CN109145995A - A kind of method of opposing electricity-stealing based on cluster discrete point detection - Google Patents
A kind of method of opposing electricity-stealing based on cluster discrete point detection Download PDFInfo
- Publication number
- CN109145995A CN109145995A CN201811006756.1A CN201811006756A CN109145995A CN 109145995 A CN109145995 A CN 109145995A CN 201811006756 A CN201811006756 A CN 201811006756A CN 109145995 A CN109145995 A CN 109145995A
- Authority
- CN
- China
- Prior art keywords
- cluster
- data
- stealing
- density
- electricity
- 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
- 238000000034 method Methods 0.000 title claims abstract description 18
- 238000001514 detection method Methods 0.000 title claims abstract description 17
- 230000005611 electricity Effects 0.000 claims abstract description 27
- 238000005201 scrubbing Methods 0.000 claims abstract description 6
- 238000013501 data transformation Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000013480 data collection Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims 1
- 238000011835 investigation Methods 0.000 abstract description 5
- 241001074085 Scophthalmus aquosus Species 0.000 abstract 1
- 238000006243 chemical reaction Methods 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 5
- 238000012795 verification Methods 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 240000002853 Nelumbo nucifera Species 0.000 description 1
- 235000006508 Nelumbo nucifera Nutrition 0.000 description 1
- 235000006510 Nelumbo pentapetala Nutrition 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000011160 research Methods 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
- 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)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Public Health (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Evolutionary Biology (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to a kind of methods of opposing electricity-stealing based on cluster discrete point detection, specially acquire the electricity consumption data service condition in user power utilization system first, carry out data scrubbing, data regularization and data conversion process, i.e. data prediction to electricity consumption data collected;Secondly, establishing Data Detection model and the pretreated data of input data using the k- mean algorithm based on density;Finally, doing further drill down operator to the electricity consumption data after cluster, judged to doubt stealing user according to lower brill result.The present invention passes through the electricity consumption data service condition in acquisition user power utilization system, data judgment models are established as core algorithm using the k- mean algorithm based on density, enable accurately to filter out suspectable stealing user, reduce investigation range, saves investment of the company in terms of stealing.
Description
Technical field
The present invention relates to electric power big data application field, especially a kind of side of opposing electricity-stealing based on cluster discrete point detection
Method.
Background technique
In recent years, with the growth of economy and increasing for electricity consumption, stealing problem is more and more prominent, and this behavior is seriously damaged
The interests of country, grid company and other normal electricity consumptions user have been done harm to, and have upset the normal order of power generation, power supply and electricity consumption,
Great negative effect is brought to society.Meanwhile high-tech electricity stealing gradually increases, and is such as stolen using wireless remote controller
Electricity carries out stealing in such a way that programmable device adjusts electricity, the code of falling table etc. to ammeter, these modes both increase the difficulty opposed electricity-stealing
Degree.But with the development of the advanced technologies such as Information and Communication Technology, computer technology, big data technology, by these advanced skills
Art and theory be integrated into management of opposing electricity-stealing, in terminal power consumption management at an important directions of research of opposing electricity-stealing.
Currently, traditional monitoring means of opposing electricity-stealing is manually to carry out data period by the metering ammeter data of GPRS teletransmission
Comparison and analysis, it is possible to find voltage system and misphase sequential mode stealing, the experienced Field Force in part can also be negative by analyzing
The artificial investigation discovery current system electricity stealing of lotus and scene.These method instantaneities are poor, to establish and acquire data completely just
Really and on the basis of a large amount of artificial experiences, the high-tech stealing mode such as shunting, remote controler is difficult to effectively prevent, can only be located afterwards
Reason such as can not prevent at the outstanding problems in advance.
Summary of the invention
In view of this, the purpose of the present invention is to propose to a kind of method of opposing electricity-stealing based on cluster discrete point detection, it can be right
User power utilization data carry out clustering, and obtain suspicious stealing user, and can push early warning to administrator.
The present invention is realized using following scheme: a kind of method of opposing electricity-stealing based on cluster discrete point detection, including following step
It is rapid:
Step S1: carrying out initial data acquisition, user power utilization data in electric system is obtained, to obtain based on density
Detection data collection needed for k- mean algorithm;
Step S2: carrying out data prediction, carries out data scrubbing, data regularization and data to user power utilization data and converts;
Step S3: carrying out the clustering of the k- mean algorithm based on density, firstly, initial poly- using being chosen based on density
The k- mean algorithm of class point is learnt and is excavated to user power utilization data, and the data for calculating each data object region are close
Degree, chooses the cluster of wherein k big density, and the data object in data set is separately dispensed into nearest k big Density Clusters
In, the center of this k density area is exactly initial cluster center, then obtains cluster result using classical k- mean algorithm;
Step S4: difference degree height is found out by difference degree descending sort according to the cluster result that the step S3 is generated
Numerical value, i.e. discrete point, and as doubtful stealing user point pushes warning message in systems automatically, realizes to doubtful stealing
User's forewarning function.
Further, step S2 specifically comprises the following steps:
Step S21: data scrubbing carried out to user power utilization data: ammeter asset number in user power utilization data, registration type,
Electricity consumption address, the incoherent attribute of the mode of connection weed out, and leave behind Customs Assigned Number and electricity consumption;
Step S22: carrying out data regularization, constructs a sub- attribute average annual use of electricity;
Step S23: it carries out data transformation: data transformation being defined, minAAnd maxABe respectively attribute A most
Small value and maximum value pass through min-max normalizing:
By the value v of AiIt is mapped to section [new_minA,new_maxA] in vi', wherein desirable new_minA=0.000,
new_maxA=1.000, wherein new_minAIndicate A can value minimum zone, new_maxAIndicate A can value maximum model
It encloses, this standardization is able to maintain the connection between former data.
Further, step S3 specifically comprises the following steps:
Step S31: choosing initial clustering point based on density, and it is each right in the data set D after step S2 is processed to calculate
As the dot density dens (x) and mean value dot density Adens (x) of x, dot density dens (x) be using x as the centre of sphere, r be radius spherical shape
The object number for including in domain, i.e. dens (x)=x | dist (x, o)≤r, x ∈ D }, wherein r=C × l, C are constants, and o is indicated
Object in cluster, l indicate the mean value in data set D between every two object, generally take the 1%- of data set D total number n
2%,xjIndicate j-th of object.Mean value dot density Adens (x) is data
Collect the average value of each object dot density in D, i.e.,By dens (xi) >
Adens(xi) object xiThat is in kernel object deposit set S, and other all objects, object A included in its cluster are recorded
Euclidean distance between object B isWherein, p indicates p dimensional vector number, AiIndicate object
The i-th dimension numerical value of A, BiIndicate the i-th dimension numerical value of object B;
Step S32: for each object in data set D, each cluster center in each object and k big Density Cluster is calculated
Euclidean distance, each object is assigned in most like cluster;
Step S33: the mean value of k big Density Cluster is recalculated;
Step S34: repeating step S32 and step S33, continues iteration, until the C that distribution is stable or alliVariation it is small
It is identical as the cluster that previous round is formed in the cluster of given threshold value, i.e. epicycle formation.
Further, step S31 specifically includes the following steps:
Step S311: the dot density dens (x) and mean value of each object x in the data set D after step S2 is processed are calculated
Dot density Adens (x), by dens (xi) > Adens (xi) object xiThat is it in kernel object deposit set S, and records in its cluster
The other all objects for being included;
Step S312: merge all clusters with common core object;
Step S313: the cluster of wherein k big density is chosen, meets C between clusteri∩Cj=φ, wherein CiIt indicates i-th
Cluster, CjJ-th of cluster calculates the cluster density Cdens (C of each clusteri), cluster density Cdens (Ci) to be that data set D is divided into big
Object number m included in Density Cluster accounts for the ratio of total number n, i.e.,And calculate its central point
xi', central point is initial cluster center;
Further, the selection calculation method of the central point described in step S313 are as follows: choose with a distance from the centre of sphere nearest
Object is as initial cluster center point, i.e.,Q indicates the cluster number ultimately generated, xjTable
Show j-th of object.
Further, in stating step S4, specifically comprise the following steps:
Step S41: difference degree diff (x, the x' of cluster result are calculatedi),WhereinIt is
Each object assignment is to central point x' in clusteriBetween average distance,Wherein m is included in cluster
Object number, and difference degree descending sort is pressed, find out the high numerical value of difference program, i.e. discrete point;
Step S42: doing further drill down operator to discrete point, and each own demand average value and every month in 6-9 month are used
Electricity compares, if Urban Annual Electrical Power Consumption amount average value is greater than the electricity consumption of every month in 6-9 month, illustrates that this user has very probably
Rate stealing.
Preferably, in order to mitigate manual examination and verification burden, improve working efficiency, and the loss of enterprise and country is finally retrieved,
The present invention treats user power utilization data from computer angle, suspicious stealing user is excavated in user power utilization data, by adopting
With suspicious stealing user is excavated based on the k- mean algorithm of density, this method can carry out cluster point to user power utilization data
Analysis, and suspicious stealing user is obtained, and early warning can be pushed to administrator, enable accurately to filter out suspectable stealing use
Family reduces investigation range, saves enterprise in the investment of aspect of opposing electricity-stealing.
Compared with prior art, the invention has the following beneficial effects:
1. the present invention can reduce manual examination and verification burden, improve working efficiency, and finally retrieve the loss of enterprise and country.
2. present invention uses big data technology, preferably the mass data of power application enterprise and national big number can be agreed with
According to strategy.
3. the present invention can push early warning to administrator, enables accurately to filter out suspectable stealing user, contract
Small investigation range saves enterprise in the investment of aspect of opposing electricity-stealing.
Detailed description of the invention
Fig. 1 is the flow chart of the embodiment of the present invention.
Fig. 2 is the k- mean algorithm schematic diagram based on density of the embodiment of the present invention.
Specific embodiment
The present invention will be further described with reference to the accompanying drawings and embodiments.
As depicted in figs. 1 and 2, a kind of method of opposing electricity-stealing based on cluster discrete point detection is present embodiments provided, specifically
The following steps are included:
Step S1: carrying out initial data acquisition, user power utilization data in electric system is obtained, to obtain based on density
Detection data collection needed for k- mean algorithm;
Step S2: carrying out data prediction, carries out data scrubbing, data regularization and data to user power utilization data and converts;
Step S3: carrying out the clustering of the k- mean algorithm based on density, firstly, initial poly- using being chosen based on density
The k- mean algorithm of class point is learnt and is excavated to user power utilization data, and the data for calculating each data object region are close
Degree, chooses the cluster of wherein k big density, and the data object in data set is separately dispensed into nearest k big Density Clusters
In, the center of this k density area is exactly initial cluster center, then obtains cluster result using classical k- mean algorithm;
Step S4: difference degree height is found out by difference degree descending sort according to the cluster result that the step S3 is generated
Numerical value, i.e. discrete point, and as doubtful stealing user point pushes warning message in systems automatically, realizes to doubtful stealing
User's forewarning function.
In the present embodiment, step S2 specifically comprises the following steps:
Step S21: data scrubbing carried out to user power utilization data: ammeter asset number in user power utilization data, registration type,
Electricity consumption address, the incoherent attribute of the mode of connection weed out, and leave behind Customs Assigned Number and electricity consumption;
Step S22: carrying out data regularization, constructs a sub- attribute average annual use of electricity;
Step S23: it carries out data transformation: data transformation being defined, minAAnd maxABe respectively attribute A most
Small value maximum value, passes through min-max normalizing:
By the value v of AiIt is mapped to section [new_minA,new_maxA] in v'i, wherein desirable new_minA=0.000,
new_maxA=1.000, wherein new_minAIndicate A can value minimum zone, new_maxAIndicate A can value maximum model
It encloses, this standardization is able to maintain the connection between former data.
In the present embodiment, step S3 specifically comprises the following steps:
Step S31: choosing initial clustering point based on density, and it is each right in the data set D after step S2 is processed to calculate
As the dot density dens (x) and mean value dot density Adens (x) of x, dot density dens (x) be using x as the centre of sphere, r be radius spherical shape
The object number for including in domain, i.e. dens (x)=x | dist (x, o)≤r, x ∈ D }, wherein r=C × l, C are constants, and l is indicated
In data set D between every two object distance mean value, generally take the 1%-2% of data set D total number n, o is indicated in cluster
Object, l are the mean values of distance between every two object in data set D,
xjIndicate j-th of object.Mean value dot density Adens (x) is the average value of each object dot density in data set D, i.e.,By dens (xi) > Adens (xi) object xiI.e. kernel object is stored in
In set S, and records other all objects, the Euclidean distance between object A and object B included in its cluster and beWherein, p indicates p dimensional vector number, AiIndicate the i-th dimension numerical value of object A, BiIndicate object
The i-th dimension numerical value of B;
Step S32: for each object in data set D, each cluster center in each object and k big Density Cluster is calculated
Euclidean distance, each object is assigned in most like cluster;
Step S33: the mean value of k big Density Cluster is recalculated;
Step S34: repeating step S32 and step S33, continues iteration, until the C that distribution is stable or alliVariation it is small
It is identical as the cluster that previous round is formed in the cluster of given threshold value, i.e. epicycle formation.
In the present embodiment, step S31 specifically includes the following steps:
Step S311: the dot density dens (x) and mean value of each object x in the data set D after step S2 is processed are calculated
Dot density Adens (x), by dens (xi) > Adens (xi) object xiThat is it in kernel object deposit set S, and records in its cluster
The other all objects for being included;
Step S312: merge all clusters with common core object;
Step S313: the cluster of wherein k big density is chosen, meets C between clusteri∩Cj=φ, wherein CiIt indicates i-th
Cluster, CjIt indicates j-th of cluster, calculates the cluster density Cdens (C of each clusteri), cluster density Cdens (Ci) it is that data set D is divided into
Big Density Cluster included in object number m account for the ratio of total number n, i.e.,And calculate its center
Point xi', central point is initial cluster center;
In the present embodiment, the selection calculation method of the central point described in step S313 are as follows: choose with a distance from the centre of sphere most
Close object is as initial cluster center point, i.e.,K indicates the cluster ultimately generated
Number.
In the present embodiment, in step s 4, specifically comprise the following steps:
Step S41: difference degree diff (x, the x' of cluster result are calculatedi),WhereinIt is
Each object assignment is to central point x' in clusteriBetween average distance,Wherein m is included in cluster
Object number, and difference degree descending sort is pressed, find out the high numerical value of difference program, i.e. discrete point;
Step S42: doing further drill down operator to discrete point, and each own demand average value and every month in 6-9 month are used
Electricity compares, if Urban Annual Electrical Power Consumption amount average value is greater than the electricity consumption of every month in 6-9 month, illustrates that this user has very probably
Rate stealing.
Preferably, in order to mitigate manual examination and verification burden, improve working efficiency, and the loss of enterprise and country is finally retrieved,
The present embodiment treats user power utilization data from computer angle, and suspicious stealing user is excavated in user power utilization data, is passed through
Using suspicious stealing user is excavated based on the k- mean algorithm of density, this method can cluster user power utilization data
Analysis, and suspicious stealing user is obtained, and early warning can be pushed to administrator, enable accurately to filter out suspectable stealing
User.
Particularly, embodiment is to by carrying out to crawl user power utilization data and to it data prediction, and using improving
K- mean algorithm optimized accordingly as core clustering algorithm, and to some steps of this algorithm, enable more to have
Efficient, more accurately processes user data reduces stealing investigation range, saves investment of the company in terms of stealing.
The foregoing is merely presently preferred embodiments of the present invention, all equivalent changes done according to scope of the present invention patent with
Modification, is all covered by the present invention.
Claims (6)
1. a kind of method of opposing electricity-stealing based on cluster discrete point detection, characterized by the following steps:
Step S1: carrying out initial data acquisition, obtains user power utilization data in electric system, equal to obtain the k- based on density
Detection data collection needed for value-based algorithm;
Step S2: data prediction is carried out;
Step S3: the clustering of the k- mean algorithm based on density is carried out, cluster result is obtained;
Step S4: the high number of difference degree is found out by difference degree descending sort according to the cluster result that the step S3 is generated
Value, i.e. discrete point, and as doubtful stealing user point, it pushes warning message in systems automatically, realizes to doubtful stealing user
Forewarning function.
2. a kind of method of opposing electricity-stealing based on cluster discrete point detection according to claim 1, it is characterised in that: the step
Rapid S2 specifically comprises the following steps:
Step S21: data scrubbing: ammeter asset number, registration type, electricity consumption in user power utilization data is carried out to user power utilization data
Address, the incoherent attribute of the mode of connection weed out, and leave behind Customs Assigned Number and electricity consumption;
Step S22: data regularization is carried out: one sub- attribute average annual use of electricity of construction;
Step S23: it carries out data transformation: data transformation being defined, minAAnd maxAIt is the minimum value of attribute A respectively
Maximum value passes through min-max normalizing:
By the value v of AiIt is mapped to section [new_minA,new_maxA] in vi', wherein desirable new_minA=0.000, new_
maxA=1.000, wherein new_minAIndicate A can value minimum zone, new_maxAIndicate A can value maximum magnitude,
This standardization is able to maintain the connection between former data.
3. a kind of method of opposing electricity-stealing based on cluster discrete point detection according to claim 1, it is characterised in that: the step
Rapid S3 specifically comprises the following steps:
Step S31: initial clustering point is chosen based on density;
Step S32: for each object in data set D, the Europe at each cluster center in each object and k big Density Cluster is calculated
Each object is assigned in most like cluster by family name's distance;
Step S33: the mean value of k big Density Cluster is recalculated;
Step S34: repeating step S32 and step S33, continues iteration, until the C that distribution is stable or alliVariation be less than it is given
The cluster that threshold value, i.e. epicycle are formed is identical as the cluster that previous round is formed.
4. a kind of method of opposing electricity-stealing based on cluster discrete point detection according to claim 3, it is characterised in that: the step
Rapid S31 specifically includes the following steps:
Step S311: it is close that the dot density dens (x) of each object x and average point in the data set D after step S2 is processed are calculated
It spends Adens (x), by dens (xi) > Adens (xi) object xiThat is it in kernel object deposit set S, and records and is wrapped in its cluster
The other all objects contained;
Step S312: merge all clusters with common core object;
Step S313: the cluster of wherein k big density is chosen, meets C between clusteri∩Cj=φ, wherein CiIndicate i-th of cluster, CjTable
Show j-th of cluster, calculates the cluster density Cdens (C of each clusteri), calculate its central point x 'i, central point is initial cluster center.
5. a kind of method of opposing electricity-stealing based on cluster discrete point detection according to claim 4, it is characterised in that: the step
The selection calculation method of central point described in rapid S313 are as follows: choose nearest object with a distance from the centre of sphere as initial cluster center
Point, i.e.,K indicates the cluster number ultimately generated, xjIndicate j-th of object.
6. a kind of method of opposing electricity-stealing based on cluster discrete point detection according to claim 1, which is characterized in that the step
In rapid S4, specifically comprise the following steps:
Step S41: difference degree diff (x, x ' of cluster result are calculatedi), and difference degree descending sort is pressed, find out difference journey
The high numerical value of sequence, i.e. discrete point;
Step S42: doing further drill down operator to discrete point, each own demand average value and electricity consumption every month in 6-9 month
It compares, if Urban Annual Electrical Power Consumption amount average value is greater than the electricity consumption of every month in 6-9 month, illustrates that this user has very maximum probability to steal
Electricity.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811006756.1A CN109145995A (en) | 2018-08-31 | 2018-08-31 | A kind of method of opposing electricity-stealing based on cluster discrete point detection |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811006756.1A CN109145995A (en) | 2018-08-31 | 2018-08-31 | A kind of method of opposing electricity-stealing based on cluster discrete point detection |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109145995A true CN109145995A (en) | 2019-01-04 |
Family
ID=64825715
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811006756.1A Pending CN109145995A (en) | 2018-08-31 | 2018-08-31 | A kind of method of opposing electricity-stealing based on cluster discrete point detection |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109145995A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110223196A (en) * | 2019-06-04 | 2019-09-10 | 国网浙江省电力有限公司电力科学研究院 | Analysis method of opposing electricity-stealing based on typical industry feature database and sample database of opposing electricity-stealing |
CN111414933A (en) * | 2020-01-15 | 2020-07-14 | 武汉烽火众智数字技术有限责任公司 | Electric vehicle stolen area analysis method and system based on RFID and clustering algorithm |
CN111667144A (en) * | 2020-04-30 | 2020-09-15 | 北京中电普华信息技术有限公司 | User identification method and device |
CN114330583A (en) * | 2021-12-31 | 2022-04-12 | 四川大学 | Abnormal electricity utilization identification method and abnormal electricity utilization identification system |
CN114371438A (en) * | 2021-12-30 | 2022-04-19 | 国网河北省电力有限公司营销服务中心 | Measuring equipment misalignment judgment method based on Internet of things |
CN117332453A (en) * | 2023-11-30 | 2024-01-02 | 山东街景智能制造科技股份有限公司 | Safety management system for product database |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104462819A (en) * | 2014-12-09 | 2015-03-25 | 国网四川省电力公司信息通信公司 | Local outlier detection method based on density clustering |
CN106682079A (en) * | 2016-11-21 | 2017-05-17 | 云南电网有限责任公司电力科学研究院 | Detection method of user's electricity consumption behavior of user based on clustering analysis |
CN107659973A (en) * | 2017-08-23 | 2018-02-02 | 南京邮电大学 | Super-intensive network cluster dividing method based on density K means algorithms |
-
2018
- 2018-08-31 CN CN201811006756.1A patent/CN109145995A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104462819A (en) * | 2014-12-09 | 2015-03-25 | 国网四川省电力公司信息通信公司 | Local outlier detection method based on density clustering |
CN106682079A (en) * | 2016-11-21 | 2017-05-17 | 云南电网有限责任公司电力科学研究院 | Detection method of user's electricity consumption behavior of user based on clustering analysis |
CN107659973A (en) * | 2017-08-23 | 2018-02-02 | 南京邮电大学 | Super-intensive network cluster dividing method based on density K means algorithms |
Non-Patent Citations (2)
Title |
---|
张琳等: "一种基于密度的K-means算法研究", 《计算机应用研究》 * |
蔡耀年等: "一种基于离群算法的窃电行为检测的研究", 《计算技术与自动化》 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110223196A (en) * | 2019-06-04 | 2019-09-10 | 国网浙江省电力有限公司电力科学研究院 | Analysis method of opposing electricity-stealing based on typical industry feature database and sample database of opposing electricity-stealing |
CN110223196B (en) * | 2019-06-04 | 2021-08-31 | 国网浙江省电力有限公司营销服务中心 | Anti-electricity-stealing analysis method based on typical industry feature library and anti-electricity-stealing sample library |
CN111414933A (en) * | 2020-01-15 | 2020-07-14 | 武汉烽火众智数字技术有限责任公司 | Electric vehicle stolen area analysis method and system based on RFID and clustering algorithm |
CN111667144A (en) * | 2020-04-30 | 2020-09-15 | 北京中电普华信息技术有限公司 | User identification method and device |
CN114371438A (en) * | 2021-12-30 | 2022-04-19 | 国网河北省电力有限公司营销服务中心 | Measuring equipment misalignment judgment method based on Internet of things |
CN114371438B (en) * | 2021-12-30 | 2022-09-06 | 国网河北省电力有限公司营销服务中心 | Measuring equipment misalignment judgment method based on Internet of things |
CN114330583A (en) * | 2021-12-31 | 2022-04-12 | 四川大学 | Abnormal electricity utilization identification method and abnormal electricity utilization identification system |
CN114330583B (en) * | 2021-12-31 | 2022-11-08 | 四川大学 | Abnormal electricity utilization identification method and abnormal electricity utilization identification system |
CN117332453A (en) * | 2023-11-30 | 2024-01-02 | 山东街景智能制造科技股份有限公司 | Safety management system for product database |
CN117332453B (en) * | 2023-11-30 | 2024-02-23 | 山东街景智能制造科技股份有限公司 | Safety management system for product database |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109145995A (en) | A kind of method of opposing electricity-stealing based on cluster discrete point detection | |
Jiang et al. | A fused load curve clustering algorithm based on wavelet transform | |
CN109492667A (en) | A kind of feature selecting discrimination method for non-intrusive electrical load monitoring | |
CN111126429A (en) | Low-voltage distribution area user access point identification method based on PCA (principal component analysis) degradation and K-Means clustering | |
CN103093394A (en) | Clustering fusion method based on user electrical load data subdivision | |
CN111598330A (en) | Residential electricity load prediction method based on load identification technology | |
CN107958395B (en) | Method for identifying abnormal users of power system | |
CN109948909A (en) | A kind of electric network data capturing analysis method and system | |
CN106777005A (en) | User power utilization behavior analysis method based on big data technological improvement clustering algorithm | |
CN113036759A (en) | Power consumer load fine-grained identification method and identification system | |
CN115065078A (en) | Energy storage capacity configuration method and system in micro-grid environment | |
CN112615428A (en) | Line loss analysis and treatment system and method | |
Miraftabzadeh et al. | K-means and alternative clustering methods in modern power systems | |
CN105550450B (en) | Electric energy quality interference source characteristic harmonic modeling method | |
Li et al. | Identification of distribution network topology parameters based on multidimensional operation data | |
CN110555619A (en) | Power supply capacity evaluation method based on intelligent power distribution network | |
CN104915681B (en) | Take into account substation's clustering method of voltage dip monitoring information and its relation factor | |
CN110059869A (en) | A kind of charging station based on the magnitude of traffic flow and power distribution network coordinated planning method | |
CN105445577A (en) | Power quality disturbance source working condition identifying method | |
Zhang et al. | User power interaction behavior clustering analysis that is based on the self-organizing-center K-means algorithm | |
CN116488159A (en) | Power grid characteristic extraction and source load collaborative analysis method and device and storage medium | |
CN114186631A (en) | Load identification method based on non-invasive intelligent terminal | |
Shen et al. | A Novel AI-based Method for EV Charging Load Profile Clustering | |
CN114662576A (en) | Non-invasive storage battery car charging detection method and system based on supervised classification | |
CN112085381A (en) | Multi-objective optimization electric vehicle charging station planning method |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190104 |