CN115374210A - Power distribution network diagnostic analysis method and terminal - Google Patents
Power distribution network diagnostic analysis method and terminal Download PDFInfo
- Publication number
- CN115374210A CN115374210A CN202210905172.8A CN202210905172A CN115374210A CN 115374210 A CN115374210 A CN 115374210A CN 202210905172 A CN202210905172 A CN 202210905172A CN 115374210 A CN115374210 A CN 115374210A
- Authority
- CN
- China
- Prior art keywords
- analysis
- data
- distribution network
- daily load
- items
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 211
- 238000007405 data analysis Methods 0.000 claims abstract description 61
- 238000000034 method Methods 0.000 claims abstract description 36
- 238000003745 diagnosis Methods 0.000 claims description 54
- 238000012795 verification Methods 0.000 claims description 29
- 230000005611 electricity Effects 0.000 claims description 20
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 238000007621 cluster analysis Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 8
- 238000012800 visualization Methods 0.000 abstract description 40
- 238000005516 engineering process Methods 0.000 abstract description 25
- 238000013079 data visualisation Methods 0.000 abstract description 5
- 238000012545 processing Methods 0.000 abstract description 4
- 230000002452 interceptive effect Effects 0.000 abstract description 3
- 230000000007 visual effect Effects 0.000 description 7
- 230000002159 abnormal effect Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000006116 polymerization reaction Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 238000012098 association analyses Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000007794 visualization technique Methods 0.000 description 1
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
- G06F16/26—Visual data mining; Browsing structured data
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- 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
- G06F16/2455—Query execution
- G06F16/24564—Applying rules; Deductive 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
- G06F16/245—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
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Business, Economics & Management (AREA)
- Probability & Statistics with Applications (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Public Health (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- Water Supply & Treatment (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The invention discloses a power distribution network diagnostic analysis method and a terminal, wherein when the power distribution network is diagnosed and analyzed, a representation visualization technology and an exploration visualization technology are combined, the analysis data can be displayed in a proper mode through the representation visualization technology, a user can conveniently and accurately select proper analysis data and an analysis method to conduct exploration visualization analysis, the user can conduct intervention processing in the data visualization process in the visualization analysis process, an intermediate analysis result can be visually output in the analysis process, after the user conducts preference selection on the intermediate analysis result, data analysis is continued on the basis of the intermediate analysis result after preference selection, and the accuracy of visualization data analysis is improved through comprehensive application of different types of visualization technologies and adoption of an interactive visualization analysis process.
Description
Technical Field
The invention relates to the field of data processing of a power distribution network, in particular to a power distribution network diagnosis and analysis method and a terminal.
Background
In data visualization schema analysis, visualization can be used in a number of ways that enable one to visually understand complex schemas in multidimensional data. By observing the existence form of data in multiple dimensions and multiple graphic windows, the data trend and the exposure layer can be intuitively and rapidly revealed. During data pattern analysis, the visualization may also help to review data prior to modeling, and may verify the results of its data mining tools. In addition, visualization also plays an important role in local data pattern discovery. Visualization techniques can be classified into three categories, exploratory, confirmatory, and representational, depending on the purpose. The exploration type means that people do not have any knowledge about data in advance, and the structure and the change trend of the data are analyzed by using a visualization technology to obtain the hypothesis about the data; the verification type refers to that people have assumptions about data in advance, and the assumptions are verified or rejected by using a visualization technology; the representation refers to selecting effective means or technology to represent data.
In view of the superiority of visualization technology in data display, visualization technology is also increasingly applied in the process of analyzing data of the power distribution network. However, currently, data visualization technologies are generally applied only to visualization of a presentation result, and a single visualization technology is adopted, and the visualization technology is not well applied, so that the accuracy of a visualized data analysis result needs to be further improved.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the power distribution network diagnosis and analysis method and the terminal can improve the accuracy of visual data analysis.
In order to solve the technical problems, the invention adopts a technical scheme that:
a power distribution network diagnosis and analysis method comprises the following steps:
s1, receiving a power distribution network diagnosis request, wherein the diagnosis request comprises a diagnosis object;
s2, displaying an analysis data object corresponding to the diagnosis object and a recommended analysis data representation mode according to the diagnosis object;
s3, receiving an analysis data display request, wherein the display request comprises a selected analysis data representation mode, and displaying the analysis data corresponding to the diagnosis object according to the selected analysis data representation mode;
s4, receiving a data analysis request of the diagnosis object, wherein the analysis request comprises selected analysis data and an analysis method, carrying out data analysis on the diagnosis object according to the selected analysis data and the analysis method, outputting an intermediate analysis result in the analysis process, receiving a preferred selection of the intermediate analysis result, continuing carrying out data analysis on the diagnosis object according to the preferred selection, and outputting a data analysis result.
In order to solve the technical problem, the invention adopts another technical scheme as follows:
a power distribution network diagnosis and analysis terminal comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the computer program to realize the steps of the power distribution network diagnosis and analysis method.
The invention has the beneficial effects that: when the power distribution network is diagnosed and analyzed, the representation visualization technology and the exploration visualization technology are combined, the analysis data can be displayed in a proper mode through the representation visualization technology, a user can conveniently and accurately select proper analysis data and an analysis method to conduct exploration visualization analysis, in the visualization analysis process, the user can conduct intervention processing in the data visualization process, an intermediate analysis result can be visually output in the analysis process, after the user conducts preference selection on the intermediate analysis result, data analysis is continued on the basis of the intermediate analysis result after the preference selection, the visualization technologies of different types are comprehensively used, and an interactive visualization analysis process is adopted, so that the accuracy of visualization data analysis is improved.
Drawings
Fig. 1 is a flowchart illustrating steps of a power distribution network diagnostic analysis method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a power distribution network diagnostic analysis terminal according to an embodiment of the present invention.
Detailed Description
In order to explain technical contents, achieved objects, and effects of the present invention in detail, the following description is made with reference to the accompanying drawings in combination with the embodiments.
Referring to fig. 1, a power distribution network diagnostic analysis method includes the steps of:
s1, receiving a power distribution network diagnosis request, wherein the diagnosis request comprises a diagnosis object;
s2, displaying an analysis data object corresponding to the diagnosis object and a recommended analysis data representation mode according to the diagnosis object;
s3, receiving an analysis data display request, wherein the display request comprises a selected analysis data representation mode, and displaying the analysis data corresponding to the diagnosis object according to the selected analysis data representation mode;
s4, receiving a diagnostic object data analysis request, wherein the analysis request comprises selected analysis data and an analysis method, carrying out data analysis on the diagnostic object according to the selected analysis data and the analysis method, outputting an intermediate analysis result in the analysis process, receiving a preferred selection of the intermediate analysis result, continuing to carry out data analysis on the diagnostic object according to the preferred selection, and outputting a data analysis result.
As can be seen from the above description, the beneficial effects of the present invention are: when the power distribution network is diagnosed and analyzed, the representation visualization technology and the exploration visualization technology are combined, the analysis data can be displayed in a proper mode through the representation visualization technology, a user can conveniently and accurately select proper analysis data and an analysis method to conduct exploration visualization analysis, in the visualization analysis process, the user can conduct intervention processing in the data visualization process, an intermediate analysis result can be visually output in the analysis process, after the user conducts preference selection on the intermediate analysis result, data analysis is continued on the basis of the intermediate analysis result after the preference selection, the visualization technologies of different types are comprehensively used, and an interactive visualization analysis process is adopted, so that the accuracy of visualization data analysis is improved.
Further, the step S4 is followed by the step of:
and S5, receiving a verification request for the data analysis result, verifying the data analysis result according to the verification request, and outputting a verification result.
According to the above description, after the exploration type visualized data analysis is performed and the data analysis result is output, the verification type visualization technology is further adopted to verify the data analysis result and visualize the verification result, so that the accuracy of the data analysis result can be further ensured.
Further, the diagnosis object comprises a daily load curve of the distribution transformer of which the power utilization mode is to be determined;
the analysis data object corresponding to the diagnosis object in the step S2 comprises daily load curves of distribution transformers in various different power consumption modes stored in a distribution network diagnosis analysis database, and the recommended analysis data representation mode comprises a curve graph;
if the selected analysis data representation manner in the step S3 is a graph, the displaying the analysis data corresponding to the diagnosis object according to the selected analysis data representation manner includes:
displaying daily load curves of the distribution transformers with different power consumption modes stored in the distribution network diagnostic analysis database in a curve graph mode;
the analysis method in the step S4 includes cluster analysis;
if the analysis method is cluster analysis, then:
the step S4 of selecting the analysis data comprises deleting the daily load curves which cannot form a data cluster with other daily load curves;
the outputting an intermediate analysis result in the analysis process, receiving a preferred selection of the intermediate analysis result, and continuing to perform data analysis on the diagnostic object according to the preferred selection comprises:
performing clustering analysis on the daily load curve data after the daily load curves which cannot form a data cluster with other daily load curves are deleted to obtain a clustering result;
receiving selection operation performed on the clustering results, and determining a daily load curve corresponding to each cluster according to the clustering results after the selection operation to obtain a typical daily load curve corresponding to each power consumption mode;
and identifying the daily load curve of the distribution transformer with the electricity utilization mode to be determined according to the typical daily load curve corresponding to each electricity utilization mode, and determining and displaying the corresponding electricity utilization mode.
It can be known from the above description that, when the power distribution network diagnostic object is a daily load curve of a distribution transformer with a to-be-determined power consumption pattern, and visual data analysis is performed by using a cluster analysis method, the daily load curve to be analyzed may be displayed in a graph manner, and a user may visually find out a daily load curve that is relatively abnormal through the displayed daily load curve, so as to conveniently screen and exclude abnormal data, and in the process of performing cluster analysis, after obtaining a preliminary cluster result, the preliminary cluster result may be displayed in a circle manner, each circle represents one classification, so that each classification may be displayed very visually, and if two classifications intersect or data in a certain classification are relatively loose, that is, data in the circle are relatively discretely distributed, the user may directly adjust based on the displayed intermediate analysis result, for example, delete several data that are relatively discretely distributed, so as to leave compactly distributed data, or reduce one circle of two intersected circles, delete data in the intersected part of the circles, thereby implementing the preliminary cluster result, and then determine each type of the daily load curve that should be discretely distributed after finishing the cluster analysis, and then determine the daily load curve that should be closely distributed through the daily load curve that is identified and the daily load curve that is displayed by the power distribution pattern.
Further, the verification request in the step S5 includes a daily load curve of the distribution transformer with a known power consumption pattern;
the verifying the data analysis result according to the verification request comprises:
and identifying the daily load curve of the distribution transformer with the known power utilization mode according to the typical daily load curve corresponding to each power utilization mode, determining the corresponding power utilization mode, and comparing the determined power utilization mode with the known power utilization mode to verify the data analysis result.
As can be seen from the above description, when the determined electricity usage pattern is verified, the daily load curve of the known electricity usage pattern and the daily load curve representing each electricity usage pattern obtained by clustering may be used to compare, determine the corresponding electricity usage pattern, and then compare the determined electricity usage pattern with the known electricity usage pattern, if the determined electricity usage pattern is the same as the known electricity usage pattern, the accuracy of the performed visualized data analysis is described, and if the determined electricity usage pattern is not the same as the known electricity usage pattern, the clustering process needs to be adjusted.
Further, the diagnostic object includes a strong association of a low voltage;
the analysis data object corresponding to the diagnosis object in the step S2 includes a candidate associated with a low voltage;
the selecting of the analysis data in the step S4 includes selecting a preset number of candidates from the candidates associated with the low voltage;
the analysis method in the step S4 includes Apriori algorithm;
if the analysis method includes an Apriori algorithm, outputting an intermediate analysis result in the analysis process, receiving a preferred selection of the intermediate analysis result, and continuing to perform data analysis on the diagnostic object according to the preferred selection includes:
searching a project set containing the selected candidate items from the power distribution network diagnostic analysis database based on the selected preset number of candidate items;
determining and displaying the support degree count of each 1 item candidate set in the frequent 1 item candidate set according to the item set;
receiving a minimum support degree determined according to the support degree of each displayed 1 candidate set;
determining a frequent 1 item set according to the minimum support degree;
constructing a frequent 2 item candidate set according to the frequent 1 item set, and calculating the support degree count of each frequent 2 item candidate set in the frequent 2 item candidate set according to the item set;
determining a frequent 2 item set according to the minimum support and the support count of each frequent 2 item candidate set;
adding 1 to the number of the items of the frequent candidate set, and repeating the steps until no frequent candidate set with larger number of the items exists;
determining association rules containing low-voltage items according to all the determined frequent candidate sets, and calculating the confidence coefficient of each association rule;
displaying each association rule and the corresponding confidence level thereof;
receiving a minimum confidence level determined from the displayed confidence levels;
determining strong association rules according to the minimum confidence and the confidence of each association rule;
and determining a strong association item of low voltage according to the strong association rule.
From the above description, when the diagnostic analysis object is a low-voltage strong association, a suitable Apriori algorithm may be used for performing visual data analysis, and the two most important indexes in the Apriori algorithm are the minimum support and the minimum confidence, the conventional Apriori algorithm is to preset the minimum support and the minimum confidence before the algorithm is executed, and through the visual implementation of the Apriori algorithm, a user may calculate and determine a suitable minimum support based on the calculated support of each candidate set, and determine a suitable minimum confidence based on the determined confidence of each association rule, obtain a calculation result first, and then determine a suitable minimum support and a minimum confidence based on the calculation result, so that the minimum support and the minimum confidence may be more suitable for actual data, and thus the robustness and accuracy of the determined strong association are ensured.
Further, the verifying the data analysis result according to the verification request in step S5 includes:
searching items containing the strong association items from a power distribution network diagnostic analysis database according to the determined strong association items, counting the number of low voltages contained in the items containing the strong association items, determining the proportion of the number of the low voltages contained in the items containing the strong association items according to the number, and taking the proportion as a verification result.
According to the description, after the high-voltage association item is determined, the items containing the high-voltage association item are searched from the power distribution network diagnosis and analysis database according to the determined high-voltage association item, the proportion of the items containing the low-voltage in the searched items is determined, the data analysis result is verified through the proportion, and the intuitiveness of the verification result is guaranteed.
Referring to fig. 2, a power distribution network diagnostic analysis terminal includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the processor executes the computer program to implement each step in the power distribution network diagnostic analysis method.
The power distribution network diagnosis and analysis method and the terminal can be applied to the visual data analysis of the power distribution network, and are described in the following through specific embodiments:
example one
Referring to fig. 1, a power distribution network diagnostic analysis method includes the steps of:
s1, receiving a power distribution network diagnosis request, wherein the diagnosis request comprises a diagnosis object;
the diagnostic objects may include various objects that can be used for diagnostic analysis in the power distribution network, such as analyzing a relationship associated with a certain index in the power distribution network, for example, low voltage, high load, or predicting a load of a certain distribution area in the power distribution network;
s2, displaying an analysis data object corresponding to the diagnosis object and a recommended analysis data representation mode according to the diagnosis object;
for example, if it is to predict the load of a certain distribution area in the distribution network to be diagnosed and analyzed, the analysis data object corresponding to the load prediction is displayed: current, voltage and impedance, and to give a recommended representation of the analysis data for the user to select an adapted representation of the analysis data, such as a dot plot, a graph, etc.;
s3, receiving an analysis data display request, wherein the display request comprises a selected analysis data representation mode, and displaying the analysis data corresponding to the diagnosis object according to the selected analysis data representation mode;
specifically, the analysis data corresponding to the diagnostic object is displayed according to the analysis data representation mode selected by the user, so that the user can further modify and adjust the analysis data based on the displayed analysis data;
s4, receiving a data analysis request of a diagnosis object, wherein the analysis request comprises selected analysis data and an analysis method, carrying out data analysis on the diagnosis object according to the selected analysis data and the analysis method, outputting an intermediate analysis result in the analysis process, receiving a preferred selection of the intermediate analysis result, continuing carrying out data analysis on the diagnosis object according to the preferred selection, and outputting a data analysis result;
after the analysis data corresponding to the diagnostic object is displayed according to the analysis data representation mode selected by the user, the user can adjust and modify the analysis data corresponding to the diagnostic object according to the display result, for example, delete the data which are obviously abnormal, or select some data to analyze;
assuming that the load of a certain platform area is to be predicted, the user can select the load according to the displayed data of voltage, current and impedance, such as voltage and current or voltage and impedance or current and impedance;
in the data analysis process, if the intermediate analysis result is related, the intermediate analysis result can be visually displayed, and a user can intervene in the data analysis process after analyzing the intermediate analysis result, for example, the intermediate analysis result can be further screened, data which are obviously abnormal are eliminated, or a threshold value is set, and the intermediate analysis result data which are smaller than the threshold value are deleted;
s5, receiving a verification request for the data analysis result, verifying the data analysis result according to the verification request, and outputting a verification result;
after the data analysis result is displayed, in order to verify the accuracy of the data analysis result, the data analysis result may be further verified, and a specific verification manner may be set according to a specific diagnostic object, for example, if the load of a certain distribution room is predicted, the load of a certain distribution room with known actual load may be predicted by using a model used in the prediction process, and then the predicted load is compared with the actual load to verify the accuracy of the prediction.
Example two
The embodiment describes a visualized data analysis method when the diagnosis object is a daily load curve of a distribution transformer with an electricity consumption mode to be determined, specifically:
the analysis data object corresponding to the diagnosis object in the step S2 comprises daily load curves of distribution transformers in various different power consumption modes stored in a distribution network diagnosis analysis database, and the recommended analysis data representation mode comprises a curve graph;
if the selected analysis data representation manner in the step S3 is a graph, the displaying the analysis data corresponding to the diagnosis object according to the selected analysis data representation manner includes:
displaying daily load curves of the distribution transformers in different power consumption modes stored in the distribution network diagnostic analysis database in a curve chart mode;
the analysis method in the step S4 comprises cluster analysis;
if the analysis method is cluster analysis, then:
the step S4 of selecting the analysis data comprises deleting the daily load curves which cannot form a data cluster with other daily load curves;
the daily load curve can be the load power of each time point, the load power of each time point reflects the power utilization situation of the user in different time periods, and the users with the same power utilization characteristics have similar load characteristics, so the daily load curves of the users in different categories have stronger distinctiveness, that is, the daily load curves of the users in different power utilization modes have stronger distinctiveness, therefore, after the daily load curve data of the distribution transformers in various power utilization modes stored in the distribution network diagnostic analysis database are displayed, the users can visually see the difference based on the power utilization modes based on the display result, the displayed distribution transformers with different power utilization modes show respective clustering phenomena, and based on the clustering phenomena, a user can quickly judge that the daily load curves of the distribution transformers with the power utilization modes to be determined can be diagnosed and analyzed by adopting a clustering analysis method;
after daily load curve data of distribution transformers in different power utilization modes are displayed, abnormal data which are obviously deviated from the clustering phenomenon and can be displayed can be directly removed, so that the reliability of the clustered data is ensured, and the data can be preliminarily judged to be clustered into several categories through the displayed daily load curve data, so that the corresponding clustering number is set;
in this embodiment, a K-means method may be adopted to perform cluster analysis on daily load curves of distribution transformers of various power consumption modes to cluster daily load curves of corresponding power consumption modes, so that the classification number may be set to K according to a preliminarily displayed data result, and the K-means method cluster analysis may be performed based on the set K;
wherein the outputting an intermediate analysis result in the analysis process, receiving a preferred selection of the intermediate analysis result, and continuing to perform data analysis on the diagnostic object according to the preferred selection comprises:
carrying out clustering analysis on the daily load curve data after the daily load curves which cannot form data clusters with other daily load curves are deleted, and obtaining a clustering result;
receiving selection operation performed on the clustering results, and determining a daily load curve corresponding to each cluster according to the clustering results after the selection operation to obtain a typical daily load curve corresponding to each power consumption mode;
identifying the daily load curve of the distribution transformer with the electricity utilization mode to be determined according to the typical daily load curve corresponding to each electricity utilization mode, and determining and displaying the corresponding electricity utilization mode;
specifically, after daily load curves of distribution transformers in different power consumption modes are clustered by adopting a K-means method, preliminary clustering results corresponding to the power consumption modes are obtained, namely each cluster represents a power consumption mode, the preliminary clustering results are analyzed and are displayed as intermediate analysis results, the quantity corresponding to each mode can be displayed by using a histogram at the same time of displaying all the daily load curves corresponding to the power consumption modes after the preliminary clustering, a user can visually determine whether the clustering results are reasonable from the quantity contained in the clusters, for example, if the quantity contained in a certain cluster is only 3 and is far smaller than the average clustering quantity, the cluster is deleted, or the quantity contained in a certain cluster is too much, the cluster can be seen to be in a discrete distribution state from a visual view of the cluster, and the degree of polymerization is not enough, the K-means method can be adopted for clustering again aiming at the classification, so that several sub-classes with higher degree of polymerization are classified;
therefore, the clustering result with higher accuracy can be determined by the visual display of the intermediate analysis result and the intervention adjustment;
after the clustering result after the selection operation is obtained, for each classification, summing and averaging daily load curves corresponding to each classification, and taking the average value as a typical daily load curve corresponding to each classification;
after the typical daily load curves corresponding to different power utilization modes are determined, similarity calculation is carried out only on the daily load curves of the distribution transformer with the power utilization mode to be determined and each typical daily load curve, and the power utilization mode corresponding to the highest similarity is taken as the power utilization mode of the distribution transformer with the power utilization mode to be determined;
wherein, the verification request in the step S5 includes a daily load curve of the distribution transformer with a known power consumption mode;
the verifying the data analysis result according to the verification request comprises:
and identifying the daily load curve of the distribution transformer with the known power utilization mode according to the typical daily load curve corresponding to each power utilization mode, determining the corresponding power utilization mode, and comparing the determined power utilization mode with the known power utilization mode to verify the data analysis result.
EXAMPLE III
The embodiment describes a visualized data analysis process of a strongly associated item with a low voltage as the diagnosis object, and specifically includes:
the analysis data object corresponding to the diagnosis object in the step S2 includes a candidate associated with a low voltage;
the selecting of the analysis data in step S4 includes selecting a preset number of candidates from the candidates associated with the low voltage;
for example, the following candidates with low voltage may be listed: load information (distribution transformer average load rate, annual maximum load rate), user average distribution transformer capacity, public power grid scale analysis (the number of power supply users), 10kV line N-1 passing rate and 10kV line contact rate;
then receiving index items which are selected by a user based on listed candidate items and used for determining strong association items, such as selecting distribution transformation average load rate, annual maximum load rate, user average distribution transformation capacity and the number of power supply users;
the analysis method in step S4 includes Apriori algorithm;
if the analysis method includes an Apriori algorithm, outputting an intermediate analysis result in the analysis process, receiving a preferred selection of the intermediate analysis result, and continuing to perform data analysis on the diagnostic object according to the preferred selection includes:
searching a project set containing the selected candidate items from the power distribution network diagnostic analysis database based on the selected preset number of candidate items;
for example, the selected index items for determining the strong association items include distribution transformer average load rate, annual maximum load rate, user average distribution transformer capacity and power supply user number, I5 represents the distribution transformer average load rate, I15 represents the user average distribution transformer capacity, I23 represents low voltage, I10 represents the annual maximum load rate, I20 represents the power supply user number, and the item set shown in table 1 is obtained through retrieval:
TABLE 1
| TID | Item set |
| 1 | I5,I15,I23 |
| 2 | I10,I23 |
| 3 | I20,I23 |
| 4 | I5,I23 |
| 5 | I5,I20 |
| 6 | I20,I23 |
| 7 | I5,I20 |
| 8 | I5,I15,I20,I23 |
| 9 | I5,I20,I23 |
Then, an Apriori algorithm is used to find all frequent item sets:
determining and displaying the support degree count of each 1 item candidate set in the frequent 1 item candidate set according to the item set, wherein the calculation result is shown in table 2:
TABLE 2 frequently 1 item candidate set C1 and frequently 1 item set L1
Receiving the minimum support degree determined according to the support degree counts of the 1 displayed candidate sets;
determining a frequent 1 item set according to the minimum support degree;
after displaying each candidate item in the candidate set and the corresponding support count thereof, the user may set the minimum support, for example, may set the minimum support to be 2, and then may delete the item set smaller than the minimum support, and the rest are the candidate items, as shown in table 2, that is, delete the item set { I10} with the support of 1;
constructing a frequent 2 item candidate set according to the frequent 1 item set, and calculating the support degree count of each frequent 2 item candidate set in the frequent 2 item candidate set according to the item set;
determining a frequent 2 item set according to the minimum support and the support count of each frequent 2 item candidate set;
adding 1 to the number of the items of the frequent candidate set, and repeating the steps until no frequent candidate set with larger number of the items exists;
taking the item set in table 1 as an example, a frequent candidate set with an item number of 3 can be finally calculated, as shown in table 3:
TABLE 3 frequent 3 candidate set C3 and frequent 3 set L3
Determining association rules containing low-voltage items according to all the determined frequent candidate sets, and calculating the confidence coefficient of each association rule;
the confidence coefficient calculation formula is as follows:
in the formula, support _ count represents a support count, and A and B represent index items for determining an association relationship;
the association rules are generated as follows:
for each frequent item set l, all its non-empty-true subsets are generated, and then for each non-empty-true subset s, a confidence is calculated: support _ count (l)/support _ count (l-s), and the corresponding association rule is s = > (l-s);
displaying each association rule and the corresponding confidence level thereof;
for example, for the frequent set { I5, I15, I23}, the non-empty proper subset of the frequent set has { I5, I15}, { I5, I23}, { I15, I23}, { I5}, { I23} and { I15}, the corresponding confidence levels are as follows:
receiving a minimum confidence level determined from the displayed confidence levels;
determining strong association rules according to the minimum confidence and the confidence of each association rule;
after all the association rules and the corresponding confidence degrees are displayed, a user can determine a reasonable minimum confidence degree based on the displayed data, so that strong association rules are screened out;
determining a strong association item of low voltage according to the strong association rule;
taking the association rule calculated by the above frequent set { I5, I15, I23} as an example, the minimum confidence may be set to 80%, and the strong rule has
Finally, a strong association rule with the conclusion of I23 (low voltage generation in the transformer area) is screened out:
wherein the verifying the data analysis result according to the verification request in step S5 includes:
searching items containing the strong association items from a power distribution network diagnostic analysis database according to the determined strong association items, counting the number of low voltages contained in the items containing the strong association items, determining the proportion of the number of the low voltages contained in the items containing the strong association items according to the number, and taking the proportion as a verification result;
for example, if the result of verification is that each item of the items containing strong correlation contains a low voltage, it indicates that the analyzed item of strong correlation is accurate, and if only fifty percent of the items containing strong correlation contain a low voltage, it indicates that the analyzed item of strong correlation is not accurate enough;
in an alternative embodiment, in order to further increase the reliability of the verification, a search may be performed for matching from similar data in the distribution network diagnostic analysis database that is not used for the low-voltage strong association analysis, such as a data item associated with a low voltage, which is also the same distribution area, but which does not participate in the previous low-voltage strong association diagnostic analysis.
Example four
Referring to fig. 2, a power distribution network diagnostic analysis terminal includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the computer program to implement the steps of a power distribution network diagnostic analysis method according to any one of the first to third embodiments.
In summary, according to the power distribution network diagnostic analysis method and the power distribution network diagnostic analysis terminal provided by the present invention, when a power distribution network is diagnosed and analyzed, the representational visualization technology, the exploratory visualization technology and the verification visualization technology are combined, and the analytical data can be displayed in a suitable manner through the representational visualization technology, so that a user can more accurately select the suitable analytical data and the analytical method for the exploratory visualization analysis.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all equivalent changes made by using the contents of the present specification and the drawings, or applied directly or indirectly to the related technical fields, are included in the scope of the present invention.
Claims (7)
1. A power distribution network diagnosis and analysis method is characterized by comprising the following steps:
s1, receiving a power distribution network diagnosis request, wherein the diagnosis request comprises a diagnosis object;
s2, displaying an analysis data object corresponding to the diagnosis object and a recommended analysis data representation mode according to the diagnosis object;
s3, receiving an analysis data display request, wherein the display request comprises a selected analysis data representation mode, and displaying the analysis data corresponding to the diagnosis object according to the selected analysis data representation mode;
s4, receiving a diagnostic object data analysis request, wherein the analysis request comprises selected analysis data and an analysis method, carrying out data analysis on the diagnostic object according to the selected analysis data and the analysis method, outputting an intermediate analysis result in the analysis process, receiving a preferred selection of the intermediate analysis result, continuing to carry out data analysis on the diagnostic object according to the preferred selection, and outputting a data analysis result.
2. The power distribution network diagnostic analysis method according to claim 1, characterized in that the step S4 is followed by the step of:
and S5, receiving a verification request for the data analysis result, verifying the data analysis result according to the verification request, and outputting a verification result.
3. The power distribution network diagnostic analysis method according to claim 2, wherein the diagnostic object comprises a daily load curve of a distribution transformer for which the power consumption mode is to be determined;
the analysis data object corresponding to the diagnosis object in the step S2 comprises daily load curves of distribution transformers in various different power consumption modes stored in a distribution network diagnosis analysis database, and the recommended analysis data representation mode comprises a curve graph;
if the selected analysis data representation manner in the step S3 is a graph, the displaying the analysis data corresponding to the diagnosis object according to the selected analysis data representation manner includes:
displaying daily load curves of the distribution transformers in different power consumption modes stored in the distribution network diagnostic analysis database in a curve chart mode;
the analysis method in the step S4 includes cluster analysis;
if the analysis method is cluster analysis, then:
the step S4 of selecting the analysis data comprises deleting daily load curves which cannot form a data cluster with other daily load curves;
outputting an intermediate analysis result in the analysis process, receiving a preferred selection of the intermediate analysis result, and continuing to perform data analysis on the diagnostic object according to the preferred selection comprises:
carrying out clustering analysis on the daily load curve data after the daily load curves which cannot form data clusters with other daily load curves are deleted, and obtaining a clustering result;
receiving selection operation performed on the clustering results, and determining a daily load curve corresponding to each cluster according to the clustering results after the selection operation to obtain a typical daily load curve corresponding to each power consumption mode;
and identifying the daily load curve of the distribution transformer with the electricity utilization mode to be determined according to the typical daily load curve corresponding to each electricity utilization mode, and determining and displaying the corresponding electricity utilization mode.
4. The method according to claim 3, wherein the verification request in step S5 includes a daily load curve of the distribution transformer with a known power consumption pattern;
the verifying the data analysis result according to the verification request comprises:
and identifying the daily load curve of the distribution transformer in the known power consumption mode according to the typical daily load curve corresponding to each power consumption mode, determining the corresponding power consumption mode, and comparing the determined power consumption mode with the known power consumption mode to verify the data analysis result.
5. The power distribution network diagnostic analysis method according to claim 2, wherein the diagnostic object comprises a strong correlation term of low voltage;
the analysis data object corresponding to the diagnosis object in the step S2 includes a candidate associated with a low voltage;
the selecting of the analysis data in the step S4 includes selecting a preset number of candidates from the candidates associated with the low voltage;
the analysis method in the step S4 includes Apriori algorithm;
if the analysis method includes an Apriori algorithm, outputting an intermediate analysis result in the analysis process, receiving a preferred selection of the intermediate analysis result, and continuing to perform data analysis on the diagnostic object according to the preferred selection includes:
searching a project set containing the selected candidate items from the power distribution network diagnostic analysis database based on the selected preset number of candidate items;
determining and displaying the support degree count of each 1 item candidate set in the frequent 1 item candidate set according to the item set;
receiving a minimum support degree determined according to the support degree of each displayed 1 candidate set;
determining a frequent 1 item set according to the minimum support degree;
constructing a frequent 2 item candidate set according to the frequent 1 item set, and calculating the support degree count of each frequent 2 item candidate set in the frequent 2 item candidate set according to the item set;
determining a frequent 2 item set according to the minimum support and the support count of each frequent 2 item candidate set;
adding 1 to the number of the items of the frequent candidate set, and repeating the steps until no frequent candidate set with larger number of the items exists;
determining association rules containing low-voltage items according to all the determined frequent candidate sets, and calculating the confidence coefficient of each association rule;
displaying each association rule and the corresponding confidence level thereof;
receiving a minimum confidence level determined from the displayed confidence levels;
determining strong association rules according to the minimum confidence and the confidence of each association rule;
and determining a strong association item of low voltage according to the strong association rule.
6. The power distribution network diagnostic analysis method according to claim 5, wherein the verifying the data analysis result according to the verification request in step S5 includes:
searching items containing the strong association items from a power distribution network diagnostic analysis database according to the determined strong association items, counting the number of low voltages contained in the items containing the strong association items, determining the proportion of the number of the low voltages contained in the items containing the strong association items according to the number, and taking the proportion as a verification result.
7. A power distribution network diagnostic analysis terminal comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of a power distribution network diagnostic analysis method according to any one of claims 1 to 6 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210905172.8A CN115374210A (en) | 2022-07-29 | 2022-07-29 | Power distribution network diagnostic analysis method and terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210905172.8A CN115374210A (en) | 2022-07-29 | 2022-07-29 | Power distribution network diagnostic analysis method and terminal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115374210A true CN115374210A (en) | 2022-11-22 |
Family
ID=84063117
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210905172.8A Pending CN115374210A (en) | 2022-07-29 | 2022-07-29 | Power distribution network diagnostic analysis method and terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115374210A (en) |
-
2022
- 2022-07-29 CN CN202210905172.8A patent/CN115374210A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hristidis et al. | PREFER: A system for the efficient execution of multi-parametric ranked queries | |
| Wu et al. | Visualizing flow of uncertainty through analytical processes | |
| Rao | Data mining and clustering techniques | |
| CN110287382B (en) | Mining method for association rule of battery production data | |
| Yatsyshyn et al. | Technology of relational database management systems performance evaluation during computer systems design | |
| CN112860769B (en) | Energy planning data management system | |
| CN114638234B (en) | Big data mining method and system applied to online business handling | |
| Petrak | Fast subsampling performance estimates for classification algorithm selection | |
| Shi et al. | Clustering framework based on multi-scale analysis of intraday financial time series | |
| Zhao et al. | Call to order: a hierarchical browsing approach to eliciting users' preference | |
| CN113094448B (en) | Analysis method and analysis device for residence empty state and electronic equipment | |
| CN111353529A (en) | Mixed attribute data set clustering method for automatically determining clustering center | |
| CN109271460B (en) | Method and device for classifying merchants in electronic platform | |
| Cheng et al. | A clustering analysis method with high reliability based on Wilcoxon-Mann-Whitney testing | |
| CN109828984B (en) | Analysis processing method and device, computer storage medium and terminal | |
| CN116450757A (en) | Method, device, equipment and storage medium for determining evaluation index of data asset | |
| Ordonez et al. | Interactive exploration and visualization of OLAP cubes | |
| Zhou et al. | A user-driven sampling model for large-scale geographical point data visualization via convolutional neural networks | |
| CN116933130A (en) | Enterprise industry classification method, system, equipment and medium based on big data | |
| CN115374210A (en) | Power distribution network diagnostic analysis method and terminal | |
| Cao et al. | Research on variable weight CLIQUE clustering algorithm based on partial order set 1 | |
| Li et al. | A novel approach to remote sensing image retrieval with multi-feature VP-tree indexing and online feature selection | |
| Yang et al. | Adaptive density peak clustering for determinging cluster center | |
| CN114358167A (en) | Landslide incidence prediction model based on principal component analysis and extreme learning machine | |
| CN111552814B (en) | Assessment scheme generation method and device based on assessment index map |
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 |