CN108399221A - Indoor electric equipment classifying identification method and system based on big data association analysis - Google Patents
Indoor electric equipment classifying identification method and system based on big data association analysis Download PDFInfo
- Publication number
- CN108399221A CN108399221A CN201810141174.8A CN201810141174A CN108399221A CN 108399221 A CN108399221 A CN 108399221A CN 201810141174 A CN201810141174 A CN 201810141174A CN 108399221 A CN108399221 A CN 108399221A
- Authority
- CN
- China
- Prior art keywords
- equipment
- cluster
- electric
- electric parameter
- big 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.)
- Granted
Links
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
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Medical Informatics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of indoor electric equipment classifying identification methods and system based on big data association analysis, acquire the electrical parameters of electrical equipment；According to electric parameter information, each harmonic information is extracted, the one-dimensional matrix of combination of the proportion and current value shared by each harmonic is obtained, using DBSCAN clusterings to combining one-dimensional matrix, carries out clustering, output cluster division result and cluster barycenter；Type is manually demarcated according to electrical equipment, determine cluster classification type, the type identification for not identifying equipment for carrying out belonging to the cluster with cluster classification type, when there is new equipment addition, or when in mobile device to other sockets, the electric parameter of the equipment acquired by the socket and the Euclidean distance size of other cluster barycenter determine device type.
Description
Technical field
The present invention relates to a kind of indoor electric equipment classifying identification methods and system based on big data association analysis.
Background technology
With the universal development with cloud of Internet of Things, a large amount of electrical equipment is linked by modules such as intelligent sockets
In Internet of things system network, acquisition and the processing of electrical parameters of equipment information become more convenient.Currently to the mark of device type
Know mostly by way of manual entry, with the operation of Internet of things system, high in the clouds will build up on the electrical equipment parameter information of magnanimity,
The automatic identification of device type can be realized by the method for big data association analysis.
Existing device class method is mainly realized according to the electric load feature of equipment, paper《Based on big data
The household appliance recognizer of Bayes classification》By analyzing the classification of the behavior and electrical behavior realization equipment of people, this method needs
The a large amount of data of long time integration under experimental situation that will be more harsh, the interference by people's behavior is larger, similar to electrical behavior
Device resolution it is low.Paper《Electrical equipment harmonic characteristic research based on NILM》By the harmonic characteristic for studying electrical equipment
The Classification and Identification of equipment is carried out, it is to the similar device resolution of harmonic characteristic low.Two papers are finally all made of Bayes point
The method of class realizes that device class, bayes classification method belong to supervised learning, need to know in advance operation electric parameter and its
Classification, this method assumes that data are mutual indepedent, sensitive to abnormal point, there is a problem of that flexibility is low, applicability is weaker.
Invention content
The present invention is to solve the above-mentioned problems, it is proposed that a kind of indoor electric equipment classification based on big data association analysis
Recognition methods and system, the electric parameter when present invention is using its operation of different classes of, different model electrical equipment with it is electrical
Behavior is different, the electrical parameters of equipment information based on magnanimity, and the present invention uses electric parameter by the method for big data DBSCAN
Clustering is carried out to equipment for the data splitting of harmonic wave and electric current Value Data, if some or certain electrical equipments of certain class equipment
Type manually marked, realize the unassorted equipment of such equipment in Internet of Things automatically using existing device type
Classification decision.The clustering that indoor electric equipment is carried out by the method for big data DBSCAN, without there is surveillance requirements
Lower training pattern realizes that device class decision, device type are more various, it can be achieved that finer grain automatically using the participation of user
Device class, model flexibility is preferable；The electric parameter that uses is the data splitting of harmonic wave and electric current Value Data simultaneously, from setting
Standby harmonic characteristic carries out the differentiation of device type with electrical behavioural characteristic, differentiates accuracy rate higher.
To achieve the goals above, the present invention adopts the following technical scheme that：
A kind of indoor electric equipment classifying identification method based on big data association analysis, includes the following steps：
Acquire the electrical parameters of electrical equipment；
The pretreatment for carrying out electric parameter extracts each harmonic information, obtains each harmonic institute according to electric parameter information
The one-dimensional matrix of combination of the proportion and current value that account for；
Electric parameter data are input in Clustering Model, to combining one-dimensional matrix, carry out clustering, output cluster is drawn
Divide result；
If the type of certain class electrical equipment has been marked, using the classification logotype as corresponding cluster that identifies marked；If having
Multiple identification informations realize its of the cluster equipment using the category automatically using the type identification more than proportion as the classification of the cluster
The classification decision of his unfiled equipment；
Device type is determined by the electric parameter of the equipment newly connected and the Euclidean distance size of each cluster barycenter；
By the comparison of the electric parameter feature with other known devices, the base for not identifying equipment more than certain time length is determined
This classification.
Further, electric parameter includes electrical harmonic wave and current value, wherein electrical harmonic wave is the combination of each harmonic.
Further, the electric parameter of acquisition is pre-processed, specifically includes noise processed, missing values processing and normalizing
Change is handled.
Further, the process of clustering includes：
Initialize kernel object set, cluster number of clusters and non-access-sample set；
The radius of neighbourhood is set and includes the minimal amount of point in given neighborhood；
Kernel object is randomly choosed, a kernel object is taken out in current cluster kernel object queue, according to neighborhood distance
Threshold value finds out all neighborhood subsample collection, updates current cluster sample set, updates non-access-sample set, carries out cluster division.
Further, according to the division of cluster, the cluster barycenter of each cluster is calculated using averaging method, when away from certain cluster barycenter it is European away from
It is short from most, while when less than threshold value, it is determined that the cluster belonging to the equipment updates the cluster barycenter of corresponding cluster.
Further, if there is the artificial classification mark mark for having made certain electrical equipment in internet-of-things system of building electric device
Know, using the mark as the classification logotype of corresponding cluster；If there are more people to be identified the equipment, made with the type identification more than number
For the classification of the cluster；
When further, when there is new equipment addition or in mobile device to other sockets, set by what the socket acquired
The Euclidean distance size of standby electric parameter and other cluster barycenter determines device type, when most short away from certain cluster barycenter Euclidean distance,
When simultaneously less than threshold value, it is determined that the cluster belonging to the equipment updates the cluster barycenter of corresponding cluster.
When further, when there is new equipment addition or in mobile device to other sockets, the multiple ginsengs of the equipment are inputted
Number, the cluster belonging to the equipment is determined by KNN algorithms, rear to update cluster barycenter.
For identified equipment does not judge electrical equipment by analyzing its electrical parameters of equipment feature after a period of time
Basic class passes through the electric parameter feature with the other equipments such as air-conditioning, computer, water dispenser for not identifying equipment for a long time
Comparison, determine its basic class.
A kind of indoor electric equipment classifying and identifying system based on big data association analysis, including：
Several Internet of things node, each Internet of things node connect multiple intelligent sockets, and receive each of intelligent socket acquisition
Data are uploaded to cloud server by the electric parameter information of electric appliances operation, Internet of things node according to the communication protocol of standard
It is stored in database；System provides user equipment information typing interface, and typing information includes the classification information of equipment, system fortune
After row a period of time, it will be stored with the electrical equipment parameter information of magnanimity in the database of server, and there are certain customers to institute
The classification of the electrical equipment of management marks；
It is database, real time historical database, equipment identification module etc. to be disposed on the cloud server related；
Further, be stored in the relational database of the cloud server intelligent socket information, electrical equipment information,
Cluster classified types information.
Further, real-time, the history electric parameter information of all kinds of electric operations are stored in real time history relationship library；
Further, the equipment identification module disposed on cloud server extraction equipment from historical data base is electrical
Parameter information normalizes harmonic information and current information, obtains the one-dimensional square of combination of the proportion and current value shared by each harmonic
Battle array carries out clustering, exports cluster division result using DBSCAN clusterings to combining one-dimensional matrix；
Further, the equipment identification module is according to cluster division result, if the type of certain class electrical equipment has been marked,
Using the classification logotype as corresponding cluster that identifies marked；If there is multiple identification informations, using the type identification more than proportion as should
The classification of cluster realizes the classification decision of the unassorted equipment of the cluster equipment using the category automatically；
Device type is determined by the electric parameter of the equipment newly connected and the Euclidean distance size of each cluster barycenter；
By the comparison of the electric parameter feature with other known devices, the base for not identifying equipment more than certain time length is determined
This classification.
Compared with prior art, beneficial effects of the present invention are：
1, the present invention carries out the clustering of indoor electric equipment by the method for big data DBSCAN, without there is supervision
Under the conditions of training pattern, realize device class decision automatically using the participation of user, device type is more various, it can be achieved that relatively thin
The device class of granularity, model flexibility are preferable；
2, the electric parameter that uses of the present invention is for the data splitting of harmonic wave and electric current Value Data, from the harmonic characteristic of equipment and
Electrical behavioural characteristic carries out the differentiation of device type, differentiates accuracy rate higher.
Description of the drawings
The accompanying drawings which form a part of this application are used for providing further understanding of the present application, and the application's shows
Meaning property embodiment and its explanation do not constitute the improper restriction to the application for explaining the application.
Fig. 1 is the system construction drawing of the present invention；
Fig. 2 is the relational database E-R models of the present invention；
Fig. 3 is running example of the present invention；
Specific implementation mode：
The invention will be further described with embodiment below in conjunction with the accompanying drawings.
It is noted that following detailed description is all illustrative, it is intended to provide further instruction to the application.Unless another
It indicates, all technical and scientific terms used herein has usual with the application person of an ordinary skill in the technical field
The identical meanings of understanding.
It should be noted that term used herein above is merely to describe specific implementation mode, and be not intended to restricted root
According to the illustrative embodiments of the application.As used herein, unless the context clearly indicates otherwise, otherwise singulative
It is also intended to include plural form, additionally, it should be understood that, when in the present specification using term "comprising" and/or " packet
Include " when, indicate existing characteristics, step, operation, device, component and/or combination thereof.
In the present invention, term for example "upper", "lower", "left", "right", "front", "rear", "vertical", "horizontal", " side ",
The orientation or positional relationship of the instructions such as "bottom" is to be based on the orientation or positional relationship shown in the drawings, only to facilitate describing this hair
Bright each component or component structure relationship and the relative of determination, not refer in particular to either component or element in the present invention, cannot understand
For limitation of the present invention.
In the present invention, term such as " affixed ", " connected ", " connection " shall be understood in a broad sense, and indicate may be a fixed connection,
Can also be to be integrally connected or be detachably connected；It can be directly connected, it can also be indirectly connected through an intermediary.For
The related scientific research of this field or technical staff can determine the concrete meaning of above-mentioned term in the present invention as the case may be,
It is not considered as limiting the invention.
As shown in Figure 1, the present invention provides a kind of indoor electric equipment classifying identification method based on big data association analysis
With system, harmonic wave, current electrical when the present invention is using different brands, its operation of different classes of, different model electrical equipment
Parameter is different, and the clustering of indoor electric equipment is carried out by the method for big data DBSCAN, automatic using the participation of user
Realize device class decision, it can be achieved that finer grain device class, participate in the scheduling of energy saving optimizing and building energy, to build
It builds Energy Conservation and supplies new approach.
The network architecture of the system of the present invention and patent CN201010176017.4 internet-of-things system of building electric device framves
Structure is identical, and it is database that including intelligent socket, Internet of things node, server, on server, deployment is related, historical data base, is set
Standby Classification and Identification judges algoritic module etc..All electrical equipments are connected to by intelligent socket in Internet of Things, intelligent socket acquisition
The electric parameters such as electric current, voltage, the harmonic wave of all electrical equipments are uploaded in database by node and carry out unified storage.Object
Networked system provides user equipment information typing interface, and typing information includes the classification information of equipment.When one section of system operation
Between after, the electrical equipment parameter information of magnanimity will be stored in the database of server, and have certain customers to the electricity that is managed
The classification of gas equipment marks.
Internet-of-things system of building electric device carries out clustering by the method for big data DBSCAN to equipment first, and
Cluster result is exported, if the type of some or certain electrical equipments of certain class equipment is manually marked, utilizes artificial mark class
Type realizes the classification decision of the unassorted equipment of such equipment in electrical equipment Internet of Things automatically.For not identifying equipment,
The electric parameter feature for comparing itself and air-conditioning, computer, water dispenser etc., determines its basic class.
A kind of indoor electric equipment classifying and identifying system based on big data association analysis includes with lower part：
It can be with certain frequency collection electrical equipment harmonic parameters, the intelligent socket of current value and voltage value；
It can carry out the Internet of things node of data conversion and upload；
It can carry out real-time, the historical data base of electric parameter data storage；
It can carry out data organization and pretreated module；
The intelligent socket can at least be adopted with certain frequency collection electrical equipment harmonic parameters, current value, harmonic wave
Collect the 20th subharmonic；
The Internet of things node has the function of data conversion and upload；
The intelligent socket is connect with Internet of things node, and the electrical harmonic parameters of acquisition are sent to Internet of things node, object
Networked node receives the data of intelligent socket, data is transmitted to according to the communication protocol of standard in real-time data base, Jin Erzhuan
It is stored in historical data base；
The electric parameter includes electrical harmonic wave, electric current equivalence, wherein electrical harmonic wave is the combination of multiple harmonic waves, including base
Wave, second harmonic, triple-frequency harmonics ...
Be deployed with database and device class algorithm on cloud server, user by the ends PC can recording device information, close
Join intelligent socket module.Intelligent socket acquires the electric parameter information of all kinds of electric operations, is pressed data by Internet of things node
The communication protocol of sighting target standard is uploaded in the database of cloud server and is stored.System operation for a period of time after, on server will
Store a large amount of electric equipment operation parameter information；
It is database, real time historical database, equipment identification module etc. to be disposed on the cloud server related；
Further, as shown in Fig. 2, being stored with intelligent socket information in the relational database of the cloud server, using
Electric electrical equipment information, cluster classified types.The ID of intelligent socket storage receptacle, socket title；Equipment list storage device ID, equipment
Title, manual identification's type, system identification cluster ID, association socket ID；Cluster classified types table is stored with device cluster ID, device cluster class
Not, device cluster barycenter；Wherein, socket ID, device id, device cluster ID have uniqueness.
Further, the equipment identification module disposed on cloud server extraction equipment from historical data base is electrical
Parameter information normalizes harmonic information and current information, and the group for obtaining proportion and electric current value sequence shared by each harmonic is unified
Matrix is tieed up, using DBSCAN clusterings to combining one-dimensional matrix, clustering is carried out, exports cluster division result；
Further, the equipment identification module is identified device class, according to cluster division result to each cluster meter
It calculates cluster barycenter and stores, determined according to the Euclidean distance size of the new real-time electric parameter cluster barycenter that equipment is added and equipment is newly added
Type, constantly update cluster barycenter.
The device class algoritic module carries out equipment by DBSCAN clustering methods according to electric parameter feature first
Clustering, when have user demarcated by the ends PC certain class electrical equipment some electrical equipment type, then to such equipment
Other equipment identified with the type；For equipment is not identified, the electric parameter for comparing itself and air-conditioning, computer, water dispenser etc. is special
Sign, determines its basic class.
Included the following steps based on big data device class algorithm：
Step 1：Data prediction
Intelligent socket acquires in the electrical parameters storage to server of connected all devices, needed when device class
Data prediction is carried out first；
Described data prediction, including the processing of noise processed, missing values, normalized etc., finally obtain each harmonic
The one-dimensional matrix of combination of shared proportion and current value, as follows：
(L1-Lmin)/(Lmax-Lmin),(L2-
Lmin)/(Lmax-Lmin),…(Ln-Lmin)/(Lmax-Lmin)]
Wherein,For each harmonic proportion value, wherein highest subharmonic is 20 subharmonic, (L1, L2, L3,
L4…Ln) be the equipment operation when current value, consersion unit behavioural characteristic (moving law), LmaxIt is transported for all devices of monitoring
Capable current maxima, LminThe current maxima run for all devices of monitoring；
Step 2：Equipment clustering based on DBSCAN
It will carry out the electric parameter data after data prediction to be input in DBSCAN Clustering Models, clustered
Analysis exports cluster division result, and the distance metric mode between sample uses Euclidean distance, formula as follows：
Wherein (l1,l2,l3...ln) and (m1,m2,m3....mn) respectively represent different electric parameter samples；
For the identification for realizing to different classes of electrical equipment, the sample x of input sample collection DiThe following institute of data format
Show：
Wherein, Num is (l1,l2,l3...ln) the affiliated electrical equipment of sample device identification, have uniqueness；
Wherein, DBSCAN algorithm steps are as follows：Equipment clustering based on DBSCAN, the radius of neighbourhood needed for DBSCAN
The ∈ and minimal amount Minpts for including point in given neighborhood, can be realized by being manually entered, and can also be tied to classification by user
The satisfaction of fruit, the adjust automatically radius of neighbourhood ∈ and minimal amount Minpts for including point in given neighborhood.
Input：Electric parameter sample set D=(x1,x2,...,xm), Neighbourhood parameter (∈, MinPts)
Output：Cluster divides C.
A) initialization kernel object set omega=0, initialization cluster number of clusters k=0, the non-access-sample set Γ of initialization=
D, cluster divide C=0；
B) for j=1,2 ... m is found out all kernel objects by following step；
C) by distance metric mode, ∈-neighborhood subsample collection N ∈ (xj) of sample xj are found；
If d) collection number of samples in subsample meets | N ∈ (xj) | sample xj is added to kernel object sample by >=MinPts
This set：Ω=Ω ∪ { xj }；
If e) kernel object set omega=0, algorithm terminates, and is otherwise transferred to step d；
F) in kernel object set omega, a kernel object o is randomly choosed, initializes current cluster kernel object queue
Ωcur={ o }, initializes classification sequence number k=k+1, and initialization current cluster sample set Ck={ o } updates non-access-sample set
Γ=Γ-{ o }；
If g) current cluster kernel object queue Ωcur=0, then current clustering cluster Ck generations finish, and update cluster divides C=
{C1,C2,...,Ck, update kernel object set omega=Ω-Ck, it is transferred to step c.
H) in current cluster kernel object queue ΩcurOne kernel object o ' of middle taking-up, is looked for by neighborhood distance threshold ∈ ∈
Go out all ∈-neighborhood subsample collection N ∈ (o '), enables Δ=N ∈ (o ') ∩ Γ, update current cluster sample set Ck=Ck ∪
Δ, updates non-access-sample set Γ=Γ-Δ, and update Ω cur=Ω cur ∪ (N ∈ (o ') ∩ Ω) are transferred to step e.
Exporting result is：Cluster divides C={ C1,C2,...,Ck}。
Step 3：Device class signature identification
Cluster ID is encoded, according to cluster division result, classification logotype is carried out to the equipment of the cluster with cluster ID, while storing drawing for cluster
Point, to each cluster CjCluster barycenter is calculated, cluster barycenter is calculated using averaging method, and calculation formula is as follows：
If there is the artificial classification mark for having made the connect electrical equipment of certain intelligent socket in internet-of-things system of building electric device
Mark, using the mark as the classification logotype of corresponding cluster；If there is more people to be identified the equipment, with the type identification more than number
Classification as the cluster；
Equipment for being newly added can be determined by the electric parameter of the equipment and the Euclidean distance size of other cluster barycenter
Device type, when most short away from certain cluster barycenter Euclidean distance, while when less than threshold value beta, it is determined that the cluster belonging to the equipment, update pair
Answer the cluster barycenter of cluster；Also the equipment multiple parameters can be inputted, the cluster belonging to the equipment is determined by KNN algorithms, it is rear to update cluster matter
The heart；
For identified equipment does not judge electrical equipment by analyzing its electrical parameters of equipment feature after a period of time
Basic class.For equipment is not identified for a long time, the electric parameter feature of itself and air-conditioning, computer, water dispenser etc. is compared, determines it
Basic class.
Fig. 3 shows that final running example, figure (a) are not the obtained cluster result of this patent algorithm, is only used as gathering
One two dimension displaying of alanysis example, table b indicate that device cluster table example, table c indicate electrical equipment table example.
The foregoing is merely the preferred embodiments of the application, are not intended to limit this application, for the skill of this field
For art personnel, the application can have various modifications and variations.Within the spirit and principles of this application, any made by repair
Change, equivalent replacement, improvement etc., should be included within the protection domain of the application.
Above-mentioned, although the foregoing specific embodiments of the present invention is described with reference to the accompanying drawings, not protects model to the present invention
The limitation enclosed, those skilled in the art should understand that, based on the technical solutions of the present invention, those skilled in the art are not
Need to make the creative labor the various modifications or changes that can be made still within protection scope of the present invention.
Claims (10)
1. a kind of indoor electric equipment classifying identification method based on big data association analysis, it is characterized in that：Include the following steps：
Acquire the electrical parameters of electrical equipment；
The pretreatment for carrying out electric parameter is extracted each harmonic information, is obtained shared by each harmonic according to electric parameter information
The one-dimensional matrix of combination of proportion and current value；
Electric parameter data are input in Clustering Model, to combining one-dimensional matrix, carry out clustering, output cluster divides knot
Fruit；
If the type of certain class electrical equipment has been marked, using the classification logotype as corresponding cluster that identifies marked；If having multiple
Identification information, using the type identification more than proportion as the classification of the cluster, realized automatically using the category cluster equipment other not
The classification decision of sorting device；
Device type is determined by the electric parameter of the equipment newly connected and the Euclidean distance size of each cluster barycenter；
By the comparison of the electric parameter feature with other known devices, the basic class for not identifying equipment more than certain time length is determined
Not.
2. a kind of indoor electric equipment classifying identification method based on big data association analysis as described in claim 1, special
Sign is：Electric parameter includes electrical harmonic wave and current value, wherein electrical harmonic wave is the combination of each harmonic.
3. a kind of indoor electric equipment classifying identification method based on big data association analysis as described in claim 1, special
Sign is：The electric parameter of acquisition is pre-processed, noise processed, missing values processing and normalized are specifically included.
4. a kind of indoor electric equipment classifying identification method based on big data association analysis as described in claim 1, special
Sign is：The process of clustering includes：
Initialize kernel object set, cluster number of clusters and non-access-sample set；
The radius of neighbourhood is set and includes the minimal amount of point in given neighborhood；
Kernel object is randomly choosed, a kernel object is taken out in current cluster kernel object queue, according to neighborhood distance threshold
All neighborhood subsample collection are found out, current cluster sample set is updated, update non-access-sample set, carry out cluster division.
5. a kind of indoor electric equipment classifying identification method based on big data association analysis as claimed in claim 4, special
Sign is：According to the division of cluster, the cluster barycenter of each cluster is calculated using averaging method, when most short away from certain cluster barycenter Euclidean distance, simultaneously
When less than threshold value, it is determined that the cluster belonging to the equipment updates the cluster barycenter of corresponding cluster.
6. a kind of indoor electric equipment classifying identification method based on big data association analysis as described in claim 1, special
Sign is：If there is the artificial classification mark mark for having made certain electrical equipment in internet-of-things system of building electric device, made with the mark
For the classification logotype of corresponding cluster.
7. a kind of indoor electric equipment classifying identification method based on big data association analysis as described in claim 1, special
Sign is：If with the presence of multiple marks to certain equipment, the classification of the correspondence cluster using the type identification more than quantity as the equipment.
8. a kind of indoor electric equipment classifying identification method based on big data association analysis as described in claim 1, special
Sign is：When there is new equipment addition or in mobile device to other sockets, pass through the electric parameter for the equipment that the socket acquires
Device type is determined with the Euclidean distance size of other cluster barycenter, when most short away from certain cluster barycenter Euclidean distance, while being less than threshold value
When, it is determined that the cluster belonging to the equipment updates the cluster barycenter of corresponding cluster；When there is new equipment addition or mobile device arrives other
When on socket, the equipment multiple parameters can be also inputted, the cluster belonging to the equipment is determined by KNN algorithms, it is rear to update cluster barycenter.
9. a kind of indoor electric equipment classifying identification method based on big data association analysis as described in claim 1, special
Sign is：For identified equipment does not judge that electrical equipment is basic by analyzing its electrical parameters of equipment feature after a period of time
Classification passes through the ratio of the electric parameter feature with the other equipments such as air-conditioning, computer, water dispenser for not identifying equipment for a long time
It is right, determine its basic class.
10. a kind of indoor electric equipment classifying and identifying system based on big data association analysis, it is characterized in that：Including：
Several Internet of things node, each Internet of things node connect multiple intelligent sockets, and receive all kinds of electricity of intelligent socket acquisition
Data are uploaded to the data of cloud server by the electric parameter information of device operation, Internet of things node according to the communication protocol of standard
It is stored in library；
Deployment is in relation to being database, real time historical database and equipment identification module on the cloud server, wherein：Relationship number
According to being stored with intelligent socket information, electrical equipment information and cluster classified types information in library；
The real-time and history electric parameter information of all kinds of electric operations is stored in real time history relationship library；
Equipment identification module extraction equipment electric parameter information from historical data base normalizes harmonic information and current information,
The one-dimensional matrix of combination of the proportion and current value shared by each harmonic is obtained, using DBSCAN clusterings to combining one-dimensional square
Battle array carries out clustering, exports cluster division result；
The equipment identification module is according to cluster division result, if the type of certain class electrical equipment has been marked, with the mark marked
Know the classification logotype as corresponding cluster；If there are multiple identification informations, using the type identification more than proportion as the classification of the cluster, utilize
The category realizes the classification decision of the unassorted equipment of the cluster equipment automatically；By the electric parameter of equipment that newly connects with
The Euclidean distance size of each cluster barycenter determines device type；By the comparison of the electric parameter feature with other known devices,
Determine the basic class for not identifying equipment more than certain time length.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810141174.8A CN108399221B (en) | 2018-02-11 | 2018-02-11 | Indoor electrical equipment classification and identification method and system based on big data correlation analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810141174.8A CN108399221B (en) | 2018-02-11 | 2018-02-11 | Indoor electrical equipment classification and identification method and system based on big data correlation analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108399221A true CN108399221A (en) | 2018-08-14 |
| CN108399221B CN108399221B (en) | 2021-07-30 |
Family
ID=63095951
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810141174.8A Active CN108399221B (en) | 2018-02-11 | 2018-02-11 | Indoor electrical equipment classification and identification method and system based on big data correlation analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108399221B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109377435A (en) * | 2018-09-18 | 2019-02-22 | 深圳市中电数通智慧安全科技股份有限公司 | A kind of method, device and equipment configuring fire-fighting equipment |
| CN109978075A (en) * | 2019-04-04 | 2019-07-05 | 江苏满运软件科技有限公司 | Vehicle dummy location information identifying method, device, electronic equipment, storage medium |
| CN110070048A (en) * | 2019-04-23 | 2019-07-30 | 山东建筑大学 | Device type recognition methods and system based on double secondary K-means clusters |
| CN110381126A (en) * | 2019-07-02 | 2019-10-25 | 山东建筑大学 | Electrical equipment recognition methods, system, equipment and medium based on edge calculations |
| CN112650174A (en) * | 2020-12-21 | 2021-04-13 | 佳都新太科技股份有限公司 | Identity identification method and system of environment control equipment and computer storage medium |
| CN113223625A (en) * | 2021-05-07 | 2021-08-06 | 中国石油化工股份有限公司 | Catalytic cracking reaction process modeling method and device |
| CN114679386A (en) * | 2022-05-25 | 2022-06-28 | 杭州海康威视数字技术股份有限公司 | Cloud-edge cooperative Internet of things device role judgment and management method, system and device |
| CN115879037A (en) * | 2023-02-23 | 2023-03-31 | 深圳合众致达科技有限公司 | Student apartment load identification method and system based on intelligent electric meter |
| CN116028829A (en) * | 2021-01-20 | 2023-04-28 | 国义招标股份有限公司 | Correction clustering processing method, device and storage medium based on transmission step length adjustment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US2372762A (en) * | 1943-02-20 | 1945-04-03 | Frank R Brick | Synchronizing system |
| CN104181898A (en) * | 2014-09-01 | 2014-12-03 | 东北电力大学 | Intelligent control method and system for interactive home appliances on basis of time-of-use electricity price response |
| CN106093652A (en) * | 2016-07-07 | 2016-11-09 | 天津求实智源科技有限公司 | A kind of non-intrusive electrical load monitoring System and method for possessing self-learning function |
| CN106228280A (en) * | 2016-07-06 | 2016-12-14 | 吴本刚 | Grid operating monitoring information identification categorizing system |
| CN106646043A (en) * | 2016-12-13 | 2017-05-10 | 国网江苏省电力公司淮安供电公司 | Ferromagnetic resonance online monitoring system and ferromagnetic resonance classification recognition method for power distribution network |
| CN106855597A (en) * | 2016-12-28 | 2017-06-16 | 天津求实智源科技有限公司 | A kind of non-intrusion type quality of power supply interference source online adaptive monitoring system and method |
| CN107330517A (en) * | 2017-06-14 | 2017-11-07 | 华北电力大学 | One kind is based on S_Kohonen non-intrusion type resident load recognition methods |
-
2018
- 2018-02-11 CN CN201810141174.8A patent/CN108399221B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US2372762A (en) * | 1943-02-20 | 1945-04-03 | Frank R Brick | Synchronizing system |
| GB581485A (en) * | 1943-02-20 | 1946-10-15 | Finch Telecommunications Inc | Synchronising and phasing arrangements for electric facsimile transmission systems |
| CN104181898A (en) * | 2014-09-01 | 2014-12-03 | 东北电力大学 | Intelligent control method and system for interactive home appliances on basis of time-of-use electricity price response |
| CN106228280A (en) * | 2016-07-06 | 2016-12-14 | 吴本刚 | Grid operating monitoring information identification categorizing system |
| CN106093652A (en) * | 2016-07-07 | 2016-11-09 | 天津求实智源科技有限公司 | A kind of non-intrusive electrical load monitoring System and method for possessing self-learning function |
| CN106646043A (en) * | 2016-12-13 | 2017-05-10 | 国网江苏省电力公司淮安供电公司 | Ferromagnetic resonance online monitoring system and ferromagnetic resonance classification recognition method for power distribution network |
| CN106855597A (en) * | 2016-12-28 | 2017-06-16 | 天津求实智源科技有限公司 | A kind of non-intrusion type quality of power supply interference source online adaptive monitoring system and method |
| CN107330517A (en) * | 2017-06-14 | 2017-11-07 | 华北电力大学 | One kind is based on S_Kohonen non-intrusion type resident load recognition methods |
Non-Patent Citations (2)
| Title |
|---|
| MAURO BIAG等: ""An experimental survey of LV equipment for 4their c4lustering and control in a n-grid"", 《2015 IEEE 15TH INTERNATIONAL CONFERENCE ON ENVIRONMENT AND ELECTRICAL ENGINEERING (EEEIC)》 * |
| 靳江红等: ""防爆电气设备分类及其选型"", 《安全》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109377435A (en) * | 2018-09-18 | 2019-02-22 | 深圳市中电数通智慧安全科技股份有限公司 | A kind of method, device and equipment configuring fire-fighting equipment |
| CN109978075A (en) * | 2019-04-04 | 2019-07-05 | 江苏满运软件科技有限公司 | Vehicle dummy location information identifying method, device, electronic equipment, storage medium |
| CN110070048B (en) * | 2019-04-23 | 2020-11-10 | 山东建筑大学 | Equipment type identification method and system based on double K-means clustering |
| CN110070048A (en) * | 2019-04-23 | 2019-07-30 | 山东建筑大学 | Device type recognition methods and system based on double secondary K-means clusters |
| CN110381126B (en) * | 2019-07-02 | 2021-07-23 | 山东建筑大学 | Electric equipment identification method, system, equipment and medium based on edge calculation |
| CN110381126A (en) * | 2019-07-02 | 2019-10-25 | 山东建筑大学 | Electrical equipment recognition methods, system, equipment and medium based on edge calculations |
| CN112650174A (en) * | 2020-12-21 | 2021-04-13 | 佳都新太科技股份有限公司 | Identity identification method and system of environment control equipment and computer storage medium |
| CN116028829A (en) * | 2021-01-20 | 2023-04-28 | 国义招标股份有限公司 | Correction clustering processing method, device and storage medium based on transmission step length adjustment |
| CN116028829B (en) * | 2021-01-20 | 2023-10-24 | 国义招标股份有限公司 | Correction clustering processing method, device and storage medium based on transmission step length adjustment |
| CN113223625A (en) * | 2021-05-07 | 2021-08-06 | 中国石油化工股份有限公司 | Catalytic cracking reaction process modeling method and device |
| CN114679386A (en) * | 2022-05-25 | 2022-06-28 | 杭州海康威视数字技术股份有限公司 | Cloud-edge cooperative Internet of things device role judgment and management method, system and device |
| CN114679386B (en) * | 2022-05-25 | 2022-08-05 | 杭州海康威视数字技术股份有限公司 | Cloud-edge cooperative Internet of things device role judgment and management method, system and device |
| CN115879037A (en) * | 2023-02-23 | 2023-03-31 | 深圳合众致达科技有限公司 | Student apartment load identification method and system based on intelligent electric meter |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108399221B (en) | 2021-07-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108399221A (en) | Indoor electric equipment classifying identification method and system based on big data association analysis | |
| CN109167835B (en) | Physical resource scheduling method and system based on kubernets | |
| WO2021073462A1 (en) | 10 kv static load model parameter identification method based on similar daily load curves | |
| CN110288113A (en) | A kind of non-intrusion type load intelligent identifying system | |
| Das et al. | A bacterial evolutionary algorithm for automatic data clustering | |
| CN110381126A (en) | Electrical equipment recognition methods, system, equipment and medium based on edge calculations | |
| CN108734217A (en) | A kind of customer segmentation method and device based on clustering | |
| CN109799726B (en) | Smart home system combined with living environment detection | |
| CN106327357B (en) | A kind of load identification method based on improvement probabilistic neural network | |
| CN103577883A (en) | Grid-load intelligent interaction method and device | |
| CN115422452B (en) | Smart home control method, device, equipment and storage medium based on big data | |
| CN109309382A (en) | A kind of Short-Term Load Forecasting Method | |
| CN114553475A (en) | Network attack detection method based on network flow attribute directed topology | |
| CN109948909A (en) | A kind of electric network data capturing analysis method and system | |
| CN112684301B (en) | Method and device for detecting power grid faults | |
| CN112819054A (en) | Slice template configuration method and device | |
| CN112686456A (en) | Power load prediction system and method combining edge calculation and energy consumption identification | |
| CN110738120A (en) | Environment data adjusting method and device, electronic equipment and medium | |
| CN111817935B (en) | Internet intelligent home data processing method and system | |
| CN114119292B (en) | Building management system based on Internet of things and big data | |
| CN105139277B (en) | A kind of power matching network information cluster system and method | |
| CN109978598A (en) | Based on big data analysis sales data algorithm | |
| CN111525703B (en) | Power system monitoring method and system for climate self-adaptive adjustment of monitoring parameters | |
| CN109639839A (en) | A kind of expansible signal data collecting system and its working method based on cloud platform | |
| CN109214721A (en) | A kind of long-term cool and thermal power load classification method in multi-energy system |
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 |