CN108923426A - A kind of load recognition methods, device, equipment and computer readable storage medium - Google Patents
A kind of load recognition methods, device, equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN108923426A CN108923426A CN201810915986.3A CN201810915986A CN108923426A CN 108923426 A CN108923426 A CN 108923426A CN 201810915986 A CN201810915986 A CN 201810915986A CN 108923426 A CN108923426 A CN 108923426A
- Authority
- CN
- China
- Prior art keywords
- power
- appliance
- decomposed
- temporal characteristics
- group
- 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
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
This application discloses a kind of load recognition methods, device, equipment and computer readable storage medium, wherein method includes:Obtain the total consumed power curve of ammeter;Multiple power to be decomposed are determined according to the total consumed power order of a curve ladder type feature and the corresponding temporal characteristics of each power to be decomposed, the temporal characteristics include:Opening time and end time;In appliance power database, according to each power to be decomposed and its corresponding temporal characteristics, the corresponding appliance power group of each power to be decomposed is determined, the appliance power database includes:The corresponding temporal characteristics of each appliance power in the appliance power group and each appliance power group being made of each appliance power.Existing load identification is solved because data volume is huge, the technical issues of having higher requirements to the computing capability of equipment.
Description
Technical field
The application belongs to technical field of electric power more particularly to a kind of load recognition methods, device, equipment and computer-readable
Storage medium.
Background technique
With the development of society, the specific gravity that electricity consumption of resident accounts for power distribution network total electricity consumption is increasing, for user side
Load identifies to have obtained the extensive concern of researcher.Load identification refers under home scenarios, by the total consumed power of ammeter point
Each household electrical appliance are solved, the result that power grid can be identified according to load understands the consumption habit of user, promotes the pipe to user
Reason is horizontal.
But existing load recognition methods data volume is huge, has higher requirement to the computing capability of equipment, such as:Often
A second sampled point needs to carry out 24*60*60=86400 point if analyzing intraday load decomposition situation at this time
Analysis, data volume are more huge.
Summary of the invention
This application provides a kind of load recognition methods, device, equipment and computer readable storage mediums, are used for user terminal
The load of electricity consumption identifies solve existing review identification because data volume is huge, the skill having higher requirements to the computing capability of equipment
Art problem.
In view of this, the application first aspect provides a kind of load recognition methods, including:
Obtain the total consumed power curve of ammeter;
Multiple power to be decomposed and each described to be decomposed are determined according to the total consumed power order of a curve ladder type feature
The corresponding temporal characteristics of power, the temporal characteristics include:Opening time and end time;
In appliance power database, according to each power to be decomposed and its corresponding temporal characteristics, determine every
The corresponding appliance power group of one power to be decomposed, the appliance power database include:The electricity being made of each appliance power
The corresponding temporal characteristics of each appliance power in device power packages and each appliance power group.
Preferably, described that multiple power to be decomposed and each are determined according to the total consumed power order of a curve ladder type feature
The corresponding temporal characteristics of the power to be decomposed, the temporal characteristics include:Opening time and end time:
According to the total consumed power order of a curve ladder type feature, each ladder on the total consumed power curve is determined
Power mean value and the corresponding temporal characteristics of each ladder, the temporal characteristics include opening time and end time;
Using the power mean value of multiple ladders as multiple power to be decomposed, the temporal characteristics conduct of each ladder
The temporal characteristics of corresponding power to be decomposed.
Preferably, described in appliance power database, according to each power to be decomposed and its corresponding time
Feature determines that the corresponding appliance power group of each power to be decomposed specifically includes:
In appliance power database, determining all appliance power groups to be matched corresponding with each power to be decomposed
And the corresponding temporal characteristics of each appliance power group to be matched, each power to be decomposed and each institute corresponding to it
State in appliance power group to be matched the power of all electric appliances and equal;
According to the temporal characteristics of each power to be decomposed and its each of the corresponding appliance power group to be matched when
Between feature, determine the corresponding appliance power group of each power to be decomposed.
Preferably, the temporal characteristics according to each power to be decomposed and its each of the corresponding electric appliance to be matched
The temporal characteristics of power packages determine that the corresponding appliance power group of each power to be decomposed specifically includes:
Each of at the beginning of according to each power to be decomposed and its corresponding appliance power group to be matched
At the beginning of, at the beginning of calculating the power to be decomposed of each appliance power group to be matched corresponding to it on
Unlatching probability, and determine the first preset quantity unlatching maximum probability appliance power group to be matched;
In the appliance power group to be matched of the first preset quantity of each power to be decomposed, it is based on maximum likelihood degree
The estimation technique determines the maximum appliance power to be matched of likelihood score according to the end time of each appliance power group to be matched
Group, the maximum appliance power group to be matched of likelihood score be with its corresponding to power to be decomposed appliance power group.
Preferably, the method also includes:
Acquire the appliance power and the corresponding temporal characteristics of each appliance power when each electric appliance isolated operation in user family;
According to each operating power and the temporal characteristics of each operating power, the work of same time feature is determined
The rate of doing work constitutes appliance power group, obtains appliance power database.
Preferably, the appliance power in the acquisition user man when each electric appliance isolated operation and each appliance power are corresponding
Temporal characteristics specifically include:
Obtain operating power curve when each electric appliance isolated operation in user family;
The corresponding appliance power of operating power curve when each electric appliance isolated operation is obtained according to Unsupervised clustering algorithm
And the temporal characteristics of each appliance power.
Preferably, further include after the total consumed power curve for obtaining ammeter:
The total consumed power curve is pre-processed.
The application second aspect provides a kind of load identification device, including:
Acquiring unit, for obtaining the total consumed power curve of ammeter;
First unit, for determining multiple power to be decomposed and every according to the total consumed power order of a curve ladder type feature
The corresponding temporal characteristics of a power to be decomposed, the temporal characteristics include:Opening time and end time;
Second unit, in appliance power database, according to each power to be decomposed and its it is corresponding when
Between feature, determine the corresponding appliance power group of each power to be decomposed, the appliance power database includes:By each electric appliance
The corresponding temporal characteristics of each appliance power in the appliance power group and each appliance power group that power is constituted.
The application third aspect provides a kind of load identification equipment, and the equipment includes processor and memory:
Said program code is transferred to the processor for storing program code by the memory;
The processor is used for the load recognition methods above-mentioned according to the instruction execution in said program code.
The application fourth aspect provides a kind of computer readable storage medium, and the computer readable storage medium is for depositing
Program code is stored up, said program code is for executing above-mentioned load recognition methods.
As can be seen from the above technical solutions, the embodiment of the present application has the following advantages that:
This application provides a kind of load recognition methods, device, equipment and computer readable storage medium, wherein method packet
It includes:The total consumed power curve for obtaining ammeter first, because stepped variation is presented in total consumed power curve, each ladder is corresponding
One performance number, each performance number are corresponding with the use state of one group of household appliances, when total consumed power value is constant, family's electricity
The use state of device will not change, therefore determine multiple function to be decomposed according to total consumed power order of a curve ladder type feature
Then rate need to only decompose these power to be decomposed, obtain appliance power group (the use shape of household appliances corresponding to it
State), the use state of the household appliances of total consumed power curve entirety corresponding to these power to be decomposed can be obtained, be not necessarily to
To all point analysis on total consumed power curve, reduce data volume when calculating, so that load identification can also calculate energy
It is carried out in the not strong equipment of power, solves existing load identification because data volume is huge, have higher requirements to the computing capability of equipment
The technical issues of.
Detailed description of the invention
Fig. 1 is a kind of flow diagram of the first embodiment of load recognition methods in the embodiment of the present application;
Fig. 2 is a kind of flow diagram of the second embodiment of load recognition methods in the embodiment of the present application;
Fig. 3 is a kind of structural schematic diagram of load identification device in the embodiment of the present application;
Fig. 4 is the schematic diagram of the total consumed power curve of ammeter in the embodiment of the present application.
Specific embodiment
The embodiment of the present application provides a kind of load recognition methods, device, equipment and computer readable storage medium, is used for
The load of user terminal electricity consumption identifies solve existing review identification because data volume is huge, have higher want to the computing capability of equipment
The technical issues of asking.
In order to make those skilled in the art more fully understand application scheme, below in conjunction in the embodiment of the present application
Attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is only this
Apply for a part of the embodiment, instead of all the embodiments.Based on the embodiment in the application, those of ordinary skill in the art exist
Every other embodiment obtained under the premise of creative work is not made, shall fall in the protection scope of this application.
Referring to Fig. 1, a kind of flow diagram of the first embodiment of load recognition methods in the embodiment of the present application, packet
It includes:
Step 101, the total consumed power curve for obtaining ammeter.
It should be noted that obtaining the total consumed power curve of ammeter first when carrying out load identification.It is understood that
The abscissa for being consumption power curve is the time, and ordinate is power, as shown in Figure 4.
Step 102 determines multiple power to be decomposed and each to be decomposed according to total consumed power order of a curve ladder type feature
The corresponding temporal characteristics of power, temporal characteristics include:Opening time and end time.
It should be noted that each ladder corresponds to a performance number because stepped variation is presented in total consumed power curve,
Each performance number is corresponding with the use state of one group of household appliances, and when total consumed power value is constant, household appliances use shape
State will not change, therefore determine multiple power to be decomposed according to total consumed power order of a curve ladder type feature, and each
The temporal characteristics of power to be decomposed.
Step 103, in appliance power database, according to each power to be decomposed and its corresponding temporal characteristics, really
Determine the corresponding appliance power group of each power to be decomposed, appliance power database includes:The electric appliance function being made of each appliance power
The corresponding temporal characteristics of each appliance power in rate group and each appliance power group.
It should be noted that after determining multiple power to be decomposed on total consumed power curve, in appliance power database
In, according to each power to be decomposed and its corresponding temporal characteristics, determine the corresponding appliance power group of each power to be decomposed,
Appliance power database includes:Each appliance power in the appliance power group and each appliance power group being made of each appliance power
Corresponding temporal characteristics.
In the present embodiment, the total consumed power curve of ammeter is obtained first, because step type is presented in total consumed power curve
Variation, the corresponding performance number of each ladder, each performance number is corresponding with the use state of one group of household appliances, when wastage in bulk or weight function
When rate value is constant, the use state of household appliances will not change, therefore special according to total consumed power order of a curve ladder type
Sign determines multiple power to be decomposed, then need to only decompose to these power to be decomposed, obtain the appliance power corresponding to it
The family of total consumed power curve entirety corresponding to these power to be decomposed can be obtained in group (use states of household appliances)
The use state of electric appliance, without reducing data volume when calculating to all point analysis on total consumed power curve, so that negative
Lotus identification can also carry out in the not strong equipment of computing capability, solve existing load identification because data volume is huge, to equipment
The technical issues of computing capability has higher requirements.
The above are a kind of first embodiments of load recognition methods provided by the embodiments of the present application, and the following are the application implementations
A kind of second embodiment for load recognition methods that example provides.
Referring to Fig. 2, a kind of flow diagram of the second embodiment of load recognition methods in the embodiment of the present application, packet
It includes:
Appliance power and each appliance power in step 200, acquisition user man when each electric appliance isolated operation is corresponding
Temporal characteristics.
It should be noted that in order to create appliance power database, each electric appliance isolated operation in acquisition user man first
When appliance power and the corresponding temporal characteristics of each appliance power.
Further, the appliance power in acquisition user man when each electric appliance isolated operation and each appliance power are corresponding
Temporal characteristics specifically include:Obtain operating power curve when each electric appliance isolated operation in user family;According to Unsupervised clustering
The time of the corresponding appliance power of operating power curve and each appliance power when algorithm obtains each electric appliance isolated operation is special
Sign.It can be understood that the abscissa of the operating power curve of each electric appliance is the time, ordinate is power.It is understood that
It, can to each performance number when being although single electric appliance has a fixed operating power, but acquiring the operating power curve of electric appliance
Fluctuation can be had, therefore obtains according to Unsupervised clustering algorithm the operating power and each work function when each electric appliance isolated operation
The corresponding temporal characteristics of rate.Specifically, obtained according to Unsupervised clustering algorithm operating power when each electric appliance isolated operation and
The corresponding temporal characteristics of each operating power include:According to complete clustering algorithm obtain each electric appliance possibility operating power and and
The corresponding temporal characteristics of each possibility operating power, then according to class Center Fusion algorithm to may operating power merge
To the temporal characteristics of appliance power and each appliance power when each electric appliance isolated operation.
Step 201, according to each operating power and the temporal characteristics of each operating power, determine the work of same time feature
The rate of doing work constitutes appliance power group, obtains appliance power database.
It should be noted that appliance power and each appliance power pair in acquisition user man when each electric appliance isolated operation
After the temporal characteristics answered, it can determine that the operating power of same time feature constitutes appliance power group, all appliance power groups
Combination obtain appliance power database.
Step 202, the total consumed power curve for obtaining ammeter.
It should be noted that can pre-process to total consumed power curve, pretreatment includes but is not limited to using equal
Value filter is filtered.
Step 203, according to total consumed power order of a curve ladder type feature, determine each ladder on total consumed power curve
Power mean value and the corresponding temporal characteristics of each ladder, temporal characteristics include opening time and end time.
Step 204, using the power mean value of multiple ladders as multiple power to be decomposed, the temporal characteristics conduct of each ladder
The temporal characteristics of corresponding power to be decomposed.
Step 205, in appliance power database, determining all electric appliance function to be matched corresponding with each power to be decomposed
Rate group and the corresponding temporal characteristics of each appliance power group to be matched, each power to be decomposed with its corresponding to each of it is to be matched
The power of all electric appliances and equal in appliance power group.Such as the power to be decomposed of ammeter be 200W when, temporal characteristics are:Start
Time 13:00, the end time 14:00, it acquires appliance power in family and all appliance power groups to be matched when for 200W is:Family
The power of middle desk lamp and television set and be 200W, corresponding temporal characteristics are:Time started:13:00, the end time 15:00,
It there are also the power of washing machine and dish-washing machine and is 200W, corresponding temporal characteristics are:Time started:12:00, the end time
14:00, it there are also the power of computer and air-conditioning and is 200W, corresponding temporal characteristics are:Time started:13:00, the end time
14:00, it is 200W there are also the power of micro-wave oven, and micro-wave oven generally in the morning 7:00 uses, the end time 7:10, in the time
Section is used without other electric appliances.
It is understood that in order to enable the speed calculated faster, can be first by power in electric appliance data library and equal
Appliance power group merge into a class group, such as all power and be a class group for the appliance power group of 200W, institute is active
Rate and be a class group for the appliance power group of 300W, when decomposing appliance power group corresponding to power to be decomposed, it is known that
It after the performance number for decomposing power, need to only be found inside the corresponding class group of the value, substantially reduce and calculate the time.
Step 206, according to the temporal characteristics of each power to be decomposed and its each of corresponding appliance power group to be matched
Temporal characteristics, determine the corresponding appliance power group of each power to be decomposed.
It should be noted that in order to accelerate calculating speed, can according to each power to be decomposed at the beginning of and its institute
At the beginning of corresponding each appliance power group to be matched, calculate each appliance power group to be matched corresponding to it to point
Unlatching probability at the beginning of solution power, and determine the appliance power to be matched of the unlatching maximum probability of the first preset quantity
Group;Such as power to be decomposed be 200W when, can determine that the corresponding appliance power group to be matched of power packages to be decomposed is:Desk lamp and
The appliance power group to be matched that appliance power group, computer and the air-conditioning to be matched that television set is constituted are constituted.It is understood that
It is that the first preset quantity can be set according to actual needs.
In the appliance power group to be matched of the first preset quantity of each power to be decomposed, estimated based on maximum likelihood degree
Method determines the likelihood score of each electric appliance appliance power group to be matched according to the end time of each appliance power group to be matched, will
Appliance power group of the maximum appliance power group to be matched of likelihood score as corresponding power to be decomposed.For example, existing at this time
In 2 appliance power groups to be matched that previous step acquires, the likelihood score of each appliance power group end time to be matched is calculated, is asked
The likelihood score of appliance power group to be matched that is constituted of computer and air-conditioning is maximum, at this time i.e. by computer and air-conditioning constituted to
Appliance power group is matched as appliance power group.It is understood that the maximum likelihood degree estimation technique belongs to the prior art, herein not
It repeats again.
In the present embodiment, the total consumed power curve of ammeter is obtained first, because step type is presented in total consumed power curve
Variation, the corresponding performance number of each ladder, each performance number is corresponding with the use state of one group of household appliances, when wastage in bulk or weight function
When rate value is constant, the use state of household appliances will not change, therefore special according to total consumed power order of a curve ladder type
Sign determines multiple power to be decomposed, then need to only decompose to these power to be decomposed, obtain the appliance power corresponding to it
The family of total consumed power curve entirety corresponding to these power to be decomposed can be obtained in group (use states of household appliances)
The use state of electric appliance, without reducing data volume when calculating to all point analysis on total consumed power curve, so that negative
Lotus identification can also carry out in the not strong equipment of computing capability, solve existing load identification because data volume is huge, to equipment
The technical issues of computing capability has higher requirements.
The above are a kind of second embodiments of load recognition methods provided by the embodiments of the present application, and the following are the application implementations
A kind of embodiment for load identification device that example provides, please refers to Fig. 3.
A kind of load identification device provided in the embodiment of the present application, including:
Acquiring unit 301, for obtaining the total consumed power curve of ammeter;
First unit 302, for determining multiple power to be decomposed and every according to total consumed power order of a curve ladder type feature
The corresponding temporal characteristics of a power to be decomposed, temporal characteristics include:Opening time and end time;
Second unit 303 was used in appliance power database, according to each power to be decomposed and its corresponding time
Feature, determines the corresponding appliance power group of each power to be decomposed, and appliance power database includes:It is made of each appliance power
The corresponding temporal characteristics of each appliance power in appliance power group and each appliance power group.
In the present embodiment, the total consumed power curve of ammeter is obtained first, because step type is presented in total consumed power curve
Variation, the corresponding performance number of each ladder, each performance number is corresponding with the use state of one group of household appliances, when wastage in bulk or weight function
When rate value is constant, the use state of household appliances will not change, therefore special according to total consumed power order of a curve ladder type
Sign determines multiple power to be decomposed, then need to only decompose to these power to be decomposed, obtain the appliance power corresponding to it
The family of total consumed power curve entirety corresponding to these power to be decomposed can be obtained in group (use states of household appliances)
The use state of electric appliance, without reducing data volume when calculating to all point analysis on total consumed power curve, so that negative
Lotus identification can also carry out in the not strong equipment of computing capability, solve existing load identification because data volume is huge, to equipment
The technical issues of computing capability has higher requirements.
The embodiment of the present application also provides a kind of loads to identify equipment, and equipment includes processor and memory:Memory
Processor is transferred to for storing program code, and by program code;Processor is used for according to the instruction execution in program code
Above-mentioned load recognition methods.
The embodiment of the present application also provides a kind of computer readable storage medium, computer readable storage medium is for storing
Program code, program code is for executing above-mentioned load recognition methods.
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 system, device and method can be with
It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the unit
It divides, only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components
It can be combined or can be integrated into another system, or some features can be ignored or not executed.Another point, it is shown or
The mutual coupling, direct-coupling or communication connection discussed can be through some interfaces, the indirect coupling of device or unit
It closes or communicates to connect, can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, each functional unit in each embodiment of the application can integrate in one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can store in a computer readable storage medium.Based on this understanding, the technical solution of the application is substantially
The all or part of the part that contributes to existing technology or the technical solution can be in the form of software products in other words
It embodies, which is stored in a storage medium, including some instructions are used so that a computer
Equipment (can be personal computer, server or the network equipment etc.) executes the complete of each embodiment the method for the application
Portion or part steps.And storage medium above-mentioned includes:USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), magnetic or disk etc. are various can store journey
The medium of sequence code.
The above, above embodiments are only to illustrate the technical solution of the application, rather than its limitations;Although referring to before
Embodiment is stated the application is described in detail, those skilled in the art should understand that:It still can be to preceding
Technical solution documented by each embodiment is stated to modify or equivalent replacement of some of the technical features;And these
It modifies or replaces, the spirit and scope of each embodiment technical solution of the application that it does not separate the essence of the corresponding technical solution.
Claims (10)
1. a kind of load recognition methods, which is characterized in that including:
Obtain the total consumed power curve of ammeter;
Multiple power to be decomposed and each power to be decomposed are determined according to the total consumed power order of a curve ladder type feature
Corresponding temporal characteristics, the temporal characteristics include:Opening time and end time;
In appliance power database, according to each power to be decomposed and its corresponding temporal characteristics, each institute is determined
The corresponding appliance power group of power to be decomposed is stated, the appliance power database includes:The electric appliance function being made of each appliance power
The corresponding temporal characteristics of each appliance power in rate group and each appliance power group.
2. the method according to claim 1, wherein described special according to the total consumed power order of a curve ladder type
Sign determines multiple power to be decomposed and the corresponding temporal characteristics of each power to be decomposed, the temporal characteristics include:It opens
Time and end time:
According to the total consumed power order of a curve ladder type feature, the function of each ladder on the total consumed power curve is determined
Rate mean value and the corresponding temporal characteristics of each ladder, the temporal characteristics include opening time and end time;
Using the power mean value of multiple ladders as multiple power to be decomposed, the temporal characteristics of each ladder are as correspondence
Power to be decomposed temporal characteristics.
3. the method according to claim 1, wherein described in appliance power database, according to each described
Power to be decomposed and its corresponding temporal characteristics determine that the corresponding appliance power group of each power to be decomposed is specifically wrapped
It includes:
In appliance power database, determining all appliance power groups to be matched corresponding with each power to be decomposed and often
The corresponding temporal characteristics of a appliance power group to be matched, each power to be decomposed and its corresponding to each of it is described to
Match in appliance power group the power of all electric appliances and equal;
It is special according to the time of the temporal characteristics of each power to be decomposed and its each of the corresponding appliance power group to be matched
Sign determines the corresponding appliance power group of each power to be decomposed.
4. according to the method described in claim 3, it is characterized in that, the temporal characteristics according to each power to be decomposed and its
The temporal characteristics of each of corresponding appliance power group to be matched determine the corresponding electric appliance function of each power to be decomposed
Rate group specifically includes:
Each of at the beginning of according to each power to be decomposed and its corresponding appliance power group to be matched is opened
Begin the time, at the beginning of calculating the power to be decomposed of each appliance power group to be matched corresponding to it on open
Probability is opened, and determines the appliance power group to be matched of the unlatching maximum probability of the first preset quantity;
In the appliance power group to be matched of the first preset quantity of each power to be decomposed, estimated based on maximum likelihood degree
Method determines the maximum appliance power group to be matched of likelihood score, institute according to the end time of each appliance power group to be matched
State the maximum appliance power group to be matched of likelihood score be with its corresponding to power to be decomposed appliance power group.
5. the method according to claim 1, wherein the method also includes:
Acquire the appliance power and the corresponding temporal characteristics of each appliance power when each electric appliance isolated operation in user family;
According to each operating power and the temporal characteristics of each operating power, the work function of same time feature is determined
Rate constitutes appliance power group, obtains appliance power database.
6. according to the method described in claim 5, it is characterized in that, it is described acquisition user family in each electric appliance isolated operation when
Appliance power and the corresponding temporal characteristics of each appliance power specifically include:
Obtain operating power curve when each electric appliance isolated operation in user family;
The corresponding appliance power of operating power curve when each electric appliance isolated operation and each is obtained according to Unsupervised clustering algorithm
The temporal characteristics of a appliance power.
7. the method according to claim 1, wherein also being wrapped after the total consumed power curve for obtaining ammeter
It includes:
The total consumed power curve is pre-processed.
8. a kind of load identification device, which is characterized in that including:
Acquiring unit, for obtaining the total consumed power curve of ammeter;
First unit, for determining multiple power to be decomposed and each institute according to the total consumed power order of a curve ladder type feature
The corresponding temporal characteristics of power to be decomposed are stated, the temporal characteristics include:Opening time and end time;
Second unit is used in appliance power database, special according to each power to be decomposed and its corresponding time
Sign, determines the corresponding appliance power group of each power to be decomposed, and the appliance power database includes:By each appliance power
The corresponding temporal characteristics of each appliance power in the appliance power group of composition and each appliance power group.
9. a kind of load identifies equipment, which is characterized in that the equipment includes processor and memory:
Said program code is transferred to the processor for storing program code by the memory;
The processor is used for the load according to instruction execution any one of claims 1 to 7 in said program code
Recognition methods.
10. a kind of computer readable storage medium, which is characterized in that the computer readable storage medium is for storing program generation
Code, said program code is for load recognition methods described in any one of perform claim requirement 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810915986.3A CN108923426B (en) | 2018-08-13 | 2018-08-13 | Load identification method, device, equipment and computer readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810915986.3A CN108923426B (en) | 2018-08-13 | 2018-08-13 | Load identification method, device, equipment and computer readable storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108923426A true CN108923426A (en) | 2018-11-30 |
CN108923426B CN108923426B (en) | 2021-09-03 |
Family
ID=64404371
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810915986.3A Active CN108923426B (en) | 2018-08-13 | 2018-08-13 | Load identification method, device, equipment and computer readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108923426B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113159988A (en) * | 2021-04-14 | 2021-07-23 | 杭州电力设备制造有限公司 | User electric appliance load state analysis method, device, equipment and readable storage medium |
CN116454924A (en) * | 2023-06-16 | 2023-07-18 | 华东交通大学 | Flexible load power regulation and control method based on correlation coefficient |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2015059272A1 (en) * | 2013-10-24 | 2015-04-30 | Universite Libre De Bruxelles | Improved non-intrusive appliance load monitoring method and device |
CN104915559A (en) * | 2015-06-10 | 2015-09-16 | 武汉阿帕科技有限公司 | Electric equipment determination method and electric equipment determination system |
CN106815677A (en) * | 2016-12-09 | 2017-06-09 | 国网北京市电力公司 | The recognition methods of non-intrusion type load and device |
-
2018
- 2018-08-13 CN CN201810915986.3A patent/CN108923426B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2015059272A1 (en) * | 2013-10-24 | 2015-04-30 | Universite Libre De Bruxelles | Improved non-intrusive appliance load monitoring method and device |
CN104915559A (en) * | 2015-06-10 | 2015-09-16 | 武汉阿帕科技有限公司 | Electric equipment determination method and electric equipment determination system |
CN106815677A (en) * | 2016-12-09 | 2017-06-09 | 国网北京市电力公司 | The recognition methods of non-intrusion type load and device |
Non-Patent Citations (1)
Title |
---|
程祥等: "非侵入式负荷监测与分解研究综述", 《电网技术》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113159988A (en) * | 2021-04-14 | 2021-07-23 | 杭州电力设备制造有限公司 | User electric appliance load state analysis method, device, equipment and readable storage medium |
CN113159988B (en) * | 2021-04-14 | 2022-08-02 | 杭州电力设备制造有限公司 | User electric appliance load state analysis method, device, equipment and readable storage medium |
CN116454924A (en) * | 2023-06-16 | 2023-07-18 | 华东交通大学 | Flexible load power regulation and control method based on correlation coefficient |
CN116454924B (en) * | 2023-06-16 | 2023-09-29 | 华东交通大学 | Flexible load power regulation and control method based on correlation coefficient |
Also Published As
Publication number | Publication date |
---|---|
CN108923426B (en) | 2021-09-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110262899A (en) | Monitor component elastic telescopic method, apparatus and controlled terminal based on Kubernetes cluster | |
CN105404690B (en) | The method and apparatus for inquiring database | |
CN107957992B (en) | Automatic processing method and system for user feedback information | |
CN114721833B (en) | Intelligent cloud coordination method and device based on platform service type | |
CN107404740B (en) | Method for switching network, device and the terminal device of safety | |
CN108923426A (en) | A kind of load recognition methods, device, equipment and computer readable storage medium | |
CN108989397A (en) | Data recommendation method, device and storage medium | |
CN110162390B (en) | Task allocation method and system for fog computing system | |
CN109450987A (en) | Number generation method, apparatus and system and storage medium | |
Shaoshuai et al. | MODM-based evaluation model of service quality in the Internet of Things | |
CN110161300A (en) | A kind of monitoring method and monitoring device of low-voltage power supply | |
CN110968920A (en) | Method for placing chain type service entity in edge computing and edge computing equipment | |
CN109117039A (en) | Display method and terminal equipment | |
CN109783494A (en) | Date storage method and relevant apparatus | |
CN109710542A (en) | A kind of completely N-ary tree construction method and device | |
CN109149574A (en) | Charging method and system based on electricity price | |
CN109633283A (en) | Bus capacitor capacitance monitoring method, device and terminal device | |
CN110399534B (en) | Terminal performance report generation method, device, equipment and storage medium | |
CN106210120B (en) | A kind of recommended method and its device of server | |
CN109359011A (en) | Method and device for monitoring blockage of Android system and terminal equipment | |
Ping et al. | FL-TAC: Enhanced Fine-Tuning in Federated Learning via Low-Rank, Task-Specific Adapter Clustering | |
US10264061B2 (en) | User service access allocation method and system | |
CN110222014A (en) | Distributed file system crush map maintaining method and associated component | |
CN112437137B (en) | Internet of things data connection method and system | |
CN114449466B (en) | User charging intelligent monitoring method and device, electronic equipment and storage medium |
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 |