CN110727662A - Low-voltage transformer area user phase identification method and system based on correlation analysis - Google Patents
Low-voltage transformer area user phase identification method and system based on correlation analysis Download PDFInfo
- Publication number
- CN110727662A CN110727662A CN201910854523.5A CN201910854523A CN110727662A CN 110727662 A CN110727662 A CN 110727662A CN 201910854523 A CN201910854523 A CN 201910854523A CN 110727662 A CN110727662 A CN 110727662A
- Authority
- CN
- China
- Prior art keywords
- analysis
- phase
- correlation
- user
- users
- 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
Images
Classifications
-
- 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
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- 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
- 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
- G06F16/248—Presentation of query results
-
- 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
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] 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
- 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
Abstract
The invention discloses a low-voltage transformer area user phase identification method and system based on correlation analysis. The method of the invention comprises the following steps: selecting a platform area to be analyzed, selecting the platform area to be analyzed from the power utilization information acquisition system, extracting 96-point daily load data of all users, determining each user of A, B, C users through inspection, and maintaining the platform area in the system to be used as a reference point for correlation analysis; data to be analyzed after arrangement is obtained through data cleaning and standardization processing; and performing relevance analysis on the load characteristics within a period of time by adopting a Pearson relevance analysis method to obtain a relevance result of each day within an analysis period, performing statistical analysis on the mean value and the maximum value belonging phase, performing predictive analysis on the phase to which each user belongs according to the statistical result, and performing visual presentation by using a maximum and minimum normalization method. The invention does not depend on a front-line electric power staff home-investigation line, and realizes the on-line topology analysis of massive users.
Description
Technical Field
The invention belongs to the technical field of power supply networks, and particularly relates to a low-voltage transformer area user phase identification method and system based on correlation analysis.
Background
The low-voltage distribution area is located in the last link of the whole power supply network, and due to the fact that the power supply area of the low-voltage distribution area is complicated and complicated, and the types of users are various, the user topology files of the low-voltage distribution area often have the problems of more errors and difficulty in troubleshooting. At present, there are two main methods for checking the topology information error of the subscriber station area: manual on-site investigation and low-voltage carrier communication technology; the former mainly depends on the on-site investigation of electric power line staff, and sometimes the work of 'switching off and checking electricity' is needed; the low-voltage carrier communication technology mainly depends on a novel electricity meter collecting device and a handheld carrier communication instrument, and whether user topology information is correct or not is judged according to the message receiving condition between a user and a transformer.
However, both of the two checking modes need manual home checking, cannot predict in advance, and can only check every household, so that a large amount of manpower and material resources are consumed, the 'brake-off electricity-checking' mode of the former greatly affects normal electricity utilization of other users in a distribution area, the latter needs to rely on a novel user electricity utilization information acquisition device at present, and the condition is not met in some old communities, and carrier communication equipment needs to be put into, so that the operation cost of an electric power enterprise is increased.
Disclosure of Invention
The technical problem to be solved by the invention is to overcome the defects in the prior art and provide a low-voltage transformer area user phase identification method based on correlation analysis, which does not depend on a front-line power staff to check lines, and can directly adopt the 96-point daily load information of the acquisition terminal and the phase judgment of each phase reference user to realize on-line topology analysis on massive users.
Therefore, the technical scheme adopted by the invention is as follows: the low-voltage transformer area user phase identification method based on correlation analysis comprises the following steps:
1) selecting a platform area to be analyzed, selecting the platform area to be analyzed from the power utilization information acquisition system, extracting 96-point daily load data of all users, determining each user of A, B, C users through inspection, and maintaining the platform area in the system to be used as a reference point for correlation analysis;
2) data to be analyzed after arrangement is obtained through data cleaning and standardization processing;
3) and performing relevance analysis on the load characteristics within a period of time by adopting a Pearson relevance analysis method to obtain a relevance result of each day within an analysis period, performing statistical analysis on the mean value and the maximum value belonging phase, performing predictive analysis on the phase to which each user belongs according to the statistical result, and performing visual presentation by using a maximum and minimum normalization method.
According to the invention, through analyzing the historical load data of each user in the same power utilization information acquisition system, the phase information of each user and the phase registration error user information contained in the historical load data are mined, and a reference is provided for the final topology manual check.
Further, in step 2), the data cleansing is: and selecting the date of the full-day load data of the user for analysis, wherein in order to ensure the accuracy, a complete analysis day of more than sixty days for the full-96-point day load data is required.
Further, in step 3), analysis of pearson correlation coefficient: providing a reference user group under three phases of a platform area to be analyzed, wherein each phase of user only needs one to two users, and the users need to be ensured to have enough days of full 96-point data; next, for the remaining users to be analyzed, pearson correlation analysis of the reference point users is performed according to the days, that is, three groups of pearson correlation coefficients are calculated every day, the time span is 96 points, and finally, each user obtains 3 × N groups of data, where N is the number of days of analysis.
Further, in step 3), a pearson correlation coefficient, also called pearson product moment correlation coefficient, is used to measure the correlation between two variables in statistics, and the calculation formula is as follows:
in the formula: cov (X, Y) denotes the covariance, σ, between two variables X, YX,σYRepresenting the variance of two variables, the value of the Pearson correlation coefficient being between 1 and-1, muX、μYThe means of the variables X and Y, respectively, and E the mathematical expectation.
Further, in step 3), the statistical analysis is as follows: after the correlation analysis of all the users in all days and all the phases in the area to be analyzed is completed, a total correlation calculation result matrix is obtained, correlation analysis is performed on the users according to the days, correlation characteristic values between the users and a three-phase reference point are counted, the phase to which the mean value and the maximum correlation belong is analyzed, and two reference indexes of correlation coefficient mean value sorting between the users and the three-phase reference point and phase statistics to which the maximum correlation coefficient belongs are obtained.
Further, in step 3), the visualization is presented as: and performing maximum and minimum normalization presentation on the correlation analysis result between each user and the three-phase reference point by adopting a maximum and minimum normalization method in statistics.
And further, performing field check according to the analysis result, verifying the reliability of the low-voltage transformer area user phase identification method, and analyzing the reason causing the judgment error.
The other technical scheme adopted by the invention is as follows: low-voltage transformer area user phase identification system based on correlation analysis comprises:
correlation analysis reference point determination unit: selecting a platform area to be analyzed, selecting the platform area to be analyzed from the power utilization information acquisition system, extracting 96-point daily load data of all users, determining each user of A, B, C users through inspection, and maintaining the platform area in the system to be used as a reference point for correlation analysis;
a data cleaning and processing unit: data to be analyzed after arrangement is obtained through data cleaning and standardization processing;
a correlation analysis unit: and performing relevance analysis on the load characteristics within a period of time by adopting a Pearson relevance analysis method to obtain a relevance result of each day within an analysis period, performing statistical analysis on the mean value and the maximum value belonging phase, performing predictive analysis on the phase to which each user belongs according to the statistical result, and performing visual presentation by using a maximum and minimum normalization method.
The low-voltage transformer area user phase identification system further comprises a field check and inspection unit: and performing on-site check according to the analysis result, verifying the reliability of the low-voltage station area user phase identification method, and analyzing the reason causing the judgment error.
The method adopts a data preprocessing technology and a correlation analysis technology in machine learning, firstly extracts the original 96-point daily load data of a user from an electricity utilization information acquisition system, performs correlation analysis between the daily load data of the user to be analyzed and a reference point after basic data cleaning and preprocessing, predicts the phase of the user according to the statistical result of the correlation analysis, performs visual presentation, compares the phase with the original registered file, can find whether the user has a potential registration error, and provides reference for manual on-site investigation, thereby realizing the error correction of the topology file.
The invention does not depend on the on-door troubleshooting line of a line of electric power staff, can directly adopt the 96-point daily load information of the acquisition terminal and the reference users of each phase to judge the phase, thereby integrating the phase identification method in the electricity utilization information acquisition system, realizing the on-line topological analysis of mass users and finally realizing the large-scale popularization.
Drawings
Fig. 1 is a flowchart of a low-voltage transformer area user phase identification method based on correlation analysis according to embodiment 1 of the present invention;
FIG. 2 is a graph showing a user load curve of a user in a distribution room to be analyzed within a certain two days in an application example of the present invention;
FIG. 3 is a graph of correlation analysis of three users with reference points over an analysis period in accordance with an embodiment of the present invention;
FIG. 4 is a graph illustrating the maximum and minimum normalization of the correlation analysis results of three users in an application example of the present invention;
fig. 5 is a block diagram of a low-voltage station subscriber phase identification system based on correlation analysis according to embodiment 3 of the present invention.
Detailed Description
The invention is further described with reference to the drawings and the detailed description.
Example 1
The present embodiment provides a method for identifying a subscriber phase in a low-voltage distribution area based on correlation analysis, as shown in fig. 1, which includes the steps of:
1) selecting a platform area to be analyzed, selecting the platform area to be analyzed from the power utilization information acquisition system, extracting 96-point daily load data of all users, determining each user of A, B, C users through inspection, and maintaining the platform area in the system to be used as a reference point for correlation analysis;
2) data to be analyzed after arrangement is obtained through data cleaning and standardization processing;
3) and performing relevance analysis on the load characteristics within a period of time by adopting a Pearson relevance analysis method to obtain a relevance result of each day within an analysis period, performing statistical analysis on the mean value and the maximum value belonging phase, performing predictive analysis on the phase to which each user belongs according to the statistical result, and performing visual presentation by using a maximum and minimum normalization method.
In step 2), the data cleaning is as follows: and selecting the date of the full-day load data of the user for analysis, wherein in order to ensure the accuracy, a complete analysis day of more than sixty days for the full-96-point day load data is required.
In step 3), analysis of Pearson correlation coefficient: providing a reference user group under three phases of a platform area to be analyzed, wherein each phase of user only needs one to two users, and the users need to be ensured to have enough days of full 96-point data; next, for the remaining users to be analyzed, pearson correlation analysis of the reference point users is performed according to the days, that is, three groups of pearson correlation coefficients are calculated every day, the time span is 96 points, and finally, each user obtains 3 × N groups of data, where N is the number of days of analysis.
The pearson correlation coefficient, also called pearson product-moment correlation coefficient, is used in statistics to measure the correlation between two variables, and is calculated as follows:
in the formula: cov (X, Y) denotes two variables X, YCovariance between, σX,σYRepresenting the variance of two variables, the value of the pearson correlation coefficient is between 1 and-1.
The statistical analysis comprises the following steps: after the correlation analysis of all the users in all days and all the phases in the area to be analyzed is completed, a total correlation calculation result matrix is obtained, correlation analysis is performed on the users according to the days, correlation characteristic values between the users and a three-phase reference point are counted, the phase to which the mean value and the maximum correlation belong is analyzed, and two reference indexes of correlation coefficient mean value sorting between the users and the three-phase reference point and phase statistics to which the maximum correlation coefficient belongs are obtained.
The visual presentation is as follows: and performing maximum and minimum normalization presentation on the correlation analysis result between each user and the three-phase reference point by adopting a maximum and minimum normalization method in statistics.
And performing on-site check according to the analysis result, verifying the reliability of the low-voltage station area user phase identification method, and analyzing the reason causing the judgment error.
Application example
The method for identifying the subscriber phase in the low-voltage distribution area described in embodiment 1 is actually applied.
1. Data source
The data mainly come from a national power grid electricity utilization information acquisition system, and specifically include 96-point daily load data of all users in a certain district in the jurisdiction of Jiaxing city, the number of users in the district is 158, the total analysis time period is two months, and the total analysis time period contains more than forty thousand pieces of data.
2. Data observation
Fig. 2 shows the voltage load change of 192 points in two days for all users, and it can be seen that although the general change trends are similar, there is still a certain fluctuation difference between different users, which implies the difference caused by the phase difference.
3. Correlation analysis
Load data of each user under three phases are selected under the platform area to serve as reference of the phase, and Pearson correlation calculation is carried out on the rest users respectively to obtain a correlation calculation result matrix. Fig. 2 shows the correlation curve result of part of users in the statistical period.
The three groups of users belong to three phases A, B and C, and it can be seen that the degree of correlation between the three groups of users and a three-phase reference point has a certain difference due to different phases to which the users belong, although the degree of correlation can basically reach more than 0.9 and the correlation is strong, the difference between the associated phase and the non-associated phase can be seen more obviously due to the weak unbalance degree between the three phases, and subsequent statistical results and maximum and minimum visual presentation are required to amplify the difference.
4. Statistics of results
Performing statistical analysis on the user characteristic matrix obtained by the correlation analysis calculation, performing statistics on the correlation mean value between the user and each phase and the correlation maximum value correlation phase of the user in each day, and judging the phase with the maximum correlation mean value or the phase occupying the maximum correlation days as the phase to which the user belongs according to the statistical result, wherein part of the analysis results are shown in table 1:
TABLE 1 correlation calculation statistical analysis results
In table 1, a first column Index represents a user number, a second column phase represents a user phase obtained by actual investigation and used for final check, a third column represents an access point condition of a user in an actual topology, a fourth column sus _ by _ cout represents phase prediction performed according to a user maximum correlation coefficient correlation phase frequency in a statistical time period, a fifth column sus _ by _ mean represents phase prediction performed depending on a user and each phase correlation mean in the statistical time period, 6 th to 8 th column Count fields represent a maximum correlation phase statistical result of each user in an analysis time period, and 9 th to 11 th column mean fields represent a correlation coefficient mean of each user and three reference points in the analysis time period.
5. Visual presentation (maximum minimized presentation)
From the correlation calculation result, the correlations between each user and the three-phase reference point are relatively close, which is also because the three-phase unbalance degree of the platform area to be analyzed is relatively low, the treatment is relatively good, the sequencing analysis can be performed only through the statistical result, however, if the maximum and minimum normalization analysis is used, the correlation difference and the sequencing between each user and the three-phase reference point can be more intuitively displayed, fig. 4 is a graph obtained by performing the maximum and minimum normalization on the correlation analysis result of a certain user, and it can be seen that each of the three users belongs to the most relevant phase in each analysis day, and the conclusion is also matched with the result of the statistical analysis.
6. Investigation result and accuracy
According to the investigation condition of the analysis result, under the condition of average value judgment, 17 users with analysis errors are determined, under the condition of maximum value judgment, 14 users with analysis errors are determined, 158 groups of users are totally determined under the platform area to be analyzed, 3 reference points are removed, and the accuracy of two analysis results is obtained:
TABLE 2 correlation analysis findings
As can be seen from the results shown in table 2, the users with problems are mainly distributed in A, C two phases, i.e. the users in phase a and phase C are easily misjudged as the other phase, as the users circled in table 3. From the specific statistical result, the three-phase mean values are very close, the maximum correlation phase statistical frequency is also close, and compared with the criterion obtained by the statistical results of other users, the criterion is not sufficient, namely the analysis result of the user is not high in reliability, and the user belongs to the user with low reliability of the judgment result. This may be due to its particular topological location, such as: the three-phase lines led out are not greatly different when the three-phase lines are closer to the general table; or may be too far from the summary table, resulting in too much variation in its fluctuation characteristics. For such users, the analysis scale needs to be increased, a sliding window is set for time-division correlation analysis, the judgment result may be improved, or due to the limitation of the acquisition precision and frequency of the current acquisition device, the analysis work cannot be completed temporarily, and other methods need to be adopted for phase judgment.
TABLE 3 analysis of abnormal results
7. Analysis of model application conditions
From the final investigation accuracy, the method of the invention reaches the applicable level, and can provide help for the investigation of the phase files of users in the low-voltage distribution room, but because the three-phase unbalance degree of the analyzed distribution room is low, the current message precision of the total table data can only be kept to an integer, the frequency only supports 96-point data, and the correlation statistics with high precision can not be supported, so that each group of users in three phases needs to be investigated in advance to be used as a direct reference point, and certain manpower and material resources are consumed. In fact, if the station area has a high degree of unbalance, it can be considered that the total table data is directly used as a reference to directly perform three-phase analysis with the user, and tests performed before find that the scheme can achieve high accuracy, and the analysis is simpler, and only the load data of the total table and the user needs to be directly called from the system. Therefore, in the actual analysis, it is necessary to select an appropriate analysis scheme in consideration of both the precision of the acquisition device and the three-phase imbalance of the stage area to be analyzed.
Example 2
The present embodiment provides a low-voltage station area subscriber phase identification system based on correlation analysis, as shown in fig. 5, which includes:
correlation analysis reference point determination unit: selecting a platform area to be analyzed, selecting the platform area to be analyzed from the power utilization information acquisition system, extracting 96-point daily load data of all users, determining each user of A, B, C users through inspection, and maintaining the platform area in the system to be used as a reference point for correlation analysis;
a data cleaning and processing unit: data to be analyzed after arrangement is obtained through data cleaning and standardization processing;
a correlation analysis unit: performing relevance analysis on load characteristics within a period of time by adopting a Pearson relevance analysis method to obtain relevance results of each day within an analysis period, performing statistical analysis on the mean value and the maximum value attribution phase, performing predictive analysis on the phase to which each user belongs according to the statistical results, and performing visual presentation by using a maximum and minimum normalization method;
the field check inspection unit: and performing on-site check according to the analysis result, verifying the reliability of the low-voltage station area user phase identification method, and analyzing the reason causing the judgment error.
In the data cleaning and processing unit, the data cleaning is as follows: and selecting the date of the full-day load data of the user for analysis, wherein in order to ensure the accuracy, a complete analysis day of more than sixty days for the full-96-point day load data is required.
The Pearson correlation coefficient analysis method comprises the following steps: providing a reference user group under three phases of a platform area to be analyzed, wherein each phase of user only needs one to two users, and the users need to be ensured to have enough days of full 96-point data; next, for the remaining users to be analyzed, pearson correlation analysis of the reference point users is performed according to the days, that is, three groups of pearson correlation coefficients are calculated every day, the time span is 96 points, and finally, each user obtains 3 × N groups of data, where N is the number of days of analysis.
The pearson correlation coefficient, also called pearson product-moment correlation coefficient, is used in statistics to measure the correlation between two variables, and is calculated as follows:
in the formula: cov (X, Y) denotes the covariance, σ, between two variables X, YX,σYRepresenting the variance of two variables, the value of the Pearson correlation coefficient being between 1 and-1, muX、μYThe means of the variables X and Y, respectively, and E the mathematical expectation.
The foregoing shows and describes the general principles and broad features of the present invention and advantages thereof. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (10)
1. The low-voltage transformer area user phase identification method based on correlation analysis is characterized by comprising the following steps:
step 1), selecting a platform area to be analyzed, selecting the platform area to be analyzed from an electricity utilization information acquisition system, extracting 96-point daily load data of all users, determining A, B, C users by checking, and maintaining in the system to be used as a reference point for correlation analysis;
step 2), obtaining the sorted data to be analyzed through data cleaning and standardization processing;
and 3) carrying out correlation analysis on the load characteristics within a period of time by adopting a Pearson correlation analysis method to obtain correlation results of each day within an analysis period, carrying out statistical analysis on the mean value and the maximum value attribution phase, carrying out predictive analysis on the phase to which each user belongs according to the statistical results, and carrying out visual presentation by using a maximum and minimum normalization method.
2. The correlation analysis-based low-pressure station user phase identification method as claimed in claim 1, wherein in step 2), the data cleaning is as follows: and selecting the date of the full-day load data of the user for analysis, wherein in order to ensure the accuracy, a complete analysis day of more than sixty days for the full-96-point day load data is required.
3. The method for identifying the phase of the low-voltage station user based on the correlation analysis as claimed in claim 1, wherein in the step 3), the Pearson correlation coefficient analysis method is as follows: providing a reference user group under three phases of a platform area to be analyzed, wherein each phase of user only needs one to two users, and the users need to be ensured to have enough days of full 96-point data; next, for the remaining users to be analyzed, pearson correlation analysis of the reference point users is performed according to the days, that is, three groups of pearson correlation coefficients are calculated every day, the time span is 96 points, and finally, each user obtains 3 × N groups of data, where N is the number of days of analysis.
4. The method for identifying the phase of the low-voltage station user based on the correlation analysis as claimed in claim 1, wherein in step 3), the pearson correlation coefficient, also called pearson product-moment correlation coefficient, is statistically used to measure the correlation between two variables, and the calculation formula is as follows:
in the formula: cov (X, Y) denotes the covariance, σ, between two variables X, YX,σYRepresenting the variance of two variables, the value of the Pearson correlation coefficient being between 1 and-1, muX、μYThe means of the variables X and Y, respectively, and E the mathematical expectation.
5. The method for identifying the subscriber phase in the low-voltage transformer area based on the correlation analysis as claimed in claim 1, wherein in the step 3), the statistical analysis is as follows: after the correlation analysis of all the users in all days and all the phases in the area to be analyzed is completed, a total correlation calculation result matrix is obtained, correlation analysis is performed on the users according to the days, correlation characteristic values between the users and a three-phase reference point are counted, the phase to which the mean value and the maximum correlation belong is analyzed, and two reference indexes of correlation coefficient mean value sorting between the users and the three-phase reference point and phase statistics to which the maximum correlation coefficient belongs are obtained.
6. The correlation analysis-based low-pressure station area user phase identification method according to claim 1, wherein in step 3), the visualization is presented as: and performing maximum and minimum normalization presentation on the correlation analysis result between each user and the three-phase reference point by adopting a maximum and minimum normalization method in statistics.
7. The method for identifying the phase of the low-voltage transformer area user based on the correlation analysis as claimed in claim 1, wherein the field check is performed according to the analysis result, the reliability of the method for identifying the phase of the low-voltage transformer area user is verified, and the reason for the judgment error is analyzed.
8. Low pressure platform district user phase place identification system based on correlation analysis, its characterized in that includes:
correlation analysis reference point determination unit: selecting a platform area to be analyzed, selecting the platform area to be analyzed from the power utilization information acquisition system, extracting 96-point daily load data of all users, determining each user of A, B, C users through inspection, and maintaining the platform area in the system to be used as a reference point for correlation analysis;
a data cleaning and processing unit: data to be analyzed after arrangement is obtained through data cleaning and standardization processing;
a correlation analysis unit: and performing relevance analysis on the load characteristics within a period of time by adopting a Pearson relevance analysis method to obtain a relevance result of each day within an analysis period, performing statistical analysis on the mean value and the maximum value belonging phase, performing predictive analysis on the phase to which each user belongs according to the statistical result, and performing visual presentation by using a maximum and minimum normalization method.
9. The correlation analysis-based low-voltage transformer area subscriber phase identification system of claim 8, further comprising an on-site verification unit: and performing on-site check according to the analysis result, verifying the reliability of the low-voltage station area user phase identification method, and analyzing the reason causing the judgment error.
10. The correlation analysis-based low-voltage transformer area subscriber phase identification system as claimed in claim 8, wherein the Pearson correlation coefficient analysis method is as follows: providing a reference user group under three phases of a platform area to be analyzed, wherein each phase of user only needs one to two users, and the users need to be ensured to have enough days of full 96-point data; next, for the remaining users to be analyzed, pearson correlation analysis of the reference point users is performed according to the days, that is, three groups of pearson correlation coefficients are calculated every day, the time span is 96 points, and finally, each user obtains 3 × N groups of data, where N is the number of days of analysis.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910854523.5A CN110727662A (en) | 2019-09-10 | 2019-09-10 | Low-voltage transformer area user phase identification method and system based on correlation analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910854523.5A CN110727662A (en) | 2019-09-10 | 2019-09-10 | Low-voltage transformer area user phase identification method and system based on correlation analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110727662A true CN110727662A (en) | 2020-01-24 |
Family
ID=69217968
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910854523.5A Pending CN110727662A (en) | 2019-09-10 | 2019-09-10 | Low-voltage transformer area user phase identification method and system based on correlation analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110727662A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111505433A (en) * | 2020-04-10 | 2020-08-07 | 国网浙江余姚市供电有限公司 | Low-voltage transformer area family variable relation error correction and phase identification method |
| CN111597505A (en) * | 2020-06-17 | 2020-08-28 | 南方电网科学研究院有限责任公司 | Correlation analysis method and correlation device for electricity users in power network |
| CN112485525A (en) * | 2020-11-27 | 2021-03-12 | 中国电力科学研究院有限公司 | Transformer phase identification method and device, equipment and storage medium |
| CN112485748A (en) * | 2020-10-15 | 2021-03-12 | 国网江苏省电力有限公司南京供电分公司 | Phase-to-phase judgment method for single-phase electric meter |
| CN112668173A (en) * | 2020-12-24 | 2021-04-16 | 国网江西省电力有限公司电力科学研究院 | Method for calculating 10kV line topological relation threshold based on skewed distribution |
| CN112699913A (en) * | 2020-11-25 | 2021-04-23 | 国网湖南省电力有限公司 | Transformer area household variable relation abnormity diagnosis method and device |
| CN112730984A (en) * | 2021-03-31 | 2021-04-30 | 国网江西省电力有限公司供电服务管理中心 | Low-voltage distribution network phase identification method based on intelligent electric meter |
| CN112886582A (en) * | 2021-02-08 | 2021-06-01 | 国网上海市电力公司 | Method for identifying station area phase based on voltage correlation of load rate and topology |
| CN113189418A (en) * | 2021-04-12 | 2021-07-30 | 中能瑞通（北京）科技有限公司 | Topological relation identification method based on voltage data |
| CN113538165A (en) * | 2021-05-28 | 2021-10-22 | 国网上海市电力公司 | Resident electricity consumption behavior perception analysis method serving for energy conservation and emission reduction of users |
| CN114626487A (en) * | 2022-05-16 | 2022-06-14 | 南昌工程学院 | Line-variable relation checking method based on random forest classification algorithm |
| CN114912526A (en) * | 2022-05-13 | 2022-08-16 | 北京市腾河电子技术有限公司 | Method and system for identifying distribution area, electronic device and storage medium |
| CN115344567A (en) * | 2022-10-18 | 2022-11-15 | 国网天津市电力公司营销服务中心 | Low-voltage transformer area data cleaning and treatment method and device suitable for edge calculation |
| CN117557118A (en) * | 2023-11-13 | 2024-02-13 | 国网江苏省电力有限公司镇江供电分公司 | UPS system power supply topological graph generation method based on machine learning |
| CN114912526B (en) * | 2022-05-13 | 2024-04-26 | 北京市腾河电子技术有限公司 | Method and system for identifying areas, electronic equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3121772A1 (en) * | 2015-07-20 | 2017-01-25 | Accenture Global Services Limited | Common data repository for improving transactional efficiencies across one or more communication channels |
| CN108805457A (en) * | 2018-06-19 | 2018-11-13 | 宁波迦南智能电气股份有限公司 | A kind of electric energy meter taiwan area recognition methods of high accuracy |
| CN109344144A (en) * | 2018-09-06 | 2019-02-15 | 葛得辉 | A kind of low-voltage platform area family change relation recognition method and system |
-
2019
- 2019-09-10 CN CN201910854523.5A patent/CN110727662A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3121772A1 (en) * | 2015-07-20 | 2017-01-25 | Accenture Global Services Limited | Common data repository for improving transactional efficiencies across one or more communication channels |
| CN108805457A (en) * | 2018-06-19 | 2018-11-13 | 宁波迦南智能电气股份有限公司 | A kind of electric energy meter taiwan area recognition methods of high accuracy |
| CN109344144A (en) * | 2018-09-06 | 2019-02-15 | 葛得辉 | A kind of low-voltage platform area family change relation recognition method and system |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111505433A (en) * | 2020-04-10 | 2020-08-07 | 国网浙江余姚市供电有限公司 | Low-voltage transformer area family variable relation error correction and phase identification method |
| CN111505433B (en) * | 2020-04-10 | 2022-06-28 | 国网浙江余姚市供电有限公司 | Low-voltage transformer area indoor variable relation error correction and phase identification method |
| CN111597505A (en) * | 2020-06-17 | 2020-08-28 | 南方电网科学研究院有限责任公司 | Correlation analysis method and correlation device for electricity users in power network |
| CN111597505B (en) * | 2020-06-17 | 2023-05-26 | 南方电网科学研究院有限责任公司 | Correlation analysis method and correlation device for electricity utilization users in power network |
| CN112485748A (en) * | 2020-10-15 | 2021-03-12 | 国网江苏省电力有限公司南京供电分公司 | Phase-to-phase judgment method for single-phase electric meter |
| CN112485748B (en) * | 2020-10-15 | 2023-10-24 | 国网江苏省电力有限公司南京供电分公司 | Single-phase ammeter phase judging method |
| CN112699913A (en) * | 2020-11-25 | 2021-04-23 | 国网湖南省电力有限公司 | Transformer area household variable relation abnormity diagnosis method and device |
| CN112699913B (en) * | 2020-11-25 | 2023-08-29 | 国网湖南省电力有限公司 | Method and device for diagnosing abnormal relationship of household transformer in transformer area |
| CN112485525A (en) * | 2020-11-27 | 2021-03-12 | 中国电力科学研究院有限公司 | Transformer phase identification method and device, equipment and storage medium |
| CN112485525B (en) * | 2020-11-27 | 2022-12-20 | 中国电力科学研究院有限公司 | Transformer phase identification method and device, equipment and storage medium |
| CN112668173B (en) * | 2020-12-24 | 2022-06-10 | 国网江西省电力有限公司电力科学研究院 | Method for calculating 10kV line topological relation threshold based on skewed distribution |
| CN112668173A (en) * | 2020-12-24 | 2021-04-16 | 国网江西省电力有限公司电力科学研究院 | Method for calculating 10kV line topological relation threshold based on skewed distribution |
| CN112886582A (en) * | 2021-02-08 | 2021-06-01 | 国网上海市电力公司 | Method for identifying station area phase based on voltage correlation of load rate and topology |
| CN112730984A (en) * | 2021-03-31 | 2021-04-30 | 国网江西省电力有限公司供电服务管理中心 | Low-voltage distribution network phase identification method based on intelligent electric meter |
| CN113189418B (en) * | 2021-04-12 | 2022-10-25 | 中能瑞通（北京）科技有限公司 | Topological relation identification method based on voltage data |
| CN113189418A (en) * | 2021-04-12 | 2021-07-30 | 中能瑞通（北京）科技有限公司 | Topological relation identification method based on voltage data |
| CN113538165A (en) * | 2021-05-28 | 2021-10-22 | 国网上海市电力公司 | Resident electricity consumption behavior perception analysis method serving for energy conservation and emission reduction of users |
| CN114912526A (en) * | 2022-05-13 | 2022-08-16 | 北京市腾河电子技术有限公司 | Method and system for identifying distribution area, electronic device and storage medium |
| CN114912526B (en) * | 2022-05-13 | 2024-04-26 | 北京市腾河电子技术有限公司 | Method and system for identifying areas, electronic equipment and storage medium |
| CN114626487A (en) * | 2022-05-16 | 2022-06-14 | 南昌工程学院 | Line-variable relation checking method based on random forest classification algorithm |
| CN114626487B (en) * | 2022-05-16 | 2023-09-05 | 南昌工程学院 | Linear transformation relation checking method based on random forest classification algorithm |
| CN115344567A (en) * | 2022-10-18 | 2022-11-15 | 国网天津市电力公司营销服务中心 | Low-voltage transformer area data cleaning and treatment method and device suitable for edge calculation |
| CN117557118A (en) * | 2023-11-13 | 2024-02-13 | 国网江苏省电力有限公司镇江供电分公司 | UPS system power supply topological graph generation method based on machine learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110727662A (en) | Low-voltage transformer area user phase identification method and system based on correlation analysis | |
| CN107462863B (en) | Operation error operation diagnosis and analysis method and system for intelligent electric energy meter | |
| CN106154209B (en) | Electrical energy meter fault prediction technique based on decision Tree algorithms | |
| CN111505433B (en) | Low-voltage transformer area indoor variable relation error correction and phase identification method | |
| CN107832927B (en) | 10kV line variable relation evaluation method based on grey correlation analysis method | |
| JP2009089594A (en) | Temporal-spatial load analysis system of power facility utilizing inspection data and calculation method of load | |
| KR102029031B1 (en) | Apparatus and method for estimating power loss of distribution line | |
| CN109635950B (en) | Electric energy meter running state monitoring method based on genetic algorithm and community clustering | |
| CN110968703B (en) | Method and system for constructing abnormal metering point knowledge base based on LSTM end-to-end extraction algorithm | |
| CN112698123A (en) | Low-voltage distribution area user topological relation identification method based on decision tree | |
| CN111832174B (en) | Multi-regression-based wiring line loss rate processing method and device | |
| CN113033617A (en) | Deep mining analysis method based on line loss data of big data transformer area | |
| CN113902062A (en) | Transformer area line loss abnormal reason analysis method and device based on big data | |
| CN111612149A (en) | Main network line state detection method, system and medium based on decision tree | |
| CN115293257A (en) | Detection method and system for abnormal electricity utilization user | |
| CN112016856B (en) | Comprehensive magnification abnormity identification method and device, metering system and storage medium | |
| CN112345972B (en) | Power distribution network line transformation relation abnormity diagnosis method, device and system based on power failure event | |
| CN112182499A (en) | Low-voltage distribution network topological structure identification method based on time sequence electric quantity data | |
| CN113282594B (en) | Automatic extraction and analysis method and system for basic data of distribution transformer | |
| CN115809805A (en) | Power grid multi-source data processing method based on edge calculation | |
| CN114740419A (en) | Method, device, equipment and medium for analyzing error of district ammeter based on three-dimensional graph | |
| CN112611997B (en) | Online verification method and system for hitching relation of platform area gateway table | |
| CN112434954A (en) | Power failure sensitivity evaluation method and device | |
| CN112925827A (en) | User property abnormity analysis method based on power acquisition Internet of things data | |
| CN104361422A (en) | Power consumer power quality data collection method based on economic evaluation |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210325 Address after: 311100 Building 5, 138 Yunlian Road, Yuhang District, Hangzhou City, Zhejiang Province Applicant after: Marketing service center of State Grid Zhejiang Electric Power Co.,Ltd. Applicant after: ZHEJIANG HUAYUN INFORMATION TECHNOLOGY Co.,Ltd. Address before: The eight district of Hangzhou city in Zhejiang province 310014 Huadian Zhaohui under No. 1 Lane Applicant before: STATE GRID ZHEJIANG ELECTRIC POWER COMPANY LIMITED ELECTRIC POWER Research Institute Applicant before: ZHEJIANG HUAYUN INFORMATION TECHNOLOGY Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200124 |