CN113705710B - Method and device for identifying electricity usage violations of electric vehicle charging facilities - Google Patents
Method and device for identifying electricity usage violations of electric vehicle charging facilities Download PDFInfo
- Publication number
- CN113705710B CN113705710B CN202111027540.5A CN202111027540A CN113705710B CN 113705710 B CN113705710 B CN 113705710B CN 202111027540 A CN202111027540 A CN 202111027540A CN 113705710 B CN113705710 B CN 113705710B
- Authority
- CN
- China
- Prior art keywords
- electricity
- behavior characteristic
- characteristic variable
- target
- target object
- 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.)
- Active
Links
- 230000005611 electricity Effects 0.000 title claims abstract description 168
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000005070 sampling Methods 0.000 claims description 31
- 238000011835 investigation Methods 0.000 abstract description 6
- 230000008569 process Effects 0.000 abstract description 6
- 230000006399 behavior Effects 0.000 description 80
- 238000010586 diagram Methods 0.000 description 19
- 238000007689 inspection Methods 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 4
- 238000001744 unit root test Methods 0.000 description 3
- 238000012885 constant function Methods 0.000 description 2
- 230000000630 rising effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000001747 exhibiting effect Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000005612 types of electricity Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- 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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
- G06Q10/063114—Status monitoring or status determination for a person or group
-
- 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)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Educational Administration (AREA)
- Bioinformatics & Computational Biology (AREA)
- Game Theory and Decision Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Operations Research (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
Abstract
本发明公开了一种电动车充电设施违约用电识别方法及装置，包括：对电动汽车充电数据进行分析，获得第一用电行为特征变量；对电动汽车日负荷曲线分布进行分析，确定第二用电行为特征变量；将所述第一用电行为特征变量和所述第二用电行为特征变量进行组合，获得目标用电行为特征变量；根据所述目标用电行为特征变量对充电桩进行聚类，确定聚类中心；计算目标对象到聚类中心的相对距离，并基于所述相对距离识别所述目标对象是否为违约用电用户。在本发明中识别过程无需依靠人工排查，提升了电动车充电设施违约用户识别效率和覆盖率。
The present invention discloses a method and device for identifying a default electricity user of an electric vehicle charging facility, comprising: analyzing the charging data of an electric vehicle to obtain a first electricity behavior characteristic variable; analyzing the daily load curve distribution of the electric vehicle to determine a second electricity behavior characteristic variable; combining the first electricity behavior characteristic variable and the second electricity behavior characteristic variable to obtain a target electricity behavior characteristic variable; clustering charging piles according to the target electricity behavior characteristic variable to determine the cluster center; calculating the relative distance from the target object to the cluster center, and identifying whether the target object is a default electricity user based on the relative distance. In the present invention, the identification process does not need to rely on manual investigation, which improves the efficiency and coverage of identifying default users of electric vehicle charging facilities.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a method and a device for identifying illegal electricity consumption of an electric vehicle charging facility.
Background
The electric automobile charging facility is a facility for providing energy supplement for an electric automobile and mainly comprises an alternating current charging pile, a direct current charging pile and a large-scale power exchanging station. Because the types of the charging piles are different, the types of electricity prices are classified in a plurality of ways, and the difference of the executed electricity prices of different types is large, partial high-electricity price customers execute lower electricity prices in all or part through various means, and the self electricity cost is reduced through high-price low-electricity connection. The illegal electricity utilization behavior of the charging facility jeopardizes the electricity supply safety and disturbs the normal electricity supply order.
In order to reduce the loss of a power supply company, the power supply company mainly relies on methods of manual regular inspection, random sampling, user reporting and the like, and researches and analyzes a large amount of inspection data, so that the workload is large, marketing inspection clues are unclear, random spot inspection is adopted, and the judgment is carried out by relying on experience of staff, so that the inspection range is small and potential abnormal users cannot be found.
Therefore, the conventional electric vehicle charging default electricity utilization identification is dependent on manual investigation, and the problems of high manpower resource consumption, low working efficiency, insufficient coverage rate and the like exist.
Disclosure of Invention
Aiming at the problems, the invention provides a method and a device for identifying illegal electricity consumption of an electric vehicle charging facility, which are used for solving the problems that the traditional electric vehicle charging illegal electricity consumption identification depends on manual investigation, and has large manpower resource consumption, low working efficiency, insufficient coverage rate and the like.
In order to achieve the above object, the present invention provides the following technical solutions:
an electric vehicle charging facility default electricity consumption identification method comprises the following steps:
analyzing the charging data of the electric automobile to obtain a first electric behavior characteristic variable;
Analyzing the daily load curve distribution of the electric automobile to determine a second electricity consumption behavior characteristic variable;
Combining the first electricity behavior characteristic variable and the second electricity behavior characteristic variable to obtain a target electricity behavior characteristic variable;
Clustering the charging piles according to the target electricity behavior characteristic variables to determine a clustering center;
And calculating the relative distance between the target object and the clustering center, and identifying whether the target object is a default electricity utilization user or not based on the relative distance.
Optionally, the first electrical behavior characteristic variable comprises a median, a number of days at intervals, a variation coefficient and a mean difference order of a time sequence of the daily electricity consumption;
the median represents average power consumption capability, the interval days represent days when the power consumption is lower than a power consumption threshold, the variation coefficient represents fluctuation condition of data, and the stationary differential order represents stationary degree of the data.
Optionally, the second electricity behavior characteristic variables comprise a load intermittent duration and a differential stable duration, wherein the load intermittent duration represents the time of day without charging, the differential stable duration is the first-order difference of the extracted power curve, and the differential stable duration with the differential value within a preset range.
Optionally, the analyzing the daily load curve distribution of the electric automobile to determine the second electricity consumption behavior characteristic variable includes:
Analyzing daily load curve distribution of the electric automobile to obtain a power curve of a target sampling point, wherein the target sampling point is a sampling point obtained by sampling every 15 minutes within 24 hours;
And determining a second electricity utilization behavior characteristic variable based on the power curve of the target sampling point.
Optionally, the clustering the charging piles according to the target electricity behavior characteristic variable, and determining a clustering center includes:
clustering the charging piles according to the target electricity behavior characteristic variables to obtain clustered clusters, wherein probability density functions of each cluster are different;
And determining a cluster center corresponding to each cluster.
Optionally, the calculating the relative distance between the target object and the clustering center, and identifying whether the target object is a default electricity utilization user based on the relative distance, includes:
Calculating the relative distance between a target object and the clustering center of the cluster corresponding to the target object;
and determining the target object with the relative distance larger than the distance threshold as an illegal electricity utilization user.
An electric vehicle charging facility default electricity consumption identification device, comprising:
The first analysis unit is used for analyzing the charging data of the electric automobile to obtain a first electric behavior characteristic variable;
The second analysis unit is used for analyzing the daily load curve distribution of the electric automobile and determining a second electricity consumption behavior characteristic variable;
the combination unit is used for combining the first electricity behavior characteristic variable and the second electricity behavior characteristic variable to obtain a target electricity behavior characteristic variable;
The clustering unit is used for clustering the charging piles according to the target electricity consumption behavior characteristic variables and determining a clustering center;
and the identification unit is used for calculating the relative distance between the target object and the clustering center and identifying whether the target object is a default electricity utilization user or not based on the relative distance.
Optionally, the first electrical behavior characteristic variable comprises a median, a number of days at intervals, a variation coefficient and a mean difference order of a time sequence of the daily electricity consumption;
the median represents average power consumption capacity, the interval days represent days when the power consumption is lower than a power consumption threshold, the variation coefficient represents fluctuation condition of data, and the stationary differential order represents stationary degree of the data;
The second electricity consumption behavior characteristic variables comprise load intermittent duration and differential stable duration, wherein the load intermittent duration represents the time of day of uncharged time, the differential stable duration is the first-order difference of the extracted power curve, and the differential stable duration with the differential value within a preset range.
Optionally, the second analysis unit is specifically configured to:
Analyzing daily load curve distribution of the electric automobile to obtain a power curve of a target sampling point, wherein the target sampling point is a sampling point obtained by sampling every 15 minutes within 24 hours;
And determining a second electricity utilization behavior characteristic variable based on the power curve of the target sampling point.
Optionally, the clustering unit is specifically configured to:
clustering the charging piles according to the target electricity behavior characteristic variables to obtain clustered clusters, wherein probability density functions of each cluster are different;
Determining a clustering center corresponding to each cluster;
The identification unit is specifically configured to:
Calculating the relative distance between a target object and the clustering center of the cluster corresponding to the target object;
and determining the target object with the relative distance larger than the distance threshold as an illegal electricity utilization user.
Compared with the prior art, the invention provides a method and a device for identifying illegal electricity consumption of an electric vehicle charging facility, which comprise the steps of analyzing charging data of an electric vehicle to obtain a first electricity behavior characteristic variable, analyzing daily load curve distribution of the electric vehicle to determine a second electricity behavior characteristic variable, combining the first electricity behavior characteristic variable and the second electricity behavior characteristic variable to obtain a target electricity behavior characteristic variable, clustering charging piles according to the target electricity behavior characteristic variable to determine a clustering center, calculating the relative distance between a target object and the clustering center, and identifying whether the target object is an illegal electricity consumption user or not based on the relative distance. According to the invention, the identification process does not need to rely on manual investigation, so that the identification efficiency and coverage rate of the illegal users of the electric vehicle charging facilities are improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a method for identifying default electricity consumption of an electric vehicle charging facility according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a high power curve according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a medium-power curve according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a low power curve according to an embodiment of the present invention;
FIG. 5 is a 96-point active power curve of a user on a certain day according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a cluster of 96-point daily active power curves for a user for one month in succession, provided by an embodiment of the present invention;
FIG. 7 is a schematic diagram of low-voltage power consumption median distribution according to an embodiment of the present invention;
FIG. 8 is a diagram showing a low-voltage electric wave distribution diagram according to an embodiment of the present invention;
FIG. 9 is a probability density chart of each attribute of cluster 1 according to an embodiment of the present invention;
FIG. 10 is a probability density chart of each attribute of cluster 2 according to an embodiment of the present invention;
FIG. 11 is a probability density chart of each attribute of cluster 3 according to an embodiment of the present invention;
FIG. 12 is a schematic diagram of a discrete point detection distance error according to an embodiment of the present invention;
fig. 13 is a schematic structural diagram of an electric vehicle charging facility default electricity consumption identification device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The terms first and second and the like in the description and in the claims and in the above-described figures are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to the listed steps or elements but may include steps or elements not expressly listed.
According to the method for identifying the illegal electricity consumption of the electric vehicle charging facility, based on the characteristic analysis of the charging electric quantity time sequence and the daily load curve, the average value, the discontinuous days, the variation coefficient, the stability differential order, the intermittent duration of the daily load curve and the differential stable duration of the daily electric quantity time sequence are extracted to serve as electricity consumption behavior characteristic variables through statistical analysis of the charging characteristics and the travel rule of the electric vehicle, the charging piles are clustered according to the extracted electricity consumption characteristics, the relative distance from a sample object to a clustering center is calculated, the degree that the object belongs to a clustering cluster is evaluated, and then the illegal electricity consumption suspected user is identified based on a preset reasonable threshold.
Referring to fig. 1, the method for identifying default electricity consumption of an electric vehicle charging facility provided by the embodiment of the invention may include the following steps:
s101, analyzing charging data of the electric automobile to obtain a first electric behavior characteristic variable.
S102, analyzing the daily load curve distribution of the electric automobile, and determining a second electricity utilization behavior characteristic variable.
S103, combining the first electricity behavior characteristic variable and the second electricity behavior characteristic variable to obtain a target electricity behavior characteristic variable.
In order to extract complete characteristic variables of a charging electric quantity time sequence, the embodiment of the invention mainly analyzes charging data of an electric vehicle and daily load curve distribution of the electric vehicle to respectively obtain a first electric behavior characteristic variable and a second electric behavior characteristic variable, wherein the first electric behavior characteristic variable and the second electric behavior characteristic variable comprise a plurality of characteristic variables. The first electricity behavior characteristic variable comprises a median, a number of interval days, a variation coefficient and a smooth differential order of a daily electricity consumption time sequence, wherein the median represents average electricity consumption capacity, the number of interval days represents the number of days when the electricity consumption is lower than an electricity consumption threshold, the variation coefficient represents fluctuation condition of data, and the smooth differential order represents stability of the data.
The second electricity consumption behavior characteristic variables comprise load intermittent duration and differential stable duration, wherein the load intermittent duration represents the time of day of uncharged time, the differential stable duration is the first-order difference of the extracted power curve, and the differential stable duration with the differential value within a preset range.
And then, combining the first electricity behavior characteristic variable and the second electricity behavior characteristic variable to obtain a target electricity behavior characteristic variable, namely all behavior characteristic variables for subsequent analysis.
S104, clustering the charging piles according to the target electricity consumption behavior characteristic variables, and determining a clustering center.
S105, calculating the relative distance between the target object and the clustering center, and identifying whether the target object is a default electricity utilization user or not based on the relative distance.
And clustering the charging piles according to the extracted target electricity behavior characteristic variables, and determining a corresponding clustering center in the clustering process. The target object is a user needing to be identified, then the relative distance between the target object and the clustering center is calculated, and the relative distance is compared with a preset threshold value, so that whether the target object belongs to a clustering cluster corresponding to the clustering center can be determined, and whether the target object is a suspected user with illegal electricity consumption is determined.
In one embodiment of the invention, the analysis of the daily load curve distribution of the electric automobile to determine the second electricity consumption behavior characteristic variable comprises the steps of analyzing the daily load curve distribution of the electric automobile to obtain a power curve of a target sampling point, wherein the target sampling point is a sampling point obtained by sampling every 15 minutes within 24 hours, and determining the second electricity consumption behavior characteristic variable based on the power curve of the target sampling point.
In the embodiment of the invention, the characteristic variables are selected as final target electricity consumption characteristic variables, and the characteristic variables of the electricity consumption behaviors can reflect the actual electricity consumption behaviors of users by analyzing the daily electricity consumption curve rule and the 96-point load curve rule, so that accurate judgment can be made.
When the daily electricity quantity curve rule is analyzed, the daily electricity quantity curve set in the adjacent range of the average value of the 3-section daily electricity quantity is randomly extracted, the distribution and change rule is observed, and as can be seen from the figures 2-4, the curve has large fluctuation up and down, the trend is stable, no obvious rising or falling trend exists, the continuous electricity utilization interruption of the high electricity quantity is not obvious, the intermittent electricity utilization of the medium electricity quantity is obvious, and the intermittent electricity utilization of the low electricity quantity is obvious. Fig. 2 is a high-power curve schematic diagram, fig. 3 is a medium-power curve schematic diagram, and fig. 4 is a low-power curve schematic diagram.
Referring to fig. 5 and 6, fig. 5 is a 96-point active power curve of a certain user on a certain day, and fig. 6 is a schematic diagram of a 96-point active power curve cluster of a certain user on a day for one month. 96 points means that the instantaneous power value is sampled every 15 minutes, so that there are 96 points of power values per day. And analyzing a 96-point load curve rule, wherein the power rises and continues instantaneously when charging, the power decreases instantaneously after charging is finished, and the power remains low all the time when not charging, namely, the daily load curve becomes intermittent power utilization, the power utilization starts to finish, and the abrupt rise and fall mutation appears as superposition of a plurality of piecewise constant function curves. Putting together the daily power curves for each period of time finds that the daily charging periods are similar, and indicates that the user travels regularly.
And selecting the median, the break days, the variation coefficient and the stationarity differential order of the daily electricity quantity time sequence as the electricity consumption behavior characteristic attribute according to the characteristics of the service data.
The median can describe the average power consumption capability, and can avoid the influence of extreme values to a certain extent, and can judge from the distribution of the power consumption capability, the median is lower than the average value, and referring to fig. 7, a schematic diagram of the low-voltage power consumption median distribution provided by the embodiment of the invention is shown, and the distribution of low-voltage power consumption low-power users is more dense.
When the electricity consumption of one day is empty or lower than 0.2, the day is estimated to be unmanned, the day is defined as the discontinuous day, the discontinuous day of the charging pile is counted, and as can be seen from the table 1, 67% of low-voltage users have discontinuous electricity consumption, and the low-voltage discontinuous electricity consumption is estimated to belong to normal electricity consumption behaviors.
TABLE 1
| Statistics of days of interval | Low voltage user |
| count | 5233 |
| mean | 34.96 |
| std | 36.82 |
| min | 0 |
| 25% | 0 |
| 50% | 18 |
| 75% | 72 |
| max | 92 |
| Number of users with a break of 92 days | 710 |
| Number of users with number of break days of 0 | 1726 |
The variation coefficient is that the variation coefficient (standard deviation/mean) can describe the fluctuation condition of data to a certain extent, and the larger the variation coefficient is, the larger the sequence fluctuation is. As can be seen from the low-voltage electric fluctuation distribution diagram shown in fig. 8, the low-voltage charging pile has large electric fluctuation in normal use.
And (3) stability, namely carrying out stability check on the data by adopting a unit root check (ADF) method, determining whether the data sequence has trend, and when the data is stable, gradually differentiating and checking until the data is stable, and recording the final differentiation order. When the order is 0, the data is stable, other numbers represent that the data is not stable, and the data is stable after n steps are different. It can be seen from table 2 that the low-voltage user is mostly stationary.
TABLE 2
| N-order difference post-stabilization | Stability of the product | Low voltage subscriber number | Duty ratio of |
| 0 | Smooth and steady | 4335 | 82.84% |
| 1 | Non-stationary | 862 | 16.47% |
| >=2 | Non-stationary | 36 | 0.69% |
When the characteristic variable of the daily load curve is refined, the intermittent duration and the differential stable duration of the daily load curve are selected as the characteristic attribute of the electricity consumption behavior, namely the characteristic variable of the second electricity consumption behavior according to the characteristics of the service data.
And the load intermittence is that the electric power used by the charging pile in the two charging intermittence periods is very low, when the active power is lower than 2, the charging pile is supposed to be uncharged, and the charging time of the day is counted and is defined as the load intermittence time. The long intermittent time presumes normal electricity consumption, and the short intermittent time indicates that the long continuous electricity consumption presumes abnormal electricity consumption.
Load step-wise-during a charging event, the charging power is relatively stable, with the power rising or falling instantaneously when charging begins or ends, and therefore, the individual charging peg daily power profile typically exhibits a piecewise constant function characteristic, i.e., a step-wise. Fitting a power curve function, deriving a derivative function, the derivative function value exhibiting a majority of fluctuations around zero values with a minority of extremes. Taking the first-order difference of the power curve, defining the difference as stable when the difference value is between plus and minus 0.1, counting the stable duration of the difference, and presuming that normal electricity is used for a long time, otherwise, abnormal electricity is used.
In one possible implementation manner of the invention, the clustering of the charging piles according to the target electricity behavior characteristic variable comprises the steps of clustering the charging piles according to the target electricity behavior characteristic variable to obtain clustered clusters, wherein probability density functions of each cluster are different, and determining a clustering center corresponding to each cluster.
Correspondingly, calculating the relative distance between the target object and the clustering center, and identifying whether the target object is a default electricity utilization user based on the relative distance comprises calculating the relative distance between the target object and the clustering center of the cluster corresponding to the target object, and determining the target object with the relative distance larger than a distance threshold as the default electricity utilization user.
Specifically, the electric charging piles are clustered according to the extracted electric characteristic variables (also called as electric characteristic attributes), the distance (or relative distance) from the target object to the clustering center is calculated, the degree of the object belonging to the clustering cluster is estimated according to the distance, and the illegal electric user identification is performed.
And aiming at the sample data condition, selecting the median, the break days, the variation coefficient, the stability differential order, the 96-point active power curve batch duration of the recent week and the differential stability duration of the recent daily electric quantity time sequence of one month as the power consumption behavior characteristic attribute. Since 96 points of load data are not collected by the common electric meter, the characteristic attribute of the time sequence of the recent daily electric quantity for one month is selected. Aiming at the existing sample data situation, a K-Means clustering algorithm is adopted and is divided into 3 classes, probability density functions of each cluster are shown in fig. 9 to 11, fig. 9 shows probability density diagrams of each attribute of a cluster 1, fig. 10 shows probability density diagrams of each attribute of a cluster 2, and fig. 11 shows probability density diagrams of each attribute of a cluster 3.
The group 1 is characterized in that the solar electricity quantity median is concentrated between 0 and 2, the variation coefficient is concentrated between 1 and 4, and the discontinuous days are concentrated between 30 and 90 days.
The group 2 is characterized in that the solar electricity quantity median is concentrated between 0 and 80, the variation coefficient is concentrated between 0 and 3, and the discontinuous days are concentrated between 0 and 30 days.
The group 3 is characterized in that the solar electricity quantity median is concentrated between 0 and 120, the variation coefficient is concentrated between 0 and 2, and the discontinuous days are concentrated between 0 and 10 days.
The electric quantity middles of the 1 day of the subgroups are smaller, the fluctuation is large, the intermittence is obvious, meanwhile, the electric quantity middles of the 2 day of the subgroups are smooth according to the unit root test (ADF), the intermittence is at a medium level, meanwhile, the electric quantity middles of the 2 day of the subgroups are smooth according to the unit root test (ADF), the electric quantity middles of the 4 day of the subgroups are large, the fluctuation is small, the intermittence is not obvious, and the electric quantity middles of the 3 day of the subgroups are non-smooth according to the unit root test (ADF), and the electric quantity of the 4 day of the subgroups is a commercial electric charging pile with large capacity.
The relative distance between each sample (i.e., the target object) and each cluster center is calculated, the outlier samples are analyzed, the threshold is set to 3, and 111 default electricity utilization users are identified from 5233 low-voltage users, see fig. 12, which is a distance error diagram, the abscissa is the number, the ordinate is the relative distance, the light gray represents the normal users, and the dark gray represents the abnormal users.
The embodiment of the invention provides an electric vehicle charging facility default electricity consumption identification method, which comprises the steps of analyzing electric vehicle charging data to obtain a first electricity behavior characteristic variable, analyzing daily load curve distribution of an electric vehicle to determine a second electricity behavior characteristic variable, combining the first electricity behavior characteristic variable and the second electricity behavior characteristic variable to obtain a target electricity behavior characteristic variable, clustering charging piles according to the target electricity behavior characteristic variable to determine a clustering center, calculating the relative distance between a target object and the clustering center, and identifying whether the target object is a default electricity consumption user or not based on the relative distance. According to the invention, the identification process does not need to rely on manual investigation, so that the identification efficiency and coverage rate of the illegal users of the electric vehicle charging facilities are improved.
Based on the above embodiment, the embodiment of the present invention further provides an electric vehicle charging facility default electricity consumption identification device, referring to fig. 13, including:
The first analysis unit 10 is configured to analyze the electric vehicle charging data to obtain a first electrical behavior characteristic variable;
The second analysis unit 20 is configured to analyze the daily load curve distribution of the electric vehicle, and determine a second electricity consumption behavior feature variable;
a combination unit 30, configured to combine the first electrical behavior feature variable and the second electrical behavior feature variable to obtain a target electrical behavior feature variable;
A clustering unit 40, configured to cluster the charging piles according to the target electricity behavior feature variable, and determine a clustering center;
the identifying unit 50 is configured to calculate a relative distance between the target object and the clustering center, and identify whether the target object is a default electricity user based on the relative distance.
Further, the first electrical behavior characteristic variables comprise a median, a number of days at intervals, a variation coefficient and a mean difference order of a time sequence of the daily electricity consumption;
the median represents average power consumption capacity, the interval days represent days when the power consumption is lower than a power consumption threshold, the variation coefficient represents fluctuation condition of data, and the stationary differential order represents stationary degree of the data;
The second electricity consumption behavior characteristic variables comprise load intermittent duration and differential stable duration, wherein the load intermittent duration represents the time of day of uncharged time, the differential stable duration is the first-order difference of the extracted power curve, and the differential stable duration with the differential value within a preset range.
Further, the second analysis unit is specifically configured to:
Analyzing daily load curve distribution of the electric automobile to obtain a power curve of a target sampling point, wherein the target sampling point is a sampling point obtained by sampling every 15 minutes within 24 hours;
And determining a second electricity utilization behavior characteristic variable based on the power curve of the target sampling point.
Further, the clustering unit is specifically configured to:
clustering the charging piles according to the target electricity behavior characteristic variables to obtain clustered clusters, wherein probability density functions of each cluster are different;
Determining a clustering center corresponding to each cluster;
The identification unit is specifically configured to:
Calculating the relative distance between a target object and the clustering center of the cluster corresponding to the target object;
and determining the target object with the relative distance larger than the distance threshold as an illegal electricity utilization user.
The embodiment of the invention provides an electric vehicle charging facility default electricity consumption identification device which comprises a first analysis unit for analyzing electric vehicle charging data to obtain a first electricity behavior characteristic variable, a second analysis unit for analyzing daily load curve distribution of the electric vehicle to determine a second electricity behavior characteristic variable, a combination unit for combining the first electricity behavior characteristic variable and the second electricity behavior characteristic variable to obtain a target electricity behavior characteristic variable, a clustering unit for clustering charging piles according to the target electricity behavior characteristic variable to determine a clustering center, and an identification unit for calculating the relative distance from a target object to the clustering center and identifying whether the target object is a default electricity consumption user based on the relative distance. According to the invention, the identification process does not need to rely on manual investigation, so that the identification efficiency and coverage rate of the illegal users of the electric vehicle charging facilities are improved.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (7)
1. The utility model provides an electric motor car charging facility violating electricity consumption identification method which is characterized by comprising the following steps:
analyzing the charging data of the electric automobile to obtain a first electric behavior characteristic variable;
Analyzing the daily load curve distribution of the electric automobile to determine a second electricity consumption behavior characteristic variable;
Combining the first electricity behavior characteristic variable and the second electricity behavior characteristic variable to obtain a target electricity behavior characteristic variable;
Clustering the charging piles according to the target electricity behavior characteristic variables to determine a clustering center;
Calculating the relative distance between a target object and a clustering center, and identifying whether the target object is a default electricity utilization user or not based on the relative distance;
The first electricity behavior characteristic variable comprises a median, a number of days at intervals, a variation coefficient and a smooth difference order of a daily electricity consumption time sequence;
the median represents average power consumption capacity, the interval days represent days when the power consumption is lower than a power consumption threshold, the variation coefficient represents fluctuation condition of data, and the stationary differential order represents stationary degree of the data;
The second electricity consumption behavior characteristic variables comprise load intermittent duration and differential stable duration, wherein the load intermittent duration represents the time of day of uncharged time, the differential stable duration is the first-order difference of the extracted power curve, and the differential stable duration with the differential value within a preset range.
2. The method of claim 1, wherein analyzing the daily load profile of the electric vehicle to determine the second electrical performance characteristic variable comprises:
Analyzing daily load curve distribution of the electric automobile to obtain a power curve of a target sampling point, wherein the target sampling point is a sampling point obtained by sampling every 15 minutes within 24 hours;
And determining a second electricity utilization behavior characteristic variable based on the power curve of the target sampling point.
3. The method of claim 1, wherein the clustering the charging piles according to the target electricity behavior feature variable, determining a cluster center, comprises:
clustering the charging piles according to the target electricity behavior characteristic variables to obtain clustered clusters, wherein probability density functions of each cluster are different;
And determining a cluster center corresponding to each cluster.
4. The method of claim 3, wherein the calculating the relative distance of the target object to the cluster center and identifying whether the target object is a contraband electricity consumer based on the relative distance comprises:
Calculating the relative distance between a target object and the clustering center of the cluster corresponding to the target object;
and determining the target object with the relative distance larger than the distance threshold as an illegal electricity utilization user.
5. An electric vehicle charging facility default electricity consumption identification device, characterized by comprising:
The first analysis unit is used for analyzing the charging data of the electric automobile to obtain a first electric behavior characteristic variable;
The second analysis unit is used for analyzing the daily load curve distribution of the electric automobile and determining a second electricity consumption behavior characteristic variable;
the combination unit is used for combining the first electricity behavior characteristic variable and the second electricity behavior characteristic variable to obtain a target electricity behavior characteristic variable;
The clustering unit is used for clustering the charging piles according to the target electricity consumption behavior characteristic variables and determining a clustering center;
The identification unit is used for calculating the relative distance between the target object and the clustering center and identifying whether the target object is a default electricity utilization user or not based on the relative distance;
The first electricity behavior characteristic variable comprises a median, a number of days at intervals, a variation coefficient and a smooth difference order of a daily electricity consumption time sequence;
the median represents average power consumption capacity, the interval days represent days when the power consumption is lower than a power consumption threshold, the variation coefficient represents fluctuation condition of data, and the stationary differential order represents stationary degree of the data;
The second electricity consumption behavior characteristic variables comprise load intermittent duration and differential stable duration, wherein the load intermittent duration represents the time of day of uncharged time, the differential stable duration is the first-order difference of the extracted power curve, and the differential stable duration with the differential value within a preset range.
6. The apparatus according to claim 5, wherein the second analysis unit is specifically configured to:
Analyzing daily load curve distribution of the electric automobile to obtain a power curve of a target sampling point, wherein the target sampling point is a sampling point obtained by sampling every 15 minutes within 24 hours;
And determining a second electricity utilization behavior characteristic variable based on the power curve of the target sampling point.
7. The apparatus of claim 5, wherein the clustering unit is specifically configured to:
clustering the charging piles according to the target electricity behavior characteristic variables to obtain clustered clusters, wherein probability density functions of each cluster are different;
Determining a clustering center corresponding to each cluster;
The identification unit is specifically configured to:
Calculating the relative distance between a target object and the clustering center of the cluster corresponding to the target object;
and determining the target object with the relative distance larger than the distance threshold as an illegal electricity utilization user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111027540.5A CN113705710B (en) | 2021-09-02 | 2021-09-02 | Method and device for identifying electricity usage violations of electric vehicle charging facilities |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111027540.5A CN113705710B (en) | 2021-09-02 | 2021-09-02 | Method and device for identifying electricity usage violations of electric vehicle charging facilities |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113705710A CN113705710A (en) | 2021-11-26 |
| CN113705710B true CN113705710B (en) | 2025-02-28 |
Family
ID=78657527
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111027540.5A Active CN113705710B (en) | 2021-09-02 | 2021-09-02 | Method and device for identifying electricity usage violations of electric vehicle charging facilities |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113705710B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116968586B (en) * | 2022-09-15 | 2025-03-04 | 中移物联网有限公司 | Charging control method, device, communication equipment and readable storage medium |
| CN115923573B (en) * | 2022-11-14 | 2024-10-25 | 中国南方电网有限责任公司 | Charging pile power regulation and control method and system |
| CN116756638B (en) * | 2023-08-17 | 2023-11-14 | 广东电网有限责任公司汕头供电局 | Method, device, equipment and storage medium for detecting electric load demand of electric vehicle |
| CN117565724B (en) * | 2023-10-12 | 2024-07-19 | 国网浙江省电力有限公司金华供电公司 | Method for identifying abnormal state of charging pile |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111738364A (en) * | 2020-08-05 | 2020-10-02 | 国网江西省电力有限公司供电服务管理中心 | An electricity theft detection method based on the combination of user load and electricity consumption parameters |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105825298B (en) * | 2016-03-14 | 2020-05-01 | 梁海东 | Power grid metering early warning system and method based on load characteristic estimation |
| CN109947815B (en) * | 2018-09-30 | 2023-06-23 | 国网浙江长兴县供电有限公司 | A Method of Stealing Electricity Identification Based on Outlier Algorithm |
| CN109752613B (en) * | 2018-12-31 | 2021-01-26 | 天津求实智源科技有限公司 | Non-invasive load monitoring-based default electricity detection system and method |
| CN112183900B (en) * | 2020-11-05 | 2022-08-09 | 山东德佑电气股份有限公司 | Cluster analysis-based power consumption analysis and optimal scheduling method |
| CN112632153B (en) * | 2020-12-29 | 2023-10-20 | 国网安徽省电力有限公司 | Illegal electricity consumption identification method and device |
| CN113033598A (en) * | 2021-01-20 | 2021-06-25 | 昆明理工大学 | Electricity stealing identification method based on curve similarity and integrated learning algorithm |
-
2021
- 2021-09-02 CN CN202111027540.5A patent/CN113705710B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111738364A (en) * | 2020-08-05 | 2020-10-02 | 国网江西省电力有限公司供电服务管理中心 | An electricity theft detection method based on the combination of user load and electricity consumption parameters |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113705710A (en) | 2021-11-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113705710B (en) | Method and device for identifying electricity usage violations of electric vehicle charging facilities | |
| CN109146705B (en) | Method for detecting electricity stealing by using electricity characteristic index dimension reduction and extreme learning machine algorithm | |
| CN113853528A (en) | Method, device and computer-readable storage medium for identifying abnormal electrical usage | |
| US9156368B2 (en) | Method for detection of plug-in electric vehicle charging via interrogation of smart meter data | |
| CN112633924B (en) | District electric energy substitution demand analysis method based on load decomposition | |
| CN112946483A (en) | Comprehensive evaluation method for battery health of electric vehicle and storage medium | |
| CN111553444A (en) | A load identification method based on non-intrusive load terminal data | |
| CN112488738B (en) | Resident vacant resident identification method and equipment based on electric power big data | |
| CN115660225A (en) | Electricity load prediction management method and system based on ammeter communication module | |
| CN118962573B (en) | A method for detecting a user's power load using an intelligent electric energy meter | |
| CN105096060A (en) | Enterprise operating rate obtaining method based on electric energy service management platform | |
| CN118152836B (en) | Stability evaluation method for operation process of electric energy meter | |
| CN118753096A (en) | A battery aging analysis and monitoring method, system, electronic device and storage medium | |
| CN110047013B (en) | Discontinuous Electricity Stealing Method for Anti-Special User | |
| CN105139287A (en) | Comprehensive electric energy metering device state assessment method integrating safety domain | |
| CN113420728B (en) | Non-invasive air conditioner load identification method and system integrating multi-time scale information | |
| Grigoraş et al. | Use of data from smart meters in optimal operation of distribution systems | |
| CN117565724B (en) | Method for identifying abnormal state of charging pile | |
| US9889759B1 (en) | Market-adaptive detection of plug-in electric vehicle charging using whole house energy metering data | |
| CN118484694A (en) | A precise positioning method for indoor illegal charging | |
| CN112345824A (en) | Variable frequency air conditioner non-invasive identification method based on piecewise linear approximation algorithm | |
| CN117856245A (en) | Grid management-based method, device and storage medium for analyzing line loss of transformer area | |
| Shen et al. | A Novel AI-based Method for EV Charging Load Profile Clustering | |
| Chen et al. | Data-driven residential customer aggregation based on seasonal behavioral patterns | |
| CN110298996B (en) | Electricity consumption information acquisition system and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |