CN109934303A - A kind of non-invasive household electrical appliance load recognition methods, device and storage medium - Google Patents
A kind of non-invasive household electrical appliance load recognition methods, device and storage medium Download PDFInfo
- Publication number
- CN109934303A CN109934303A CN201910225700.3A CN201910225700A CN109934303A CN 109934303 A CN109934303 A CN 109934303A CN 201910225700 A CN201910225700 A CN 201910225700A CN 109934303 A CN109934303 A CN 109934303A
- Authority
- CN
- China
- Prior art keywords
- electrical appliance
- neural network
- household electrical
- network model
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000003860 storage Methods 0.000 title claims abstract description 16
- 238000003062 neural network model Methods 0.000 claims abstract description 53
- 238000012549 training Methods 0.000 claims abstract description 23
- 238000001228 spectrum Methods 0.000 claims abstract description 22
- 238000012360 testing method Methods 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 6
- 230000002068 genetic effect Effects 0.000 claims description 6
- 210000002569 neuron Anatomy 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000013499 data model Methods 0.000 abstract description 3
- 230000000694 effects Effects 0.000 abstract description 2
- 238000013528 artificial neural network Methods 0.000 description 12
- 238000005520 cutting process Methods 0.000 description 5
- 238000005070 sampling Methods 0.000 description 5
- 241000208340 Araliaceae Species 0.000 description 3
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 3
- 235000003140 Panax quinquefolius Nutrition 0.000 description 3
- 235000008434 ginseng Nutrition 0.000 description 3
- 230000035772 mutation Effects 0.000 description 3
- 241000894007 species Species 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 210000004205 output neuron Anatomy 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 240000002853 Nelumbo nucifera Species 0.000 description 1
- 235000006508 Nelumbo nucifera Nutrition 0.000 description 1
- 235000006510 Nelumbo pentapetala Nutrition 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000003556 assay Methods 0.000 description 1
- 210000000349 chromosome Anatomy 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Abstract
This application discloses a kind of non-invasive household electrical appliance load recognition methods, including calculating the second target component according to the first object parameter obtained；Second target component is normalized；FFT transform is carried out to obtain harmonic spectrum and amplitude to the second target data after normalized, and using frequency spectrum and amplitude as sample data；Neural network model is constructed according to sample data, and neural network model is trained；It is identified according to load of the neural network model after training to household electrical appliance.This method, after calculating the second target data, not only the second target data is normalized, also to treated, the second target data carries out FFT transform, it can ensure that the accuracy of sample data, it obtains the higher neural network model of accuracy, and then the load identification accuracy of household electrical appliance can be improved.In addition, present invention also provides a kind of non-invasive household electrical appliance load identification device and storage medium, effect are as above.
Description
Technical field
This application involves electric system identification field more particularly to a kind of non-invasive household electrical appliance load recognition methods,
Device and storage medium.
Background technique
There are two types of electric appliance cutting load testing knowledge method for distinguishing is usual, i.e., invasive cutting load testing and non-invasive cutting load testing are known
Not.The realization of traditional invasive load identification mainly obtains house by installing detection sensor on each household electrical appliance
Then the electricity consumption data of front yard electric appliance transfers data to terminal by network, terminal is unified to be analyzed and handled to data.This
Although kind of method technical difficulty is relatively low, and be easily achieved, wiring is complicated, implements and maintenance cost is high, be it is a kind of very
Uneconomic scheme.Non-invasive cutting load testing identification technology is directly to survey setting loop detector in subscriber bus, at this
Software and hardware technology is utilized on device, and household electricity data are analyzed, the type of different electrical equipments are identified, at present to family
When the load of electrical appliance is identified, there is no handling data relevant to household electrical appliance, identification accuracy is lower.
It can be seen that the accuracy problem for how improving the identification of household electrical appliance load is that those skilled in the art are urgently to be resolved
The problem of.
Summary of the invention
This application provides a kind of non-invasive household electrical appliance load recognition methods, solve and how to improve in the prior art
The accuracy problem of household electrical appliance load identification.
In order to solve the above technical problems, this application provides a kind of non-invasive household electrical appliance load recognition methods, comprising:
The second target component is calculated according to the first object parameter obtained；
Second target component is normalized；
FFT transform is carried out to second target data after normalized to obtain harmonic spectrum and amplitude, and will
The frequency spectrum and amplitude are as sample data；
Neural network model is constructed according to the sample data, and the neural network model is trained；
The load of household electrical appliance is identified according to the neural network model after training.
Preferably, after the first object parameter according to acquisition calculates the second target component, further includes:
Duplicate removal processing is carried out to second target data.
It is preferably, described that the neural network model is trained specifically:
The sample data is divided into training data and test data；
The neural network model is trained using the training data, using the test data to the nerve
Network model is tested.
Preferably, described be trained using the training data to the neural network model includes:
Determine the interstitial content, weight and threshold value of the hidden layer of the neural network model；
The weight and the threshold value are optimized by genetic algorithm, make the output error of the neural network model
It is minimum.
Preferably, the neuron of the hidden layer uses S type tangent function.
In order to solve the above technical problems, present invention also provides a kind of and non-invasive household electrical appliance load recognition methods pair
The non-invasive household electrical appliance load identification device answered, comprising:
Computing module, for calculating the second target component according to the first object parameter obtained；
Processing module, for second target component to be normalized；
FFT transform module, for carrying out FFT transform to second target data after normalized to obtain harmonic wave
Frequency spectrum and amplitude, and using the frequency spectrum and amplitude as sample data；
Construct module, for according to the sample data construct neural network model, and to the neural network model into
Row training；
Identification module, for being identified according to the neural network model after training to the load of household electrical appliance.
In order to solve the above technical problems, present invention also provides another and non-invasive household electrical appliance load recognition methods
Corresponding non-invasive household electrical appliance load identification device, comprising:
Memory, for storing computer program；
Processor, for executing the calculation procedure to realize that non-invasive household electrical appliance described in above-mentioned any one are negative
The step of lotus recognition methods.
In order to solve the above technical problems, present invention also provides a kind of and non-invasive household electrical appliance load recognition methods pair
The computer readable storage medium answered is stored with computer program, the computer journey on the computer readable storage medium
Sequence is executed by processor the step of to realize non-invasive household electrical appliance load recognition methods described in any one of the above.
Compared with the prior art, a kind of non-invasive household electrical appliance load recognition methods provided herein, including according to
The second target component is calculated according to the first object parameter of acquisition；Second target component is normalized；To normalization
The second target data that treated carries out FFT transform to obtain harmonic spectrum and amplitude, and using frequency spectrum and amplitude as sample number
According to；Neural network model is constructed according to sample data, and neural network model is trained；According to the neural network after training
Model identifies the load of household electrical appliance.It can be seen that using this recognition methods, calculate the second target data it
Afterwards, not only the second target data is normalized, FFT also is carried out to the second target data after normalized later
Transformation, it can be ensured that the accuracy of sample data obtains the higher neural network model of accuracy, and then household electric can be improved
The load of device identifies accuracy.In addition, present invention also provides a kind of non-invasive household electrical appliance load identification device and storages
Medium, effect are as above.
Detailed description of the invention
For the clearer technical solution for illustrating the application, letter will be made to attached drawing needed in the embodiment below
The introduction wanted, it should be apparent that, it for those of ordinary skills, can be under the premise of not paying creativeness
It obtains other drawings based on these drawings.
Fig. 1 is a kind of non-invasive household electrical appliance load recognition methods flow chart provided by the embodiment of the present invention；
Fig. 2 is a kind of non-invasive household electrical appliance load identification device composition schematic diagram provided by the embodiment of the present invention；
Fig. 3 is the composition signal of another kind non-invasive household electrical appliance load identification device provided by the embodiment of the present invention
Figure.
Specific embodiment
In order to make those skilled in the art better understand the technical solutions in the application, below in conjunction with attached drawing, it is right
Technical solution in the embodiment of the present application carries out clear and complete description.
The core of the application is to provide a kind of non-invasive household electrical appliance load recognition methods, can solve in the prior art
How the accuracy problem of household electrical appliance load identification is improved.
Fig. 1 is a kind of non-invasive household electrical appliance load recognition methods flow chart provided by the embodiment of the present invention, such as Fig. 1
It is shown, method includes the following steps:
S101: the second target component is calculated according to the first object parameter obtained.
S102: the second target component is normalized.
S103: FFT transform is carried out to the second target data after normalized to obtain harmonic spectrum and amplitude, and will
Frequency spectrum and amplitude are as input sample data.
Particularly as being to install associated assay devices at the distribution mains of household electrical appliance, household electrical appliance are obtained by sampling
The parameters such as electric current, voltage (first object parameter) calculate active power, reactive power, nonactive electric current (the second target ginseng
Number) etc. these characteristic quantities, then calculated second target component is normalized, that is, is converted between [0,1]
Number, can be larger to avoid parameter differences such as power due to different household electrical appliance, the problem of having an impact to recognition result.It connects
FFT transform carried out to the second target component after normalized obtain particularly as being to convert frequency domain parameter for time domain parameter
To harmonic spectrum and amplitude, and using frequency spectrum and amplitude as input sample data.Preferably embodiment, in step S101
Later, further includes: duplicate removal processing is carried out to the second target data.Particularly as be in step S101 data (the second target ginseng
Number) it is screened, the data group that can represent household electrical appliance load characteristic is filtered out according to basic data screening method, to every kind of household electrical appliances
Characteristic data set, including four kinds of active power, reactive power, current harmonics, nonactive current harmonics characteristic data set duplicate removals
Processing.Processing method is by difference comparsion, and the difference d for comparing data matrix adjacent rows fundamental wave data recognizes if d >=0.1
It is effective for data.Finally, characteristic value obtained above is normalized.
S104: neural network model is constructed according to input sample data and household electrical appliance load, and to neural network model
It is trained.
S105: it is identified according to load of the neural network model after training to household electrical appliance.
Particularly as be according to the input sample data determined and household electrical appliance load building neural network model, it is then right
Neural network model is trained；It is finally identified according to load of the neural network model after training to household electrical appliance, i.e.,
As long as getting the parameters such as the electric current of household electrical appliance, voltage (first object parameter), so that it may utilize the neural network mould after training
Type obtains the load of household electrical appliance.
Preferably embodiment is trained neural network model specifically:
Sample data is divided into training data and test data；
Neural network model is trained using training data, neural network model is surveyed using test data
Examination.Preferably embodiment is trained neural network model using training data and comprises determining that neural network model
Hidden layer interstitial content, weight and threshold value；Weight and threshold value are optimized by genetic algorithm, make neural network mould
The output error of type is minimum.
Specifically, it is determined that the interstitial content of neural network hidden layer, 2N+1 node in hidden layer is set in the present embodiment,
Wherein N is characterized type number.M initial population is generated using quasi-random Halton sequenceAnd to just
Beginning population carries out binary coding, chromosome coding w11w12……wijb1……bn, wherein wijIndicate i-node and j node it
Between weight, bnIt is the threshold of node n.The input of neural network is the characteristic value of cutting load testing identification, the sampling of certain moment t is arranged
Feature vector are as follows:
Sc=[F (t)1,F(t)2,F(t)3…F(t)N]
Wherein, the species number that N is characterized, that is, neural network output layer number, C be input data set group
Number.The input value of i-th of input node of neural network is F (t)i, then corresponding hidden layer node, which exports, isThe neuron of preferably embodiment, hidden layer uses S type tangent function, S
Type tangent function are as follows:
So as to obtain the output valve of hidden layer neuron j are as follows:
The codomain range of output valve be [- 1,
1]。
It is K that hidden layer, which is arranged, to share neuron number, the electric appliance of output neuron number and load identification in the present embodiment
Species number is identical, and setting electric appliance species number is R, while the neural transferring function that output layer is arranged is S type logarithmic function, it may be assumed that
Thus to obtain the desired output of output neuron k are as follows:
The final output error for obtaining neural network are as follows:
All characteristic values that sampling obtains are defined as one group, the input data set of neural network contains 500 groups of definition
Characteristic value, sampling data rates 10k guarantees to extract apparent characteristic, with the operation week of each electric appliance
Phase is the sampling period.To obtain each state feature of electric operation.
Genetic algorithm in the present embodiment are as follows: setting Population Size is 100, and the number of iterations 50, operator uses roulette
Selection, crossover operator use single point crossing, and the training rate of crossover probability 0.8, mutation probability 0.02, neural network is
0.01, the number of iterations be set as 20 complete setting the number of iterations or target value less than 0.0001 when deconditioning.
Selection operator uses roulette selection algorithm, the selected probability of individual are as follows:
The cumulative probability of each individual is calculated, and generates the random number between one [0,1], if the value of random number exists
Between two individuals or it is equal to some individual, then the individual is genetic to the next generation.
The fitness function of each individual is
Using single point crossover operation, the selection random in genes of individuals of the individual of two random pairs intersects position in group
It sets, if the random number generated at this time is less than the crossover probability of setting, generates new individual later and be added into new population.
Same variation is less than mutation probability with the random number that should be generated still using a basic bit mutation is randomly selected
When individual be added in new population.
300 groups of load characteristic sampled datas of neural network input data set, experiment takes being averaged for ten operation results every time
Value, by the continuous iteration of genetic algorithm, the weight and threshold value of optimization neural network keep the output error of network minimum.
A kind of non-invasive household electrical appliance load recognition methods provided herein, including according to the first object obtained
Parameter calculates the second target component；Second target component is normalized；To the second target after normalized
Data carry out FFT transform to obtain harmonic spectrum and amplitude, and using frequency spectrum and amplitude as sample data；According to sample data structure
Neural network model is built, and neural network model is trained；According to the neural network model after training to household electrical appliance
Load is identified.It can be seen that using this recognition methods, after calculating the second target data, not only to the second target
Data are normalized, and also carry out FFT transform to the second target data after normalized later, it can be ensured that sample
The accuracy of data obtains the higher neural network model of accuracy, and then the load identification that household electrical appliance can be improved is accurate
Property.
It is described in detail, is based on above for a kind of embodiment of non-invasive household electrical appliance load recognition methods
A kind of non-invasive household electrical appliance load recognition methods of above-described embodiment description the embodiment of the invention also provides one kind and is somebody's turn to do
A kind of corresponding non-invasive household electrical appliance load identification device of method.Due to the embodiment of device part and the reality of method part
Example reciprocal correspondence is applied, therefore the embodiment of device part please refers to the embodiment description of method part, which is not described herein again.
Fig. 2 is a kind of non-invasive household electrical appliance load identification device composition schematic diagram provided by the embodiment of the present invention,
As shown in Fig. 2, the device includes computing module 201, processing module 202, FFT transform module 203, building module 204 and knowledge
Other module 205.
Computing module 201, for calculating the second target component according to the first object parameter obtained；
Processing module 202, for the second target component to be normalized；
FFT transform module 203, for carrying out FFT transform to the second target data after normalized to obtain harmonic wave
Frequency spectrum and amplitude, and using frequency spectrum and amplitude as sample data；
Module 204 is constructed, for constructing neural network model according to sample data, and neural network model is instructed
Practice；
Identification module 205, for being identified according to load of the neural network model after training to household electrical appliance.
A kind of non-invasive household electrical appliance load identification device provided herein, according to the first object ginseng obtained
Number calculates after the second target component；Just the second target component is normalized；Then to normalized after
Second target data carries out FFT transform to obtain harmonic spectrum and amplitude, and using frequency spectrum and amplitude as sample data；According to sample
Notebook data constructs neural network model, and is trained to neural network model；According to the neural network model after training to family
The load of electrical appliance is identified.It can be seen that using this identification device, it is not only right after calculating the second target data
Second target data is normalized, and also carries out FFT transform to the second target data after normalized later, can be with
The accuracy for ensuring sample data obtains the higher neural network model of accuracy, and then the load of household electrical appliance can be improved
Identify accuracy.
It is described in detail, is based on above for a kind of embodiment of non-invasive household electrical appliance load recognition methods
A kind of non-invasive household electrical appliance load recognition methods of above-described embodiment description, the embodiment of the invention also provides it is another with
A kind of corresponding non-invasive household electrical appliance load identification device of this method.Embodiment and method part due to device part
Embodiment corresponds to each other, therefore the embodiment of device part please refers to the embodiment description of method part, and which is not described herein again.
Fig. 3 is the composition signal of another kind non-invasive household electrical appliance load identification device provided by the embodiment of the present invention
Figure, as shown in figure 3, the device includes memory 301 and processor 302.
Memory 301, for storing computer program；
Processor 302 realizes non-invasive man provided by any one above-mentioned embodiment for executing calculation procedure
The step of electrical appliance load recognition methods.
Another non-invasive household electrical appliance load identification device provided herein, is calculating the second target data
Later, not only the second target data is normalized, also the second target data after normalized is carried out later
FFT transform, it can be ensured that the accuracy of sample data obtains the higher neural network model of accuracy, and then house can be improved
The load of electrical appliance identifies accuracy.
It is described in detail, is based on above for a kind of embodiment of non-invasive household electrical appliance load recognition methods
The non-invasive household electrical appliance load recognition methods of above-described embodiment description, the embodiment of the invention also provides a kind of and this method
Corresponding computer readable storage medium.Due to the embodiment of computer readable storage medium part and the embodiment of method part
It corresponds to each other, therefore the embodiment of computer readable storage medium part please refers to the embodiment description of method part, here not
It repeats again.
A kind of computer readable storage medium is stored with computer program, computer journey on computer readable storage medium
The step that sequence is executed by processor to realize the non-invasive household electrical appliance load recognition methods of above-mentioned any one embodiment offer
Suddenly.
A kind of computer readable storage medium provided by the present invention, processor can read in readable storage medium storing program for executing and store
Program, it can realize non-invasive household electrical appliance load recognition methods provided by above-mentioned any one embodiment, can be with
The accuracy for ensuring sample data obtains the higher neural network model of accuracy, and then the load of household electrical appliance can be improved
Identify accuracy.
Those skilled in the art will readily occur to its of the application after considering specification and practicing application disclosed herein
His embodiment.This application is intended to cover any variations, uses, or adaptations of the application, these modifications, purposes or
Person's adaptive change follow the general principle of the application and include common knowledge in the art disclosed in the present application or
Conventional techniques.Description and embodiments are considered only as exemplary, and the just true range of the application is pointed out by claim.
It should be understood that the application is not limited to the precise structure that has been described above and shown in the drawings, and
And various modifications and changes may be made without departing from the scope thereof.Above-described the application embodiment is not constituted to this Shen
Please protection scope restriction.
Claims (8)
1. a kind of non-invasive household electrical appliance load recognition methods characterized by comprising
The second target component is calculated according to the first object parameter obtained；
Second target component is normalized；
FFT transform is carried out to second target data after normalized to obtain harmonic spectrum and amplitude, and will be described
Frequency spectrum and amplitude are as sample data；
Neural network model is constructed according to the sample data, and the neural network model is trained；
The load of household electrical appliance is identified according to the neural network model after training.
2. non-invasive household electrical appliance load recognition methods according to claim 1, which is characterized in that obtained in the foundation
The first object parameter taken calculates after the second target component, further includes:
Duplicate removal processing is carried out to second target data.
3. non-invasive household electrical appliance load recognition methods according to claim 2, which is characterized in that described to the mind
It is trained through network model specifically:
The sample data is divided into training data and test data；
The neural network model is trained using the training data, using the test data to the neural network
Model is tested.
4. non-invasive household electrical appliance load recognition methods according to claim 3, which is characterized in that described in the utilization
Training data is trained the neural network model
Determine the interstitial content, weight and threshold value of the hidden layer of the neural network model；
The weight and the threshold value are optimized by genetic algorithm, make the output error of the neural network model most
It is small.
5. non-invasive household electrical appliance load recognition methods according to claim 4, which is characterized in that the hidden layer
Neuron uses S type tangent function.
6. a kind of non-invasive household electrical appliance load identification device characterized by comprising
Computing module, for calculating the second target component according to the first object parameter obtained；
Processing module, for second target component to be normalized；
FFT transform module, for carrying out FFT transform to second target data after normalized to obtain harmonic spectrum
And amplitude, and using the frequency spectrum and amplitude as sample data；
Module is constructed, for constructing neural network model according to the sample data, and the neural network model is instructed
Practice；
Identification module, for being identified according to the neural network model after training to the load of household electrical appliance.
7. a kind of non-invasive household electrical appliance load identification device characterized by comprising
Memory, for storing computer program；
Processor, for executing the calculation procedure to realize the non-invasive household as described in claim 1 to 5 any one
The step of electric appliance load recognition methods.
8. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program, the computer program are executed by processor to realize the non-invasive household as described in claim 1 to 5 any one
The step of electric appliance load recognition methods.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910225700.3A CN109934303A (en) | 2019-03-25 | 2019-03-25 | A kind of non-invasive household electrical appliance load recognition methods, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910225700.3A CN109934303A (en) | 2019-03-25 | 2019-03-25 | A kind of non-invasive household electrical appliance load recognition methods, device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109934303A true CN109934303A (en) | 2019-06-25 |
Family
ID=66988114
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910225700.3A Pending CN109934303A (en) | 2019-03-25 | 2019-03-25 | A kind of non-invasive household electrical appliance load recognition methods, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109934303A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110381126A (en) * | 2019-07-02 | 2019-10-25 | 山东建筑大学 | Electrical equipment recognition methods, system, equipment and medium based on edge calculations |
| CN110516743A (en) * | 2019-08-28 | 2019-11-29 | 珠海格力智能装备有限公司 | Recognition methods, device, storage medium and the processor of electrical equipment |
| CN110571806A (en) * | 2019-09-25 | 2019-12-13 | 北方民族大学 | Feature extraction and identification method for load category of power distribution network |
| CN110991263A (en) * | 2019-11-12 | 2020-04-10 | 华中科技大学 | Non-invasive load identification method and system for resisting background load interference |
| CN111191671A (en) * | 2019-11-18 | 2020-05-22 | 广东浩迪智云技术有限公司 | Electrical appliance waveform detection method and system, electronic equipment and storage medium |
| CN111898694A (en) * | 2020-08-07 | 2020-11-06 | 广东电网有限责任公司计量中心 | Non-invasive load identification method and device based on random tree classification |
| CN113420584A (en) * | 2021-03-16 | 2021-09-21 | 国网河南省电力公司安阳供电公司 | Load identification method and device based on genetic optimization neural network and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107122790A (en) * | 2017-03-15 | 2017-09-01 | 华北电力大学 | Non-intrusion type load recognizer based on hybrid neural networks and integrated study |
| CN107330517A (en) * | 2017-06-14 | 2017-11-07 | 华北电力大学 | One kind is based on S_Kohonen non-intrusion type resident load recognition methods |
| CN108537385A (en) * | 2018-04-12 | 2018-09-14 | 广东电网有限责任公司 | A kind of non-intrusion type residential electricity consumption load recognition methods |
| CN108616120A (en) * | 2018-04-28 | 2018-10-02 | 西安理工大学 | A kind of non-intrusive electrical load decomposition method based on RBF neural |
-
2019
- 2019-03-25 CN CN201910225700.3A patent/CN109934303A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107122790A (en) * | 2017-03-15 | 2017-09-01 | 华北电力大学 | Non-intrusion type load recognizer based on hybrid neural networks and integrated study |
| CN107330517A (en) * | 2017-06-14 | 2017-11-07 | 华北电力大学 | One kind is based on S_Kohonen non-intrusion type resident load recognition methods |
| CN108537385A (en) * | 2018-04-12 | 2018-09-14 | 广东电网有限责任公司 | A kind of non-intrusion type residential electricity consumption load recognition methods |
| CN108616120A (en) * | 2018-04-28 | 2018-10-02 | 西安理工大学 | A kind of non-intrusive electrical load decomposition method based on RBF neural |
Non-Patent Citations (1)
| Title |
|---|
| 徐琳: "基于改进遗传算法的非入侵式电器负荷识别", 《沈阳工业大学学报》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110381126A (en) * | 2019-07-02 | 2019-10-25 | 山东建筑大学 | Electrical equipment recognition methods, system, equipment and medium based on edge calculations |
| CN110381126B (en) * | 2019-07-02 | 2021-07-23 | 山东建筑大学 | Electric equipment identification method, system, equipment and medium based on edge calculation |
| CN110516743A (en) * | 2019-08-28 | 2019-11-29 | 珠海格力智能装备有限公司 | Recognition methods, device, storage medium and the processor of electrical equipment |
| CN110571806A (en) * | 2019-09-25 | 2019-12-13 | 北方民族大学 | Feature extraction and identification method for load category of power distribution network |
| CN110571806B (en) * | 2019-09-25 | 2023-05-12 | 北方民族大学 | Feature extraction and identification method for load category of power distribution network |
| CN110991263A (en) * | 2019-11-12 | 2020-04-10 | 华中科技大学 | Non-invasive load identification method and system for resisting background load interference |
| CN110991263B (en) * | 2019-11-12 | 2022-03-18 | 华中科技大学 | Non-invasive load identification method and system for resisting background load interference |
| CN111191671A (en) * | 2019-11-18 | 2020-05-22 | 广东浩迪智云技术有限公司 | Electrical appliance waveform detection method and system, electronic equipment and storage medium |
| CN111191671B (en) * | 2019-11-18 | 2023-11-14 | 广东浩迪智云技术有限公司 | Electrical appliance waveform detection method, system, electronic equipment and storage medium |
| CN111898694A (en) * | 2020-08-07 | 2020-11-06 | 广东电网有限责任公司计量中心 | Non-invasive load identification method and device based on random tree classification |
| CN111898694B (en) * | 2020-08-07 | 2021-09-17 | 广东电网有限责任公司计量中心 | Non-invasive load identification method and device based on random tree classification |
| CN113420584A (en) * | 2021-03-16 | 2021-09-21 | 国网河南省电力公司安阳供电公司 | Load identification method and device based on genetic optimization neural network and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109934303A (en) | A kind of non-invasive household electrical appliance load recognition methods, device and storage medium | |
| Wang et al. | Wind speed forecasting based on multi-objective grey wolf optimisation algorithm, weighted information criterion, and wind energy conversion system: A case study in Eastern China | |
| Cheng et al. | Enhanced state estimation and bad data identification in active power distribution networks using photovoltaic power forecasting | |
| CN109359665B (en) | Household appliance load identification method and device based on support vector machine | |
| Manohar et al. | Microgrid protection under weather uncertainty using joint probabilistic modeling of solar irradiance and wind speed | |
| CN104636985A (en) | Method for predicting radio disturbance of electric transmission line by using improved BP (back propagation) neural network | |
| CN110111606A (en) | A kind of vessel traffic flow prediction technique based on EEMD-IAGA-BP neural network | |
| CN115422788B (en) | Power distribution network line loss analysis management method, device, storage medium and system | |
| CN114580829A (en) | Power utilization safety sensing method, equipment and medium based on random forest algorithm | |
| Fu et al. | A compound framework incorporating improved outlier detection and correction, VMD, weight-based stacked generalization with enhanced DESMA for multi-step short-term wind speed forecasting | |
| CN115640969A (en) | Power grid operation and maintenance cost distribution method based on equipment state and operation age | |
| CN115129607A (en) | Power grid safety analysis machine learning model test method, device, equipment and medium | |
| Li et al. | Multi-objective evolutionary algorithms applied to non-intrusive load monitoring | |
| Ni et al. | Power quality disturbances identification based on adaptive symplectic geometric mode decomposition and improved marine predators algorithm | |
| CN116776209A (en) | Method, system, equipment and medium for identifying operation state of gateway metering device | |
| CN116707331A (en) | Inverter output voltage high-precision adjusting method and system based on model prediction | |
| Vinayagam et al. | Heterogeneous learning method of ensemble classifiers for identification and classification of power quality events and fault transients in wind power integrated microgrid | |
| CN113449968B (en) | New energy power grid frequency risk assessment method and device based on deep learning | |
| Wei et al. | Using a model structure selection technique to forecast short-term wind speed for a wind power plant in North China | |
| CN114897032A (en) | Current transformer fault diagnosis method and device based on width learning | |
| CN111784381B (en) | Power customer subdivision method and system based on privacy protection and SOM network | |
| Macêdo et al. | A new technique based on genetic algorithms for tracking of power system harmonics | |
| CN116340765B (en) | Electricity larceny user prediction method and device, storage medium and electronic equipment | |
| CN113159405B (en) | Wind power prediction method for optimizing LSSVR (least Square support vector regression) based on improved satin blue gardener algorithm | |
| CN117763504A (en) | Electric energy data null value processing method, system 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190625 |
|
| RJ01 | Rejection of invention patent application after publication |