CN106204335A - A kind of electricity price performs abnormality judgment method, Apparatus and system - Google Patents
A kind of electricity price performs abnormality judgment method, Apparatus and system Download PDFInfo
- Publication number
- CN106204335A CN106204335A CN201610581022.0A CN201610581022A CN106204335A CN 106204335 A CN106204335 A CN 106204335A CN 201610581022 A CN201610581022 A CN 201610581022A CN 106204335 A CN106204335 A CN 106204335A
- Authority
- CN
- China
- Prior art keywords
- electricity price
- user
- power load
- data
- load data
- 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
- 230000005611 electricity Effects 0.000 title claims abstract description 113
- 238000000034 method Methods 0.000 title claims abstract description 38
- 230000005856 abnormality Effects 0.000 title claims abstract description 20
- 230000002159 abnormal effect Effects 0.000 claims abstract description 27
- 238000012545 processing Methods 0.000 claims description 4
- 238000007689 inspection Methods 0.000 description 6
- 206010008190 Cerebrovascular accident Diseases 0.000 description 5
- 208000006011 Stroke Diseases 0.000 description 5
- 239000011159 matrix material Substances 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 240000002853 Nelumbo nucifera Species 0.000 description 2
- 235000006508 Nelumbo nucifera Nutrition 0.000 description 2
- 235000006510 Nelumbo pentapetala Nutrition 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000003064 k means clustering Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 241000196324 Embryophyta Species 0.000 description 1
- 240000007594 Oryza sativa Species 0.000 description 1
- 235000007164 Oryza sativa Nutrition 0.000 description 1
- 238000012271 agricultural production Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000003973 irrigation Methods 0.000 description 1
- 230000002262 irrigation Effects 0.000 description 1
- 210000003127 knee Anatomy 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 235000009566 rice Nutrition 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000005201 scrubbing Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention provides a kind of electricity price and perform abnormality judgment method, by obtaining the history power load data of each electricity consumption type of user, described history power load data are clustered, generate multiple target load geometric locus, obtain the real-time power load data of user to be detected, calculate the similarity of described real-time power load data and each described target load geometric locus, determine described similarity less than the user presetting similarity threshold and perform abnormal user for electricity price.Visible, use this programme, it is possible to judge electricity price abnormal user, and then ensure the stability of electricity system.
Description
Technical field
The present invention relates to electrical network technical field of measurement and test, particularly relate to a kind of electricity price and perform abnormality judgment method, device and be
System.
Background technology
Along with economic growth and social progress, need for electricity is increased by people day by day, and electrity market expands the most therewith, electric power
Company is annual causes inartful loss huge because of illegal power consumer stealing, and concrete, electricity price performs extremely to include portion
Point low pressure commercial user is not performing properly business electricity price, but mistake performs agricultural production electricity price and rice field irrigation and drainage, threshing electricity price
Deng, occur that high price is low and connect behavior.This be probably client self have a mind to do, it is also possible to be power supply enterprise's manual entry or shelves
Case updates not in time, power utility check deficiency causes the loss of ERM and economy.
Existing marketing inspection method rely primarily on human at periodic intervals patrol and examine, stochastic sampling, the method such as user's report, by right
Substantial amounts of inspection source investigation is analyzed, and workload is big and marketing inspection clue is unintelligible;Take random inspection, and dependence is checked
The experience looking into personnel is the most normal to judge that electricity price performs, but in this case, often cannot because the scope of inspection is little
Find potential abnormal user.
Therefore, under the big data age of nowadays electric power, how to provide a kind of electricity price to perform abnormality judgment method and detect surreptitiously
Electricity behavior is the big technical problem of the most urgently to be resolved hurrily one.
Summary of the invention
The invention provides a kind of electricity price and perform abnormality judgment method, Apparatus and system, it is possible to judge that electricity price is abnormal and use
Family, and then ensure the stability of electricity system.
The invention provides a kind of electricity price and perform abnormality judgment method, including:
Obtain the history power load data of each electricity consumption type of user;
Described history power load data are clustered, generates multiple target load geometric locus;
Obtain the real-time power load data of user to be detected;
Calculate the similarity of described real-time power load data and each described target load geometric locus;
Determine described similarity and perform abnormal user less than the user presetting similarity threshold for electricity price.
Preferably, also include:
Store described target load geometric locus, build electricity price data base.
Preferably, also include:
Determine in described electricity price data base, the electricity consumption class corresponding with the similarity maximum of described real-time power load data
Type is the electricity consumption type that described electricity price performs abnormal user.
Preferably, after the history power load data of described acquisition each electricity consumption type of user, also include:
According to box traction substation, described history power load data are carried out data process.
Preferably, described described history power load data are clustered, generate multiple target load geometric locus, bag
Include:
According to cosine similitude clustering center selection rule, determine cluster centre;
The load geometric locus with described cluster centre with same load fluctuation tendency is defined as a class.
A kind of electricity price performs abnormality judgment method device, including:
First acquisition module, for obtaining the history power load data of each electricity consumption type of user;
Cluster module, for clustering described history power load data, generates multiple target load geometric locus;
Second acquisition module, for obtaining the real-time power load data of user to be detected;
Computing module, similar to each described target load geometric locus for calculating described real-time power load data
Degree;
First determines module, for determining that described similarity performs exception less than the user presetting similarity threshold for electricity price
User.
Preferably, also include:
Memory module, is used for storing described target load geometric locus, builds electricity price data base;
Second determines module, is used for determining in described electricity price data base, with the similarity of described real-time power load data
The electricity consumption type that maximum is corresponding is the electricity consumption type that described electricity price performs abnormal user.
Preferably, also include:
Data processing module, for carrying out data process according to box traction substation to described history power load data.
Preferably, described cluster module includes:
Determine unit, for according to cosine similitude clustering center selection rule, determine cluster centre;
Cluster cell, for being defined as the load geometric locus with described cluster centre with same load fluctuation tendency
One class.
A kind of electricity price performs extremely to judge system, and the electricity price above-mentioned including any one performs abnormity judgement set.
From such scheme, the invention provides a kind of electricity price and perform abnormality judgment method by obtaining each electricity consumption type
Described history power load data are clustered by the history power load data of user, generate multiple target load track bent
Line, obtains the real-time power load data of user to be detected, calculates described real-time power load data and bears with each described target
The similarity of lotus geometric locus, determines described similarity less than the user presetting similarity threshold and performs abnormal user for electricity price.
Visible, use this programme, it is possible to judge electricity price abnormal user, and then ensure the stability of electricity system.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
In having technology to describe, the required accompanying drawing used is briefly described, it should be apparent that, the accompanying drawing in describing below is only this
Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, it is also possible to
Other accompanying drawing is obtained according to these accompanying drawings.
Fig. 1 is the schematic flow sheet that a kind of electricity price disclosed in the embodiment of the present invention performs abnormality judgment method;
Fig. 2 is the structural representation that a kind of electricity price disclosed in the embodiment of the present invention performs abnormity judgement set.
Detailed description of the invention
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Describe, it is clear that described embodiment is only a part of embodiment of the present invention rather than whole embodiments wholely.Based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under not making creative work premise
Embodiment, broadly falls into the scope of protection of the invention.
As it is shown in figure 1, a kind of electricity price execution abnormality judgment method provided for the embodiment of the present invention, including:
S1, obtain the history power load data of each electricity consumption type of user;
First from metering with marketing system, extract the use of the different electricity consumption in different regions type (electricity price execution) user respectively
Electricity data.When extracting 24 day of user's history power load data, the present invention combines the electricity price of inspection in the past and performs abnormal case
By suspicion abnormal user and history, example storehouse, has found out that abnormal user sample weeds out, form electricity price and perform normal users Sample Storehouse.
S2, described history power load data are clustered, generate multiple target load geometric locus;
Preferably, described described history power load data are clustered, generate multiple target load geometric locus, bag
Include:
According to cosine similitude clustering center selection rule, determine cluster centre;
The load geometric locus with described cluster centre with same load fluctuation tendency is defined as a class.
Concrete, electricity price is performed normal users historical load data and carries out clustering processing.The present invention proposes to cluster load
Trajectory analysis method, comprises the following steps:
1, initializing clusters number interval isAnd use in a kind of succinct quickly similar initial clustering of cosine
Heart selection rule chooses initial cluster center.
2, the 1st step cluster uses the clustering algorithm using cosine similarity as similarity measurements flow function to customer charge track
Classification, the load curve that will have like load fluctuation trend is classified as a class.
3, to each type load track of output after the 1st step cluster using based on Euclidean distance as the clustering algorithm of metric function
Its 2nd step is instructed to cluster.
4, the clusters number initializing load track the 2nd step cluster is intervalPress Euclidean distance initial clustering again
Center selection rule chooses all kinds of initial cluster center.
5, determine, by Euclidean distance Cluster Validity Index, the preferable clustering number mesh that load track the 2nd step clusters, output
Whole load tracks after two step clusters.
6, its typical load track is taken out, maximum Euclidean distance threshold value, minimum phase in calculating the class of each type load track collection
Seemingly spend threshold value, form industry typical load track storehouse and threshold library.
Wherein, the 1st step cluster uses clustering algorithm based on cosine similarity.X=[X1,X2,...,Xn-λ]TPre-for data
Customer charge track data sample after process, two groups of load track vector Xi,XjCosine similarity C be expressed as
Sensitive to initial cluster center for k-means clustering algorithm, randomly selecting of initial cluster center easily causes
The problem of object function local minimization, proposes the initial cluster center selection rule of a kind of applicable cosine similarity criterion, becomes
It is randomly provided initial value for have purpose to choose cluster centre by rule.
X=[X1,X2,...,Xn-λ]TBeing the sample after data process, in determining sample initial cluster center class, sample is with poly-
Apoplexy due to endogenous wind maximum similarity threshold value a in the heartcosWith clusters number k, initial cluster center selecting step is:
Calculate the cosine similarity of any two groups of load track vector in sample, and generate cosine similarity matrix S, by phase
It is set to a class, as first initial cluster center like spending two the highest electricity consumption track vector;
Select according to similarity matrix S and be below threshold value a with two load track vector similarities of the first kindcosElectricity consumption
Track vector, and select the highest two the load track vector of similarity as a class in these load track vector, and define
It is second initial cluster center;
In like manner, select in remaining load track and the load track vector similarity of above two initial cluster centers
Both less than threshold value acosLoad track.And two the highest for similarity load tracks are classified as a class, it is defined as the 3rd and initially gathers
Class center;
Repeat the above steps, till finding k class.
S3, obtain the real-time power load data of user to be detected;
S4, calculate the similarity of described real-time power load data and each described target load geometric locus;
When determining the 1st step clusters number, k need not give in advance, but needs to limit the border of k:Root again
Optimal cluster number is chosen according to clustering and discriminant index.To the cluster using cosine similarity as tolerance, here with classics
Clustering Effect appraisal procedure based on figure on the basis of propose new judgment criteria and select suitable clusters number, judging quota
It is expressed as
Wherein, Ci、CjFor the data acquisition system of all kinds of bunches, nkThe user's number of samples comprised for class bunch k.
V index increases along with being incremented by of clusters number, and clusters number is not The more the better.Here, use elbow method,
Determine the value of k.
Along with the increase of cluster numbers, the similar degree in the class sum of each class can increase, and between class, object similarity sum can subtract
Few.This is because there is more class can capture thinner data object, increasingly similar between apoplexy due to endogenous wind object.Therefore, Yi Zhongxuan
The heuristic method selecting correct cluster numbers is, uses judging quota V about the knee of curve of class number.When V functional value increase tendency
Time no longer substantially, definition k is suitable clusters number.
2nd step cluster uses k-means clustering algorithm based on Euclidean distance.Space in conjunction with customer charge track vector
Characteristic distributions, it is proposed that the empirical equation of Euclidean distance cluster initial center selected threshold parameter is set.
Definition 1: according to the Euclidean distance between spatially user power utilization track vector, maximum 2 users of diversity it
Between standard deviation maximum, it is assumed that k class to be divided into, it is determined that apoplexy due to endogenous wind minimum euclidean distance threshold expression in the heart during initial cluster center
It is defined as
Determine the 2nd step clusters number k and corresponding minimum euclidean distance threshold value adist, initial cluster center selecting step
For:
1) calculate the distance between arbitrary sample, and generate Distance matrix D, closest 2 samples are set to 1 class, and take 2
Individual center of a sample is first initial cluster center;
2) according to minimum euclidean distance threshold value adist, utilize distance matrix to select the distance with the 1st 2 samples of class both greater than
adistAll samples, and in these samples, nearest 2 samples of chosen distance are a class, as the 2nd initial cluster center;
3) in like manner, remaining sample finds the sample distance both greater than a with above 2 initial cluster centersdist's
Sample, and therefrom nearest 2 of chosen distance are the 3rd initial cluster center;
4) repeat the above steps, till finding k class.
Assuming that cluster numbers is k, the data acquisition system of all kinds of bunches is Ck, ckFor all kinds of bunches of CkCluster centre, each apoplexy due to endogenous wind comprises
Number of samples be nk, i.e.X1,j、X2,jFor the load in different user j moment, X1、X2Between Euclidean distance
It is expressed as
Davies-Bouldinindicator (DBI) index comprehensive is used to consider compactedness and the class of Euclidean distance in class
Between dispersibility, computing formula is
Wherein:
In formula: d (Ck) and d (Cj) it is Euclidean distance in class bunch;d(ck,cj) it is the distance between typical load track.
In class, Euclidean distance computing formula is expressed as
IDBIEuclidean distance and the business of each cluster centre spacing in index characterization class, its value is the least, the tightest in showing class
Gathering, distinguish the most obvious between class, Clustering Effect is the best.
By limiting the 2nd step clusters number k, i.e.Taking out makes Cluster Validity DBI index minimum corresponding
K, namely preferable clustering number mesh K.
Calculate user trajectory data XiWith generic typical load track data ckEuclidean distance similarity sim1(Xi,
ck) and cosine similarity sim2(Xi,ck)
sim1(Xi,ck)=d (Xi,ck)
sim2(Xi,ck)=cos (Xi,ck)
Obtain minimum cosine similarity threshold value minSim2(k) and maximum European similarity threshold maxSim1(k), the most defeated
Go out all industry typical load tracks and similarity threshold thereof after the 2nd step cluster, form track storehouse and threshold library.
S5, determine described similarity less than preset similarity threshold user for electricity price execution abnormal user.
Maximum Euclidean distance threshold in the typical load track obtaining zones of different different industries (electricity price classification) and class thereof
After value, minimum cosine similarity threshold value, by comparing real-time daily load curve data and the typical load geometric locus number of user
According to similarity differentiate whether user deviates electricity price and perform normal users colony electrical characteristics track, thus show that suspicion is abnormal
User.Comprise the concrete steps that:
The method real-time daily load data to user are analyzed by combination distinguishing based on cosine similarity and Euclidean distance
Detect, it can be deduced that the amplitude of industry new samples deviation normal electricity consumption typical load track sample.In specifying every apoplexy due to endogenous wind class
Sample is that such uses the European threshold value of maximum of typical user of electrical characteristics, cosine with the Euclidean distance maximum of typical load track
Similarity minima is minimum cosine threshold value, by calculating each typical load track coefficient of deviation ε, takes its maximum and is expressed as
Big coefficient of deviation threshold value is to be calculated as follows:
Two threshold value exception coefficients are first introduced at this:
Definition 2: European coefficient of deviation refers to Euclidean distance and its maximum Europe of sample and its typical load track in class
The ratio of formula threshold value, is expressed as
Definition 3: cosine coefficient of deviation refers to minimum cosine similarity threshold value and sample in class and its typical load track
The ratio of similarity, is expressed as
In class, sample is expressed as with its typical load track coefficient of deviation:
ε=ε1+ε2
By calculating the coefficient of deviation ε of new samples and the sector each typical load track, then compare it maximum allowable partially
From coefficient, when the coefficient of deviation of user Yu industry each typical load track is both greater than its maximum allowable coefficient of deviation threshold value, should
User is labeled as electricity price and performs abnormal suspicion user.
Preferably, also include:
Store described target load geometric locus, build electricity price data base.
Preferably, also include:
Determine in described electricity price data base, the electricity consumption class corresponding with the similarity maximum of described real-time power load data
Type is the electricity consumption type that described electricity price performs abnormal user.
Further clear and definite electricity price perform the electricity price classification of the abnormal actual execution of suspicion user can be power supply enterprise retrieve through
Ji loss.First, the typical electricity consumption action trail of industry-by-industry put together formation typical case electricity consumption action trail storehouse;Then count
Calculation suspicion user and the coefficient of deviation ε of the every kind of typical load curve in other industry exemplary trajectory storehouse, then compare it maximum allowable
Coefficient of deviation threshold value, uses less than the typical load track place industry of maximum deviation coefficient threshold coefficient of deviation as this suspicion
Family may the actual electricity price classification performed.
Preferably, after the history power load data of described acquisition each electricity consumption type of user, also include:
According to box traction substation, described history power load data are carried out data process.
The load data detected for metering system occurs losing under hardware and software fault, communication disruption or signal disturbing
Genuine problem, uses box traction substation (box-plot) method to carry out rejecting outliers.
Box traction substation is the method for the exceptional value that a kind of figure is similar and labelling occurs, single argument large sample is compared by it to be had
Effect, convenient directly perceived.It is divided into mile abnormality value and extreme exceptional value two kinds.Definition:
IfThen x can be labeled as exceptional value (outlier), wherein IQR=
Q3-Q1。
Reject daily load track data in the sample and there is the user of Mutiple-outliers, when the data exception of certain load curve
Amount reach collection capacity 10% or more than, it is believed that this curve is invalid, note reject invalid curve sum be λ, then use Gauss put down
The load curve that sliding filtering technique is less than 10% to abnormal amount is removed noise processed.After data scrubbing, note X is (n-
λ) the matrix that bar effective daily load track is constituted.
Visible, use this programme, it is possible to judge electricity price abnormal user, and then ensure the stability of electricity system.
Except this, the present embodiment additionally provides a kind of electricity price and performs abnormality judgment method device, as in figure 2 it is shown, include:
First acquisition module 100, for obtaining the history power load data of each electricity consumption type of user;
Cluster module 200, for clustering described history power load data, generates multiple target load track bent
Line;
Second acquisition module 300, for obtaining the real-time power load data of user to be detected;
Computing module 400, for calculating described real-time power load data and each described target load geometric locus
Similarity;
First determines module 500, performs for electricity price less than the user presetting similarity threshold for determining described similarity
Abnormal user.
Preferably, also include:
Memory module, is used for storing described target load geometric locus, builds electricity price data base;
Second determines module, is used for determining in described electricity price data base, with the similarity of described real-time power load data
The electricity consumption type that maximum is corresponding is the electricity consumption type that described electricity price performs abnormal user.
Preferably, also include:
Data processing module, for carrying out data process according to box traction substation to described history power load data.
Preferably, described cluster module includes:
Determine unit, for according to cosine similitude clustering center selection rule, determine cluster centre;
Cluster cell, for being defined as the load geometric locus with described cluster centre with same load fluctuation tendency
One class.
A kind of electricity price performs extremely to judge system, and the electricity price above-mentioned including any one performs abnormity judgement set.
From such scheme, the invention provides a kind of electricity price and perform abnormality judgment method by obtaining each electricity consumption type
Described history power load data are clustered by the history power load data of user, generate multiple target load track bent
Line, obtains the real-time power load data of user to be detected, calculates described real-time power load data and bears with each described target
The similarity of lotus geometric locus, determines described similarity less than the user presetting similarity threshold and performs abnormal user for electricity price.
Visible, use this programme, it is possible to judge electricity price abnormal user, and then ensure the stability of electricity system.
If the function described in the present embodiment method realizes and as independent product pin using the form of SFU software functional unit
When selling or use, a calculating device-readable can be stored in and take in storage medium.Based on such understanding, the embodiment of the present invention
The part contributing prior art or the part of this technical scheme can embody with the form of software product, and this is soft
Part product is stored in a storage medium, including some instructions with so that calculating equipment (can be personal computer,
Server, mobile computing device or the network equipment etc.) perform completely or partially walking of method described in each embodiment of the present invention
Suddenly.And aforesaid storage medium includes: USB flash disk, portable hard drive, read only memory (ROM, Read-Only Memory), deposit at random
The various media that can store program code such as access to memory (RAM, Random Access Memory), magnetic disc or CD.
In this specification, each embodiment uses the mode gone forward one by one to describe, and what each embodiment stressed is and other
The difference of embodiment, between each embodiment, same or similar part sees mutually.
Described above to the disclosed embodiments, makes professional and technical personnel in the field be capable of or uses the present invention.
Multiple amendment to these embodiments will be apparent from for those skilled in the art, as defined herein
General Principle can realize without departing from the spirit or scope of the present invention in other embodiments.Therefore, the present invention
It is not intended to be limited to the embodiments shown herein, and is to fit to and principles disclosed herein and features of novelty phase one
The widest scope caused.
Claims (10)
1. an electricity price performs abnormality judgment method, it is characterised in that including:
Obtain the history power load data of each electricity consumption type of user;
Described history power load data are clustered, generates multiple target load geometric locus;
Obtain the real-time power load data of user to be detected;
Calculate the similarity of described real-time power load data and each described target load geometric locus;
Determine described similarity and perform abnormal user less than the user presetting similarity threshold for electricity price.
A kind of electricity price the most according to claim 1 performs abnormality judgment method, it is characterised in that also include:
Store described target load geometric locus, build electricity price data base.
A kind of electricity price the most according to claim 2 performs abnormality judgment method, it is characterised in that also include:
Determining in described electricity price data base, the electricity consumption type corresponding with the similarity maximum of described real-time power load data is
Described electricity price performs the electricity consumption type of abnormal user.
A kind of electricity price the most according to claim 1 performs abnormality judgment method, it is characterised in that in each electricity consumption of described acquisition
After the history power load data of type of user, also include:
According to box traction substation, described history power load data are carried out data process.
A kind of electricity price the most according to claim 1 performs abnormality judgment method, it is characterised in that described use described history
Electric load data cluster, and generate multiple target load geometric locus, including:
According to cosine similitude clustering center selection rule, determine cluster centre;
The load geometric locus with described cluster centre with same load fluctuation tendency is defined as a class.
6. an electricity price performs abnormality judgment method device, it is characterised in that including:
First acquisition module, for obtaining the history power load data of each electricity consumption type of user;
Cluster module, for clustering described history power load data, generates multiple target load geometric locus;
Second acquisition module, for obtaining the real-time power load data of user to be detected;
Computing module, for calculating the similarity of described real-time power load data and each described target load geometric locus;
First determines module, performs abnormal use less than the user presetting similarity threshold for electricity price for determining described similarity
Family.
A kind of electricity price the most according to claim 6 performs abnormity judgement set, it is characterised in that also include:
Memory module, is used for storing described target load geometric locus, builds electricity price data base;
Second determines module, is used for determining in described electricity price data base, maximum with the similarity of described real-time power load data
The electricity consumption type that electricity consumption type is described electricity price execution abnormal user that value is corresponding.
A kind of electricity price the most according to claim 6 performs abnormity judgement set, it is characterised in that also include:
Data processing module, for carrying out data process according to box traction substation to described history power load data.
A kind of electricity price the most according to claim 6 performs abnormity judgement set, it is characterised in that described cluster module bag
Include:
Determine unit, for according to cosine similitude clustering center selection rule, determine cluster centre;
Cluster cell, for being defined as one by the load geometric locus with described cluster centre with same load fluctuation tendency
Class.
10. an electricity price performs extremely to judge system, it is characterised in that include as described in any one in claim 6-9
Electricity price performs abnormity judgement set.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610581022.0A CN106204335A (en) | 2016-07-21 | 2016-07-21 | A kind of electricity price performs abnormality judgment method, Apparatus and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610581022.0A CN106204335A (en) | 2016-07-21 | 2016-07-21 | A kind of electricity price performs abnormality judgment method, Apparatus and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106204335A true CN106204335A (en) | 2016-12-07 |
Family
ID=57492078
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610581022.0A Pending CN106204335A (en) | 2016-07-21 | 2016-07-21 | A kind of electricity price performs abnormality judgment method, Apparatus and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106204335A (en) |
Cited By (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107145966A (en) * | 2017-04-12 | 2017-09-08 | 山大地纬软件股份有限公司 | Logic-based returns the analysis and early warning method of opposing electricity-stealing of probability analysis Optimized model |
CN107396292A (en) * | 2017-07-29 | 2017-11-24 | 陈剑桃 | A kind of soil humidity information for precision agriculture obtains system |
CN108900975A (en) * | 2018-06-05 | 2018-11-27 | 广州杰赛科技股份有限公司 | The detection method and device of user's motion track, equipment, storage medium |
CN109189771A (en) * | 2018-08-17 | 2019-01-11 | 浙江捷尚视觉科技股份有限公司 | It is a kind of based on offline and on-line talking model data library cleaning method |
CN109492048A (en) * | 2019-01-21 | 2019-03-19 | 国网河北省电力有限公司经济技术研究院 | A kind of extracting method, system and the terminal device of power consumer electrical characteristics |
CN109543943A (en) * | 2018-10-17 | 2019-03-29 | 国网辽宁省电力有限公司电力科学研究院 | A kind of electricity price inspection execution method based on big data deep learning |
CN109558467A (en) * | 2018-12-07 | 2019-04-02 | 国网江苏省电力有限公司常州供电分公司 | The recognition methods of electricity consumption class of subscriber and system |
CN109636667A (en) * | 2018-12-07 | 2019-04-16 | 国网江苏省电力有限公司扬州供电分公司 | A kind of low-voltage customer multiplexing electric abnormality detection method based on user's week electrical feature |
CN109739736A (en) * | 2018-12-13 | 2019-05-10 | 浙江每日互动网络科技股份有限公司 | A kind of user's anomaly detection method based on mobile terminal data |
CN110147871A (en) * | 2019-04-17 | 2019-08-20 | 中国电力科学研究院有限公司 | A kind of stealing detection method and system based on SOM neural network Yu K- mean cluster |
WO2019184131A1 (en) * | 2018-03-29 | 2019-10-03 | 清华大学 | Entropy method and density clustering method integrated power stealing detection method and apparatus |
CN110503145A (en) * | 2019-08-21 | 2019-11-26 | 广东电网有限责任公司 | A kind of typical load curve acquisition methods based on k-shape cluster |
CN110825724A (en) * | 2019-10-11 | 2020-02-21 | 深圳供电局有限公司 | User charging data exception interception system and method in electricity price system |
CN110851892A (en) * | 2019-11-07 | 2020-02-28 | 山东大学 | Park level comprehensive energy system aided design method and system |
CN110955650A (en) * | 2019-11-20 | 2020-04-03 | 云南电网有限责任公司电力科学研究院 | Cleaning method for out-of-tolerance data of digital hygrothermograph in standard laboratory |
CN111223007A (en) * | 2019-12-31 | 2020-06-02 | 深圳供电局有限公司 | User abnormal electricity utilization behavior analysis early warning method, device, equipment and medium |
CN111709790A (en) * | 2020-06-19 | 2020-09-25 | 广东电网有限责任公司 | Method, device, equipment and storage medium for identifying abnormal electricity price of day-ahead market |
CN112095292A (en) * | 2019-05-28 | 2020-12-18 | 青岛海尔洗衣机有限公司 | Abnormity detection method for washing machine |
US10917426B2 (en) | 2017-12-29 | 2021-02-09 | Advanced New Technologies Co., Ltd. | Method and device for determining data anomaly |
CN112541016A (en) * | 2020-11-26 | 2021-03-23 | 南方电网数字电网研究院有限公司 | Power consumption abnormality detection method, device, computer equipment and storage medium |
CN113450550A (en) * | 2021-06-24 | 2021-09-28 | 张�杰 | Alarming method and device in blood transfusion process |
CN117787572A (en) * | 2024-02-27 | 2024-03-29 | 国网山西省电力公司临汾供电公司 | Abnormal electricity utilization user identification method and device, storage medium and electronic equipment |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103036231A (en) * | 2012-12-07 | 2013-04-10 | 温州电力局 | Forecasting method, device, and upper computer of power load |
CN105574642A (en) * | 2015-11-06 | 2016-05-11 | 广东工业大学 | Smart grid big data-based electricity price execution checking method |
CN105608512A (en) * | 2016-03-24 | 2016-05-25 | 东南大学 | Short-term load forecasting method |
-
2016
- 2016-07-21 CN CN201610581022.0A patent/CN106204335A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103036231A (en) * | 2012-12-07 | 2013-04-10 | 温州电力局 | Forecasting method, device, and upper computer of power load |
CN105574642A (en) * | 2015-11-06 | 2016-05-11 | 广东工业大学 | Smart grid big data-based electricity price execution checking method |
CN105608512A (en) * | 2016-03-24 | 2016-05-25 | 东南大学 | Short-term load forecasting method |
Cited By (31)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107145966A (en) * | 2017-04-12 | 2017-09-08 | 山大地纬软件股份有限公司 | Logic-based returns the analysis and early warning method of opposing electricity-stealing of probability analysis Optimized model |
CN107396292A (en) * | 2017-07-29 | 2017-11-24 | 陈剑桃 | A kind of soil humidity information for precision agriculture obtains system |
CN107396292B (en) * | 2017-07-29 | 2021-04-16 | 黑龙江禾发农业科技有限公司 | Soil humidity information acquisition system for precision agriculture |
US10917424B2 (en) | 2017-12-29 | 2021-02-09 | Advanced New Technologies Co., Ltd. | Method and device for determining data anomaly |
US10917426B2 (en) | 2017-12-29 | 2021-02-09 | Advanced New Technologies Co., Ltd. | Method and device for determining data anomaly |
WO2019184131A1 (en) * | 2018-03-29 | 2019-10-03 | 清华大学 | Entropy method and density clustering method integrated power stealing detection method and apparatus |
CN108900975A (en) * | 2018-06-05 | 2018-11-27 | 广州杰赛科技股份有限公司 | The detection method and device of user's motion track, equipment, storage medium |
CN109189771A (en) * | 2018-08-17 | 2019-01-11 | 浙江捷尚视觉科技股份有限公司 | It is a kind of based on offline and on-line talking model data library cleaning method |
CN109543943A (en) * | 2018-10-17 | 2019-03-29 | 国网辽宁省电力有限公司电力科学研究院 | A kind of electricity price inspection execution method based on big data deep learning |
CN109543943B (en) * | 2018-10-17 | 2023-07-25 | 国网辽宁省电力有限公司电力科学研究院 | Electric price checking execution method based on big data deep learning |
CN109636667A (en) * | 2018-12-07 | 2019-04-16 | 国网江苏省电力有限公司扬州供电分公司 | A kind of low-voltage customer multiplexing electric abnormality detection method based on user's week electrical feature |
CN109558467B (en) * | 2018-12-07 | 2020-09-15 | 国网江苏省电力有限公司常州供电分公司 | Method and system for identifying user category of electricity utilization |
CN109558467A (en) * | 2018-12-07 | 2019-04-02 | 国网江苏省电力有限公司常州供电分公司 | The recognition methods of electricity consumption class of subscriber and system |
CN109739736B (en) * | 2018-12-13 | 2022-07-08 | 每日互动股份有限公司 | User abnormal behavior detection method based on mobile terminal data |
CN109739736A (en) * | 2018-12-13 | 2019-05-10 | 浙江每日互动网络科技股份有限公司 | A kind of user's anomaly detection method based on mobile terminal data |
CN109492048A (en) * | 2019-01-21 | 2019-03-19 | 国网河北省电力有限公司经济技术研究院 | A kind of extracting method, system and the terminal device of power consumer electrical characteristics |
CN110147871A (en) * | 2019-04-17 | 2019-08-20 | 中国电力科学研究院有限公司 | A kind of stealing detection method and system based on SOM neural network Yu K- mean cluster |
CN112095292B (en) * | 2019-05-28 | 2023-06-30 | 重庆海尔洗衣机有限公司 | Abnormality detection method for washing machine |
CN112095292A (en) * | 2019-05-28 | 2020-12-18 | 青岛海尔洗衣机有限公司 | Abnormity detection method for washing machine |
CN110503145A (en) * | 2019-08-21 | 2019-11-26 | 广东电网有限责任公司 | A kind of typical load curve acquisition methods based on k-shape cluster |
CN110825724A (en) * | 2019-10-11 | 2020-02-21 | 深圳供电局有限公司 | User charging data exception interception system and method in electricity price system |
CN110825724B (en) * | 2019-10-11 | 2023-08-08 | 深圳供电局有限公司 | System and method for intercepting user charging data abnormality in electricity price system |
CN110851892A (en) * | 2019-11-07 | 2020-02-28 | 山东大学 | Park level comprehensive energy system aided design method and system |
CN110955650A (en) * | 2019-11-20 | 2020-04-03 | 云南电网有限责任公司电力科学研究院 | Cleaning method for out-of-tolerance data of digital hygrothermograph in standard laboratory |
CN111223007A (en) * | 2019-12-31 | 2020-06-02 | 深圳供电局有限公司 | User abnormal electricity utilization behavior analysis early warning method, device, equipment and medium |
CN111709790B (en) * | 2020-06-19 | 2022-01-07 | 广东电网有限责任公司 | Method, device, equipment and storage medium for identifying abnormal electricity price of day-ahead market |
CN111709790A (en) * | 2020-06-19 | 2020-09-25 | 广东电网有限责任公司 | Method, device, equipment and storage medium for identifying abnormal electricity price of day-ahead market |
CN112541016A (en) * | 2020-11-26 | 2021-03-23 | 南方电网数字电网研究院有限公司 | Power consumption abnormality detection method, device, computer equipment and storage medium |
CN113450550A (en) * | 2021-06-24 | 2021-09-28 | 张�杰 | Alarming method and device in blood transfusion process |
CN117787572A (en) * | 2024-02-27 | 2024-03-29 | 国网山西省电力公司临汾供电公司 | Abnormal electricity utilization user identification method and device, storage medium and electronic equipment |
CN117787572B (en) * | 2024-02-27 | 2024-05-17 | 国网山西省电力公司临汾供电公司 | Abnormal electricity utilization user identification method and device, storage medium and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106204335A (en) | A kind of electricity price performs abnormality judgment method, Apparatus and system | |
Hyndman et al. | Large-scale unusual time series detection | |
US20130103656A1 (en) | Event identification | |
Li et al. | Dissecting ethereum blockchain analytics: What we learn from topology and geometry of the ethereum graph? | |
AU2017274576B2 (en) | Classification of log data | |
Smirnov et al. | Time series classification with recurrent neural networks | |
Hung et al. | Customer segmentation using hierarchical agglomerative clustering | |
Kim et al. | Detecting the change of customer behavior based on decision tree analysis | |
Oprea et al. | Machine learning classification algorithms and anomaly detection in conventional meters and Tunisian electricity consumption large datasets | |
CN109446193A (en) | It opposes electricity-stealing model generating method and device | |
CN109934301B (en) | Power load cluster analysis method, device and equipment | |
CN110133488A (en) | Switchgear health status evaluation method and device based on optimal number of degrees | |
Vu et al. | Feature selection methods and sampling techniques to financial distress prediction for Vietnamese listed companies | |
CN109374063B (en) | Cluster management-based transformer anomaly detection method, device and equipment | |
WO2011058328A2 (en) | Event identification | |
Wang et al. | An adaptive high-voltage direct current detection algorithm using cognitive wavelet transform | |
KR101879829B1 (en) | Method and device for detecting frauds by using click log data | |
CN107274025B (en) | System and method for realizing intelligent identification and management of power consumption mode | |
CA3035539A1 (en) | Systems and methods for measuring collected content significance | |
Petladwala et al. | Canonical correlation based feature extraction with application to anomaly detection in electric appliances | |
CN109118250A (en) | Electricity market main body act of unfair competition evaluation method and device | |
CN113589034A (en) | Electricity stealing detection method, device, equipment and medium for power distribution system | |
Smith et al. | Predicting congressional votes based on campaign finance data | |
Hu et al. | Utilizing users' tipping points in E-commerce Recommender systems | |
Jiang et al. | Comparing Electricity Consumer Categories Based on Load Pattern Clustering with Their Natural Types |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into 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: 20161207 |