CN112215479B - Electric meter anti-electricity-stealing analysis method based on self-adaptive shrinkage ridge regression - Google Patents
Electric meter anti-electricity-stealing analysis method based on self-adaptive shrinkage ridge regression Download PDFInfo
- Publication number
- CN112215479B CN112215479B CN202011032743.9A CN202011032743A CN112215479B CN 112215479 B CN112215479 B CN 112215479B CN 202011032743 A CN202011032743 A CN 202011032743A CN 112215479 B CN112215479 B CN 112215479B
- Authority
- CN
- China
- Prior art keywords
- line loss
- user
- coefficient
- data
- curve
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
-
- 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
- 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
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/80—Management or planning
- Y02P90/82—Energy audits or management systems therefor
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- Educational Administration (AREA)
- Mathematical Analysis (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Pure & Applied Mathematics (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- Computational Mathematics (AREA)
- Mathematical Physics (AREA)
- Mathematical Optimization (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Probability & Statistics with Applications (AREA)
- Life Sciences & Earth Sciences (AREA)
- Algebra (AREA)
- Primary Health Care (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an electric meter anti-electricity-stealing analysis method based on self-adaptive shrinkage ridge regression, which comprises the following steps of: acquiring daily freezing data of the electric quantity of users in the whole transformer area and daily freezing data of the electric quantity of an assessment total table in the transformer area from an electric information acquisition system; subtracting the sum of the daily freezing data of each user electric meter in all user areas from the daily freezing data of the examination total table of the areas to obtain an area line loss value curve; defining an objective function of the line loss value and daily freezing data of all sub-tables in the transformer area, and calculating an initial solution of an estimation coefficient according to a ridge regression model; contracting the initial solution of the estimation coefficient through a self-adaptive iteration process to obtain a final solution of the estimation coefficient; calculating a Pearson correlation coefficient of a user regression fitting curve and a line loss value curve; and judging suspected electricity stealing users according to the values of the Pearson correlation coefficient and the estimation coefficient. According to the invention, no additional equipment is needed, and the anti-electricity-stealing analysis can be carried out by only acquiring the data of the user ammeter and the distribution room general table, so that the method is easy to realize, and the time and the economic cost are saved.
Description
Technical Field
The invention relates to the technical field of distribution network automation, in particular to an electric meter anti-electricity-stealing analysis method based on self-adaptive shrinkage ridge regression.
Background
Nowadays, electricity becomes a necessary energy source in social production life, however, electric energy loss often occurs in the processes of power generation, power transmission and power distribution, especially the phenomenon of increasing electricity stealing, which brings about economic loss which is difficult to estimate. The consequences of electricity theft include a surge in the supply of electricity, overloading of the power system, a significant loss to the utility, and frequent occurrences of public safety threats such as 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.
The conventional electricity stealing detection method includes checking installation or configuration of a suspicious electric meter, comparing readings of an abnormal electric meter with readings of a normal electric meter, checking a bypass power line, installing a specific detection device, and the like. However, these methods are very time consuming, expensive and inefficient and do not match the demands of today's large-scale electricity usage. In recent years, the construction and development of strong smart grids and ubiquitous power internet of things enable mass power utilization data to be collected and stored. Therefore, more intelligent electricity stealing detection methods are receiving increasing attention.
Disclosure of Invention
Aiming at the problems, the invention overcomes the defects of the prior art, provides an electric meter anti-electricity-stealing analysis method based on self-adaptive shrinkage ridge regression, solves and estimates a regression coefficient through a self-adaptive shrinkage ridge regression model, and then positions suspected electricity-stealing users according to the similarity and regression coefficient of a regression fitting line loss curve of the users and an actual line loss curve. According to the method, additional equipment is not needed, and the anti-electricity-stealing analysis can be carried out only by acquiring data of the district user electricity meter and the district general meter.
In order to achieve the purpose of the invention, the invention adopts the following technical scheme:
an electric meter anti-electricity-stealing analysis method based on self-adaptive shrinkage ridge regression comprises the following steps:
step 1, acquiring daily freezing data of user electric quantity of a whole transformer area and daily freezing data of electric quantity of a transformer area assessment summary table from an electric quantity information acquisition system;
step 2, subtracting the sum of daily freezing data of each user electric meter in the distribution area from daily freezing data of a distribution area assessment total meter to obtain a distribution area line loss value curve;
step 3, defining a target function of the line loss value and all sub-table daily freezing data of the transformer area, and calculating an estimation coefficient initial solution according to a ridge regression model;
step 4, shrinking the initial solution of the estimation coefficient through a self-adaptive iteration process to obtain a final solution of the estimation coefficient;
and 6, judging suspected electricity stealing users according to the values of the Pearson correlation coefficient and the estimation coefficient.
Further, the number of data days acquired in the step 1 is more than or equal to two times of the number of users in the distribution area.
Further, the calculation formula of the platform area line loss value curve in the step 2 is as follows:
wherein ltDenotes the line loss value, y, of the t-th daytDenotes the assessment summary reading, x, on day ttiAnd (4) representing the meter reading of the ith user on the t day, wherein m is the number of the users in the region.
Further, the objective function defined in step 3 is as follows:
writing in a matrix form is:
whereinRepresenting the estimated coefficients (the factor of electricity stealing), the superscripts (k +1) and (k) representing the (k +1) th and kth iterations, respectively, n representing the number of days of data acquisition, the subscript i representing the ith user, the vector L ∈ RnRepresenting the line loss value curve, the matrix X belongs to Rm×nData representing daily freeze of users in a distribution area, theta(k)The adaptive shrinkage coefficient matrix representing the kth iteration, namely:
the degradation in the initial solution is a general ridge regression model, namely:
the estimation coefficient initial solution is obtained at this time:
where E denotes an identity matrix.
Further, the process of adaptively contracting the initial solution in the step 4 is as follows:
step S1: calculating an adaptive shrinkage coefficient matrix from the solution of the kth iteration
Step S3: repeating the steps S1 and S2 when the iteration number k is k +1, and if the 2 norm between the two adjacent calculation solutions is less than 10-3Stopping iteration, and outputting the final solution at the moment, which is recorded as beta ═ beta1,β2,…,βm]T。
Further, in step 5, the pearson correlation coefficient calculation formula of the user regression fitting line loss curve and the actual line loss value curve is as follows:
wherein f istRegression for day t userThe fitting value is calculated by the formula:
Further, the process of determining the suspected electricity stealing user in step 6 is as follows: firstly, evaluating the reliability of a calculation result according to the magnitude of the Pearson correlation coefficient calculated in the step 5, and considering that the data is possibly abnormal when rho is less than or equal to 0.6, the calculation result is not reliable, and the calculation is stopped; when rho is more than 0.6, the estimation coefficient is finally solved to beta ═ beta1,β2,…,βm]TThe corresponding user with the median coefficient value larger than 1 is positioned as a suspected electricity stealing user, and the label of the suspected electricity stealing user is as follows:
Ind(i)=arg{βi>1}
the invention has the beneficial effects that: and solving the estimated regression coefficient through the self-adaptive shrinkage ridge regression model, and positioning the suspected electricity stealing users according to the similarity and the regression coefficient of the regression fitting line loss curve of the users and the actual line loss curve. According to the method, additional equipment is not needed, and electricity stealing prevention analysis can be carried out only by acquiring data of the district user ammeter and the district general table, so that the method is easy to implement, and time and economic cost are saved.
Drawings
FIG. 1 is a general flow diagram of the present invention.
Fig. 2 is a diagram of the estimated coefficients (power stealing multiples) of the cell users in the embodiment of the present invention.
Fig. 3 is a comparison graph of a table area user fitting line loss curve and an actual line loss curve in the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention.
With reference to the attached drawing 1, an electric meter anti-electricity-stealing analysis method based on adaptive shrinkage ridge regression comprises the following steps:
step 1, acquiring 384-day freezing data of 152 user electric quantities of an exemplary distribution area and 384-day freezing data of an assessment total table electric quantity of the distribution area from an electric quantity information acquisition system.
Step 2, subtracting the sum of daily freezing data of each user electric meter in the distribution area from daily freezing data of a distribution area assessment total meter to obtain a distribution area line loss value curve; the calculation formula of the distribution room line loss value curve is as follows:
wherein ltDenotes the line loss value, y, of the t-th daytDenotes the assessment summary reading, x, on day ttiAnd (4) representing the meter reading of the ith user on the t day, wherein m is the number of the users in the region.
Step 3, defining a target function of the line loss value and all sub-table daily freezing data of the transformer area, and calculating an estimation coefficient initial solution according to a ridge regression model; the defined objective function is as follows:
writing in a matrix form is:
whereinRepresenting the estimation coefficient (power stealing multiple), the superscripts (k +1) and (k) respectively represent the (k +1) th iteration and the kth iteration, and the n tableIndicating the number of days of data acquisition, the index i indicates the ith user, and the vector L ∈ RnRepresenting the line loss value curve, the matrix X belongs to Rm×nData representing daily freeze of users in a distribution area, theta(k)The adaptive shrinkage coefficient matrix representing the kth iteration, namely:
the degradation in the initial solution is a general ridge regression model, namely:
the estimation coefficient initial solution is obtained at this time:
where E denotes an identity matrix.
Step 4, shrinking the initial solution of the estimation coefficient through a self-adaptive iteration process to obtain a final solution of the estimation coefficient; the process of the adaptive shrinkage initial solution is as follows:
step S1: calculating an adaptive shrinkage coefficient matrix from the solution of the kth iteration
Step S3: repeating the steps S1 and S2 when the iteration number k is k +1, and if the 2 norm between the two adjacent calculation solutions is less than 10-3Stopping iteration, and outputting the final solution at the moment, which is recorded as beta ═ beta1,β2,…,βm]T。
Fig. 2 shows the estimated coefficients of all users in the background area after 34 iterations in the embodiment of the present invention, and it can be found that the coefficient of one user is very high, and the power stealing multiple is about 12.
wherein f istAnd fitting a line loss value for the regression of the user on the t day by using a calculation formula as follows:
Fig. 3 is a comparison graph of a table area user fitting line loss curve and an actual line loss curve in the embodiment of the present invention.
And 6, judging suspected electricity stealing users according to the values of the Pearson correlation coefficient and the estimation coefficient. The process for judging the suspected electricity stealing users is as follows: firstly, evaluating the reliability of a calculation result according to the magnitude of the Pearson correlation coefficient calculated in the step 5, and considering that the data is possibly abnormal when rho is less than or equal to 0.6, the calculation result is not reliable, and the calculation is stopped; when rho is more than 0.6, the estimation coefficient is finally solved to beta ═ beta1,β2,…,βm]TThe corresponding user with the median coefficient value larger than 1 is positioned as a suspected electricity stealing user, and the label of the suspected electricity stealing user is as follows:
Ind(i)=arg{βi>1}
in the embodiment, the calculated similarity is 0.8867, and the calculation result is credible. And (4) positioning a user stealing electricity through the graph 2, and judging that the result is consistent with the actual checking result.
The above-mentioned embodiments are illustrative of the specific embodiments of the present invention, and are not restrictive, and those skilled in the relevant art can make various changes and modifications to obtain corresponding equivalent technical solutions without departing from the spirit and scope of the present invention, so that all equivalent technical solutions should be included in the scope of the present invention.
Claims (2)
1. An electric meter anti-electricity-stealing analysis method based on self-adaptive shrinkage ridge regression is characterized by comprising the following steps:
step 1, acquiring daily freezing data of user electric quantity of a whole transformer area and daily freezing data of electric quantity of a transformer area assessment summary table from an electric quantity information acquisition system;
step 2, subtracting the sum of daily freezing data of each user electric meter in the distribution area from daily freezing data of a distribution area assessment total meter to obtain a distribution area line loss value curve; the calculation formula of the distribution room line loss value curve is as follows:
wherein ltDenotes the line loss value, y, of the t-th daytDenotes the assessment summary reading, x, on day ttiThe electricity meter reading of the ith user in the t day is shown, and m is the number of the users in the transformer area;
step 3, defining a target function of the line loss value and all sub-table daily freezing data of the transformer area, and calculating an estimation coefficient initial solution according to a ridge regression model; the objective function is as follows:
writing in a matrix form is:
whereinRepresenting the estimated coefficients, superscripts (k +1) and (k) representing the (k +1) th and kth iterations, respectively, n representing the number of days of data acquisition, subscript i representing the ith user, and vector L ∈ RnRepresenting the line loss value curve, the matrix X belongs to Rm×nData representing daily freeze of users in a distribution area, theta(k)The adaptive shrinkage coefficient matrix representing the kth iteration, namely:
the degradation in the initial solution is a ridge regression model, namely:
the estimation coefficient initial solution is obtained at this time:
wherein E represents an identity matrix;
step 4, shrinking the initial solution of the estimation coefficient through a self-adaptive iteration process to obtain a final solution of the estimation coefficient; the process of the adaptive shrinkage initial solution is as follows:
step S1: calculating an adaptive shrinkage coefficient matrix from the solution of the kth iteration
Step S3: the number of iterations k is k +1,repeating the steps S1 and S2, if the 2 norm between the two adjacent solutions is less than 10-3Stopping iteration, and outputting the final solution at the moment, which is recorded as beta ═ beta1,β2,…,βm]T;
Step 5, calculating a Pearson correlation coefficient of a user regression fitting line loss curve and a line loss value curve; the user regression fits the pearson correlation coefficient calculation formula of the line loss curve and the line loss value curve as follows:
wherein f istThe regression fitting value of the user on the t day is calculated by the following formula:
step 6, judging suspected electricity stealing users according to the values of the Pearson correlation coefficient and the estimation coefficient, wherein the judging process of the suspected electricity stealing users is as follows: firstly, evaluating the reliability of a calculation result according to the magnitude of the Pearson correlation coefficient calculated in the step 5, and considering that data is abnormal when rho is less than or equal to 0.6, the calculation result is not reliable, and the calculation is stopped; when rho is more than 0.6, the estimation coefficient is finally solved to beta ═ beta1,β2,…,βm]TThe corresponding user with the median coefficient value larger than 1 is positioned as a suspected electricity stealing user, and the label of the suspected electricity stealing user is as follows:
Ind(i)=arg{βi>1}。
2. the method as claimed in claim 1, wherein the number of days of data collected in step 1 is greater than or equal to two times the number of users in the region.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011032743.9A CN112215479B (en) | 2020-09-27 | 2020-09-27 | Electric meter anti-electricity-stealing analysis method based on self-adaptive shrinkage ridge regression |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011032743.9A CN112215479B (en) | 2020-09-27 | 2020-09-27 | Electric meter anti-electricity-stealing analysis method based on self-adaptive shrinkage ridge regression |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112215479A CN112215479A (en) | 2021-01-12 |
CN112215479B true CN112215479B (en) | 2022-03-25 |
Family
ID=74051917
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011032743.9A Active CN112215479B (en) | 2020-09-27 | 2020-09-27 | Electric meter anti-electricity-stealing analysis method based on self-adaptive shrinkage ridge regression |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112215479B (en) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113420912B (en) * | 2021-06-04 | 2022-04-26 | 国网江西省电力有限公司电力科学研究院 | Method for identifying users with low-voltage abnormality of power distribution network |
CN114217160A (en) * | 2022-02-18 | 2022-03-22 | 青岛鼎信通讯股份有限公司 | Method for installing and positioning load monitoring unit of medium-voltage distribution line |
CN115563489B (en) * | 2022-11-03 | 2023-03-28 | 中国电力科学研究院有限公司 | Super-error table detection method, device and computer storage medium |
CN115856757A (en) * | 2022-11-28 | 2023-03-28 | 国网北京市电力公司 | Electric energy meter misalignment analysis method, device, equipment and medium |
CN116008714B (en) * | 2023-03-23 | 2023-06-30 | 青岛鼎信通讯股份有限公司 | Anti-electricity-stealing analysis method based on intelligent measurement terminal |
CN116304537B (en) * | 2023-04-27 | 2023-08-22 | 青岛鼎信通讯股份有限公司 | Electricity larceny user checking method based on intelligent measuring terminal |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2012008062A (en) * | 2010-06-28 | 2012-01-12 | Jfe Steel Corp | Film thickness measuring method and device therefor |
CN103187804A (en) * | 2012-12-31 | 2013-07-03 | 萧山供电局 | Station area electricity utilization monitoring method based on bad electric quantity data identification |
KR101560504B1 (en) * | 2014-11-21 | 2015-10-15 | 성균관대학교산학협력단 | A atmospheric environmental risk factor prediction method associated with atopic dermatitis symptom deterioration |
CN111444241A (en) * | 2020-03-26 | 2020-07-24 | 南京工程学院 | Data mining-based accurate positioning method for line loss abnormity associated users of distribution room |
CN111521868A (en) * | 2020-04-28 | 2020-08-11 | 广东电网有限责任公司梅州供电局 | Method and device for screening electricity stealing users based on big metering data |
-
2020
- 2020-09-27 CN CN202011032743.9A patent/CN112215479B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2012008062A (en) * | 2010-06-28 | 2012-01-12 | Jfe Steel Corp | Film thickness measuring method and device therefor |
CN103187804A (en) * | 2012-12-31 | 2013-07-03 | 萧山供电局 | Station area electricity utilization monitoring method based on bad electric quantity data identification |
KR101560504B1 (en) * | 2014-11-21 | 2015-10-15 | 성균관대학교산학협력단 | A atmospheric environmental risk factor prediction method associated with atopic dermatitis symptom deterioration |
CN111444241A (en) * | 2020-03-26 | 2020-07-24 | 南京工程学院 | Data mining-based accurate positioning method for line loss abnormity associated users of distribution room |
CN111521868A (en) * | 2020-04-28 | 2020-08-11 | 广东电网有限责任公司梅州供电局 | Method and device for screening electricity stealing users based on big metering data |
Also Published As
Publication number | Publication date |
---|---|
CN112215479A (en) | 2021-01-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112215479B (en) | Electric meter anti-electricity-stealing analysis method based on self-adaptive shrinkage ridge regression | |
CN110321934B (en) | Method and system for detecting abnormal data of user electricity consumption | |
CN117093879A (en) | Intelligent operation management method and system for data center | |
CN116008714B (en) | Anti-electricity-stealing analysis method based on intelligent measurement terminal | |
CN112180316B (en) | Electric energy meter metering error analysis method based on adaptive shrinkage ridge regression | |
CN111930802A (en) | Anti-electricity-stealing analysis method based on Lasso analysis | |
Pan et al. | Online static voltage stability monitoring for power systems using PMU data | |
CN113762355A (en) | User abnormal electricity consumption behavior detection method based on non-invasive load decomposition | |
CN116304537B (en) | Electricity larceny user checking method based on intelligent measuring terminal | |
Sun et al. | Anomaly detection analysis for district heating apartments | |
CN114355004A (en) | Medium-voltage anti-electricity-stealing analysis method based on coding correlation | |
CN110298603B (en) | Distributed photovoltaic system capacity estimation method | |
CN113690942A (en) | Distributed new energy capacity fixing method based on multi-objective neural network optimization | |
CN112113316A (en) | Method for extracting air conditioner load | |
CN111598145A (en) | Non-invasive load monitoring method based on mixed probability label time-varying constraint distribution | |
CN117034177B (en) | Intelligent monitoring method for abnormal data of power load | |
CN111563235B (en) | Intelligent power distribution and utilization system operation scene identification and generation method | |
Yu et al. | Electricity User Consumption Feature Selection and Behavior Portraying | |
Yang et al. | Evaluating the effectiveness of conservation voltage reduction with multilevel robust regression | |
Luo et al. | Detection of abnormal power consumption patterns of power users based on machine learning | |
CN116859322B (en) | Electric energy meter metering error monitoring method based on intelligent measurement terminal | |
Rouwhorst et al. | Using clustering-based load duration curves to estimate the medium-term impact of residential heat pumps on MV/LV transformers [unpublished/under review] | |
Liang et al. | Short-term Day-to-day Maximum Load Forecasting based on Data Mining and Deep Learning | |
Su et al. | Research on Two-stage Identification of Distributed Photovoltaic Output Based on WGAN Data Reconstruction Technology | |
Yu et al. | A Data-Driven Method for Identifying Behind-the-Meter PV Systems in Active Distribution Networks |
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 |