CN111930802A - Anti-electricity-stealing analysis method based on Lasso analysis - Google Patents
Anti-electricity-stealing analysis method based on Lasso analysis Download PDFInfo
- Publication number
- CN111930802A CN111930802A CN202010763962.8A CN202010763962A CN111930802A CN 111930802 A CN111930802 A CN 111930802A CN 202010763962 A CN202010763962 A CN 202010763962A CN 111930802 A CN111930802 A CN 111930802A
- Authority
- CN
- China
- Prior art keywords
- data
- lasso
- electricity
- line loss
- stealing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 26
- 230000005611 electricity Effects 0.000 claims abstract description 42
- 230000008014 freezing Effects 0.000 claims abstract description 9
- 238000007710 freezing Methods 0.000 claims abstract description 9
- 238000000034 method Methods 0.000 claims abstract description 9
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims abstract description 4
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000009826 distribution Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000005457 optimization Methods 0.000 claims description 3
- 230000002265 prevention Effects 0.000 claims description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- 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
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- 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
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- 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
-
- 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
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Algebra (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Operations Research (AREA)
- Computing Systems (AREA)
- Fuzzy Systems (AREA)
- Computational Linguistics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an anti-electricity-stealing analysis method based on Lasso analysis, which comprises the following steps of firstly, obtaining all user electricity quantity freezing data of a whole station area and station area total meter electricity quantity freezing data from an acquisition system; step two, performing data preprocessing on all data, and performing interpolation processing on missing data; step three, subtracting the sum of all the user electricity consumption data from the station area general table data to obtain line loss values of each time period of the station area; step four, calculating the line loss of the transformer area and the regression coefficients of all the electric meters according to the Lasso regression model; step five, calculating the electricity stealing probability of each ammeter according to the line loss of the transformer area and the Lasso coefficient; and step six, positioning suspected electricity stealing users according to the electricity stealing probability. The method is simple to realize, only needs to acquire all user power consumption data and table area general table data of the whole table area, overcomes the influence of high interference of required data dimensionality, does not need artificial definition characteristics, and does not need to add excessive extra equipment.
Description
Technical Field
The invention relates to the field of distribution network automation systems, in particular to an anti-electricity-stealing analysis method based on Lasso analysis.
Background
Electric energy has become a necessity in social production and life, however, loss often occurs in the processes of power generation, power transmission and power distribution, and especially, increasing electricity stealing phenomena bring economic loss which is difficult to estimate. The consequences of power theft include a surge in power supply, overloading of the power system, a huge loss of revenue to the utility, and threats to public safety (e.g., fire and electric shock). Therefore, the research on the effective electricity stealing prevention detection technology has very practical significance for the development of the economic society.
Currently, data-driven-based electricity stealing detection methods attempt to find an abnormal pattern in the electricity usage information of all users. A large number of labeled sample sets are typically required to train the classifier, or sample data with both normal and power stealing behavior is necessary. However, it is very difficult and time consuming to establish a complete tagged normal and electricity stealing data set, especially for the latter, electricity stealing behavior is difficult to verify effectively so that the collected data tag cannot be judged accurately. Therefore, limited by the merits of the data set, the application of traditional pattern recognition modeling or cluster analysis methods is also subject to the elbow.
Disclosure of Invention
The invention aims at the problems, overcomes the defects of the prior art, provides an anti-electricity-stealing analysis method based on Lasso analysis,
in order to achieve the purpose, the invention adopts the following technical scheme:
an anti-electricity-stealing analysis method based on Lasso analysis comprises the following steps,
acquiring all user electric quantity freezing data and total table electric quantity freezing data of a whole station area from an acquisition system;
step two, performing data preprocessing on all data;
step three, subtracting the sum of all the user electricity consumption data from the station area general table data to obtain line loss values of each time period of the station area;
step four, calculating the line loss of the transformer area and the regression coefficients of all the electric meters according to the Lasso regression model;
step five, calculating the electricity stealing probability of each ammeter according to the line loss of the transformer area and the Lasso coefficient;
and step six, positioning suspected electricity stealing users according to the electricity stealing probability.
Further, in the fourth step, the line loss of the transformer area and the regression coefficients of all the electricity meters are calculated according to a Lasso regression model, wherein the optimization goal of the Lasso regression model is,
wherein y is a distribution area line loss vector, X is a power consumption matrix of all the electric meters, and lambda is a regular coefficient,is a matrix of coefficients.
Furthermore, the regression calculation formula of the elastic net in the step six is as follows,
wherein y is the active power matrix of the branch, X is the active power matrix of the ammeter, lambda, gamma are regular coefficients,is a matrix of coefficients.
Further, in the fifth step, the electricity stealing probability of each electric meter is calculated according to the line loss of the transformer area and the Lasso coefficient, wherein the calculation formula of the electricity stealing probability is as follows,
wherein beta represents a Lasso regression coefficient, alpha and gamma are coefficients of 0-1, the line loss of the v table region is more than 7% of the number of data points, and m represents the total number of data points.
Further, in the second step, data preprocessing is performed on all the data, and the preprocessing mode includes: carrying out interpolation processing on the missing data; remove > 50% of user data that is missing.
Furthermore, in the first step, the acquisition frequency of the frozen data is 30 min/time, the total acquisition success rate of the electric quantity of the transformer area is greater than 95%, and the acquisition success rate of the electric quantity of each meter is greater than 85%.
The invention has the beneficial effects that: the method solves the regression coefficient through the Lasso regression model, then calculates the electricity stealing probability of each ammeter according to the line loss of the transformer area and the Lasso coefficient, and finally positions suspected electricity stealing users according to the electricity stealing probability. The method is simple to realize, only needs to acquire all the power utilization data of the users in the whole cell and the data of the table area summary table, overcomes the influence of high interference of required data dimensionality, does not need artificial definition characteristics, and does not need to add excessive extra equipment.
Drawings
FIG. 1 is a general flow chart of the anti-electricity-stealing analysis method based on the Lasso analysis of the present invention.
Fig. 2 is a line loss diagram of the distribution room of the present invention at different time intervals.
FIG. 3 is a comparison graph of the total electricity quantity and the sum of the electricity quantities of the meters.
FIG. 4 is a plot of the Lasso regression coefficients for each table of the present invention.
Fig. 5 is a line loss fitting graph of each time period of the distribution room according to the present invention.
FIG. 6 is a graph showing the probability of electricity stealing for each meter of the present invention.
Detailed Description
The present invention will be further described with reference to the accompanying drawings 1-6 and examples to illustrate the technical solutions of the present invention. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
With reference to fig. 1, the anti-electricity-stealing analysis method based on Lasso analysis of the present invention includes the following steps,
the method comprises the steps that firstly, all user electric quantity freezing data of a whole station area and total table electric quantity freezing data of the station area are obtained from an acquisition system, the acquisition frequency of the freezing data is 30 min/time, the total acquisition success rate of the station area electric quantity is greater than 95%, and the acquisition success rate of each table meter electric quantity is greater than 85%.
Step two, carrying out data preprocessing pretreatment on all the data, wherein the method comprises the following steps: carrying out interpolation processing on the missing data; remove > 50% of user data that is missing.
And step three, subtracting the sum of all the user electricity consumption data from the station area general table data to obtain line loss values of each time period of the station area, wherein a line loss graph of each time period is shown in fig. 2, and a comparison graph of the total table electricity quantity and the electricity quantity sum of each meter is shown in fig. 3.
Step four, fitting the line loss data by using the power consumption data of each user according to a Lasso regression model, and calculating the regression coefficients of the line loss of the transformer area and all the electric meters, wherein the optimization target of the Lasso regression model is,
wherein y is a distribution area line loss vector, X is a power consumption matrix of all the electric meters, and lambda is a regular coefficient,is a matrix of coefficients. The obtained Lasso regression coefficient is shown in fig. 4, and the line loss fitting graph of each time interval of the station area is shown in fig. 5.
Step five, calculating the electricity stealing probability of each ammeter according to the transformer area line loss and the Lasso coefficient, wherein the calculation formula of the electricity stealing probability is as follows,
wherein beta represents a Lasso regression coefficient, alpha and gamma are coefficients of 0-1, the line loss of the v table region is more than 7% of the number of data points, and m represents the total number of data points. The graph of the probability of stealing electricity by each user is shown in figure 6.
And step six, positioning suspected electricity stealing users according to the electricity stealing probability.
In this embodiment: the anti-electricity-stealing analysis method based on the Lasso analysis is tested and verified by using the actual field data of a certain region. And the number of the tables is 61, 138 metering points are counted, wherein regression coefficients and power stealing probabilities of 4 users are calculated according to Lasso analysis and are larger, the users are listed as suspected power stealing users, and the calculation result is consistent with the actual power stealing situation on site.
In conclusion, the regression coefficient is solved through the Lasso regression model, then the electricity stealing probability of each ammeter is calculated according to the line loss of the transformer area and the Lasso coefficient, and finally suspected electricity stealing users are positioned according to the electricity stealing probability. The method is simple to realize, only needs to acquire all the power utilization data of the users in the whole cell and the data of the table area summary table, overcomes the influence of high interference of required data dimensionality, does not need artificial definition characteristics, and does not need to add excessive extra equipment.
The above embodiments are illustrative of specific embodiments of the present invention, and are not restrictive of the present invention, and those skilled in the relevant art can make various changes and modifications without departing from the spirit and scope of the present invention to obtain corresponding equivalent technical solutions, and therefore all equivalent technical solutions should be included in the scope of the present invention.
Claims (5)
1. An anti-electricity-stealing analysis method based on Lasso analysis is characterized by comprising the following steps:
acquiring all user electric quantity freezing data and total table electric quantity freezing data of a whole station area from an acquisition system;
step two, performing data preprocessing on all data;
step three, subtracting the sum of all the user electricity consumption data from the station area general table data to obtain line loss values of each time period of the station area;
step four, calculating the line loss of the transformer area and the regression coefficients of all the electric meters according to the Lasso regression model;
step five, calculating the electricity stealing probability of each ammeter according to the line loss of the transformer area and the Lasso coefficient;
and step six, positioning suspected electricity stealing users according to the electricity stealing probability.
2. The method of claim 1, wherein the power stealing prevention analysis method based on the Lasso analysis comprises: in the fourth step, the line loss of the transformer area and the regression coefficients of all the electric meters are calculated according to a Lasso regression model, wherein the optimization target of the Lasso regression model is,
3. The Lasso resolution-based anti-theft analysis method according to claim 1 or 2, wherein: step five, calculating the electricity stealing probability of each ammeter according to the transformer area line loss and the Lasso coefficient, wherein the electricity stealing probability calculation formula is as follows,
wherein beta represents a Lasso regression coefficient, alpha and gamma are coefficients of 0-1, the line loss of the v table region is more than 7% of the number of data points, and m represents the total number of data points.
4. The Lasso resolution-based anti-theft analysis method according to claim 1 or 2, wherein: and in the second step, data preprocessing is carried out on all the data, and the preprocessing mode comprises the following steps: carrying out interpolation processing on the missing data; remove > 50% of user data that is missing.
5. The Lasso resolution-based anti-theft analysis method according to claim 1 or 2, wherein: in the first step, the acquisition frequency of the frozen data is 30 min/time.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010763962.8A CN111930802A (en) | 2020-08-01 | 2020-08-01 | Anti-electricity-stealing analysis method based on Lasso analysis |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010763962.8A CN111930802A (en) | 2020-08-01 | 2020-08-01 | Anti-electricity-stealing analysis method based on Lasso analysis |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111930802A true CN111930802A (en) | 2020-11-13 |
Family
ID=73315123
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010763962.8A Pending CN111930802A (en) | 2020-08-01 | 2020-08-01 | Anti-electricity-stealing analysis method based on Lasso analysis |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111930802A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114548845A (en) * | 2022-04-27 | 2022-05-27 | 北京智芯微电子科技有限公司 | Distribution network management method, device and system |
CN115330202A (en) * | 2022-08-15 | 2022-11-11 | 烟台东方威思顿电气有限公司 | Data-driven low-voltage distribution station area electricity stealing analysis method |
CN116008714A (en) * | 2023-03-23 | 2023-04-25 | 青岛鼎信通讯股份有限公司 | Anti-electricity-stealing analysis method based on intelligent measurement terminal |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106066423A (en) * | 2016-05-25 | 2016-11-02 | 上海博英信息科技有限公司 | A kind of analysis method of opposing electricity-stealing based on Loss allocation suspicion analysis |
CN106936127A (en) * | 2017-02-28 | 2017-07-07 | 国家电网公司 | A kind of line load regression analysis and Forecasting Methodology and system |
US20180364287A1 (en) * | 2017-06-14 | 2018-12-20 | Cooper Technologies Company | System and method for detecting theft of electricity with integrity checks analysis |
CN110824270A (en) * | 2019-10-09 | 2020-02-21 | 中国电力科学研究院有限公司 | Electricity stealing user identification method and device combining transformer area line loss and abnormal events |
CN111292121A (en) * | 2020-01-16 | 2020-06-16 | 国家电网有限公司 | Garden load prediction method and system based on garden image |
-
2020
- 2020-08-01 CN CN202010763962.8A patent/CN111930802A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106066423A (en) * | 2016-05-25 | 2016-11-02 | 上海博英信息科技有限公司 | A kind of analysis method of opposing electricity-stealing based on Loss allocation suspicion analysis |
CN106936127A (en) * | 2017-02-28 | 2017-07-07 | 国家电网公司 | A kind of line load regression analysis and Forecasting Methodology and system |
US20180364287A1 (en) * | 2017-06-14 | 2018-12-20 | Cooper Technologies Company | System and method for detecting theft of electricity with integrity checks analysis |
CN110824270A (en) * | 2019-10-09 | 2020-02-21 | 中国电力科学研究院有限公司 | Electricity stealing user identification method and device combining transformer area line loss and abnormal events |
CN111292121A (en) * | 2020-01-16 | 2020-06-16 | 国家电网有限公司 | Garden load prediction method and system based on garden image |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114548845A (en) * | 2022-04-27 | 2022-05-27 | 北京智芯微电子科技有限公司 | Distribution network management method, device and system |
CN114548845B (en) * | 2022-04-27 | 2022-07-12 | 北京智芯微电子科技有限公司 | Distribution network management method, device and system |
CN115330202A (en) * | 2022-08-15 | 2022-11-11 | 烟台东方威思顿电气有限公司 | Data-driven low-voltage distribution station area electricity stealing analysis method |
CN116008714A (en) * | 2023-03-23 | 2023-04-25 | 青岛鼎信通讯股份有限公司 | Anti-electricity-stealing analysis method based on intelligent measurement terminal |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111930802A (en) | Anti-electricity-stealing analysis method based on Lasso analysis | |
CN102545213B (en) | System and method for managing line loss of power grid in real time | |
CN111650431B (en) | Ammeter region identification method | |
CN112215479B (en) | Electric meter anti-electricity-stealing analysis method based on self-adaptive shrinkage ridge regression | |
CN104123682A (en) | Distribution network fault risk assessment method based on meteorology influence factors | |
CN111160791A (en) | Abnormal user identification method based on GBDT algorithm and factor fusion | |
CN110749784B (en) | Line electricity stealing detection method based on electric power data wavelet analysis | |
CN103995162A (en) | Power distribution network large user real-time electricity larceny prevention method based on advanced measuring system | |
CN112380496A (en) | Pearson correlation coefficient-based anti-electricity-stealing analysis method | |
CN116008714B (en) | Anti-electricity-stealing analysis method based on intelligent measurement terminal | |
CN103018611B (en) | Non-invasive load monitoring method and system based on current decomposition | |
CN113991856B (en) | Micro-energy network multi-adaptability mu PMU optimal point distribution method | |
CN109918612B (en) | Platform area topological structure checking method based on sparse learning | |
Liu | Short-term operational reliability evaluation for power systems under extreme weather conditions | |
Lin et al. | Voltage sag severity analysis based on improved FP-Growth algorithm and AHP algorithm | |
CN112611997B (en) | Online verification method and system for hitching relation of platform area gateway table | |
CN116027687A (en) | Intelligent energy consumption building energy consumption monitoring system and energy saving effect monitoring method | |
Fan | Research on automatic user identification system of leaked electricity based on Data Mining Technology | |
Zhou et al. | Calculation and analysis method for distribution network fault location based on improved differential evolution algorithm | |
Raju et al. | Measurement Redundancy constrained Optimal PMU Locations | |
Shengquan et al. | Optimal Blocking Devices Placement for Geomagnetic Disturbance Mitigation Based on Sensitivity of Induced Geoelectric Fields | |
Linghua et al. | Research on the algorithm model of predicting line loss diagnosis based on computer multiple linear regression | |
CN116341824A (en) | Intelligent power grid transformer substation management system and method based on cloud computing | |
Yang et al. | Evaluating the effectiveness of conservation voltage reduction with multilevel robust regression | |
Shi et al. | Research on low voltage distribution network topology generation method based on “transformer-distribution box-meter box-meter” model |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |