CN116910602B - Line loss analysis method and system based on relevance analysis - Google Patents
Line loss analysis method and system based on relevance analysis Download PDFInfo
- Publication number
- CN116910602B CN116910602B CN202311183624.7A CN202311183624A CN116910602B CN 116910602 B CN116910602 B CN 116910602B CN 202311183624 A CN202311183624 A CN 202311183624A CN 116910602 B CN116910602 B CN 116910602B
- Authority
- CN
- China
- Prior art keywords
- line loss
- data
- analysis
- clustering center
- result
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 98
- 238000012937 correction Methods 0.000 claims abstract description 53
- 230000002159 abnormal effect Effects 0.000 claims abstract description 50
- 230000035945 sensitivity Effects 0.000 claims description 21
- 238000007621 cluster analysis Methods 0.000 claims description 17
- 238000004364 calculation method Methods 0.000 claims description 15
- 238000004422 calculation algorithm Methods 0.000 claims description 13
- 238000010219 correlation analysis Methods 0.000 claims description 12
- 238000005265 energy consumption Methods 0.000 claims description 12
- 230000010354 integration Effects 0.000 claims description 5
- 230000001276 controlling effect Effects 0.000 abstract 1
- 230000001105 regulatory effect Effects 0.000 abstract 1
- 230000005856 abnormality Effects 0.000 description 12
- 230000009193 crawling Effects 0.000 description 8
- 230000005540 biological transmission Effects 0.000 description 6
- 238000000034 method Methods 0.000 description 6
- 230000000875 corresponding effect Effects 0.000 description 5
- 238000012216 screening Methods 0.000 description 5
- 230000002776 aggregation Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000005611 electricity Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000002596 correlated effect Effects 0.000 description 2
- 238000003064 k means clustering Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000004220 aggregation Methods 0.000 description 1
- 238000000556 factor analysis Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Probability & Statistics with Applications (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a line loss analysis method and a line loss analysis system based on relevance analysis, which are characterized in that historical power data and a line loss abnormal factor list of a target area are obtained, relevance comparison analysis is carried out on the historical power data, clustering analysis is carried out on the first data to obtain a classification result, after line loss abnormal factor list is obtained, line loss key factors are associated with the classification result to obtain integrated data, analysis and correction are carried out on the integrated data to obtain a correction result, so that grid personnel can formulate a regulation and control plan according to the correction result, schedule the power data by utilizing the regulation and control plan, and the regulation and control efficiency of power resource is improved by singly regulating and controlling different line loss causes without singly analyzing a plurality of groups of power data.
Description
Technical Field
The invention relates to the technical field of power line loss calculation, in particular to a line loss analysis method and system based on relevance analysis.
Background
With the increasing popularity of the application of the power in society, a large-scale power coverage can be made, so that a whole set of power system can be provided in the circuit, the power system has a line loss phenomenon in the power transmission process, the line loss refers to the sum of reactive power and voltage loss generated when the power is transmitted through a power supply line, and therefore, the line loss needs to be analyzed to be beneficial to subsequent power regulation and economic analysis.
At present, the analysis of the line loss is based on single factor analysis, and the analysis limitation of only single factors is large, and the time is too long, so that the later analysis and regulation efficiency is low.
Disclosure of Invention
In order to solve the technical problems, the embodiment of the invention provides a line loss analysis method and a system based on relevance analysis, which aim to independently regulate and control different line loss reasons without independently analyzing a plurality of groups of power data in a relevance mode, so that the power resource regulation and control efficiency is improved.
A first aspect of an embodiment of the present invention provides a line loss analysis method based on relevance analysis, where the method includes:
acquiring historical power data and a line loss abnormal factor list of a target platform area, performing correlation comparison analysis on the historical power data to obtain first data, and performing cluster analysis on the first data to obtain a classification result;
according to the line loss abnormal factor list, after obtaining the line loss key factors, correlating the line loss key factors with classification results to obtain integrated data;
and after analyzing and correcting the integrated data, obtaining a correction result, so that power grid personnel can make a regulation and control plan according to the correction result, and dispatching the power data by using the regulation and control plan.
According to the embodiment, historical power data and a line loss abnormal factor list of a target area are obtained, correlation comparison analysis is carried out on the historical power data, after first data are obtained, cluster analysis is carried out on the first data to obtain a classification result, after line loss key factors are obtained according to the line loss abnormal factor list, the line loss key factors are associated with the classification result to obtain integrated data, after analysis and correction are carried out on the integrated data, a correction result is obtained, so that power grid personnel can formulate a regulation and control plan according to the correction result, and power data are scheduled by utilizing the regulation and control plan. By means of the mode of correlating multiple groups of power data, the power resource regulation and control efficiency is improved without independently analyzing different line loss reasons.
In a possible implementation manner of the first aspect, the correlation comparison analysis is performed on the historical power data to obtain first data, specifically:
performing correlation comparison analysis on the historical power data to obtain the similarity of each historical power data;
and selecting historical power data with similarity larger than preset similarity as data to be analyzed to obtain first data.
In a possible implementation manner of the first aspect, cluster analysis is performed on the first data to obtain a classification result, which specifically is:
performing cluster analysis on the first data by adopting a cluster algorithm to obtain a plurality of feature classes, and selecting the plurality of feature data in the feature classes as a first cluster center, wherein the first cluster center comprises a plurality of classes;
the feature data with the distance smaller than a first preset value from the first clustering center is classified into the first clustering center, and the feature data which is not classified is classified into the category with the distance smaller than a second preset value from the first clustering center, so that a second clustering center is obtained;
judging whether the second clustering center and the first clustering center have the same clustering center, if not, recalculating the clustering centers of the categories to obtain a target clustering center, judging whether the target clustering center is the same as the second clustering center, if so, taking the category of the target clustering center as the second category, and repeating the steps until the feature data is obtained and the classification result is obtained.
In a possible implementation manner of the first aspect, after obtaining the line loss key factor according to the line loss abnormal factor list, the line loss key factor is associated with the classification result to obtain the integrated data, which specifically includes:
carrying out correlation analysis on line loss data according to the line loss abnormal factor list to obtain a correlation result of the line loss data, and carrying out sensitivity calculation on each line loss abnormal factor to obtain a sensitivity result of the line loss data;
and obtaining a line loss key factor according to the correlation result and the sensitivity result, and obtaining integrated data of the line loss key factor after correlating the line loss key factor with the classification result.
In a possible implementation manner of the first aspect, after the integrated data is analyzed and corrected, a correction result is obtained, so that a power grid personnel makes a regulation and control plan according to the correction result, and the regulation and control plan is used for scheduling the power data, specifically:
establishing a line loss reason analysis specification, acquiring line loss resource information of the transformer area, and analyzing the line loss resource information according to the line loss reason analysis specification and the line loss resource information to obtain line loss basic information;
constructing a line loss basic information model according to the integrated data, carrying out anomaly analysis on the line loss basic information by utilizing the line loss basic information model to obtain line loss anomaly factors, and identifying the electric power data of the target station area according to the line loss anomaly factors to obtain anomaly data;
and determining the line loss problem according to the abnormal data, obtaining a correction result, and making a regulation and control plan according to the correction result, and scheduling the power data by using the regulation and control plan.
In a possible implementation manner of the first aspect, the obtaining line loss resource information of the target area specifically includes:
acquiring FTU switching information and energy consumption information in a power system of a target station area;
traversing the power system of the target area according to the FTU switch information to obtain a real-time topology network of the power system of the target area;
acquiring electrical parameters of each node and branch in a real-time topological network of a target area power system;
and obtaining line loss resource information according to the electrical parameters and the energy consumption information.
A second aspect of an embodiment of the present invention provides a line loss analysis system for correlation analysis, the system including:
the acquisition module is used for acquiring historical power data and a line loss abnormal factor list of the target area, performing correlation comparison analysis on the historical power data to obtain first data, and performing cluster analysis on the first data to obtain a classification result;
the association module is used for associating the line loss key factors with the classification results to obtain integrated data after obtaining the line loss key factors according to the line loss abnormal factor list;
and the regulation and control module is used for obtaining a correction result after analyzing and correcting the integrated data, so that power grid personnel can make a regulation and control plan according to the correction result, and the regulation and control plan is utilized to schedule the power data.
In a possible implementation manner of the second aspect, the obtaining module includes a similarity calculating unit and a selecting unit,
the similarity calculation unit is used for carrying out correlation comparison analysis on the historical power data to obtain the similarity of each historical power data;
the selecting unit is used for selecting historical power data with similarity larger than preset similarity as data to be analyzed to obtain first data.
In a possible implementation manner of the second aspect, the acquisition module further includes a clustering unit, a dividing unit and a judging unit,
the clustering unit is used for carrying out clustering analysis on the first data by adopting a clustering algorithm to obtain a plurality of feature classes, and selecting the plurality of feature data in the feature classes as a first clustering center, wherein the first clustering center comprises a plurality of classes;
the dividing unit is used for dividing the characteristic data with the distance from the first clustering center being smaller than a first preset value into the first clustering center, and dividing the undivided characteristic data into categories with the distance from the first clustering center being smaller than a second preset value to obtain a second clustering center;
the judging unit is used for judging whether the second clustering center and the first clustering center have the same clustering center, if not, the clustering centers of the categories are recalculated to obtain the target clustering center, judging whether the target clustering center is the same as the second clustering center, if so, the categories of the target clustering center are taken as the second category, and repeating the steps until the feature data are obtained and the classification result is obtained.
In a possible implementation manner of the second aspect, the association module includes a computing unit and an integration unit,
the calculating unit is used for carrying out correlation analysis on the line loss data according to the line loss abnormal factor list to obtain a correlation result of the line loss data, and carrying out sensitivity calculation on each line loss abnormal factor to obtain a sensitivity result of the line loss data;
the integration unit is used for obtaining the line loss key factors according to the correlation result and the sensitivity result, and obtaining the integrated data of the line loss key factors after correlating the line loss key factors with the classification result.
In a possible implementation manner of the second aspect, after the integrated data is analyzed and corrected, a correction result is obtained, so that a power grid personnel makes a regulation and control plan according to the correction result, and the regulation and control plan is used for scheduling the power data, specifically:
establishing a line loss reason analysis specification, acquiring line loss resource information of the transformer area, and analyzing the line loss resource information according to the line loss reason analysis specification and the line loss resource information to obtain line loss basic information;
constructing a line loss basic information model according to the integrated data, carrying out anomaly analysis on the line loss basic information by utilizing the line loss basic information model to obtain line loss anomaly factors, and identifying the electric power data of the target station area according to the line loss anomaly factors to obtain anomaly data;
and determining the line loss problem according to the abnormal data, obtaining a correction result, and making a regulation and control plan according to the correction result, and scheduling the power data by using the regulation and control plan.
In a possible implementation manner of the second aspect, the obtaining line loss resource information of the target station area specifically includes:
acquiring FTU switching information and energy consumption information in a power system of a target station area;
traversing the power system of the target area according to the FTU switch information to obtain a real-time topology network of the power system of the target area;
acquiring electrical parameters of each node and branch in a real-time topological network of a target area power system;
and obtaining line loss resource information according to the electrical parameters and the energy consumption information.
According to the method, the historical power data and the line loss abnormal factor list of the target area are obtained, correlation comparison analysis is carried out on the historical power data, clustering analysis is carried out on the first data to obtain a classification result, after the line loss key factors are obtained according to the line loss abnormal factor list, the line loss key factors are associated with the classification result to obtain integrated data, analysis and correction are carried out on the integrated data to obtain a correction result, so that a power grid personnel can formulate a regulation and control plan according to the correction result, the power data are scheduled by utilizing the regulation and control plan, and the regulation and control efficiency of power resources is improved by carrying out independent regulation and control on multiple groups of power data in a mode of associating without independent analysis of different line loss causes.
Drawings
Fig. 1: the invention provides a flow diagram of one embodiment of a line loss analysis method based on relevance analysis;
fig. 2: the line loss system structure schematic diagram of one embodiment of the line loss analysis method based on the relevance analysis is provided by the invention;
fig. 3: the invention provides a system structure schematic diagram of another embodiment of a line loss analysis method based on relevance analysis.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
Referring to fig. 1, a flow chart of an embodiment of a line loss analysis method based on relevance analysis according to the present invention includes steps S11 to S13, where the steps are as follows:
s11, acquiring historical power data and a line loss abnormality factor list of a target area, performing correlation comparison analysis on the historical power data to obtain first data, and performing cluster analysis on the first data to obtain a classification result.
In a preferred embodiment, correlation comparison analysis is performed on the historical power data to obtain first data, specifically:
performing correlation comparison analysis on the historical power data to obtain the similarity of each historical power data;
and selecting historical power data with similarity larger than preset similarity as data to be analyzed to obtain first data.
In a preferred embodiment, the first data is subjected to cluster analysis to obtain a classification result, which specifically includes:
performing cluster analysis on the first data by adopting a cluster algorithm to obtain a plurality of feature classes, and selecting the plurality of feature data in the feature classes as a first cluster center, wherein the first cluster center comprises a plurality of classes;
the feature data with the distance smaller than a first preset value from the first clustering center is classified into the first clustering center, and the feature data which is not classified is classified into the category with the distance smaller than a second preset value from the first clustering center, so that a second clustering center is obtained;
judging whether the second clustering center and the first clustering center have the same clustering center, if not, recalculating the clustering centers of the categories to obtain a target clustering center, judging whether the target clustering center is the same as the second clustering center, if so, taking the category of the target clustering center as the second category, and repeating the steps until the feature data is obtained and the classification result is obtained.
In this embodiment, the transmission data backed up and recorded in the power transmission process is checked in the background reserved and stored in the later stage, and crawled through the database in the whole power transmission station. After connection is established between the search instruction and the acquisition database, the crawling module is used for acquiring historical power data from the database.
And then, comparing and analyzing the correlation in the acquired historical electric power data to obtain a comparison result with higher similarity, and classifying the result with higher similarity after comparison by a clustering algorithm.
Then, carrying out cluster analysis on the first data based on a cluster algorithm to obtain a classification result, wherein the specific steps are as follows:
firstly, carrying out cluster analysis on the historical data by adopting a cluster algorithm to obtain feature classes, wherein the feature data is selected from a preset number of samples, and the samples are used as first cluster centers, and the first cluster centers have corresponding classes; the rest of the characteristic data are summarized into categories closest to each other, and a second aggregation center is obtained through calculation; the step of setting the category of the second aggregation center as the feature class, and setting the category of the second aggregation center as the feature class includes: judging whether the second clustering center and the first clustering center are the same clustering center or not; if the second clustering center and the first clustering center are different clustering centers, recalculating the clustering centers of the category to obtain a target clustering center; judging whether the target cluster center is the same as the second cluster center; and if the target cluster center is the same as the second cluster center, taking the class in which the target cluster center is positioned as the characteristic class.
And S12, after the line loss key factors are obtained according to the line loss abnormal factor list, the line loss key factors are correlated with the classification result, and integrated data are obtained.
In a preferred embodiment, after obtaining the line loss key factor according to the line loss abnormal factor list, correlating the line loss key factor with the classification result to obtain integrated data, specifically:
carrying out correlation analysis on line loss data according to the line loss abnormal factor list to obtain a correlation result of the line loss data, and carrying out sensitivity calculation on each line loss abnormal factor to obtain a sensitivity result of the line loss data;
and obtaining a line loss key factor according to the correlation result and the sensitivity result, and obtaining integrated data of the line loss key factor after correlating the line loss key factor with the classification result.
In this embodiment, after the line loss anomaly factor list of the target area is obtained, the correlation analysis method is adopted to analyze the correlation between each line loss anomaly factor and the line loss data according to the line loss anomaly factor list, so as to obtain the correlation result of all the line loss data. And then calculating sensitivity data of each line loss abnormal factor, acquiring the line loss key factors containing space-time characteristic quantity based on the correlation result and the sensitivity data, and extracting the line loss factors with high correlation and high sensitivity containing the space-time characteristic quantity as the line loss key factors.
And finally, after the line loss key factors are correlated with the classification result, the integrated data of the line loss key factors are obtained.
And S13, after analysis and correction are carried out on the integrated data, a correction result is obtained, so that power grid personnel can make a regulation and control plan according to the correction result, and the regulation and control plan is utilized to schedule the power data.
In a preferred embodiment, after the integrated data is analyzed and corrected, a correction result is obtained, so that a power grid personnel makes a regulation and control plan according to the correction result, and the regulation and control plan is utilized to schedule the power data, specifically:
establishing a line loss reason analysis specification, acquiring line loss resource information of the transformer area, and analyzing the line loss resource information according to the line loss reason analysis specification and the line loss resource information to obtain line loss basic information;
constructing a line loss basic information model according to the integrated data, carrying out anomaly analysis on the line loss basic information by utilizing the line loss basic information model to obtain line loss anomaly factors, and identifying the electric power data of the target station area according to the line loss anomaly factors to obtain anomaly data;
and determining the line loss problem according to the abnormal data, obtaining a correction result, and making a regulation and control plan according to the correction result, and scheduling the power data by using the regulation and control plan.
In a preferred embodiment, the obtaining line loss resource information of the target station area specifically includes:
acquiring FTU switching information and energy consumption information in a power system of a target station area;
traversing the power system of the target area according to the FTU switch information to obtain a real-time topology network of the power system of the target area;
acquiring electrical parameters of each node and branch in a real-time topological network of a target area power system;
and obtaining line loss resource information according to the electrical parameters and the energy consumption information.
In this embodiment, the line loss analysis submodule is utilized to establish line loss reasons including line loss anomaly cause definition, line loss anomaly analysis guide and line loss anomaly processing guide, obtain line loss resource information, and perform line loss resource information analysis according to the line loss cause analysis specification and the line loss resource information. The method comprises the steps of constructing a line loss basic information model, performing measurement bad data identification according to the concepts of EMS and DMS state estimation to correct a large probability reason causing line loss abnormality, obtaining a corrected large probability reason causing line loss abnormality, performing measurement bad data identification according to the concepts of EMS and DMS state estimation according to the line loss problem, determining the line loss problem according to the identification condition, and then making a regulation and control plan according to the line loss reason to regulate and control the line loss in a cloud.
Firstly, the line loss analysis submodule is used for establishing line loss reason analysis standards and acquiring line loss resource information, and the specific mode is as follows: the power network comprises FTU switching information and energy consumption information, the power network is traversed according to the FTU switching information and a breadth-first search algorithm, a real-time topology network of the power network is obtained, electric parameters corresponding to nodes and branches in the real-time topology network are obtained, and comprehensive loss of the power network is obtained according to the electric parameters and the energy consumption information.
Then analyzing the line loss abnormality according to the integrated data, searching for the approximate reason causing the line loss abnormality, and identifying the bad data through the line loss abnormality reason, wherein the specific steps are as follows:
based on the historical line loss rate K-means clustering result, the IBM SPSSStatistics25 software and the python skleam model are combined to establish a standard library and an abnormal library of the line loss rate of the transformer area, and a basis is provided for judging the abnormality of the line loss rate. Expanding from three processing aspects of electricity consumption data missing value, noise value and normalization, and preprocessing electricity consumption data to obtain a user electric quantity set { Wj } with research significance; the pearson coefficient rxy of the electric quantity and the line loss rate of each user in the effective user electric quantity set { Wj } in the abnormal time period T is calculated, the user electric quantity set { Wk } with larger relevance to the line loss abnormality is determined, the suspected user range is further reduced, and the calculation iteration time is saved; and calculating the Euclidean distance DE improved by two curves of the user electric quantity and the line loss rate in the user electric quantity set { Wk } with larger relevance to the line loss abnormality, and calculating the weight coefficient of the Pearson coefficient and the Euclidean distance to accurately locate all abnormal users.
An abnormal platform area line loss rate standard library and an abnormal library are established based on the clustering result, a platform area line loss rate standard library and an abnormal library are established based on the clustering result, an abnormal time period T is determined, the abnormal platform area line loss rate standard library and the abnormal library are established according to the K-means clustering result, the abnormal library is required to store abnormal user electric quantity, corresponding specific dates are also stored, and direct reading of the abnormal time period T is facilitated, for example, the date of electric power line loss caused by the results of illegal use and electricity stealing of users, insulating water of a power grid, adjustment, electric leakage, meter errors, meter reading, and error of nuclear charge is facilitated.
The method can be applied to a line loss analysis system based on relevance analysis, and the system structure is shown in fig. 2 and comprises a crawling module, a screening module, a relevance module and a regulation and control module.
The crawling module is connected with the screening module, and the association module is respectively connected with the crawling module and the screening module; the regulation and control module is connected with the association module;
the crawling module is used for acquiring historical power data from the acquisition database;
the screening module is used for performing class aggregation analysis on the historical data based on a clustering algorithm to obtain a classification result.
The association module is used for associating the classification result data based on the line loss key factors to obtain the integrated data after the line loss key factors are associated;
the regulation and control module is used for making a regulation and control plan according to the electric power data result related to the line loss key factors.
The crawling module comprises a searching instruction establishing sub-module and a power data obtaining sub-module;
the searching instruction establishes connection between the sub-module and the power data acquisition sub-module;
the searching instruction establishing sub-module is used for establishing connection between the searching instruction and the acquisition database;
the power data acquisition sub-module is used for acquiring historical power transmission data from the acquisition database through the established connection.
In this embodiment, the search instruction establishing submodule is configured to establish connection between a search instruction and the collection database, and then screen the collection database through the power data obtaining submodule to obtain historical power transmission data.
Secondly, the screening module comprises a comparison sub-module and a classification sub-module;
the comparison submodule is connected with the classification submodule;
the comparison sub-module is used for comparing and analyzing the correlation in the acquired historical power data to obtain a comparison result with higher similarity;
the classifying sub-module is used for classifying the results with higher similarity after comparison through a clustering algorithm.
In this embodiment, the comparison and analysis correlation is performed on the obtained historical power data to obtain a comparison result with higher similarity, and the result with higher similarity after comparison is classified by the clustering algorithm to obtain classified power data.
Thirdly, the association module comprises a line loss key factor acquisition sub-module and an association establishment sub-module;
the line loss key factor acquisition sub-module is connected with the crawling module; the establishing association sub-module is respectively connected with the line loss key factor obtaining sub-module and the classifying sub-module;
the line loss key factor obtaining sub-module obtains the line loss key factors from the acquisition database;
the association establishing sub-module establishes association data by associating the classification result data based on the obtained line loss key factors.
In this embodiment, the line loss key factor obtaining sub-module obtains the line loss key factor from the collection database through the crawling module, and then associates and establishes association data based on the obtained line loss key factor.
In addition, the regulation and control module comprises a line loss analysis sub-module, a searching sub-module, a correction module, a data processing sub-module and a pushing module;
the line loss analysis sub-module, the searching sub-module, the correction module, the data system sub-module and the pushing module are sequentially connected;
the line loss analysis submodule is used for establishing a line loss cause analysis specification;
the searching sub-module is used for acquiring line loss resource information;
the correction sub-module analyzes the line loss abnormality according to the associated data, searches for the approximate reason causing the line loss abnormality, and identifies bad data through the line loss abnormality reason;
the data system sub-module makes a determination on the line loss problem through identification conditions and makes a regulation and control plan for the line loss reason;
the pushing module is used for pushing the regulation and control plan to the cloud.
According to the invention, historical power data is analyzed, then the historical power data is obtained, the historical power data is subjected to clustering analysis through a clustering algorithm to store the power data in a classified manner, then the corresponding line loss key factors and the power data are integrated based on the correlation of the line loss key factors obtained from the acquisition database, then the correction result is finally obtained through analysis and correction according to the corresponding power data and the line loss key factors, and a regulation and control plan is formulated.
Example two
Accordingly, referring to fig. 3, fig. 3 is a line loss analysis system based on correlation analysis provided by the present invention, as shown in the drawing, the line loss analysis system based on correlation analysis includes:
the acquiring module 301 is configured to acquire historical power data and a line loss anomaly factor list of a target area, perform correlation comparison analysis on the historical power data, obtain first data, and perform cluster analysis on the first data to obtain a classification result;
the association module 302 is configured to associate the line loss key factor with the classification result to obtain integrated data after obtaining the line loss key factor according to the line loss abnormal factor list;
and the regulation and control module 303 is configured to obtain a correction result after analyzing and correcting the integrated data, so that a power grid personnel makes a regulation and control plan according to the correction result, and schedule the power data by using the regulation and control plan.
In a preferred embodiment, the acquisition module 301 comprises a similarity calculation unit 3011 and a selection unit 3012,
the similarity calculation unit 3011 is configured to perform correlation comparison analysis on the historical power data to obtain a similarity of each historical power data;
the selecting unit 3012 is configured to select, as data to be analyzed, historical power data with a similarity greater than a preset similarity, and obtain first data.
In a preferred embodiment, the acquisition module 301 further comprises a clustering unit 3013, a partitioning unit 3014 and a judging unit 3015,
the clustering unit 3013 is configured to perform cluster analysis on the first data by using a clustering algorithm to obtain a plurality of feature classes, and select a plurality of feature data in the feature classes as a first cluster center, where the first cluster center includes a plurality of classes;
the dividing unit 3014 is configured to divide feature data with a distance from the first cluster center being smaller than a first preset value into the first cluster center, and divide the feature data that is not divided into categories with a distance from the first cluster center being smaller than a second preset value, so as to obtain a second cluster center;
the judging unit 3015 is configured to judge whether the second clustering center and the first clustering center have the same clustering center, if not, recalculate the clustering center of the category to obtain a target clustering center, judge whether the target clustering center is the same as the second clustering center, and if so, repeat the step until the feature data is obtained and the classification result is obtained.
In a preferred embodiment, the association module 302 includes a computing unit 3021 and an integration unit 3022,
the calculating unit 3021 is configured to perform correlation analysis on line loss data according to the line loss anomaly factor list to obtain a correlation result of the line loss data, and perform sensitivity calculation on each line loss anomaly factor to obtain a sensitivity result of the line loss data;
the integrating unit 3022 is configured to obtain a line loss key factor according to the correlation result and the sensitivity result, and correlate the line loss key factor with the classification result to obtain integrated data of the line loss key factor.
In a preferred embodiment, after the integrated data is analyzed and corrected, a correction result is obtained, so that a power grid personnel makes a regulation and control plan according to the correction result, and the regulation and control plan is utilized to schedule the power data, specifically:
establishing a line loss reason analysis specification, acquiring line loss resource information of the transformer area, and analyzing the line loss resource information according to the line loss reason analysis specification and the line loss resource information to obtain line loss basic information;
constructing a line loss basic information model according to the integrated data, carrying out anomaly analysis on the line loss basic information by utilizing the line loss basic information model to obtain line loss anomaly factors, and identifying the electric power data of the target station area according to the line loss anomaly factors to obtain anomaly data;
and determining the line loss problem according to the abnormal data, obtaining a correction result, and making a regulation and control plan according to the correction result, and scheduling the power data by using the regulation and control plan.
In a preferred embodiment, the obtaining line loss resource information of the target station area specifically includes:
acquiring FTU switching information and energy consumption information in a power system of a target station area;
traversing the power system of the target area according to the FTU switch information to obtain a real-time topology network of the power system of the target area;
acquiring electrical parameters of each node and branch in a real-time topological network of a target area power system;
and obtaining line loss resource information according to the electrical parameters and the energy consumption information.
The more detailed working principle and the step flow of this embodiment can be, but not limited to, those described in the related embodiment one.
In summary, the embodiment of the invention has the following beneficial effects:
the method comprises the steps of obtaining historical power data and a line loss abnormal factor list of a target platform area, performing correlation comparison analysis on the historical power data, performing cluster analysis on the first data after obtaining the first data, obtaining a classification result, associating the line loss key factor with the classification result after obtaining the line loss key factor according to the line loss abnormal factor list, obtaining integrated data, and obtaining a correction result after analyzing and correcting the integrated data, so that power grid personnel can formulate a regulation and control plan according to the correction result, and scheduling the power data by utilizing the regulation and control plan. By means of the mode of correlating multiple groups of power data, the power resource regulation and control efficiency is improved without independently analyzing different line loss reasons.
The foregoing embodiments have been provided for the purpose of illustrating the general principles of the present invention, and are not to be construed as limiting the scope of the invention. It should be noted that any modifications, equivalent substitutions, improvements, etc. made by those skilled in the art without departing from the spirit and principles of the present invention are intended to be included in the scope of the present invention.
Claims (5)
1. The line loss analysis method based on the relevance analysis is characterized by comprising the following steps of:
acquiring historical power data and a line loss abnormal factor list of a target platform area, performing correlation comparison analysis on the historical power data to obtain first data, and performing cluster analysis on the first data to obtain a classification result;
according to the line loss abnormal factor list, after obtaining a line loss key factor, correlating the line loss key factor with the classification result to obtain integrated data;
after analyzing and correcting the integrated data, obtaining a correction result, so that power grid personnel can make a regulation and control plan according to the correction result, and dispatching the power data by using the regulation and control plan;
performing cluster analysis on the first data to obtain a classification result, wherein the classification result specifically comprises:
performing cluster analysis on the first data by adopting a cluster algorithm to obtain a plurality of feature classes, and selecting a plurality of feature data in the feature classes as a first cluster center, wherein the first cluster center comprises a plurality of categories;
the characteristic data with the distance smaller than a first preset value from the first clustering center are classified into the first clustering center, the characteristic data which are not classified are classified into categories with the distance smaller than a second preset value from the first clustering center, and a second clustering center is obtained;
judging whether the second clustering center and the first clustering center have the same clustering center, if not, recalculating the clustering center of the category corresponding to the first clustering center to obtain a target clustering center, judging whether the target clustering center is the same as the second clustering center, if so, taking the category of the target clustering center as a new category, and repeating the steps until the feature data is divided to obtain a classification result;
according to the line loss abnormal factor list, after obtaining the line loss key factors, correlating the line loss key factors with the classification result to obtain integrated data, wherein the integrated data specifically comprises:
performing correlation analysis on the line loss data according to the line loss abnormal factor list to obtain a correlation result of the line loss data, and performing sensitivity calculation on each line loss abnormal factor to obtain a sensitivity result of the line loss data;
obtaining a line loss key factor according to the correlation result and the sensitivity result, and obtaining integrated data of the line loss key factor after correlating the line loss key factor with the classification result;
after the integrated data is analyzed and corrected, a correction result is obtained, so that power grid personnel can make a regulation and control plan according to the correction result, and the regulation and control plan is utilized to schedule the power data, specifically:
establishing a line loss cause analysis specification, acquiring line loss resource information of the target station area, and analyzing the line loss resource information according to the line loss cause analysis specification and the line loss resource information to obtain line loss basic information;
constructing a line loss basic information model according to the integrated data, carrying out anomaly analysis on the line loss basic information by utilizing the line loss basic information model to obtain line loss anomaly factors, and identifying the electric power data of the target station area according to the line loss anomaly factors to obtain anomaly data;
and determining a line loss problem according to the abnormal data, obtaining a correction result, and making a regulation and control plan according to the correction result, and scheduling the power data by using the regulation and control plan.
2. The line loss analysis method based on relevance analysis according to claim 1, wherein the performing relevance comparison analysis on the historical power data to obtain first data specifically includes:
performing correlation comparison analysis on the historical power data to obtain the similarity of each historical power data;
and selecting the historical power data with the similarity larger than the preset similarity as data to be analyzed to obtain first data.
3. The line loss analysis method based on relevance analysis of claim 1, wherein obtaining line loss resource information of the target station area specifically includes:
acquiring FTU switching information and energy consumption information in the target area power system;
traversing the target area power system according to the FTU switch information to obtain a real-time topology network of the target area power system;
acquiring electrical parameters of each node and branch in a real-time topological network of the target area power system;
and obtaining line loss resource information according to the electrical parameters and the energy consumption information.
4. A line loss analysis system based on correlation analysis, comprising:
the acquisition module is used for acquiring historical power data and a line loss abnormal factor list of the target area, carrying out correlation comparison analysis on the historical power data to obtain first data, and carrying out cluster analysis on the first data to obtain a classification result;
the association module is used for associating the line loss key factors with the classification results after obtaining the line loss key factors according to the line loss abnormal factor list to obtain integrated data;
the regulation and control module is used for obtaining a correction result after analyzing and correcting the integrated data, so that power grid personnel can make a regulation and control plan according to the correction result, and the regulation and control plan is used for scheduling the power data;
the acquisition module also comprises a clustering unit, a dividing unit and a judging unit,
the clustering unit is used for carrying out clustering analysis on the first data by adopting a clustering algorithm to obtain a plurality of feature classes, and selecting the plurality of feature data in the feature classes as a first clustering center, wherein the first clustering center comprises a plurality of categories;
the dividing unit is used for dividing the characteristic data with the distance from the first clustering center being smaller than a first preset value into the first clustering center, and dividing the undivided characteristic data into categories with the distance from the first clustering center being smaller than a second preset value to obtain a second clustering center;
the judging unit is used for judging whether the second clustering center and the first clustering center have the same clustering center, if not, the clustering center of the category corresponding to the first clustering center is recalculated to obtain a target clustering center, whether the target clustering center is the same as the second clustering center is judged, if so, the category of the target clustering center is used as a new category, and the step is repeated until the feature data is obtained and the classification result is obtained;
the association module comprises a calculation unit and an integration unit,
the calculating unit is used for carrying out correlation analysis on the line loss data according to the line loss abnormal factor list to obtain a correlation result of the line loss data, and carrying out sensitivity calculation on each line loss abnormal factor to obtain a sensitivity result of the line loss data;
the integration unit is used for obtaining a line loss key factor according to the correlation result and the sensitivity result, and obtaining integrated data of the line loss key factor after correlating the line loss key factor with the classification result;
after the integrated data is analyzed and corrected, a correction result is obtained, so that power grid personnel can make a regulation and control plan according to the correction result, and the regulation and control plan is utilized to schedule the power data, specifically:
establishing a line loss cause analysis specification, acquiring line loss resource information of the target station area, and analyzing the line loss resource information according to the line loss cause analysis specification and the line loss resource information to obtain line loss basic information;
constructing a line loss basic information model according to the integrated data, carrying out anomaly analysis on the line loss basic information by utilizing the line loss basic information model to obtain line loss anomaly factors, and identifying the electric power data of the target station area according to the line loss anomaly factors to obtain anomaly data;
and determining a line loss problem according to the abnormal data, obtaining a correction result, and making a regulation and control plan according to the correction result, and scheduling the power data by using the regulation and control plan.
5. The line loss analysis system based on correlation analysis of claim 4, wherein the acquisition module comprises a similarity calculation unit and a selection unit,
the similarity calculation unit is used for carrying out correlation comparison analysis on the historical power data to obtain the similarity of each historical power data;
the selecting unit is used for selecting the historical power data with the similarity larger than the preset similarity as data to be analyzed to obtain first data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311183624.7A CN116910602B (en) | 2023-09-14 | 2023-09-14 | Line loss analysis method and system based on relevance analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311183624.7A CN116910602B (en) | 2023-09-14 | 2023-09-14 | Line loss analysis method and system based on relevance analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116910602A CN116910602A (en) | 2023-10-20 |
| CN116910602B true CN116910602B (en) | 2024-01-19 |
Family
ID=88360712
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311183624.7A Active CN116910602B (en) | 2023-09-14 | 2023-09-14 | Line loss analysis method and system based on relevance analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116910602B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117912133A (en) * | 2024-03-19 | 2024-04-19 | 杭州三一谦成科技有限公司 | Vehicle information coefficient acquisition system based on measured data |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007114969A (en) * | 2005-10-19 | 2007-05-10 | Chugoku Electric Power Co Inc:The | Information processor, information processing method, and information processing system |
| CN105005711A (en) * | 2015-08-21 | 2015-10-28 | 国网北京市电力公司 | Method and device for acquiring statistical line loss |
| CN112529369A (en) * | 2020-11-23 | 2021-03-19 | 国网浙江省电力有限公司 | Medium-voltage distribution network line loss key characteristic index extraction method and system |
| CN115618229A (en) * | 2022-10-24 | 2023-01-17 | 国网甘肃省电力公司电力科学研究院 | Line loss allocation algorithm based on big data |
| CN115759708A (en) * | 2022-12-20 | 2023-03-07 | 广东电网有限责任公司 | Line loss analysis method and system considering power space-time distribution characteristics |
-
2023
- 2023-09-14 CN CN202311183624.7A patent/CN116910602B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007114969A (en) * | 2005-10-19 | 2007-05-10 | Chugoku Electric Power Co Inc:The | Information processor, information processing method, and information processing system |
| CN105005711A (en) * | 2015-08-21 | 2015-10-28 | 国网北京市电力公司 | Method and device for acquiring statistical line loss |
| CN112529369A (en) * | 2020-11-23 | 2021-03-19 | 国网浙江省电力有限公司 | Medium-voltage distribution network line loss key characteristic index extraction method and system |
| CN115618229A (en) * | 2022-10-24 | 2023-01-17 | 国网甘肃省电力公司电力科学研究院 | Line loss allocation algorithm based on big data |
| CN115759708A (en) * | 2022-12-20 | 2023-03-07 | 广东电网有限责任公司 | Line loss analysis method and system considering power space-time distribution characteristics |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116910602A (en) | 2023-10-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112699913B (en) | Method and device for diagnosing abnormal relationship of household transformer in transformer area | |
| CN110335168B (en) | Method and system for optimizing power utilization information acquisition terminal fault prediction model based on GRU | |
| CN116910602B (en) | Line loss analysis method and system based on relevance analysis | |
| CN113011481A (en) | Electric energy meter function abnormity evaluation method and system based on decision tree algorithm | |
| CN111242161A (en) | Non-invasive non-resident user load identification method based on intelligent learning | |
| CN112510817A (en) | Intelligent identification method for low-voltage topological relation of transformer area | |
| CN110555619A (en) | Power supply capacity evaluation method based on intelligent power distribution network | |
| CN112615428A (en) | Line loss analysis and treatment system and method | |
| CN111091223B (en) | Matching short-term load prediction method based on intelligent sensing technology of Internet of things | |
| CN110968703B (en) | Method and system for constructing abnormal metering point knowledge base based on LSTM end-to-end extraction algorithm | |
| CN109902133B (en) | Multi-source data error correction processing method and system based on arbitrary partition area of power grid | |
| CN114722310A (en) | Photovoltaic power station equipment fault diagnosis method, device, equipment and medium | |
| CN112182499B (en) | Low-voltage distribution network topological structure identification method based on time sequence electric quantity data | |
| CN114765574B (en) | Network anomaly delimitation positioning method and device | |
| CN115859701B (en) | Extension analysis method and system based on cable detection data | |
| CN109378834A (en) | Large scale electric network voltage stability margin assessment system based on information maximal correlation | |
| CN116502149A (en) | Low-voltage power distribution network user-transformation relation identification method and system based on current characteristic conduction | |
| CN116450625A (en) | Metering abnormal data screening device based on electricity consumption information acquisition system | |
| CN116662840A (en) | Low-voltage station user phase identification method based on machine learning | |
| CN111815085A (en) | Method for realizing comprehensive energy efficiency evaluation of rail transit energy management system | |
| CN113850422A (en) | Method for quickly searching transformer area line loss point based on multiple nonlinear regression or/and parallel vector | |
| CN109816276B (en) | Method, device and equipment for evaluating reliability index of power distribution network | |
| CN116308190B (en) | Work order full life cycle monitoring method based on energy Internet of things service system | |
| CN117575542B (en) | Building engineering data control system and method based on modularized assembly | |
| CN118350679B (en) | New energy station grid-connected system electric energy supporting capability analysis method and device |
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 |