CN110381126A - Electrical equipment recognition methods, system, equipment and medium based on edge calculations - Google Patents
Electrical equipment recognition methods, system, equipment and medium based on edge calculations Download PDFInfo
- Publication number
- CN110381126A CN110381126A CN201910589435.7A CN201910589435A CN110381126A CN 110381126 A CN110381126 A CN 110381126A CN 201910589435 A CN201910589435 A CN 201910589435A CN 110381126 A CN110381126 A CN 110381126A
- Authority
- CN
- China
- Prior art keywords
- equipment
- dimensional matrix
- feature database
- identified
- electrical equipment
- 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
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- 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
-
- 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
- H04L67/50—Network services
- H04L67/54—Presence management, e.g. monitoring or registration for receipt of user log-on information, or the connection status of the users
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present disclosure discloses electrical equipment recognition methods, system, equipment and medium based on edge calculations, the electric parameter data of electrical equipment to be identified are acquired on side main circuit of registering one's residence out of building；Each harmonic and current information are extracted, by harmonic wave and currents combination at the first one-dimensional matrix；First one-dimensional matrix and room devices feature database are subjected to similitude matching；Select with the first one-dimensional highest known device type of matrix similarity, as corresponding device type label；Different type equipment in room devices feature database is combined, unit equipment feature database is obtained；First one-dimensional matrix the second one-dimensional matrix corresponding with every group of unit equipment is subjected to similitude matching；It selects and the first one-dimensional highest known combination equipment of matrix similarity, the corresponding device type label of output known combination equipment.The first one-dimensional matrix and KNN algorithm based on Architectural Equipment feature database, electrical equipment to be identified, export the device type of electrical equipment to be identified.
Description
Technical field
This disclosure relates to office building Internet of Things electrical equipment identification technology field, more particularly to one kind based on edge
Electrical equipment recognition methods, system, equipment and the medium of calculation.
Background technique
The statement of this part is only to refer to background technique relevant to the disclosure, not necessarily constitutes the prior art.
In implementing the present disclosure, following technical problem exists in the prior art in inventor:
The electric appliance of the extensive market of electrical equipment, each producer's production has a set of standard of oneself, can not set all
Standby standard unified standard gets up, this also results in that all equipment can not be made to be connected on Internet of Things using unified agreement, no
It is able to achieve intelligentized equipment management.
It is most of dependent on the one-to-one electrical equipment of collecting of detection device currently, the equipment in building field identifies
Then data are stored and are applied by acquisition module end of uploading onto the server.This mode needs to install in user side big
The hardware module of amount, not only installation cost is high, and maintenance is cumbersome, and experience sense is very poor for a user.
The data of equipment acquire, current most of electric energy and power data for being directed to equipment, still, some electrical equipments
Power consumption very little, the power consumption precision in per hour reaches 0.001, this requirement for data acquisition device is very high；Classification
Model can not classify the data of new equipment, when there is new equipment to occur, disaggregated model be no longer applicable in and can not self study, equipment knows
Other accuracy will will be greatly reduced.
Summary of the invention
In order to solve the deficiencies in the prior art, present disclose provides based on edge calculations electrical equipment recognition methods, be
System, equipment and medium；
In a first aspect, present disclose provides a kind of electrical equipment recognition methods based on edge calculations；
Electrical equipment recognition methods based on edge calculations is applied to intelligent measurement terminal, intelligent measurement terminal is considered as
Build the edge calculations equipment of Internet of Things；Include:
It registers one's residence out of building and acquires the electric parameter data of electrical equipment to be identified on the main circuit of side；
Each harmonic and current information are extracted from the electric parameter data of the electrical equipment to be identified of acquisition, by what is obtained
Each harmonic information and current value are combined into the first one-dimensional matrix；
Described first one-dimensional matrix and room devices feature database are subjected to similitude matching；If successful match, from room
Between select in equipment feature database with the described first one-dimensional highest known device type of matrix similarity, as the first one-dimensional matrix
Corresponding device type label；If it fails to match, determine electrical equipment to be identified for combination electrical equipment or new equipment；Into
Enter in next step；
Different type equipment in room devices feature database is combined, unit equipment feature database is obtained；By unit equipment
Distinct device characteristic parameter in feature database under each combination carries out parameter synthesis；By every group of unit equipment from generated data
Each harmonic and current value form the second one-dimensional matrix；
First one-dimensional matrix the second one-dimensional matrix corresponding with every group of unit equipment is subjected to similitude matching；If matching
Success is then selected from unit equipment feature database and the described first one-dimensional highest known combination equipment of matrix similarity, output
The corresponding device type label of known combination equipment.
Second aspect, the disclosure additionally provide a kind of electrical equipment identifying system based on edge calculations；
Electrical equipment identifying system based on edge calculations is applied to intelligent measurement terminal, intelligent measurement terminal is considered as
Build the edge calculations equipment of Internet of Things；Include:
Acquisition module is configured as: acquiring the electrical of electrical equipment to be identified on side main circuit of registering one's residence out of building
Supplemental characteristic；
Extraction module is configured as: extracted from the electric parameter data of the electrical equipment to be identified of acquisition each time it is humorous
Obtained each harmonic information and current value are combined into the first one-dimensional matrix by wave and current information；
First similarity matching module, is configured as: the described first one-dimensional matrix and room devices feature database are carried out
Similitude matching；If successful match, selected out of room devices feature database and the described first one-dimensional matrix similarity highest
Known device type, as the corresponding device type label of the first one-dimensional matrix；If it fails to match, use to be identified is determined
Electric equipment is combination electrical equipment or new equipment；Into composite module；
Composite module is configured as: different type equipment in room devices feature database being combined, combination is obtained and sets
Standby feature database；Distinct device characteristic parameter under combination each in unit equipment feature database is subjected to parameter synthesis；From composite number
According to middle each harmonic and current value the second one-dimensional matrix of composition by every group of unit equipment；
Second similarity matching module, is configured as: by the first one-dimensional matrix and every group of unit equipment corresponding second
One-dimensional matrix carries out similitude matching；If successful match, selected from unit equipment feature database and the described first one-dimensional square
The battle array highest known combination equipment of similarity, the corresponding device type label of output known combination equipment.
The third aspect, the disclosure additionally provide a kind of electronic equipment, including memory and processor and are stored in storage
The computer instruction run on device and on a processor when the computer instruction is run by processor, completes first aspect institute
The step of stating method.
Fourth aspect, the disclosure additionally provide a kind of computer readable storage medium, described for storing computer instruction
When computer instruction is executed by processor, complete first aspect the method the step of.
Compared with prior art, the beneficial effect of the disclosure is:
The intelligent measurement terminal that this method will test device parameter is mounted in the total line for side of registering one's residence, and utilizes edge calculations
Technology and advantage will use the methods of similarity analysis and user's mark identify indoor equipment, reach continual monitoring user
The purpose of equipment state；Edge calculations are the progress algorithm calculating in the intelligent terminal for side of registering one's residence, and reduce the response time, mitigate cloud
End pressure, it is significant to the effect of optimization of real-time and reliability.All calculating of this method require to realize in edge calculations layer.
By being compared the data of acquisition with room devices feature database, the device type of room existing device is exported；
By being compared the data of acquisition with unit equipment feature database, the device type of unit equipment is exported；
It carries out exporting the device type of new equipment apart from calculating by the data and Architectural Equipment feature database that will acquire；
The hardware cost of equipment identification can be effectively reduced in this method, and more specific data are obtained under least cost,
And it can accurately and rapidly identify that each intelligent measurement terminal is corresponding all by Internet of Things, edge calculations and the intervention of user
The real-time status of equipment, and the history that can count each equipment uses the time.
Detailed description of the invention
The accompanying drawings constituting a part of this application is used to provide further understanding of the present application, and the application's shows
Meaning property embodiment and its explanation are not constituted an undue limitation on the present application for explaining the application.
Fig. 1 is the system construction drawing of the embodiment of the present disclosure one；
Fig. 2 is the database model diagram of the embodiment of the present disclosure one；
Fig. 3 is the device identification data flow chart of the embodiment of the present disclosure one.
Specific embodiment
It is noted that described further below be all exemplary, it is intended to be further explained to the application offer.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 embodiment, 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 singular
Also it is 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 their combination.
Have unique load characteristic between the different conditions of distinct device, it is relatively fixed in the device category of building interior and
Negligible amounts, the type of the equipment in each room are more unified；It is association analysis equipment in the environment of Internet of Things big data
The condition that feature and identification equipment are provided convenience, can effectively capture Parameters variation situation, can effectively grab single in room
The case where equipment is run；And can be from the amplification of the facility information in room to more rooms the case where, the method based on data-driven calculates
Speed is fast, and stability is high, strong robustness.
Embodiment one present embodiments provides the electrical equipment recognition methods based on edge calculations；
Electrical equipment recognition methods based on edge calculations is applied to intelligent measurement terminal, intelligent measurement terminal is considered as
Build the edge calculations equipment of Internet of Things；Include:
S1: the electric parameter data of electrical equipment to be identified are acquired on side main circuit of registering one's residence out of building；
S2: extracting each harmonic and current information from the electric parameter data of the electrical equipment to be identified of acquisition, will
To each harmonic information and current value be combined into the first one-dimensional matrix；
S3: the described first one-dimensional matrix and room devices feature database are subjected to similitude matching；If successful match, from
Selected in room devices feature database with the described first one-dimensional highest known device type of matrix similarity, as the first one-dimensional square
The corresponding device type label of battle array；If it fails to match, determine electrical equipment to be identified for combination electrical equipment or new equipment；
Enter step S4；
S4: different type equipment in room devices feature database is combined, unit equipment feature database is obtained；Combination is set
Distinct device characteristic parameter in standby feature database under each combination carries out parameter synthesis；By every group of unit equipment from generated data
Each harmonic and current value form the second one-dimensional matrix；
First one-dimensional matrix the second one-dimensional matrix corresponding with every group of unit equipment is subjected to similitude matching；If matching
Success is then selected from unit equipment feature database and the described first one-dimensional highest known combination equipment of matrix similarity, output
The corresponding device type label of known combination equipment.
As one or more embodiments, the method also includes:
If it fails to match for the similitude of the first one-dimensional matrix the second one-dimensional matrix corresponding with every group of unit equipment, into
Enter step S5；
S5: the first one-dimensional matrix and KNN algorithm based on Architectural Equipment feature database, electrical equipment to be identified are exported wait know
The device type of other electrical equipment.
As one or more embodiments, the step S5 based on Architectural Equipment feature database, electrical equipment to be identified
One one-dimensional matrix and KNN algorithm, export the device type of electrical equipment to be identified；Specific steps include: that edge calculations equipment will
The one-dimensional matrix of the first of electrical equipment to be identified and known Architectural Equipment feature database, are input in KNN algorithm, carry out neighbouring
Distance analysis exports division result, if electrical equipment to be identified is at a distance from known cluster mass center in set distance threshold range
It is interior, then it is the device type label of electrical equipment to be identified apart from the nearest corresponding label of cluster mass center, utilizes use to be identified
The device type tag update room devices feature database of electric equipment；Otherwise, marking electrical equipment to be identified is new equipment.
Finally, edge calculations equipment uploads the device type recognition result of electrical equipment to be identified by Internet of things node
To Cloud Server.
It is to be understood that the building Internet of Things, comprising: Cloud Server, the Cloud Server and several Internet of things node
Connection, each Internet of things node are connect with several intelligent measurement terminals, and each intelligent measurement terminal is mounted in building
On the main circuit of family side.
As one or more embodiments, the electric parameter data, comprising: electrical harmonic wave and current value, wherein electrically
Harmonic wave is the combination of each harmonic.
As one or more embodiments, each harmonic information, comprising: first harmonic, second harmonic, triple-frequency harmonics etc..
As one or more embodiments, current value refers to the current value acquired from side main circuit of registering one's residence；
As one or more embodiments, the described first one-dimensional matrix and room devices feature database are subjected to similitude
Match, in particular to calculate the one-dimensional matrix of distinct device first in the described first one-dimensional matrix and room devices feature database it is European away from
From.
As one or more embodiments, successful match is with the measurement standard that it fails to match, by Similarity measures result
It is compared with given threshold, if it is greater than given threshold, then it represents that otherwise successful match indicates that it fails to match.
As one or more embodiments, room devices feature database is divided according to room, comprising: single in current room
The electric parameter of the title of equipment and existing device, each device type label, the corresponding current effective value of each equipment and every
The corresponding each harmonic of a equipment.The feature database is as shown in Figure 2.
As one or more embodiments, different type equipment in room devices feature database is combined, is combined
Equipment feature database；Such as: it include: refrigerator, colour TV, washing machine, printer, computer, air-conditioning, water heater in room devices feature database
And the corresponding electric parameter of each equipment；Unit equipment feature database include: [refrigerator, the electric parameter of refrigerator, colour TV, colour TV
Electric parameter], [refrigerator, the electric parameter of refrigerator, washing machine, the electric parameter of washing machine], [refrigerator, the electric parameter of refrigerator,
Colour TV, the electric parameter of colour TV, washing machine, the electric parameter of washing machine] etc. permutation and combination.
As one or more embodiments, by the distinct device characteristic parameter under combination each in unit equipment feature database into
Row parameter synthesis, such as: the periodic current of distinct device same-phase is subjected to addition of vectors, obtains combination parameter.
As one or more embodiments, the construction method of Architectural Equipment feature database, comprising:
Acquire the electrical parameters of electrical equipment；
The pretreatment for carrying out electric parameter extracts each harmonic information according to electric parameter information, obtain each harmonic with
The one-dimensional matrix of current value combination；
Electric parameter is input in clustering algorithm, clustering is carried out to one-dimensional matrix is combined, exports cluster division result；
If certain class electrical equipment type has been marked, using the classification logotype as corresponding cluster that identifies marked；If
There are multiple identification informations, then using heavy type identification as the classification of current cluster, using the classification of current cluster as current
The classification of unassorted equipment in cluster；
Device type is determined by the electric parameter of the equipment newly connected and the Euclidean distance size of each cluster mass center.
As one or more embodiments, Architectural Equipment feature database, comprising: the cluster center-of-mass coordinate of cluster result, apart from threshold
Value, each cluster labeled label, current effective value and harmonic wave.
As one or more embodiments, the electric parameter number of electrical equipment to be identified is acquired from side main circuit of registering one's residence
According to being detected by intelligent measurement terminal.The intelligent measurement terminal is intelligent electric meter or intelligent socket.
As one or more embodiments, all two cycle data using equipment in intelligent measurement terminal collection room,
It is made of 128 points, takes the equally distributed point of two cycles of the alternating current changed over time by sinusoidal rule；It is expressed
Formula are as follows:
Wherein, ImFor the attainable maximum value of sinusoidal current；ω is the speed that the phase of sinusoidal current changes over time；For phase angle of the sinusoidal current in t=0.
The interception of two cycles of supplemental characteristic is started to the data of a cycle, i.e., when i maximumPhase
The complete cycle started, which is made of 64 points, and then calculating current virtual value and 1-32 subharmonic.
Further, S2 further include: the pretreatment of electric parameter data；Pretreatment, specifically includes noise processed, missing values
Processing and normalized.
Further, the interception of two cycles of supplemental characteristic is started to the data of a cycle, i.e., when i maximumThe complete cycle that phase starts, which is made of 64 points, as sample data.
Further, the 64 calculating current virtual values and 32 subharmonic of a cycle are utilized.
Further, the calculation formula of current effective value is as follows:
The cycle data of acquisition are subjected to preliminary data filtering and FFT calculates 1 to 32 subharmonic Ihar1……Ihar32。
Using above-mentioned current effective value harmony wave component 1 × 33 dimension matrix as sample data:
D0=[Ihar1 … Ihar32 Irms]。
Further, the not chummery in building register one's residence side way circuit on install intelligent measurement terminal, intelligence examine
Two cycle data for surveying way circuit in terminal collection room after data prediction, utilize cycle data calculating current virtual value
And harmonic wave, by the one-dimensional matrix of current effective value harmony wave component first.
Further, the above-mentioned first one-dimensional matrix first carries out similitude comparison with the cluster center-of-mass coordinate of individual equipment, passes through
It is minimum that KNN algorithm calculates Euclidean distance, and within the scope of distance threshold, just determines that the device data belongs to the cluster；If minimum
Euclidean distance is more than that distance threshold then determines that the equipment is composed for new equipment or more equipment.
Further, above-mentioned to judge that the one-dimensional matrix is composed for new equipment or more equipment, room devices will be extracted
The type of all devices in feature database and the characteristic parameter of state combine, all combinations are as follows:
Wherein n is the quantity of the affiliated indoor device type and state that record in unit equipment feature database.
It is the number of combinations of i kind device type or state in n kind device type or state.
Further, combined synthesis is that the cycle electric current since 90 ° of phases of equipment in combining carries out vector
It is added；
Further, the intelligent measurement terminal of side of registering one's residence detects the supplemental characteristic of indoor electric, is judged as new equipment
Or more equipment extract 64 points of the cycle electric current since 90 ° of phases of electrical equipment to be identified, by it when being composed
Euclidean distance calculating is carried out with the data of the synthesis cycle electric current of various combination:
The corresponding generated data of the smallest d is selected, the original combined equipment situation of the generated data is indoor equipment class
Type and state status.
Further, if the above method does not find Similarity Parameter, building is searched into the Cloud Server of building
Equipment feature database carries out similitude comparison with the cluster center-of-mass coordinate of individual equipment in library, calculates Euclidean distance most by KNN algorithm
It is small and within the scope of distance threshold, determine that the device data belongs to the cluster and the device type update that will identify that is set to room
Standby feature database；Determine that the equipment is composed for new equipment or more equipment if minimum euclidean distance is more than distance threshold, more
The new new equipment library for arriving room devices feature database and Cloud Server.
Further, the parameter for the room way circuit that intelligent measurement terminal detects and the equipment in identification room use feelings
Condition uploads to Cloud Server by Internet of things node in real time, according to time series storage into equipment recognition result database,
Client by Cloud Server required parameter check in time in real time or history room devices service condition.
Further, after the parameter of equipment, which is judged as new equipment or more equipment, to be combined, when the equipment next time or
The parameter of more equipment is collected, carries out above equipment identification process, if being identified is more equipment combinations, preceding step is stored
The tag update in equipment recognition result library being the tables of data of new equipment is specific identification types, and in room devices feature database
With the parameter for deleting new equipment in new equipment library；If not identifying yet, it is saved in the same data in equipment recognition result library
In table.
Embodiment two, the disclosure additionally provide the electrical equipment identifying system based on edge calculations；
As shown in Figure 1, the electrical equipment identifying system based on edge calculations, is applied to intelligent measurement terminal, by intelligent inspection
Survey the edge calculations equipment that terminal is considered as building Internet of Things；Include:
Acquisition module is configured as: acquiring the electrical of electrical equipment to be identified on side main circuit of registering one's residence out of building
Supplemental characteristic；
Extraction module is configured as: extracted from the electric parameter data of the electrical equipment to be identified of acquisition each time it is humorous
Obtained each harmonic information and current value are combined into the first one-dimensional matrix by wave and current information；
First similarity matching module, is configured as: the described first one-dimensional matrix and room devices feature database are carried out
Similitude matching；If successful match, selected out of room devices feature database and the described first one-dimensional matrix similarity highest
Known device type, as the corresponding device type label of the first one-dimensional matrix；If it fails to match, use to be identified is determined
Electric equipment is combination electrical equipment or new equipment；Into composite module；
Composite module is configured as: different type equipment in room devices feature database being combined, combination is obtained and sets
Standby feature database；Distinct device characteristic parameter under combination each in unit equipment feature database is subjected to parameter synthesis；From composite number
According to middle each harmonic and current value the second one-dimensional matrix of composition by every group of unit equipment；
Second similarity matching module, is configured as: by the first one-dimensional matrix and every group of unit equipment corresponding second
One-dimensional matrix carries out similitude matching；If successful match, selected from unit equipment feature database and the described first one-dimensional square
The battle array highest known combination equipment of similarity, the corresponding device type label of output known combination equipment.
As one or more embodiments, the system also includes:
Second similarity matching module, is configured as: if the first one-dimensional matrix corresponding with every group of unit equipment
It fails to match for the similitude of two one-dimensional matrixes, then enters output module；
Output module is configured as: based on Architectural Equipment feature database, electrical equipment to be identified the first one-dimensional matrix and
KNN algorithm exports the device type of electrical equipment to be identified.
As one or more embodiments, the output module is configured as: based on Architectural Equipment feature database, wait know
The the first one-dimensional matrix and KNN algorithm of other electrical equipment, export the device type of electrical equipment to be identified；Specific steps include:
The first of electrical equipment to be identified one-dimensional matrix and known Architectural Equipment feature database are input to KNN by edge calculations equipment
In algorithm, adjacency analysis is carried out, division result is exported, if electrical equipment to be identified is being set at a distance from known cluster mass center
It is then the device type mark of electrical equipment to be identified apart from the nearest corresponding label of cluster mass center in set a distance threshold range
Label, utilize the device type tag update room devices feature database of electrical equipment to be identified；Otherwise, electrical equipment to be identified is marked
For new equipment.
Finally, edge calculations equipment uploads the device type recognition result of electrical equipment to be identified by Internet of things node
To Cloud Server.
Further, the parameter information of intelligent measurement terminal acquisition room way circuit, including two be made of 128 points
Complete cycle data.
Database on the Cloud Server includes equipment recognition result library, Architectural Equipment feature database and new equipment library；
Further, be stored with that each room way circuit intelligent measurement terminal in building uploads in real time in database sets
Standby recognition result and all wave parameters, Architectural Equipment feature database and new equipment library.
Further, equipment recognition result library is stored according to the Different Results that different parameters identify to different tables of data
In, each recognition result has a real-time parameter of recognition time and acquisition, recognition result also including new equipment based on
The storage of time series.
Further, Architectural Equipment feature database is stored with the cluster center-of-mass coordinate of cluster result, distance threshold, each cluster and is marked
The cycle electric current of the label of note and each label corresponding data collection, current effective value, harmonic wave etc..
Further, new equipment library refers to, final recognition result is the parameter of new equipment, as new individual equipment
It is added in Architectural Equipment feature database, is recorded in new equipment library.
For the real-time monitoring problem at present to the indoor electrical equipment of user, the identification that improves equipment only is examined by contact
The status for surveying the one-to-one detection electrical equipment of device, installs intelligent measurement terminal on the way circuit for side of registering one's residence；Utilize contact
The Architectural Equipment feature database that the parameter of formula detection is established passes through the analysis to real-time detection way circuit parameter and determines indoor electric
The situation of change of equipment running status.
For constructing the sample data set of Architectural Equipment feature database, it is divided into different data sets according to different clusters, calculates
The data set of affiliated each cluster and the mean μ and variances sigma of cluster mass center Euclidean distance2:
Training data { m in each data seti1……mi33(for from 1 to n) and cluster center-of-mass coordinate { C1……C33It is European
Distance are as follows:
Mean value computation formula:
Variance calculation formula:
Wherein { C1……C33In Ci(1≤i≤33) are that form one group of 1-32 subharmonic and current effective value is one-dimensional
Data.
The cluster mass center of individual equipment in sample data and room devices feature database is first subjected to similitude comparison, by KNN
Algorithm calculates Euclidean distance minimum and within the scope of distance threshold, just determines that the device data belongs to the cluster；If minimum European
Distance is more than that distance threshold then determines the equipment for new equipment.
According to Normal Distribution Theory, be under the jurisdiction of distribution (approximatively) Normal Distribution of the data set of each cluster, i.e., with
Machine variable X obey a mathematic expectaion be μ, variance σ2Normal distribution, data fall in the different section memories of normal distribution
In following probabilistic relation:
1 section of table and probabilistic relation
| Section | (μ-σ2, μ+σ2) | (μ-2σ2,+2 σ of μ2) | (μ-3σ2,+3 σ of μ2) |
| Probability | 0.683 | 0.954 | 0.997 |
To the extent permitted by the error, the probability for the data set that can be correctly divided reaches 99%.Therefore it can choose
The range of distance threshold are as follows: (μ -3 σ2,+3 σ of μ2)
As shown in Fig. 3 process, if the cluster mass center of individual equipment can not establish similarity relationships, edge calculations with sample data
64 data points of the periodic current in room devices feature database will be extracted, all equipment is combined, room devices are special
The all situations of all devices in sign library are combined entirely, and combined all situations include:
By the equipment in each combination, complete cycle data carry out addition of vectors, 64 obtained since 90 ° of phases
The point of synthesis, and further calculate harmonic wave and current effective value；
The calculating of current effective value is as follows:
The cycle data of acquisition are subjected to preliminary data filtering and FFT calculates 1 to 32 subharmonic Ihar1……Ihar32。
Matrix data as a comparison are tieed up into above-mentioned current effective value harmony wave component 1 × 33:
Dij=[Ihar1 … Ihar32 Irms]
Wherein i isCombined one of which, j for similitude comparative experiments equipment feature institute
The room of category.
It is subjected to the comparison of Euclidean distance similitude with data splitting, Euclidean distance calculation formula:
It carries out sample data and the data splitting to select immediate data combining respectively and be set Ji Wei the moment indoor electric
Standby service condition.
This system is identified through operation after a period of time, the storage class of meeting gradual perfection indoor equipment by being continuously improved
Precision shortens recognition time；Especially for the identification of high-power electric appliance, differentiate that accuracy rate is higher.
Embodiment three, the disclosure additionally provide a kind of electronic equipment, including memory and processor and are stored in storage
The computer instruction run on device and on a processor, it is each in Method Of Accomplishment when the computer instruction is run by processor
A operation, for sake of simplicity, details are not described herein.
The electronic equipment can be mobile terminal and immobile terminal, and immobile terminal includes desktop computer, move
Dynamic terminal includes smart phone (Smart Phone, such as Android phone, IOS mobile phone), smart glasses, smart watches, intelligence
The mobile internet device that energy bracelet, tablet computer, laptop, personal digital assistant etc. can carry out wireless communication.
It should be understood that in the disclosure, which can be central processing unit CPU, which, which can be said to be, can be it
His general processor, digital signal processor DSP, application-specific integrated circuit ASIC, ready-made programmable gate array FPGA or other
Programmable logic device, discrete gate or transistor logic, discrete hardware components etc..General processor can be micro process
Device or the processor are also possible to any conventional processor etc..
The memory may include read-only memory and random access memory, and to processor provide instruction and data,
The a part of of memory can also include non-volatile RAM.For example, memory can be with the letter of storage device type
Breath.
During realization, each step of the above method can by the integrated logic circuit of the hardware in processor or
The instruction of software form is completed.The step of method in conjunction with disclosed in the disclosure, can be embodied directly in hardware processor and execute
At, or in processor hardware and software module combination execute completion.Software module can be located at random access memory, dodge
It deposits, this fields are mature deposits for read-only memory, programmable read only memory or electrically erasable programmable memory, register etc.
In storage media.The storage medium is located at memory, and processor reads the information in memory, completes the above method in conjunction with its hardware
The step of.To avoid repeating, it is not detailed herein.Those of ordinary skill in the art may be aware that in conjunction with institute herein
Each exemplary unit, that is, algorithm steps of disclosed embodiment description, can be hard with electronic hardware or computer software and electronics
The combination of part is realized.These functions are implemented in hardware or software actually, the specific application depending on technical solution
And design constraint.Professional technician can realize described function using distinct methods to each specific application
Can, but this realization is it is not considered that exceed scope of the present application.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In several embodiments provided herein, it should be understood that disclosed systems, devices and methods, it can be with
It realizes in other way.For example, the apparatus embodiments described above are merely exemplary, for example, the unit
It divides, only a kind of division of logic function, there may be another division manner in actual implementation, such as multiple units or group
Part can be combined or can be integrated into another system, or some features can be ignored or not executed.In addition, showing
The mutual coupling or direct-coupling or communication connection shown or discussed can be through some interfaces, device or unit
Indirect coupling or communication connection, can be electrically, mechanical or other forms.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product
It is stored in a computer readable storage medium.Based on this understanding, the technical solution of the application is substantially right in other words
The part of part or the technical solution that the prior art contributes can be embodied in the form of software products, the calculating
Machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be individual
Computer, server or network equipment etc.) execute each embodiment the method for the application all or part of the steps.And it is preceding
The storage medium stated includes: USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory
The various media that can store program code such as (RAM, Random Access Memory), magnetic or disk.
The foregoing is merely preferred embodiment of the present application, are not intended to limit this application, for the skill of this field
For art personnel, various changes and changes are possible in this application.Within the spirit and principles of this application, made any to repair
Change, equivalent replacement, improvement etc., should be included within the scope of protection of this application.
Claims (10)
1. the electrical equipment recognition methods based on edge calculations, characterized in that be applied to intelligent measurement terminal, by intelligent measurement end
End is considered as the edge calculations equipment of building Internet of Things；Include:
It registers one's residence out of building and acquires the electric parameter data of electrical equipment to be identified on the main circuit of side；
Each harmonic and current information, each time will obtained are extracted from the electric parameter data of the electrical equipment to be identified of acquisition
Harmonic information and current value are combined into the first one-dimensional matrix；
Described first one-dimensional matrix and room devices feature database are subjected to similitude matching；If successful match is set from room
Selected in standby feature database with the described first one-dimensional highest known device type of matrix similarity, it is corresponding as the first one-dimensional matrix
Device type label；If it fails to match, determine electrical equipment to be identified for combination electrical equipment or new equipment；Under
One step；
Different type equipment in room devices feature database is combined, unit equipment feature database is obtained；By unit equipment feature
Distinct device characteristic parameter in library under each combination carries out parameter synthesis；By each time of every group of unit equipment from generated data
Harmonic wave and current value form the second one-dimensional matrix；
First one-dimensional matrix the second one-dimensional matrix corresponding with every group of unit equipment is subjected to similitude matching；If matching at
Function, then selected from unit equipment feature database with the described first one-dimensional highest known combination equipment of matrix similarity, output
Know the corresponding device type label of unit equipment.
2. the method as described in claim 1, characterized in that the method also includes:
If it fails to match for the similitude of the first one-dimensional matrix the second one-dimensional matrix corresponding with every group of unit equipment, enter step
Rapid S5；
S5: the first one-dimensional matrix and KNN algorithm based on Architectural Equipment feature database, electrical equipment to be identified export use to be identified
The device type of electric equipment.
3. method according to claim 2, characterized in that the step S5 is based on Architectural Equipment feature database, electricity consumption to be identified
The one-dimensional matrix of the first of equipment and KNN algorithm, export the device type of electrical equipment to be identified；Specific steps include: edge meter
Equipment is calculated by the first of electrical equipment to be identified the one-dimensional matrix and known Architectural Equipment feature database, is input in KNN algorithm,
Adjacency analysis is carried out, division result is exported, if electrical equipment to be identified is at a distance from known cluster mass center in set distance
Then it is the device type label of electrical equipment to be identified apart from the nearest corresponding label of cluster mass center in threshold range, utilizes
The device type tag update room devices feature database of electrical equipment to be identified；Otherwise, marking electrical equipment to be identified is newly to set
It is standby.
4. the method as described in claim 1, characterized in that edge calculations equipment knows the device type of electrical equipment to be identified
Other result is uploaded to Cloud Server by Internet of things node；
The building Internet of Things, comprising: Cloud Server, the Cloud Server are connect with several Internet of things node, each Internet of Things
Net node is connect with several intelligent measurement terminals, and each intelligent measurement terminal, which is mounted in building, registers one's residence on the main circuit of side.
5. the method as described in claim 1, characterized in that the described first one-dimensional matrix and room devices feature database are carried out phase
The one-dimensional matrix of distinct device first in the described first one-dimensional matrix and room devices feature database is matched, in particular to calculated like property
Euclidean distance.
6. the method as described in claim 1, characterized in that as one or more embodiments, room devices feature database, according to
Room divides, comprising: the electric parameter of the title of individual equipment and existing device in current room, each device type label,
Each corresponding current effective value of equipment and the corresponding each harmonic of each equipment.
7. the method as described in claim 1, characterized in that the construction method of Architectural Equipment feature database, comprising:
Acquire the electrical parameters of electrical equipment；
The pretreatment for carrying out electric parameter extracts each harmonic information, obtains each harmonic and electric current according to electric parameter information
It is worth the one-dimensional matrix of combination；
Electric parameter is input in clustering algorithm, clustering is carried out to one-dimensional matrix is combined, exports cluster division result；
If certain class electrical equipment type has been marked, using the classification logotype as corresponding cluster that identifies marked；If having more
A identification information, then using heavy type identification as the classification of current cluster, using the classification of current cluster as in current cluster
The classification of unassorted equipment；
Device type is determined by the electric parameter of the equipment newly connected and the Euclidean distance size of each cluster mass center.
8. the electrical equipment identifying system based on edge calculations, characterized in that be applied to intelligent measurement terminal, by intelligent measurement end
End is considered as the edge calculations equipment of building Internet of Things；Include:
Acquisition module is configured as: the electric parameter of electrical equipment to be identified is acquired on side main circuit of registering one's residence out of building
Data；
Extraction module is configured as: from the electric parameter data of the electrical equipment to be identified of acquisition extract each harmonic and
Obtained each harmonic information and current value are combined into the first one-dimensional matrix by current information；
First similarity matching module, is configured as: the described first one-dimensional matrix is similar to the progress of room devices feature database
Property matching；If successful match, selected out of room devices feature database highest with the described first one-dimensional matrix similarity
Device type is known, as the corresponding device type label of the first one-dimensional matrix；If it fails to match, determine that electricity consumption to be identified is set
Standby is combination electrical equipment or new equipment；Into composite module；
Composite module is configured as: different type equipment in room devices feature database being combined, unit equipment spy is obtained
Levy library；Distinct device characteristic parameter under combination each in unit equipment feature database is subjected to parameter synthesis；From generated data
By each harmonic and current value the second one-dimensional matrix of composition of every group of unit equipment；
Second similarity matching module, is configured as: the first one-dimensional matrix is corresponding with every group of unit equipment second one-dimensional
Matrix carries out similitude matching；If successful match, selected from unit equipment feature database and the described first one-dimensional matrix phase
Like highest known combination equipment is spent, the corresponding device type label of known combination equipment is exported.
9. a kind of electronic equipment, characterized in that on a memory and on a processor including memory and processor and storage
The computer instruction of operation when the computer instruction is run by processor, is completed described in any one of claim 1-7 method
Step.
10. a kind of computer readable storage medium, characterized in that for storing computer instruction, the computer instruction is located
When managing device execution, step described in any one of claim 1-7 method is completed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910589435.7A CN110381126B (en) | 2019-07-02 | 2019-07-02 | Electric equipment identification method, system, equipment and medium based on edge calculation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910589435.7A CN110381126B (en) | 2019-07-02 | 2019-07-02 | Electric equipment identification method, system, equipment and medium based on edge calculation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110381126A true CN110381126A (en) | 2019-10-25 |
| CN110381126B CN110381126B (en) | 2021-07-23 |
Family
ID=68251694
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910589435.7A Active CN110381126B (en) | 2019-07-02 | 2019-07-02 | Electric equipment identification method, system, equipment and medium based on edge calculation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110381126B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110658412A (en) * | 2019-10-31 | 2020-01-07 | 刘新东 | 5G base station power supply monitoring system, method, medium and equipment |
| CN111178393A (en) * | 2019-12-11 | 2020-05-19 | 广东浩迪智云技术有限公司 | Electric appliance power consumption classification metering method and device based on intelligent electric meter |
| CN111257700A (en) * | 2020-03-31 | 2020-06-09 | 国网江苏省电力有限公司无锡供电分公司 | Power distribution network single-phase earth fault positioning device and method based on edge calculation |
| CN111860692A (en) * | 2020-07-31 | 2020-10-30 | 国网重庆市电力公司电力科学研究院 | Abnormal data detection method based on K-media in Internet of things environment |
| CN112034238A (en) * | 2020-09-11 | 2020-12-04 | 山东润一智能科技有限公司 | Electric equipment identification method and system |
| CN112255480A (en) * | 2020-10-12 | 2021-01-22 | 浙江长元科技有限公司 | Hall effect based electric appliance characteristic identification method and safety early warning system thereof |
| CN113030564A (en) * | 2021-03-10 | 2021-06-25 | 南方电网数字电网研究院有限公司 | Load identification method based on double-core intelligent electric meter system |
| CN113191600A (en) * | 2021-04-13 | 2021-07-30 | 清科优能(深圳)技术有限公司 | Intelligent house non-invasive load identification method based on data mining |
| CN113325248A (en) * | 2021-04-13 | 2021-08-31 | 清科优能(深圳)技术有限公司 | Intelligent house non-invasive load identification system based on edge calculation |
| CN113408014A (en) * | 2020-03-17 | 2021-09-17 | 南宁富桂精密工业有限公司 | Terminal equipment identification system and method thereof |
| CN113822333A (en) * | 2021-08-18 | 2021-12-21 | 威胜集团有限公司 | Electric appliance identification method and device and computer readable storage medium |
| CN114996287A (en) * | 2022-06-20 | 2022-09-02 | 上海电器科学研究所（集团）有限公司 | Automatic equipment identification and capacity expansion method based on feature library |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140100805A1 (en) * | 2012-10-04 | 2014-04-10 | Kabushiki Kaisha Toshiba | Status estimation apparatus, status estimation method |
| KR101714698B1 (en) * | 2015-11-25 | 2017-03-09 | 고려대학교 산학협력단 | Apparatus and method home appliance identification using electric signal |
| CN106909101A (en) * | 2017-01-13 | 2017-06-30 | 中国海洋大学 | A kind of non-intrusion type household electrical appliance sorter and method |
| CN108399221A (en) * | 2018-02-11 | 2018-08-14 | 山东建筑大学 | Indoor electric equipment classifying identification method and system based on big data association analysis |
| CN108429254A (en) * | 2018-03-07 | 2018-08-21 | 国网四川省电力公司电力科学研究院 | A kind of non-intrusion type power load recognition methods |
| CN109164327A (en) * | 2018-10-11 | 2019-01-08 | 深圳华建电力工程设计有限公司 | Electricity system electric appliance behavior discrimination method and device based on combined type criterion |
| CN109613360A (en) * | 2018-12-13 | 2019-04-12 | 四川长虹电器股份有限公司 | A kind of load recognition methods based on non-intruding monitor system |
| CN109934303A (en) * | 2019-03-25 | 2019-06-25 | 宁夏隆基宁光仪表股份有限公司 | A kind of non-invasive household electrical appliance load recognition methods, device and storage medium |
-
2019
- 2019-07-02 CN CN201910589435.7A patent/CN110381126B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140100805A1 (en) * | 2012-10-04 | 2014-04-10 | Kabushiki Kaisha Toshiba | Status estimation apparatus, status estimation method |
| KR101714698B1 (en) * | 2015-11-25 | 2017-03-09 | 고려대학교 산학협력단 | Apparatus and method home appliance identification using electric signal |
| CN106909101A (en) * | 2017-01-13 | 2017-06-30 | 中国海洋大学 | A kind of non-intrusion type household electrical appliance sorter and method |
| CN108399221A (en) * | 2018-02-11 | 2018-08-14 | 山东建筑大学 | Indoor electric equipment classifying identification method and system based on big data association analysis |
| CN108429254A (en) * | 2018-03-07 | 2018-08-21 | 国网四川省电力公司电力科学研究院 | A kind of non-intrusion type power load recognition methods |
| CN109164327A (en) * | 2018-10-11 | 2019-01-08 | 深圳华建电力工程设计有限公司 | Electricity system electric appliance behavior discrimination method and device based on combined type criterion |
| CN109613360A (en) * | 2018-12-13 | 2019-04-12 | 四川长虹电器股份有限公司 | A kind of load recognition methods based on non-intruding monitor system |
| CN109934303A (en) * | 2019-03-25 | 2019-06-25 | 宁夏隆基宁光仪表股份有限公司 | A kind of non-invasive household electrical appliance load recognition methods, device and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 袁坤等: "基于谐波特征矩阵的负载识别", 《石家庄铁道大学学报（自然科学版）》 * |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110658412B (en) * | 2019-10-31 | 2021-12-03 | 湖北源网汇融能源技术有限公司 | 5G base station power supply monitoring system, method, medium and equipment |
| CN110658412A (en) * | 2019-10-31 | 2020-01-07 | 刘新东 | 5G base station power supply monitoring system, method, medium and equipment |
| CN111178393A (en) * | 2019-12-11 | 2020-05-19 | 广东浩迪智云技术有限公司 | Electric appliance power consumption classification metering method and device based on intelligent electric meter |
| CN113408014A (en) * | 2020-03-17 | 2021-09-17 | 南宁富桂精密工业有限公司 | Terminal equipment identification system and method thereof |
| CN111257700A (en) * | 2020-03-31 | 2020-06-09 | 国网江苏省电力有限公司无锡供电分公司 | Power distribution network single-phase earth fault positioning device and method based on edge calculation |
| CN111257700B (en) * | 2020-03-31 | 2020-10-30 | 国网江苏省电力有限公司无锡供电分公司 | Power distribution network single-phase earth fault positioning device and method based on edge calculation |
| CN111860692A (en) * | 2020-07-31 | 2020-10-30 | 国网重庆市电力公司电力科学研究院 | Abnormal data detection method based on K-media in Internet of things environment |
| CN111860692B (en) * | 2020-07-31 | 2022-05-31 | 国网重庆市电力公司电力科学研究院 | Abnormal data detection method based on K-media in Internet of things environment |
| CN112034238A (en) * | 2020-09-11 | 2020-12-04 | 山东润一智能科技有限公司 | Electric equipment identification method and system |
| CN112255480A (en) * | 2020-10-12 | 2021-01-22 | 浙江长元科技有限公司 | Hall effect based electric appliance characteristic identification method and safety early warning system thereof |
| CN113030564A (en) * | 2021-03-10 | 2021-06-25 | 南方电网数字电网研究院有限公司 | Load identification method based on double-core intelligent electric meter system |
| CN113191600A (en) * | 2021-04-13 | 2021-07-30 | 清科优能(深圳)技术有限公司 | Intelligent house non-invasive load identification method based on data mining |
| CN113325248A (en) * | 2021-04-13 | 2021-08-31 | 清科优能(深圳)技术有限公司 | Intelligent house non-invasive load identification system based on edge calculation |
| CN113822333A (en) * | 2021-08-18 | 2021-12-21 | 威胜集团有限公司 | Electric appliance identification method and device and computer readable storage medium |
| CN114996287A (en) * | 2022-06-20 | 2022-09-02 | 上海电器科学研究所（集团）有限公司 | Automatic equipment identification and capacity expansion method based on feature library |
| CN114996287B (en) * | 2022-06-20 | 2024-04-16 | 上海电器科学研究所（集团）有限公司 | Automatic equipment identification and capacity expansion method based on feature library |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110381126B (en) | 2021-07-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110381126A (en) | Electrical equipment recognition methods, system, equipment and medium based on edge calculations | |
| He et al. | Non-intrusive load disaggregation using graph signal processing | |
| WO2022110557A1 (en) | Method and device for diagnosing user-transformer relationship anomaly in transformer area | |
| Azizi et al. | Residential household non-intrusive load monitoring via smart event-based optimization | |
| CN110781332A (en) | Electric power resident user daily load curve clustering method based on composite clustering algorithm | |
| US20130138651A1 (en) | System and method employing a self-organizing map load feature database to identify electric load types of different electric loads | |
| TWI663570B (en) | Power consumption analyzing server and power consumption analyzing method thereof | |
| CN113283446B (en) | Method and device for identifying object in image, electronic equipment and storage medium | |
| CN113933556B (en) | Method and device for detecting electricity stealing behavior, computer equipment and storage medium | |
| CN111726765A (en) | WIFI indoor positioning method and system for large-scale complex scene | |
| Panapakidis et al. | Enhancing the clustering process in the category model load profiling | |
| CN113591900A (en) | Identification method and device for high-demand response potential user and terminal equipment | |
| CN111612074A (en) | Identification method and device of non-invasive load monitoring electric equipment and related equipment | |
| CN112784778A (en) | Method, apparatus, device and medium for generating model and identifying age and gender | |
| CN117041017B (en) | Intelligent operation and maintenance management method and system for data center | |
| CN113591899A (en) | Power customer portrait recognition method and device and terminal equipment | |
| WO2023005976A1 (en) | Deep-learning-based identification method and apparatus for electric device | |
| CN113627361B (en) | Training method and device for face recognition model and computer program product | |
| CN112632857A (en) | Method, device, equipment and storage medium for determining line loss of power distribution network | |
| CN115841338A (en) | Method and device for determining abnormal electricity utilization behavior and non-volatile storage medium | |
| CN113449778B (en) | Model training method for quantum data classification and quantum data classification method | |
| CN113592218A (en) | Photovoltaic user baseline load estimation method and device and terminal equipment | |
| CN115049446A (en) | Merchant identification method and device, electronic equipment and computer readable medium | |
| CN113743838A (en) | Target user identification method and device, computer equipment and storage medium | |
| CN111222688A (en) | Daily load prediction method for commercial building |
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 |