitary forest, and outputting a second sample probability that the power consumer tampers with the power consumption in the electricity distribution meter;
calculating a ratio of a tampering value to the sample subelectricity consumption which is not tampered, as a sample coefficient of the electricity consumption in the electricity distribution meter tampered by the user, wherein the tampering value is a difference value between the sample subelectricity consumption which is not tampered and the sample subelectricity consumption which is tampered;
and training a least square support vector regression machine by taking the first sample probability and the second sample probability as samples and the sample coefficient as a label.
6. The method of claim 5, wherein the simulating acts of tampering with the power usage in the electricity distribution meter, modifying the sample subpower usage, and obtaining a new sample subpower usage comprises:
multiplying the sample subpower consumption by a first tampering coefficient to serve as a new sample subpower consumption;
and/or the presence of a gas in the gas,
taking the maximum value between the sample subpower consumption and the first cutoff point as new sample subpower consumption;
and/or the presence of a gas in the gas,
taking the maximum value between the difference obtained by subtracting the second interception point from the sample subpower consumption and the second interception point as new sample subpower consumption;
and/or the presence of a gas in the gas,
taking the maximum value between the difference obtained by subtracting the third truncation point from the sample subelectricity consumption and 0 as a candidate value;
taking the minimum value between the candidate value and the fourth truncation point as the new sample subpower consumption;
and/or the presence of a gas in the gas,
assigning the sample subpower consumption setting measured in a part of second periods within the first period to be a new sample subpower consumption, adjusting the sample subpower consumption measured in the part of second periods within the first period to be 0, and assigning the sample subpower consumption setting to be a new sample subpower consumption;
and/or the presence of a gas in the gas,
setting a second tampering coefficient for each second period in the first period;
multiplying the sample sub power consumption measured in each second period by the second tampering coefficient respectively to serve as new sample sub power consumption;
and/or the presence of a gas in the gas,
setting a third tampering coefficient for each second period in the first period;
and multiplying the third tampering coefficients by the average value of the sample subelectricity consumptions respectively to obtain new sample subelectricity consumptions.
7. The method according to any one of claims 13 and 56, wherein the determining electricity consumers tampering with the electricity consumption in the electricity distribution meter according to the target coefficient comprises:
sorting the power consumers in a descending order according to the target coefficient so as to configure the order of the power consumers;
and screening and tampering the power consumption users of the electricity consumption in the electricity distribution meter according to the sequence.
8. A tampering detection device for an electricity meter, comprising:
the electric meter reading module is used for respectively reading power consumption from a total electric meter of the distribution area as target total power consumption, and reading the power consumption from a subelectric meter of each power consumer in the distribution area as target subpower consumption;
the power consumption difference calculation module is used for calculating the difference value between the target total power consumption and all the target subpower consumption to serve as the target power consumption difference;
the first target probability calculation module is used for calculating mutual information between the target subpower consumption and the target power consumption difference, and the mutual information is used as a first target probability that the power consumption user tampers with the power consumption in the electricity distribution meter;
the second target probability calculation module is used for inputting the target subelectricity consumption of the same electricity consumer into an soliton forest and outputting a second target probability that the electricity consumer tampers the electricity consumption in the electricity distribution meter;
the target coefficient calculation module is used for calculating a target coefficient of the electricity consumption amount in the electricity distribution meter tampered by the electricity consumer according to the first target probability and the second target probability;
and the electricity consumption user detection module is used for determining electricity consumption users tampering with the electricity consumption amount in the electricity distribution meter according to the target coefficient.
9. A computer device, characterized in that the computer device comprises:
one or more processors;
a memory for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the method of tamper detection for an electricity meter of any of claims 17.
10. A computerreadable storage medium, characterized in that a computer program is stored on the computerreadable storage medium, which computer program, when being executed by a processor, carries out a method of tamper detection of an electricity meter according to any one of claims 17.
Priority Applications (1)
Application Number  Priority Date  Filing Date  Title 

CN202111367099.5A CN114066261A (en)  20211118  20211118  Tampering detection method and device for electric meter, computer equipment and storage medium 
Applications Claiming Priority (1)
Application Number  Priority Date  Filing Date  Title 

CN202111367099.5A CN114066261A (en)  20211118  20211118  Tampering detection method and device for electric meter, computer equipment and storage medium 
Publications (1)
Publication Number  Publication Date 

CN114066261A true CN114066261A (en)  20220218 
Family
ID=80278396
Family Applications (1)
Application Number  Title  Priority Date  Filing Date 

CN202111367099.5A Pending CN114066261A (en)  20211118  20211118  Tampering detection method and device for electric meter, computer equipment and storage medium 
Country Status (1)
Country  Link 

CN (1)  CN114066261A (en) 
Cited By (2)
Publication number  Priority date  Publication date  Assignee  Title 

CN116346638A (en) *  20230530  20230627  南方电网数字电网研究院有限公司  Data tampering inference method based on power grid power and alarm information interaction verification 
CN117147959A (en) *  20230823  20231201  广东电网有限责任公司佛山供电局  Electricity larceny prevention analysis method and device 
Citations (5)
Publication number  Priority date  Publication date  Assignee  Title 

CN108985632A (en) *  20180716  20181211  国网上海市电力公司  A kind of electricity consumption data abnormality detection model based on isolated forest algorithm 
CN110717610A (en) *  20180711  20200121  华北电力大学（保定）  Wind power prediction method based on data mining 
CN111784392A (en) *  20200629  20201016  中国平安财产保险股份有限公司  Abnormal user group detection method, device and equipment based on isolated forest 
CN112511503A (en) *  20201113  20210316  香港中文大学（深圳）  Method, system, equipment and storage medium for improving safety of intelligent electric meter 
CN113128596A (en) *  20210421  20210716  广东电网有限责任公司汕尾供电局  Electricity stealing detection method and device and computer readable storage medium 

2021
 20211118 CN CN202111367099.5A patent/CN114066261A/en active Pending
Patent Citations (5)
Publication number  Priority date  Publication date  Assignee  Title 

CN110717610A (en) *  20180711  20200121  华北电力大学（保定）  Wind power prediction method based on data mining 
CN108985632A (en) *  20180716  20181211  国网上海市电力公司  A kind of electricity consumption data abnormality detection model based on isolated forest algorithm 
CN111784392A (en) *  20200629  20201016  中国平安财产保险股份有限公司  Abnormal user group detection method, device and equipment based on isolated forest 
CN112511503A (en) *  20201113  20210316  香港中文大学（深圳）  Method, system, equipment and storage medium for improving safety of intelligent electric meter 
CN113128596A (en) *  20210421  20210716  广东电网有限责任公司汕尾供电局  Electricity stealing detection method and device and computer readable storage medium 
NonPatent Citations (2)
Title 

周昕;张怡;王桢干;唐恬;: "基于孤立森林算法的台区线损分析与管理系统研究", 电力学报, no. 06, 25 December 2019 (20191225), pages 578  584 * 
李俊卿;李秋佳;石天宇;郭晋才;: "基于数据挖掘的风电功率预测特征选择方法", 电测与仪表, no. 10, 9 April 2019 (20190409), pages 87  92 * 
Cited By (3)
Publication number  Priority date  Publication date  Assignee  Title 

CN116346638A (en) *  20230530  20230627  南方电网数字电网研究院有限公司  Data tampering inference method based on power grid power and alarm information interaction verification 
CN116346638B (en) *  20230530  20230915  南方电网数字电网研究院有限公司  Data tampering inference method based on power grid power and alarm information interaction verification 
CN117147959A (en) *  20230823  20231201  广东电网有限责任公司佛山供电局  Electricity larceny prevention analysis method and device 
Similar Documents
Publication  Publication Date  Title 

CN110223196B (en)  Antielectricitystealing analysis method based on typical industry feature library and antielectricitystealing sample library  
CN113792825A (en)  Fault classification model training method and device for electricity information acquisition equipment  
CN103370722B (en)  The system and method that actual volatility is predicted by small echo and nonlinear kinetics  
CN114066261A (en)  Tampering detection method and device for electric meter, computer equipment and storage medium  
CN110222733B (en)  Highprecision multiorder neural network classification method and system  
CN111340086A (en)  Method, system, medium and terminal for processing labelfree data  
Park et al.  A machine learningbased early warning system for the housing and stock markets  
CN112949721A (en)  Power equipment static data quality assessment method and system  
CN111860698A (en)  Method and device for determining stability of learning model  
CN113516417A (en)  Service evaluation method and device based on intelligent modeling, electronic equipment and medium  
Dulá et al.  DEA with streaming data  
CN115617784A (en)  Data processing system and processing method for informationized power distribution  
CN106708729A (en)  Code defect predicting method and device  
Liao et al.  Simple data augmentation tricks for boosting performance on electricity theft detection tasks  
CN113591881A (en)  Intention recognition method and device based on model fusion, electronic equipment and medium  
CN117155771A (en)  Equipment cluster fault tracing method and device based on industrial Internet of things  
CN111950623A (en)  Data stability monitoring method and device, computer equipment and medium  
Bai et al.  Location‐scale monitoring of ordinal categorical processes  
CN116894687A (en)  Power consumption analysis method and system based on machine learning and electronic equipment  
CN112433952B (en)  Method, system, device and medium for testing fairness of deep neural network model  
CN116245630A (en)  Antifraud detection method and device, electronic equipment and medium  
CN115423159A (en)  Photovoltaic power generation prediction method and device and terminal equipment  
CN115063143A (en)  Account data processing method and device, computer equipment and storage medium  
Dula et al.  Data envelopment analysis (DEA) in massive data sets  
CN115081932B (en)  Method and device for detecting fairness of artificial intelligence model 
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 