CN110969539B - Photovoltaic electricity stealing discovery method and system based on curve morphology analysis - Google Patents

Photovoltaic electricity stealing discovery method and system based on curve morphology analysis Download PDF

Info

Publication number
CN110969539B
CN110969539B CN201911191055.4A CN201911191055A CN110969539B CN 110969539 B CN110969539 B CN 110969539B CN 201911191055 A CN201911191055 A CN 201911191055A CN 110969539 B CN110969539 B CN 110969539B
Authority
CN
China
Prior art keywords
output
curve
user set
photovoltaic
curves
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
Application number
CN201911191055.4A
Other languages
Chinese (zh)
Other versions
CN110969539A (en
Inventor
陈海峰
应国德
曹杰
林超
叶一博
周晨牧
陈逸婧
潘成峰
金潮
项冰野
陈肖雄
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
State Grid Zhejiang Wenling Power Supply Co ltd
Wenling Feipu Electric Co ltd
Original Assignee
State Grid Zhejiang Wenling Power Supply Co ltd
Wenling Feipu Electric Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by State Grid Zhejiang Wenling Power Supply Co ltd, Wenling Feipu Electric Co ltd filed Critical State Grid Zhejiang Wenling Power Supply Co ltd
Priority to CN201911191055.4A priority Critical patent/CN110969539B/en
Publication of CN110969539A publication Critical patent/CN110969539A/en
Application granted granted Critical
Publication of CN110969539B publication Critical patent/CN110969539B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Electricity, gas or water supply
    • 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
    • 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
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
    • Y02E40/70—Smart grids as climate change mitigation technology in the energy generation sector
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Abstract

The invention relates to a photovoltaic electricity stealing discovery method and system based on curve morphology analysis, wherein the method comprises the following steps: setting a clustering center of a normal user set, a clustering center of a fault user set and a clustering center of a power stealing user set; calculating the variance of each cluster center; calculating the distance between the variances of the actual curve and the fitting curve of the force rising section and the variances of the clustering centers, and classifying the user for the first time; calculating the distance between the variance of the actual curve and the fitting curve of the force descending section and the variance of each clustering center, and classifying the users for the second time; and judging whether the parameters of the photovoltaic equipment of the users remained in the user set to be examined after the second classification exceed a threshold value, and performing the third classification. The invention designs a discovery algorithm of the photovoltaic electricity stealing behavior, fully excavates the data information of the photovoltaic curve, has less dependence on other information of equipment and users, and has higher universality.

Description

Photovoltaic electricity stealing discovery method and system based on curve morphology analysis
Technical Field
The invention belongs to the technical field of power systems, and particularly relates to a photovoltaic electricity larceny discovery method and system based on curve morphology analysis.
Background
Because the subsidy enjoyed by the distributed photovoltaic power generation mainly depends on the self-generated energy, certain users can drive the distributed photovoltaic internet-surfing ammeter to measure the generated energy more through a certain technical means under the driving of benefits, and further the risk of high-volume subsidy is acquired, and the behavior of cheating subsidy is called as photovoltaic electricity stealing behavior. The action of photovoltaic electricity stealing cheating to get subsidy seriously influences implementation of Chinese new energy support policy, influences fairness of the power generation market, and users bring great potential safety hazards to power supply and distribution due to electricity stealing private line switching and influences normal development of the photovoltaic power generation industry.
Disclosure of Invention
Aiming at the defects of the prior art, the invention discloses a photovoltaic electricity larceny discovery method and system based on curve morphological analysis.
The technical scheme adopted by the invention is as follows:
a photovoltaic electricity stealing discovery method based on curve morphology analysis sets a clustering center of a normal user set, a clustering center of a fault user set and a clustering center of an electricity stealing user set; calculating the variance of each cluster center;
calculating variances of actual curves and fitting curves in the output rising sections aiming at the output curves of the photovoltaic devices of all users, and respectively calculating distances between the variances of the actual curves and the fitting curves of the output rising sections and the variances of the clustering centers, so as to classify the users for the first time;
aiming at the output curves of the photovoltaic devices of the users in the user set to be examined in the first classification, calculating the variances of the actual curves and the fitting curves of the output descending sections, and respectively calculating the distances between the variances of the actual curves and the fitting curves of the output descending sections and the variances of the clustering centers, so as to classify the users for the second time;
setting a highest power generation capacity threshold value and a lowest power generation capacity threshold value of the photovoltaic equipment in unit time, a first-order coefficient threshold value of a Fourier series of an output ascending section and a first-order coefficient threshold value of a Fourier series of an output descending section in an output curve; judging whether the parameters of the photovoltaic equipment of the users left in the user set to be examined after the second classification exceed the corresponding threshold values, if so, classifying the users into the electricity stealing user set, and classifying the rest users into the normal user set.
The further technical scheme is that the parameter calculation method of the Fourier series of the output curve of the photovoltaic equipment in the output rising section is as follows:
a is the zero-order coefficient of the Fourier series of the force rising section; b is a first order coefficient of a Fourier series of the output rising section; n is the data number when collecting data; m is m 0 Numbering data corresponding to sunrise time, m 1 Numbering data corresponding to the time when the output value tends to be stable or is lifted; e (E) p (n) is the amount of power generation per unit time at point n; e (E) ps (n) is the force curve obtained after fitting by using a formula; e (E) p (m 0 ) Is the power generation amount per unit time at sunrise time.
The method for calculating the variance of the actual curve and the fitting curve of the output curve of the photovoltaic equipment in the output rising section comprises the following steps:
the average load of the force rising section is shown as sigma, and the variance between the actual curve and the fitted curve of the force rising section is shown as sigma.
The further technical scheme is that the parameter calculation method of the Fourier series of the output curve of the photovoltaic equipment in the output descending section is as follows:
a' is a zero-order coefficient of a Fourier series of the output descending section; b' is a first-order coefficient of a Fourier series of the output descending section; n is the data number when the data is collected in the output descending section; m is m 2 Numbering data corresponding to the time when the output value starts to continuously decline; m is m 3 Numbering data corresponding to sunset time; e (E) p (n) the power generation amount per unit time at n points; e's' ps (n) is the force curve obtained after fitting by using a formula; e (E) p (m 2 ) Is the power generation amount per unit time in sunset time.
The further technical scheme is that the calculation method of the variance of the actual curve and the fitting curve of the output curve of the photovoltaic equipment in the output descending section is as follows:
for the average load of the force-down section,σ' is the variance of the actual curve and the fitted curve in the force-down segment.
The further technical scheme is that a clustering center of a fault user set is set as follows:
b is a first-order coefficient of a Fourier series of the output rising section; b' is a first-order coefficient of a Fourier series of the output descending section; e (E) pMax The highest generated energy of the photovoltaic equipment in unit time; e (E) pMin Is the lowest power generation amount of the photovoltaic equipment in unit time.
The further technical proposal is that whenWhen the electricity stealing user set is used, the clustering center of the electricity stealing user set is arranged on one side which is larger than the sigma value; when->And->Setting clustering centers of the electricity stealing user set on two sides of a sigma value, wherein sigma is the variance between an actual curve and a fitting curve of an output curve of the photovoltaic equipment in an output rising section; σ' represents the variance of the actual curve and the fitted curve at the force-down segment; e (E) pMax Is the highest power generation amount of the photovoltaic equipment in unit time.
In the first classification, calculating the variances of the actual curves and the fitting curves of the output ascending segments aiming at the output curves of the photovoltaic equipment of all users, and respectively calculating the distances between the variances of the actual curves and the fitting curves of the output ascending segments and the variances of the clustering centers; if the distance between the variance of the actual curve and the fitting curve of the output rising section and the variance of the clustering center of the normal user set is shortest, the users are clustered into the user set to be examined; if the distance between the variance of the actual curve and the fitting curve of the output rising section and the variance of the clustering center of the fault user set is shortest, the users are clustered into the fault user set; if the distance between the variance of the actual curve and the fitted curve of the output rising section and the variance of the clustering center of the electricity stealing user set is shortest, classifying the user sample into the electricity stealing user set;
in the second classification, calculating the variances of the actual curves of the output descending sections and the fitting curves according to the output curves of the photovoltaic devices of the users in the first classification, wherein the user belongs to the user set to be examined, and calculating the distances between the variances of the actual curves of the output descending sections and the fitting curves and the variances of the clustering centers respectively; if the distance between the variance of the actual curve and the fitting curve of the output drop section and the variance of the clustering center of the normal user set is shortest, the user is left in the user set to be inspected; if the distance between the variance of the actual curve and the fitting curve of the output drop section and the variance of the clustering center of the fault user set is shortest, the users are clustered into the fault user set; and if the distance between the variance of the actual curve and the fitted curve of the output drop section and the variance of the clustering center of the electricity stealing user set is shortest, classifying the users into the electricity stealing user set.
A photovoltaic electricity theft discovery system based on curvilinear morphology analysis, comprising:
the cluster center setting and variance calculating module is used for setting the cluster centers of the normal user set, the cluster centers of the fault user set and the cluster centers of the electricity stealing user set and calculating variances of the cluster centers;
the first classification module is used for calculating the variances of the actual curves and the fitting curves in the output ascending sections aiming at the output curves of the photovoltaic equipment of all users, and respectively calculating the distances between the variances of the actual curves and the fitting curves of the output ascending sections and the variances of the clustering centers so as to classify the users for the first time;
the second classification module is used for calculating the variances of the actual curves of the output descending sections and the fitting curves according to the output curves of the photovoltaic devices of the users in the user set to be examined in the first classification, respectively calculating the distances between the variances of the actual curves of the output descending sections and the fitting curves and the variances of the clustering centers, and carrying out the second classification on the users;
the third classification module is provided with a highest power generation capacity threshold value, a lowest power generation capacity threshold value, a first-order coefficient threshold value of the Fourier series of the output ascending section and a first-order coefficient threshold value of the Fourier series of the output descending section of the photovoltaic equipment in unit time; judging whether the parameters of the photovoltaic equipment of the users in the user set to be examined after the second classification exceed a threshold value, if any parameter exceeds the threshold value, classifying the users into the electricity stealing user set, and classifying the rest users into the normal user set.
The method comprises the following steps of obtaining and calculating parameters of the Fourier series of the output curve of the photovoltaic equipment in the output ascending section, variances of the actual curve and the fitting curve of the output curve of the photovoltaic equipment in the output ascending section, variances of the Fourier series of the output curve of the photovoltaic equipment in the output descending section and the actual curve and the fitting curve of the output curve of the photovoltaic equipment in the output descending section.
The beneficial effects of the invention are as follows:
according to the invention, through obtaining the photovoltaic curve information of the photovoltaic equipment and carrying out cluster analysis, the user sample is classified and judged for multiple times, and a discovery algorithm of the photovoltaic electricity stealing behavior is designed, so that the method belongs to the industry for the first time.
The invention fully excavates the data information of the photovoltaic curve, has less dependence on other information of equipment and users, and has higher universality.
Drawings
Fig. 1 is a flow chart of embodiment 1 of the present invention.
Fig. 2 is a flowchart of embodiment 2 of the present invention.
Fig. 3 is a frame structure diagram of embodiment 4 of the present invention.
Fig. 4 is a frame structure diagram of embodiment 5 of the present invention.
Detailed Description
The following describes specific embodiments of the present invention with reference to the drawings.
Example 1.
Fig. 1 is a flow chart of embodiment 1 of the present invention. As shown in fig. 1, the photovoltaic electricity theft discovery method based on curve morphology analysis in embodiment 1 includes:
s101, setting a clustering center of a normal user set, a clustering center of a fault user set and a clustering center of a power stealing user set; calculating the variance of each cluster center;
s102, calculating variances of actual curves and fitting curves in the output ascending sections aiming at output curves of all photovoltaic devices of users, and respectively calculating distances between the variances of the actual curves and the fitting curves of the output ascending sections and variances of clustering centers, so that the users are classified for the first time: if the variance between the actual curve and the fitted curve of the output rising section is equal to the normal user set S n The distance between the variances of the cluster centers of the (B) is shortest, and the users are clustered into a user set S to be examined u The method comprises the steps of carrying out a first treatment on the surface of the If the distance between the variance of the actual curve and the fitting curve of the output rising section and the variance of the clustering center of the fault user set is shortest, the user is clustered into a fault user set S b The method comprises the steps of carrying out a first treatment on the surface of the If the distance between the variance of the actual curve and the fitting curve of the output rising section and the variance of the clustering center of the electricity stealing user set is shortest, the user samples are clustered into the electricity stealing user set S s 。
S103, classifying the user set S to be examined in the first classification u The method comprises the steps of calculating variances of actual curves and fitting curves of the output descending segments of output curves of the photovoltaic equipment of users, calculating distances between the variances of the actual curves and the fitting curves of the output descending segments and the variances of the clustering centers of the output descending segments respectively, and classifying the users for the second time: if the variance between the actual curve and the fitted curve of the output drop section is equal to the normal user set S n The distance between the variances of the cluster centers of (a) is the shortest, leaving the user in the set of users to be examined S u The method comprises the steps of carrying out a first treatment on the surface of the Variance of actual curve and fitting curve of output drop section and fault user set S b The distance between the variances of the cluster centers of (a) is shortest, and the users are clustered into a fault user set S b The method comprises the steps of carrying out a first treatment on the surface of the Variance and sum of actual curve and fitted curve of output drop sectionSet S of electricity stealing users s The distance between the variances of the cluster centers of (a) is shortest, and the users are clustered into a power stealing user set S s 。
S104, setting a highest power generation capacity threshold value and a lowest power generation capacity threshold value of the photovoltaic equipment in unit time, a first-order coefficient threshold value of the Fourier series of the power output ascending section and a first-order coefficient threshold value of the Fourier series of the power output descending section in the power output curve; judging the user set S to be examined after the second classification s If any parameter exceeds the threshold, the users are grouped into a power stealing user set S s And judging that the user has electricity stealing behavior. The rest users are regarded as normal photovoltaic equipment and count into a normal user set S n 。
Example 1 shows the core flow of the clustering algorithm involved in the present invention.
Example 2.
Fig. 2 is a flow chart of the method of embodiment 2, as shown in fig. 2, in embodiment 2, a photovoltaic electricity theft discovery method based on curve morphology analysis includes:
s201, calculating all parameters of Fourier series of an output rising section in an output curve aiming at the output curves of all the photovoltaic devices of users:
in the formula (1), a is a starting point parameter, and is a zero-order coefficient (average value) of a Fourier series of an output rising section; b is a first-order coefficient of the Fourier series of the output rising section and is directly related to the fluctuation degree of the curve; n is the value of the abscissa of the output curve, the output curve is the discrete curve, the abscissa value is the discrete point, n represents the data number when data is acquired, the number when data is acquired for the first time every day is 0, the number when data is acquired for the second time is 1, and so on. m is m 0 At sunrise timeData number corresponding to m 1 Numbering data corresponding to the time when the output value tends to be stable or is lifted; e (E) p (n) is the amount of power generation per unit time at point n; e (E) ps (n) is the force curve obtained after fitting by using a formula; e (E) p (m 0 ) Is the power generation amount per unit time at sunrise time.
S202, variance of actual curve and fitting curve of output curve of photovoltaic equipment in output rising section:
in the formula (2), the amino acid sequence of the compound,the average load of the force-rising segment is shown, and sigma represents the variance of the actual curve and the fitted curve in the force-rising segment.
S203, calculating each parameter of the Fourier series of the output descending section in the output curve according to the output curve of the photovoltaic equipment:
in the formula (3), a' is a starting point parameter, and is a zero-order coefficient (average value) of a Fourier series of the output descending section; b' is a first-order coefficient of the Fourier series of the output descending section and is directly related to the fluctuation degree of the curve; n is the data number when collecting data; m is m 2 Numbering data corresponding to the time when the output value starts to continuously decline; m is m 3 Numbering data corresponding to sunset time; e (E) p The (n) table is the amount of power generation per unit time at the n points. The method comprises the steps of carrying out a first treatment on the surface of the E's' ps (n) is the force curve obtained after fitting by using a formula; e (E) p (m 2 ) Is the power generation amount per unit time in sunset time.
S204, variance of actual curve and fitting curve of the output curve in the output drop section:
in the formula (4), the amino acid sequence of the compound,representing the average load of the force-down segment, σ' represents the variance of the actual curve and the fitted curve in the force-down segment.
S205, calculating the highest generated energy E of the photovoltaic equipment in unit time in one day pMax Minimum electric power generation E pMin 。
S206, selecting a trusted photovoltaic user as a clustering center of the normal user set. Users in long-term partnerships with power stations may be defined as trusted photovoltaic users.
S207, setting a clustering center of a fault user set as follows:
s208, whenWhen the electricity stealing user set is used, the clustering center of the electricity stealing user set is arranged on one side which is larger than the sigma value; when (when)And->And setting clustering centers of the electricity stealing user set on two sides of the sigma value.
S209, examining the variance sigma of the actual curve and the fitting curve of the output curve of the photovoltaic equipment of the user in the output rising section. The distance is defined as follows:
d σ ＝|σ-σ c | (5)
in the formula (5), d σ Representing distance. Sigma (sigma) c Is the variance of the cluster center of each user set of the force rising section.
Calculating the distance d between the variances of the actual curve and the fitting curve of the force rising section and the variances of the clustering centers σ : if the distance between the variance of the actual curve and the fitting curve of the output rising section and the variance of the clustering center of the normal user set is shortest, the users are clustered into a user set S to be examined u The method comprises the steps of carrying out a first treatment on the surface of the If the distance between the variance of the actual curve and the fitting curve of the output rising section and the variance of the clustering center of the fault user set is shortest, the user is clustered into a fault user set S b The method comprises the steps of carrying out a first treatment on the surface of the If the distance between the variance of the actual curve and the fitting curve of the output rising section and the variance of the clustering center of the electricity stealing user set is shortest, the user samples are clustered into the electricity stealing user set S s 。
S210, in the examining step S209, a user set S to be examined u The variance sigma' of the actual curve and the fitted curve of the output drop section of the photovoltaic curve of the photovoltaic equipment of the sample in (a). The distance is defined as follows:
d σ′ ＝|σ′-σ c ′| (6)
in the formula (6), d σ′ Representing distance. Sigma (sigma) c 'is the variance σ' of the cluster centers of the individual user sets of the force-down segment.
For the inclusion of the survey user set S in step S209 u The variance of the actual curve and the fitting curve of the output drop section is calculated according to the output curve of the photovoltaic equipment of the user, and the distance between the variance of the actual curve and the fitting curve of the output drop section and the variance of each clustering center is calculated respectively: if the distance between the variance of the actual curve and the fitting curve of the output drop section and the variance of the clustering center of the normal user set is shortest, the user is left in the user set S to be inspected u The method comprises the steps of carrying out a first treatment on the surface of the If the distance between the variance of the actual curve and the fitting curve of the output drop section and the variance of the clustering center of the fault user set is shortest, the user is clustered into a fault user set S b The method comprises the steps of carrying out a first treatment on the surface of the If the distance between the variance of the actual curve and the fitting curve of the output drop section and the variance of the clustering center of the electricity stealing user set is shortest, the users are clustered into the electricity stealing user set S s 。
S211, observing the user set S remained in the step S210 to be examined u User samples of (a); setting a highest power generation capacity threshold value and a lowest power generation capacity threshold value of the photovoltaic equipment in unit time, a first-order coefficient threshold value of a Fourier series of an output ascending section and a first-order coefficient threshold value of a Fourier series of an output descending section in an output curve; maximum power generation E of photovoltaic device in unit time pMax Minimum electric power generation E pMin If any one of the first-order coefficient b of the Fourier series of the output rising section and the first-order coefficient b' of the Fourier series of the output falling section in the output curve is higher than the corresponding threshold value, judging that the electricity stealing behavior exists, and classifying the corresponding users into an electricity stealing user set S s . In step S210, the user set S to be examined is left u The remaining user samples of (a) are considered as normal photovoltaic devices, and are counted into a normal user set S n 。
Example 2 is a further detail and refinement based on example 1, specifically disclosing a method and a calculation formula for obtaining respective information of a photovoltaic curve.
Example 3.
Example 3 is a verification of the actual operation performed on the basis of example 2. The procedure of example 3 is exactly the same as that of example 2. Example 3 was targeted for a search by 386 photovoltaic users in the city of the temperature-limited, zhejiang. The daily sampling frequency of the 386 photovoltaic users is 288 points. Among the users, one user has a long-term cooperative relationship with Wen Lingshi power supply company and belongs to a trusted user, so that the index of the user is set as a clustering center.
And analyzing the data of 7 months in 2019, extracting parameters such as rising section Fourier parameters, falling section Fourier parameters, maximum and minimum power generation amount in unit time and the like of each sample for analysis. And in the Fourier parameter analysis link, the suspected electricity stealing behavior of 3 users is found. And in the clustering link of the maximum and minimum generated energy, the suspected electricity stealing behavior of 1 user is found. And after the personnel check on the door, the electricity stealing behavior of the 4 users is confirmed to be true. Example 3 directly demonstrates the reliability and convenient operability of the present invention.
Example 4.
Fig. 3 is a schematic diagram of a frame structure of embodiment 4 of the present invention. As shown in fig. 3, embodiment 4 is a photovoltaic electricity theft discovery system based on curve morphology analysis, comprising:
the cluster center setting and variance calculating module is used for setting the cluster centers of the normal user set, the cluster centers of the fault user set and the cluster centers of the electricity stealing user set and calculating variances of the cluster centers;
the first classification module is used for calculating the variances of the actual curves and the fitting curves in the output ascending sections aiming at the output curves of the photovoltaic equipment of all users, and respectively calculating the distances between the variances of the actual curves and the fitting curves of the output ascending sections and the variances of the clustering centers so as to classify the users for the first time;
the second classification module is used for calculating the variances of the actual curves of the output descending sections and the fitting curves according to the output curves of the photovoltaic devices of the users in the user set to be examined in the first classification, respectively calculating the distances between the variances of the actual curves of the output descending sections and the fitting curves and the variances of the clustering centers, and carrying out the second classification on the users;
the third classification module is provided with a highest power generation capacity threshold value, a lowest power generation capacity threshold value, a first-order coefficient threshold value of the Fourier series of the output ascending section and a first-order coefficient threshold value of the Fourier series of the output descending section of the photovoltaic equipment in unit time; judging whether the parameters of the photovoltaic equipment of the user left in the user set to be examined after the second classification exceed the threshold value, if any one parameter exceeds the corresponding threshold value, classifying the user into the electricity stealing user set, and judging that the electricity stealing behavior of the user exists.
Example 5.
Fig. 4 is a schematic diagram of a frame structure of embodiment 5 of the present invention. As shown in fig. 4, based on embodiment 4, embodiment 5 further includes a photovoltaic curve information obtaining and calculating module, which is configured to obtain and calculate parameters of a fourier series of an output curve of the photovoltaic device in an output rising section, a variance of an actual curve of the output curve of the photovoltaic device in the output rising section and a fitting curve, a fourier series of the output curve of the photovoltaic device in an output falling section, and a variance of the actual curve of the output curve of the photovoltaic device in the output falling section and the fitting curve.
The above description is illustrative of the invention and not limiting, the scope of the invention being defined by the appended claims, which may be modified in any manner without departing from the basic structure of the invention.

Claims (10)

1. A photovoltaic electricity stealing discovery method based on curve morphology analysis is characterized in that: setting a clustering center of a normal user set, a clustering center of a fault user set and a clustering center of a power stealing user set; calculating the variance of each cluster center;
calculating variances of actual curves and fitting curves in the output rising sections aiming at the output curves of the photovoltaic devices of all users, and respectively calculating distances between the variances of the actual curves and the fitting curves of the output rising sections and the variances of the clustering centers, so as to classify the users for the first time;
aiming at the output curves of the photovoltaic devices of the users in the user set to be examined in the first classification, calculating the variances of the actual curves and the fitting curves of the output descending sections, and respectively calculating the distances between the variances of the actual curves and the fitting curves of the output descending sections and the variances of the clustering centers, so as to classify the users for the second time;
setting a highest power generation capacity threshold value and a lowest power generation capacity threshold value of the photovoltaic equipment in unit time, a first-order coefficient threshold value of a Fourier series of an output ascending section and a first-order coefficient threshold value of a Fourier series of an output descending section in an output curve; judging whether the parameters of the photovoltaic equipment of the users left in the user set to be examined after the second classification exceed the corresponding threshold values, if so, classifying the users into the electricity stealing user set, and classifying the rest users into the normal user set.
2. The method for finding the photovoltaic power theft based on the curve morphology analysis according to claim 1, wherein the method for calculating the parameters of the Fourier series of the output curve of the photovoltaic equipment in the output rising section is as follows:
a is the zero-order coefficient of the Fourier series of the force rising section; b is a first order coefficient of a Fourier series of the output rising section; n is the data number when collecting data; m is m 0 Numbering data corresponding to sunrise time, m 1 Numbering data corresponding to the time when the output value tends to be stable or is lifted; e (E) p (n) is the amount of power generation per unit time at point n; e (E) ps (n) is the force curve obtained after fitting by using a formula; e (E) p (m 0 ) Is the power generation amount per unit time at sunrise time.
3. The method for finding the photovoltaic power theft based on the curve morphology analysis according to claim 2, wherein the calculation method of the variance between the actual curve and the fitted curve of the output curve of the photovoltaic device in the output rising section is as follows:
the average load of the force rising section is shown as sigma, and the variance between the actual curve and the fitted curve of the force rising section is shown as sigma.
4. The method for finding the photovoltaic power theft based on the curve morphology analysis according to claim 1, wherein the method for calculating the parameters of the Fourier series of the output curve of the photovoltaic equipment in the output decreasing section is as follows:
a' is the decrease in outputZero-order coefficients of the Fourier series of the segments; b' is a first-order coefficient of a Fourier series of the output descending section; n represents the data number when data is collected; m is m 2 Numbering data corresponding to the time when the output value starts to continuously decline; m is m 3 Numbering data corresponding to sunset time; e (E) p (n) the power generation amount per unit time at n points; e's' ps (n) is the force curve obtained after fitting by using a formula; e (E) p (m 2 ) Is the power generation amount per unit time in sunset time.
5. The photovoltaic electricity theft discovery method based on curvilinear morphology analysis of claim 4, wherein: the calculation method of the variance between the actual curve and the fitting curve of the output curve of the photovoltaic equipment in the output descending section is as follows:
for the average load of the force-down segment, σ' is the variance of the actual curve and the fitted curve in the force-down segment.
6. The method for discovering photovoltaic electricity theft based on curve morphology analysis according to claim 1, wherein the clustering center of the fault user set is set as follows:
b is a first-order coefficient of a Fourier series of the output rising section; b' is a first-order coefficient of a Fourier series of the output descending section; e (E) pMax The highest generated energy of the photovoltaic equipment in unit time; e (E) pMin Is the lowest power generation amount of the photovoltaic equipment in unit time.
7. The method according to claim 1The photovoltaic electricity stealing discovery method based on curve morphology analysis is characterized by comprising the following steps of: when (when)When the electricity stealing user set is used, the clustering center of the electricity stealing user set is arranged on one side which is larger than the sigma value; when->And is also provided withSetting clustering centers of the electricity stealing user set on two sides of a sigma value, wherein sigma is the variance between an actual curve and a fitting curve of an output curve of the photovoltaic equipment in an output rising section; σ' represents the variance of the actual curve and the fitted curve at the force-down segment; e (E) pMax Is the highest power generation amount of the photovoltaic equipment in unit time.
8. The photovoltaic electricity theft discovery method based on curve morphology analysis according to claim 1, wherein: in the first classification, calculating the variances of the actual curves and the fitting curves of the output rising sections aiming at the output curves of the photovoltaic equipment of all users, and respectively calculating the distances between the variances of the actual curves and the fitting curves of the output rising sections and the variances of the clustering centers; if the distance between the variance of the actual curve and the fitting curve of the output rising section and the variance of the clustering center of the normal user set is shortest, the users are clustered into the user set to be examined; if the distance between the variance of the actual curve and the fitting curve of the output rising section and the variance of the clustering center of the fault user set is shortest, the users are clustered into the fault user set; if the distance between the variance of the actual curve and the fitted curve of the output rising section and the variance of the clustering center of the electricity stealing user set is shortest, classifying the user sample into the electricity stealing user set;
in the second classification, calculating the variances of the actual curves of the output descending sections and the fitting curves according to the output curves of the photovoltaic devices of the users in the first classification, wherein the user belongs to the user set to be examined, and calculating the distances between the variances of the actual curves of the output descending sections and the fitting curves and the variances of the clustering centers respectively; if the distance between the variance of the actual curve and the fitting curve of the output drop section and the variance of the clustering center of the normal user set is shortest, the user is left in the user set to be inspected; if the distance between the variance of the actual curve and the fitting curve of the output drop section and the variance of the clustering center of the fault user set is shortest, the users are clustered into the fault user set; and if the distance between the variance of the actual curve and the fitted curve of the output drop section and the variance of the clustering center of the electricity stealing user set is shortest, classifying the users into the electricity stealing user set.
9. A photovoltaic electricity theft discovery system based on curvilinear morphology analysis, comprising:
the cluster center setting and variance calculating module is used for setting the cluster centers of the normal user set, the cluster centers of the fault user set and the cluster centers of the electricity stealing user set and calculating variances of the cluster centers;
the first classification module is used for calculating the variances of the actual curves and the fitting curves in the output ascending sections aiming at the output curves of the photovoltaic equipment of all users, and respectively calculating the distances between the variances of the actual curves and the fitting curves of the output ascending sections and the variances of the clustering centers so as to classify the users for the first time;
the second classification module is used for calculating the variances of the actual curves of the output descending sections and the fitting curves according to the output curves of the photovoltaic devices of the users in the user set to be examined in the first classification, respectively calculating the distances between the variances of the actual curves of the output descending sections and the fitting curves and the variances of the clustering centers, and carrying out the second classification on the users;
the third classification module is provided with a highest power generation capacity threshold value, a lowest power generation capacity threshold value, a first-order coefficient threshold value of the Fourier series of the output ascending section and a first-order coefficient threshold value of the Fourier series of the output descending section of the photovoltaic equipment in unit time; judging whether the parameters of the photovoltaic equipment of the users in the user set to be examined after the second classification exceed a threshold value, if any parameter exceeds the threshold value, classifying the users into the electricity stealing user set, and classifying the rest users into the normal user set.
10. The photovoltaic power theft discovery system based on the curve morphology analysis according to claim 9, further comprising a photovoltaic curve information acquisition and calculation module for acquiring and calculating parameters of a fourier series of an output curve of the photovoltaic device in an output rising section, variances of an actual output curve of the photovoltaic device in the output rising section and a fitting curve, fourier series of the output curve of the photovoltaic device in an output falling section, and variances of the actual output curve of the photovoltaic device in the output falling section and the fitting curve.
CN201911191055.4A 2019-11-28 2019-11-28 Photovoltaic electricity stealing discovery method and system based on curve morphology analysis Active CN110969539B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911191055.4A CN110969539B (en) 2019-11-28 2019-11-28 Photovoltaic electricity stealing discovery method and system based on curve morphology analysis

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911191055.4A CN110969539B (en) 2019-11-28 2019-11-28 Photovoltaic electricity stealing discovery method and system based on curve morphology analysis

Publications (2)

Publication Number Publication Date
CN110969539A CN110969539A (en) 2020-04-07
CN110969539B true CN110969539B (en) 2024-02-09

Family

ID=70032245

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911191055.4A Active CN110969539B (en) 2019-11-28 2019-11-28 Photovoltaic electricity stealing discovery method and system based on curve morphology analysis

Country Status (1)

Country Link
CN (1) CN110969539B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111651730B (en) * 2020-06-11 2022-03-04 西安电子科技大学 Electricity stealing detection method based on Huhart-accumulation and combined control chart

Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103389397A (en) * 2013-07-23 2013-11-13 国家电网公司 Anti-cheating system for photovoltaic power generation
CN103439572A (en) * 2013-08-15 2013-12-11 国家电网公司 Electricity larceny prevention monitoring method based on photovoltaic power generation power prediction
CN104345192A (en) * 2014-11-25 2015-02-11 国家电网公司 Photovoltaic power generation subsidy cheating prevention device based on neural network algorithm
CN105141253A (en) * 2015-08-17 2015-12-09 国家电网公司 Photovoltaic output curve slope-based photovoltaic electricity-sealing identification method
CN105139275A (en) * 2015-08-17 2015-12-09 国家电网公司 Method for establishing distributed photovoltaic power stealing cost benefit evaluation model
CN105337574A (en) * 2015-11-11 2016-02-17 国家电网公司 Robust-regression-based distributed photovoltaic generating electricity-stealing identification method
CN105808900A (en) * 2014-12-29 2016-07-27 西门子公司 Method and device for determining electricity stealing suspicion of user to be evaluated
CN106771568A (en) * 2016-11-16 2017-05-31 国家电网公司 Area distribution formula photovoltaic stealing supervisory systems
CN107145966A (en) * 2017-04-12 2017-09-08 山大地纬软件股份有限公司 Logic-based returns the analysis and early warning method of opposing electricity-stealing of probability analysis Optimized model
CN107547047A (en) * 2017-10-19 2018-01-05 广东电网有限责任公司江门供电局 A kind of grid-connected monitoring system of distributed photovoltaic and monitoring method
CN110097261A (en) * 2019-04-17 2019-08-06 三峡大学 A method of judging user power utilization exception
CN110147871A (en) * 2019-04-17 2019-08-20 中国电力科学研究院有限公司 A kind of stealing detection method and system based on SOM neural network Yu K- mean cluster
CN110288039A (en) * 2019-06-29 2019-09-27 河南工业大学 Based on user power utilization load characteristic stealing detection method

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8947194B2 (en) * 2009-05-26 2015-02-03 Solaredge Technologies Ltd. Theft detection and prevention in a power generation system

Patent Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103389397A (en) * 2013-07-23 2013-11-13 国家电网公司 Anti-cheating system for photovoltaic power generation
CN103439572A (en) * 2013-08-15 2013-12-11 国家电网公司 Electricity larceny prevention monitoring method based on photovoltaic power generation power prediction
CN104345192A (en) * 2014-11-25 2015-02-11 国家电网公司 Photovoltaic power generation subsidy cheating prevention device based on neural network algorithm
CN105808900A (en) * 2014-12-29 2016-07-27 西门子公司 Method and device for determining electricity stealing suspicion of user to be evaluated
CN105141253A (en) * 2015-08-17 2015-12-09 国家电网公司 Photovoltaic output curve slope-based photovoltaic electricity-sealing identification method
CN105139275A (en) * 2015-08-17 2015-12-09 国家电网公司 Method for establishing distributed photovoltaic power stealing cost benefit evaluation model
CN105337574A (en) * 2015-11-11 2016-02-17 国家电网公司 Robust-regression-based distributed photovoltaic generating electricity-stealing identification method
CN106771568A (en) * 2016-11-16 2017-05-31 国家电网公司 Area distribution formula photovoltaic stealing supervisory systems
CN107145966A (en) * 2017-04-12 2017-09-08 山大地纬软件股份有限公司 Logic-based returns the analysis and early warning method of opposing electricity-stealing of probability analysis Optimized model
CN107547047A (en) * 2017-10-19 2018-01-05 广东电网有限责任公司江门供电局 A kind of grid-connected monitoring system of distributed photovoltaic and monitoring method
CN110097261A (en) * 2019-04-17 2019-08-06 三峡大学 A method of judging user power utilization exception
CN110147871A (en) * 2019-04-17 2019-08-20 中国电力科学研究院有限公司 A kind of stealing detection method and system based on SOM neural network Yu K- mean cluster
CN110288039A (en) * 2019-06-29 2019-09-27 河南工业大学 Based on user power utilization load characteristic stealing detection method

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
基于LSSVM的光伏发电三层筛选窃电识别方法;郑征等;《电力电子技术》;全文 *

Also Published As

Publication number Publication date
CN110969539A (en) 2020-04-07

Similar Documents

Publication Publication Date Title
CN109307845B (en) Method and system for health state assessment of battery energy storage system used in echelon
CN107328974B (en) Electricity stealing identification method and device
CN111008510B (en) Method for identifying ammeter in transformer area and method for judging transformer area to which ammeter belongs
CN113094884A (en) Power distribution network user electricity stealing behavior diagnosis method based on three-layer progressive analysis model
CN105068009A (en) Battery cycle life prediction method
CN109359848A (en) A kind of extremely relevant electricity consumer recognition methods of line loss and system
CN110119948B (en) Power consumer credit evaluation method and system based on time-varying weight dynamic combination
CN109583679A (en) A kind of stealing Suspected Degree analysis method of more algorithm fusions
CN112434962B (en) Enterprise user state evaluation method and system based on power load data
CN110969539B (en) Photovoltaic electricity stealing discovery method and system based on curve morphology analysis
CN102156814A (en) Clustering-based typical daily load curve selecting method and device
CN115796708B (en) Big data intelligent quality inspection method, system and medium for engineering construction
CN116796271A (en) Resident energy abnormality identification method
CN110231503B (en) High-loss platform area electricity stealing user identification and positioning method based on Glandum causal test
CN112488738B (en) Resident vacant resident identification method and equipment based on electric power big data
CN111612054B (en) User electricity stealing behavior identification method based on nonnegative matrix factorization and density clustering
CN108957347B (en) High-precision dynamic estimation method and system for SOC of battery pack
CN108537385A (en) A kind of non-intrusion type residential electricity consumption load recognition methods
CN111126449A (en) Battery fault classification diagnosis method based on cluster analysis
CN108335042B (en) Method for calculating cleaning index of dynamic photovoltaic panel
CN104091227A (en) Method for analyzing load density of power consumers in city
CN104849665B (en) A kind of method and device for determining storage battery safety electric discharge duration
CN115879799A (en) Transformer substation electric energy quality analysis method
CN115618229A (en) Line loss allocation algorithm based on big data
CN110298603B (en) Distributed photovoltaic system capacity estimation 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