CN111680074B - Clustering algorithm-based power acquisition load leakage point feature mining method - Google Patents
Clustering algorithm-based power acquisition load leakage point feature mining method Download PDFInfo
- Publication number
- CN111680074B CN111680074B CN201911403417.1A CN201911403417A CN111680074B CN 111680074 B CN111680074 B CN 111680074B CN 201911403417 A CN201911403417 A CN 201911403417A CN 111680074 B CN111680074 B CN 111680074B
- Authority
- CN
- China
- Prior art keywords
- leakage point
- point
- leakage
- data
- metering
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
The invention discloses a clustering algorithm-based power acquisition load leakage point feature mining method, and relates to the field of power information acquisition. At present, in the power load data acquisition process, the condition that data acquisition is unsuccessful often appears, user load data is missing at certain moments, a leakage point phenomenon is formed, the leakage acquisition accuracy in the existing system is not high, the acquisition success rate is relatively low, and the information of the leakage point situation is not perfect. The method comprises the following steps: collecting load data; extracting leakage point data; extracting leakage point characteristic indexes through leakage point data; performing cluster analysis on the leakage point data indexes to form cluster category characteristics; and finally extracting the leakage point characteristics of the user. The leakage point result data and the acquisition process behavior data are analyzed through load acquisition, so that the leakage point condition of a user can be deeply mastered, the leakage point characteristics of equipment can be timely found, and the acquisition success rate is improved.
Description
Technical Field
The invention relates to the field of power information acquisition, in particular to a clustering algorithm-based power acquisition load leakage point feature mining method.
Background
In the power collection business, the collection of the user load data is a basic work in the power data collection, and has great significance in the collection of the user electric quantity load and other data. At present, in the process of collecting power load data, the condition that data collection is unsuccessful often occurs, and user load data is lost at certain moments to form a leakage point phenomenon. The leakage acquisition accuracy in the existing system is not high, the acquisition success rate is relatively low, and the information of the leakage point situation is not perfect.
Disclosure of Invention
The invention aims to solve the technical problems and the technical task of improving the prior art, and provides a clustering algorithm-based power acquisition load leakage point feature mining method, aiming at deeply grasping leakage point conditions and improving the success rate of leakage point acquisition. For this purpose, the present invention adopts the following technical scheme.
A clustering algorithm-based power acquisition load leakage point feature mining method comprises the following steps:
1) Collecting load data from an acquisition system;
2) Extracting corresponding metering point leakage point data;
3) Extracting leakage point characteristic indexes through leakage point data;
4) Analyzing the leakage point data index through a clustering algorithm to form clustering type characteristics of metering points;
5) And extracting the leakage point characteristic of each user through the clustering category characteristic of the metering points.
The leakage point result data and the acquisition process behavior data are analyzed through the load acquisition, the leakage point condition of a user can be deeply mastered, the leakage point characteristics of equipment can be timely found, the acquisition success rate is improved, references are provided for acquisition personnel, the acquisition work is convenient to develop, the auxiliary acquisition rate is improved, and the timely normal operation of the equipment is ensured.
As a preferable technical means: in the step 3), counting each index of each metering point of the leakage point data, wherein index content comprises the total number of the leakage points, the leakage point continuity characteristic, the leakage point week characteristic and the leakage point moment characteristic, the total number of the leakage points is used for counting the whole leakage point condition of the metering point, the leakage point continuity characteristic is used for describing the number of times of 2 or more continuous leakage points of the metering point and reflecting the serious condition of the leakage point, the leakage point week characteristic is used for describing the leakage point time law of the metering point in a week period, and the leakage point moment characteristic is used for describing the leakage point moment law of the metering point of the leakage point in 24 hours a day. The extraction of the characteristic index of the leakage point is effectively realized.
As a preferable technical means: in step 4), by a distance functionWhereinCalculating the distance between each metering point by representing each calculation index of any two metering points, and gathering the points with similar distances together to form each characteristic category. And the clustering category characteristics of the metering points are effectively realized.
The beneficial effects are that: the leakage point result data and the acquisition process behavior data are analyzed through the load acquisition, the leakage point condition of a user can be deeply mastered, the leakage point characteristics of equipment can be timely found, the acquisition success rate is improved, references are provided for acquisition personnel, the acquisition work is convenient to develop, the auxiliary acquisition rate is improved, and the timely normal operation of the equipment is ensured.
Drawings
FIG. 1 is a schematic flow chart of the present invention.
Detailed Description
The technical scheme of the invention is further described in detail below with reference to the attached drawings.
As shown in fig. 1, the power collection load leakage point feature mining method based on the clustering algorithm comprises the following steps:
1) Acquisition load data of a user of the spot transformer is acquired from an acquisition system, wherein the acquisition load data of the user of the spot transformer is acquired from the current date for one month.
2) And matching the acquired metering point, time and related load data with the complete metering point and time to extract corresponding metering point leakage point data.
3) The method comprises the steps of summarizing data indexes of the leakage point data as input of analysis and mining, counting each index of each metering point in the past month, wherein index content comprises the total number of the leakage points, the continuity characteristic of the leakage points, the week characteristic of the leakage points and the time characteristic of the leakage points, the total number of the leakage points is used for counting the condition of the whole leakage point of the metering point, the continuity characteristic of the leakage points is used for describing the number of times of 2 or more continuous leakage points of the metering point and reflecting the serious condition of the leakage point, the week characteristic of the leakage points is used for describing the time law of the leakage point of the metering point in a week period, the total number of the indexes is 7, the time characteristic of the leakage point is used for describing the time law of the leakage point of 24 hours in a day, and the total number of the leakage point is 24 leakage point indexes, and the following table is specific.
4) Analyzing the data indexes of the missing points through a clustering algorithm, carrying out clustering mining analysis on the indexes by using the clustering algorithm after counting each calculation index of the metering points to form clustering type characteristics of the metering points, and carrying out distance functionWherein->Calculating the distance between each metering point by representing each calculation index of any two metering points, and gathering the points with similar distances together to form each characteristic category. Each category is a specific embodiment of the calculation index, for example, a certain category feature may be continuous leak points in the past month, the proportion of the leak points in the Wednesday, and the proportion of the leak points in the 17 points.
5) And extracting the leakage point characteristics of each user through the clustering type characteristics of the metering points, wherein for example, the leakage point characteristics of the users under the category can be marked as the leakage point of the month is serious, the frequent leakage point is Tuesday and the frequent leakage point moment is 17 when one month is continuous leakage point, tuesday leakage point ratio is high and 17 leakage point ratio is high.
In this example, the clustering algorithm is an analysis process of grouping a collection of physical or abstract objects into multiple classes composed of similar objects, and by using a load leakage point acquisition result, through cluster analysis, the leakage point objects can be classified into different classes according to the similarity of leakage point features, leakage point information is extracted, and the load leakage point features are intuitively represented. The distribution rule of the load leakage points is studied currently, the number and the continuity of the leakage points of the object are analyzed from the existing leakage point data, the distribution rule is distributed along with time, and the leakage point condition is modeled by using a clustering algorithm according to different information.
The electric power collection load leakage point feature mining method based on the clustering algorithm shown in the figure 1 is a specific embodiment of the invention, has shown the outstanding essential characteristics and remarkable progress of the invention, can be subjected to equivalent modification in the aspects of shape, structure and the like according to actual use requirements, and is within the scope of protection of the scheme.
Claims (4)
1. The power acquisition load leakage point feature mining method based on the clustering algorithm is characterized by comprising the following steps of:
1) Collecting load data from an acquisition system;
2) Extracting corresponding metering point leakage point data;
3) Extracting leakage point characteristic indexes through leakage point data;
4) Analyzing the leakage point data index through a clustering algorithm to form clustering type characteristics of metering points;
5) Extracting the missing point characteristics of each user through the clustering category characteristics of the metering points;
in the step 3), counting each index of each metering point of the leakage point data, wherein index content comprises the total number of the leakage points, the leakage point continuity characteristic, the leakage point week characteristic and the leakage point moment characteristic, the total number of the leakage points is used for counting the whole leakage point condition of the metering point, the leakage point continuity characteristic is used for describing the number of times of 2 or more continuous leakage points of the metering point and reflecting the serious condition of the leakage point, the leakage point week characteristic is used for describing the leakage point time law of the metering point in a week period, and the leakage point moment characteristic is used for describing the leakage point moment law of the metering point of the leakage point in 24 hours a day.
2. The clustering algorithm-based power acquisition load leakage point feature mining method is characterized by comprising the following steps of: in the step 1), the period of acquiring the acquired load data from the acquisition system is that the current date is pushed back for at least one month.
3. The clustering algorithm-based power acquisition load leakage point feature mining method is characterized by comprising the following steps of: in the step 2), the acquired metering point, time and related load data are matched with the complete metering point and time, and corresponding metering point leakage point data are extracted from the metering point leakage point data.
4. The clustering algorithm-based power acquisition load leakage point feature mining method is characterized by comprising the following steps of: in step 4), by a distance functionTo calculate the distance between each metering point, and to group together the points with similar distances to form each characteristic category, wherein (x i ,y i ) Representing the respective calculation index of any two metering points.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911403417.1A CN111680074B (en) | 2019-12-31 | 2019-12-31 | Clustering algorithm-based power acquisition load leakage point feature mining method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911403417.1A CN111680074B (en) | 2019-12-31 | 2019-12-31 | Clustering algorithm-based power acquisition load leakage point feature mining method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111680074A CN111680074A (en) | 2020-09-18 |
CN111680074B true CN111680074B (en) | 2023-07-04 |
Family
ID=72451247
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911403417.1A Active CN111680074B (en) | 2019-12-31 | 2019-12-31 | Clustering algorithm-based power acquisition load leakage point feature mining method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111680074B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116756528B (en) * | 2023-08-18 | 2023-11-28 | 杭州鸿晟电力设计咨询有限公司 | Method, device, equipment and medium for complementing electricity load data |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102651116A (en) * | 2012-03-31 | 2012-08-29 | 上海市电力公司 | Power load data refining method |
CN106447206A (en) * | 2016-10-09 | 2017-02-22 | 国网浙江省电力公司信息通信分公司 | Power utilization analysis method based on acquisition data of power utilization information |
CN108681973A (en) * | 2018-05-14 | 2018-10-19 | 广州供电局有限公司 | Sorting technique, device, computer equipment and the storage medium of power consumer |
CN108761196A (en) * | 2018-03-30 | 2018-11-06 | 国家电网公司 | A kind of intelligent electric meter user missing voltage data restorative procedure |
JP2019054715A (en) * | 2017-09-15 | 2019-04-04 | 東京電力ホールディングス株式会社 | Power theft monitoring system, power theft monitoring device, power theft monitoring method and program |
CN110022226A (en) * | 2019-01-04 | 2019-07-16 | 国网浙江省电力有限公司 | A kind of data collection system and acquisition method based on object-oriented |
CN110188919A (en) * | 2019-04-22 | 2019-08-30 | 武汉大学 | A kind of load forecasting method based on shot and long term memory network |
-
2019
- 2019-12-31 CN CN201911403417.1A patent/CN111680074B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102651116A (en) * | 2012-03-31 | 2012-08-29 | 上海市电力公司 | Power load data refining method |
CN106447206A (en) * | 2016-10-09 | 2017-02-22 | 国网浙江省电力公司信息通信分公司 | Power utilization analysis method based on acquisition data of power utilization information |
JP2019054715A (en) * | 2017-09-15 | 2019-04-04 | 東京電力ホールディングス株式会社 | Power theft monitoring system, power theft monitoring device, power theft monitoring method and program |
CN108761196A (en) * | 2018-03-30 | 2018-11-06 | 国家电网公司 | A kind of intelligent electric meter user missing voltage data restorative procedure |
CN108681973A (en) * | 2018-05-14 | 2018-10-19 | 广州供电局有限公司 | Sorting technique, device, computer equipment and the storage medium of power consumer |
CN110022226A (en) * | 2019-01-04 | 2019-07-16 | 国网浙江省电力有限公司 | A kind of data collection system and acquisition method based on object-oriented |
CN110188919A (en) * | 2019-04-22 | 2019-08-30 | 武汉大学 | A kind of load forecasting method based on shot and long term memory network |
Non-Patent Citations (3)
Title |
---|
Cheng Q 等.Abnormal electricity consumption detection based on ensemble learning.《2019 9th International Conference on Information Science and Technology (ICIST)》.2019,全文. * |
罗清雷 等.基于增长模型的电力设备缺失数据筛查算法研究.《科技通报》.2019,第35卷(第08期),全文. * |
裴旭斌 等.于蚁群算法改进One-Class SVM的电力离群用户检测算法研究.《自动化与仪器仪表》.2019,(第05期),全文. * |
Also Published As
Publication number | Publication date |
---|---|
CN111680074A (en) | 2020-09-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104915334A (en) | Automatic extraction method of key information of bidding project based on semantic analysis | |
CN102426590B (en) | Quality evaluation method and device | |
CN103605651A (en) | Data processing showing method based on on-line analytical processing (OLAP) multi-dimensional analysis | |
CN104915456A (en) | Mass power utilization data mining method on the basis of data analysis system | |
CN110503136A (en) | Platform area line loss exception analysis method, computer readable storage medium and terminal device | |
CN107909208A (en) | Damage method drops in a kind of taiwan area distribution | |
CN111680074B (en) | Clustering algorithm-based power acquisition load leakage point feature mining method | |
CN111784093B (en) | Enterprise reworking auxiliary judging method based on power big data analysis | |
CN107944760A (en) | A kind of enterprise's bidding competition power analysis method and system | |
CN103164537B (en) | A kind of method of search engine logs data mining of user oriented information requirement | |
CN109286188A (en) | A kind of 10kV power distribution network theoretical line loss caluclation method based on multi-source data collection | |
CN102592201B (en) | Method for summarizing rice regional test information rapidly | |
CN105574265B (en) | Entire assembly model quantitative description towards model index | |
CN105741161A (en) | Method and system for recognizing click farming users in taxi businesses on basis of driver credit | |
CN111427725A (en) | Big data storage system and method | |
CN102567536A (en) | Key performance target analyzing method based on data statistics | |
CN104166756A (en) | Computation method for mass distribution of aircraft | |
CN109002753B (en) | Large-scene monitoring image face detection method based on convolutional neural network cascade | |
CN112181715A (en) | Visual backup and comparison method based on distribution network automation system model | |
CN105445577A (en) | Power quality disturbance source working condition identifying method | |
CN117009610A (en) | K line graph visualization system and method based on power data | |
CN114676931B (en) | Electric quantity prediction system based on data center technology | |
CN103678655A (en) | Method and device for verifying information | |
CN114611869B (en) | Low-voltage station area station household identification method | |
CN116433443A (en) | Carbon asset magnitude traceability management method based on sulfur hexafluoride |
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 |