CN111242161A - Non-invasive non-resident user load identification method based on intelligent learning - Google Patents
Non-invasive non-resident user load identification method based on intelligent learning Download PDFInfo
- Publication number
- CN111242161A CN111242161A CN201911375093.5A CN201911375093A CN111242161A CN 111242161 A CN111242161 A CN 111242161A CN 201911375093 A CN201911375093 A CN 201911375093A CN 111242161 A CN111242161 A CN 111242161A
- Authority
- CN
- China
- Prior art keywords
- load
- switching
- data
- data set
- test data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000012360 testing method Methods 0.000 claims description 60
- 238000012549 training Methods 0.000 claims description 54
- 230000006870 function Effects 0.000 claims description 13
- 238000007635 classification algorithm Methods 0.000 claims description 12
- 238000003062 neural network model Methods 0.000 claims description 12
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000005259 measurement Methods 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 abstract description 11
- 238000013528 artificial neural network Methods 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000012544 monitoring process Methods 0.000 description 5
- 238000011160 research Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005183 dynamical system Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
The invention provides a non-invasive non-resident user load identification method based on intelligent learning. Firstly, load identification is carried out on collected data of the loads of the non-resident users by using a trained K nearest algorithm model, and switching time data corresponding to different loads are obtained. And then, carrying out relevant statistical arrangement on the obtained switching time data of each load. And inputting the sorted load switching time data into a trained BP neural network, and fitting the switching time probability distribution curve of each load. And finally, judging whether the identified load type is correct or not according to the fitted switching probability distribution curve of each load. The invention can ensure the accuracy of identifying the loads of the non-resident users, and fits the switching probability distribution curve of the non-resident loads through an intelligent learning method to know the use habits of the non-resident users on different loads and help the load identification to carry out further judgment.
Description
Technical Field
The invention belongs to the technical field of intelligent power utilization and non-invasive load identification, and particularly relates to a non-invasive non-resident user load identification method based on intelligent learning.
Background
With the rapid development of smart grid construction, power demand side management, which is a management method for load control and power mining participated by customers, is continuously developed, so that power resources can be more reasonably and effectively configured in China, and the power utilization efficiency of a terminal is effectively improved. Meanwhile, the non-invasive load monitoring has a huge research space and receives wide attention at home and abroad. However, the current method is mostly applied to monitoring various electrical appliances of residential users, and for loads of non-residential users, which are important components of power grid loads, related researches are not much. Non-intrusive load monitoring is generally divided into three main steps of event detection, feature extraction and load identification. However, the load identification methods used at present have the problem that the partial load characteristics are overlapped and difficult to identify, which also results in the insufficient load identification accuracy in the present non-invasive load monitoring system.
Disclosure of Invention
The invention provides a non-intrusive non-resident user load identification method for solving the problem that partial load characteristics are overlapped and difficult to identify in the prior art.
Specifically, the invention provides a non-intrusive non-resident user load identification method based on intelligent learning, which is characterized by comprising the following steps:
step S1: collecting load characteristic sample data of each electric appliance in non-resident user data when a switching event occurs, and preprocessing the load characteristic sample data to be used as a training data set;
step S2: randomly selecting load characteristic sample data of several unknown electrical appliances when switching events occur from non-resident user data, and preprocessing the load characteristic sample data to be used as a test data set;
step S3: identifying the types of the unknown electric appliances through a K nearest neighbor classification algorithm model;
step S4: inputting the training data set into a BP neural network model until the training data set is exhausted or an error function meets requirements;
step S5: inputting the test data set into a BP neural network model to obtain the relationship between the switching probability and the switching time of a plurality of electrical appliances;
step S6: and analyzing whether the relation between the switching probability and the switching time of the plurality of electrical appliances conforms to the use habit of the corresponding electrical appliances or not, and verifying whether the identified type of the electrical appliances is correct or not.
Further, in step S1, the training data set performs fourier series expansion on the current data according to the steady-state operating current data of each electrical appliance during the switching event in the collected non-residential user data, and the expanded current harmonic amplitude with a relatively large amplitude is used as the training data set.
Further, in step S2, the test data set performs fourier series expansion on the current data according to the steady-state operating current data of the collected non-residential user data when switching events occur to a plurality of electrical appliances, and the current harmonic amplitude with a relatively large amplitude obtained after the expansion is used as the test data set.
Further, step S3 includes the following steps:
step S31: inputting the training data set and the test data set into the K nearest classification algorithm model and setting a value of K;
step S32: calculating distance measurement by adopting the weighted Euclidean distance, and obtaining K training data similar to the test data;
step S33: and judging the class of the test data as the class of the training data closer to the test data, and obtaining a classification result.
Further, in step S32, the weighted euclidean distance is expressed as:
wherein ,wkIs the weight of each sample; x is the number ofiIs the ith test data vector, xjIs the jth training data vector, xi and xjEach having n feature components; x is the number ofikI.e. the kth characteristic component, x, of the ith test datumjkI.e. the kth feature component of the jth training data.
Further, in step S33, the classification result is expressed as:
wherein ,
is the predicted classification result of the test data, xtestIs test data, x'jIs and test data xtestJth training data, f (x'j) Is x'jA category label of (1); y isiIs a class i load; δ is a 0, 1 function, δ (a, b) is 1 only if a is b, otherwise δ (a, b) is 0; y is a vector of i × 1, i is the total number of load types; w is ajIs the weight of the vote.
Further, in step S33, the weight of the vote is represented as:
furthermore, in step S5, the relationship between the switching probability and the switching time of the plurality of electrical appliances is obtained through the test data set to obtain a switching frequency distribution curve of the plurality of electrical appliances, the switching frequency distribution curve of the plurality of electrical appliances is integrated to obtain an area under each curve, and the switching probability distribution curve of the plurality of electrical appliances is divided by the area to obtain a switching probability distribution curve of the plurality of electrical appliances.
The invention has the beneficial effects that:
the method has remarkable advantages for solving the problems of various loads of non-resident users, large load identification error and the like. The non-intrusive load monitoring system is used for collecting the electricity consumption data of the non-resident users so as to monitor the energy consumption of various non-resident loads and charge the energy consumption at different periods, and then various characteristics of the loads are extracted from the data.
According to the invention, various non-resident user loads are preliminarily classified through the K nearest algorithm model, the K0 nearest algorithm model classifier does not need to use a training set for training in advance, the training time complexity is 0, and the preliminary classification of various non-resident user loads is more convenient and faster.
The invention utilizes the characteristics to carry out load identification so as to establish a generalized intelligent learning model to fit the switching probability distribution curve of the non-resident load, so as to know the use habits of people on different loads and further help the load identification to carry out further judgment. The method has the advantages of higher accuracy, obvious improvement on the load identification accuracy, simple principle and convenient implementation.
Drawings
Fig. 1 is a schematic diagram illustrating steps of a non-intrusive non-resident user load identification method based on smart learning according to an embodiment of the present invention;
fig. 2 is a current waveform diagram of a classroom electric lamp provided by an embodiment of the invention;
fig. 3 is a current waveform diagram of a projector provided by an embodiment of the present invention;
FIG. 4 is a plot of the convergence trend of the loss function of classroom lights provided by an embodiment of the present invention;
FIG. 5 is a diagram illustrating a convergence trend of the loss function of the projector according to the embodiment of the present invention;
fig. 6 is a probability distribution diagram of classroom lights provided by an embodiment of the invention;
fig. 7 is a probability distribution diagram of a projector according to an embodiment of the present invention.
Detailed Description
The technical solution of the present invention is further described in detail by the following embodiments with reference to fig. 1 to 7.
As shown in fig. 1, the embodiment of the present application provides a non-intrusive non-resident user load identification method based on smart learning, which includes the following steps:
step S1: collecting load characteristic sample data of each electric appliance in non-resident user data when a switching event occurs, and preprocessing the load characteristic sample data to be used as a training data set;
step S2: randomly selecting load characteristic sample data of several unknown electrical appliances when switching events occur from non-resident user data, and preprocessing the load characteristic sample data to be used as a test data set;
step S3: identifying the types of a plurality of unknown electrical appliances through a K nearest classification algorithm model;
step S4: inputting the training data set into a BP neural network model until the training data set is exhausted or an error function meets requirements;
step S5: inputting the test data set into a BP neural network model to obtain the relationship between the switching probability and the switching time of a plurality of electrical appliances;
step S6: and analyzing whether the relation between the switching probability and the switching time of the plurality of electrical appliances conforms to the use habit of the corresponding electrical appliances or not, and verifying whether the identified type of the electrical appliances is correct or not.
Specifically, in step S1, steady-state operating current data of each electrical appliance when a switching event occurs in the collected non-residential user data is extracted, fourier series expansion is performed on the current data, and a current harmonic amplitude with a relatively large amplitude obtained after the expansion is used as a load characteristic sample as a training data set.
In step S2, randomly selecting stable-state working current data of several unknown electrical appliances when switching events occur from the collected non-resident user data, performing fourier series expansion on the current data, and taking the current harmonic amplitude with a larger amplitude obtained after expansion as a load characteristic sample as a test data set.
In step S3, a K-nearest neighbor classification algorithm, which is an intelligent distance-based learning method, is used for non-intrusive load identification.
Since the model built using the K-nearest neighbor classification algorithm has no very obvious training process, it will not start to compute after the training data set is input, and it will only start to compute when the test data set is input for classification. For an input test data set, the K nearest classification algorithm model firstly finds K training data closest to the test data, and finally determines the class of the test data by a voting method according to class marks of the K training data.
The non-intrusive load identification process by using the K nearest neighbor algorithm model further comprises the following steps:
step S31: inputting the training data set and the testing data set into the K nearest neighbor classification algorithm model and setting the value of K.
Step S32: calculating distance measurement by adopting the weighted Euclidean distance, and obtaining K training data similar to the test data; wherein the weighted euclidean distance is expressed as:
wherein ,wkIs the weight of each sample; x is the number ofiIs the ith test data vector, xjIs the jth training data vector, xi and xjEach having n feature components; x is the number ofikI.e. the kth characteristic component, x, of the ith test datumjkI.e. the kth feature component of the jth training data.
The K nearest neighbor classification algorithm model performs weighting according to the distance between the test data and the neighbor training data, and the training data with the closer distance between the test data and the neighbor training data has the heavier weight, so that the optimal weight value is mainly selected by a traversal method. And after the traversal is finished, K training data similar to the test data are obtained according to the weight.
Step S33: the test data is judged to be the class of the training data closer to the test data, and the result obtained by classification can be represented as:
wherein ,
is the predicted classification result of the test data, xtestIs test data, x'jIs and test data xtestJth training data, f (x'j) Is x'jA category label of (1); y isiIs a class i load; δ is a 0, 1 function, δ (a, b) is 1 only if a is b, otherwise δ (a, b) is 0; y is a vector of i × 1, i is the total number of load types; w is ajIs the weight of the vote:
the types of a plurality of unknown electric appliances can be identified through the K nearest classification algorithm model. Since the K value has been determined in advance, the K training data closest to the test data are selected. We classify the training data and label, yiIt represents the ith class load, only if the reference number f (x ') of the jth training data'j) And yiSame, delta (y)i,f(x′j) ) can take 1, otherwise 0; thus, by changing yiThe value of i in (1) is calculated to yiThe sum of each value of i. By passing
The function being to select yiThe largest after the sum in, say y1Then the test data can be discriminated as a first type load.
In step S4, most of the load identification methods used at present compare the extracted features with the features in the feature library to determine the closest load as the load, so that if there is a problem that the features of several extracted loads are close to each other, erroneous determination may occur. The probability distribution research is carried out on the load switching time data obtained by non-invasive load identification, so that the use habits of users on different electrical appliances can be known, the result of load identification can be further judged, and the accuracy of load identification is ensured.
The BP neural network is used as a neural network algorithm with wide application, and has strong learning capability and storage capability for a large number of input-output mapping relations. In addition, since the BP neural network is an adaptive nonlinear dynamical system mainly composed of a large number of neurons, it has a very good effect on fitting a nonlinear function curve. Therefore, the invention adopts a BP neural network algorithm to fit the load switching probability distribution curve.
Inputting the training data set into a BP neural network model, enabling the BP neural network model to carry out 10000 times of iterative training, and continuously adjusting until the training data is exhausted or the model training is finished when an error function meets requirements, wherein the obtained actual output is closest to an expected result.
In step S5, the test data set is input into the trained BP neural network model to perform 10000 times of iterative operations, and the weights among the neural network units are continuously adjusted by a gradient descent method to select an optimal weight, so that the output result is as close to an expected value as possible, the problem of error correction in the BP neural network model is solved, and the switching frequency distribution curves of a plurality of electrical appliances can be obtained. And then, normalizing the switching frequency distribution curve chart of the plurality of electric appliances, namely integrating the switching frequency distribution curve of each electric appliance to obtain the area under each curve, dividing the switching frequency distribution curve of each electric appliance by the obtained area, and obtaining the switching probability distribution curve chart of the plurality of electric appliances through normalization.
In step S6, whether the switching probability distribution curves of the plurality of electrical appliances conform to the usage habits of the corresponding electrical appliances is analyzed. Therefore, the obtained switching probability distribution curve graphs of the plurality of electric appliances are analyzed, the abscissa in the graph is 24 hours a day, and the ordinate is the probability density, so that the probability that the electric appliance is used in each time period is the area below the time curve corresponding to the time period. The result identified by the K nearest algorithm is judged again through the obtained probability distribution curve graph, the misjudgment condition of the K nearest algorithm is corrected, and the accuracy of load identification is ensured.
As shown in fig. 2-3, in an embodiment, steady-state working current data of each electrical appliance in a school when a switching event occurs is collected, current harmonic amplitudes with larger amplitudes are selected as training data through fourier series expansion, and the training data are input into a load identification model in the school established by a nearest K algorithm; and collecting the steady-state working current data of two electric appliances in the school at random when switching events occur, expanding the steady-state working current data through Fourier series, selecting the current harmonic amplitude with larger amplitude as test data, and inputting the test data into a load identification model in the school established by a nearest K algorithm. Two types of unknown electric appliances are identified through a K nearest classification algorithm model: classroom lights and projectors.
As shown in fig. 4-5, training data is input into the BP neural network model for training, and the loss function loss tends to 0 after 10000 iterations in the obtained loss function loss convergence trend graph of each electrical appliance, so that the input test data can obtain the optimal effect.
As shown in fig. 6-7, the test data is input into the trained BP neural network model to perform iterative operation, so as to obtain the switching frequency distribution curves of the two electrical appliances, and the switching frequency distribution curves of the two electrical appliances are normalized to obtain the switching probability distribution curves of the two electrical appliances.
The classroom electric light is analyzed firstly, the fact that the electric light is basically used in one day and the used time period shows a very regular pattern can be found, the probability that the classroom electric light is normally used after six hours at night is higher, the classroom electric light is rarely used even in other time periods, therefore, the fact that the electric appliance corresponding to the switching probability distribution curve is not the classroom electric light can be known, misjudgment can be judged when load identification is carried out through a K nearest neighbor algorithm, at the moment, the electric appliance is classified into a second large type of electric appliance found when the load is identified, namely a refrigerator of a school supermarket, and the fact that the used time period of the refrigerator of the school supermarket is consistent with the condition shown by the switching probability distribution curve can be found. The same can judge that the time of the projector is used accords with the teaching habit, and the projector is used frequently in the morning, afternoon and evening every day. Therefore, the invention can improve the accuracy of load identification according to the use habits of non-residential users on the electric appliances.
Although the present invention has been described in terms of the preferred embodiment, it is not intended that the invention be limited to the embodiment. Any equivalent changes or modifications made without departing from the spirit and scope of the present invention also belong to the protection scope of the present invention. The scope of the invention should therefore be determined with reference to the appended claims.
Claims (8)
1. A non-intrusive non-resident user load identification method based on intelligent learning is characterized in that the collaborative management and control method comprises the following steps:
step S1: collecting load characteristic sample data of each electric appliance in non-resident user data when a switching event occurs, and preprocessing the load characteristic sample data to be used as a training data set;
step S2: randomly selecting load characteristic sample data of several unknown electrical appliances when switching events occur from non-resident user data, and preprocessing the load characteristic sample data to be used as a test data set;
step S3: identifying the types of the unknown electric appliances through a K nearest neighbor classification algorithm model;
step S4: inputting the training data set into a BP neural network model until the training data set is exhausted or an error function meets requirements;
step S5: inputting the test data set into a BP neural network model to obtain the relationship between the switching probability and the switching time of a plurality of electrical appliances;
step S6: and analyzing whether the relation between the switching probability and the switching time of the plurality of electrical appliances conforms to the use habit of the corresponding electrical appliances or not, and verifying whether the identified type of the electrical appliances is correct or not.
2. The user load identification method according to claim 1, wherein in step S1, the training data set performs fourier series expansion on the current data according to the steady-state operating current data of each electrical appliance in the collected non-residential user data when a switching event occurs, and the current harmonic amplitude with a relatively large amplitude obtained after the expansion is used as the training data set.
3. The cooperative management and control method according to claim 1, wherein in step S2, the test data set performs fourier series expansion on current data through steady-state operating current data of several electric appliances in the collected non-residential user data when switching events occur, and current harmonic amplitudes with relatively large amplitudes obtained after the fourier series expansion are used as the test data set.
4. The cooperative management and control method according to claim 1, wherein in step S3, the method further includes the steps of:
step S31: inputting the training data set and the test data set into the K nearest classification algorithm model and setting a value of K;
step S32: calculating distance measurement by adopting the weighted Euclidean distance, and obtaining K training data similar to the test data;
step S33: and judging the class of the test data as the class of the training data closer to the test data, and obtaining a classification result.
5. The cooperative management and control method according to claim 4, wherein in step S32, the weighted euclidean distance is expressed as:
wherein ,wkIs the weight of each sample; x is the number ofiIs the ith test data vector, xjIs the jth training data vector, xi and xjEach having n feature components; x is the number ofikI.e. the kth characteristic component, x, of the ith test datumjkI.e. jth training numberAccording to the k-th feature component.
6. The cooperative management and control method according to claim 5, wherein in step S33, the classification result is expressed as:
wherein ,
is the predicted classification result of the test data, xtestIs test data, x'jIs and test data xtestJth training data, f (x'j) Is x'jA category label of (1); y isiIs a class i load; δ is a 0, 1 function, δ (a, b) is 1 only if a is b, otherwise δ (a, b) is 0; y is a vector of i × 1, i is the total number of load types; w is ajIs the weight of the vote.
7. The cooperative management and control method according to claim 6, wherein in step S33, the weight of the vote is expressed as:
8. the cooperative management and control method according to claim 1, wherein in step S5, the relationship between the switching probability and the switching time of the plurality of electrical appliances is obtained by obtaining switching frequency distribution curves of the plurality of electrical appliances through the test data set, integrating the switching frequency distribution curves of the plurality of electrical appliances to obtain areas under the curves, and dividing the switching frequency distribution curves of the plurality of electrical appliances by the areas to obtain switching probability distribution maps of the plurality of electrical appliances.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911375093.5A CN111242161B (en) | 2019-12-27 | 2019-12-27 | Non-invasive non-resident user load identification method based on intelligent learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911375093.5A CN111242161B (en) | 2019-12-27 | 2019-12-27 | Non-invasive non-resident user load identification method based on intelligent learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111242161A true CN111242161A (en) | 2020-06-05 |
| CN111242161B CN111242161B (en) | 2023-08-25 |
Family
ID=70865575
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911375093.5A Active CN111242161B (en) | 2019-12-27 | 2019-12-27 | Non-invasive non-resident user load identification method based on intelligent learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111242161B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112381264A (en) * | 2020-10-20 | 2021-02-19 | 昆明理工大学 | Electricity load identification method based on improved graph convolution neural network |
| CN112446416A (en) * | 2020-10-09 | 2021-03-05 | 国网山东省电力公司日照供电公司 | Non-invasive load monitoring and identifying method and system |
| CN112989131A (en) * | 2021-03-29 | 2021-06-18 | 广州水沐青华科技有限公司 | Graph representation learning electric appliance equipment power fingerprint decomposition method, storage medium and system |
| CN113033775A (en) * | 2021-03-10 | 2021-06-25 | 南方电网数字电网研究院有限公司 | Non-invasive load identification network architecture based on supervised learning |
| CN114977176A (en) * | 2022-07-19 | 2022-08-30 | 深圳江行联加智能科技有限公司 | Power load decomposition method, device, equipment and storage medium |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050037515A1 (en) * | 2001-04-23 | 2005-02-17 | Nicholson Jeremy Kirk | Methods for analysis of spectral data and their applications osteoporosis |
| US20120212213A1 (en) * | 2011-02-18 | 2012-08-23 | Honeywell International Inc. | Non-invasive energy consumption monitoring |
| US20140207398A1 (en) * | 2013-01-23 | 2014-07-24 | Samsung Electronics Co., Ltd | Transient Normalization for Appliance Classification, Disaggregation, and Power Estimation in Non-Intrusive Load Monitoring |
| CN105972761A (en) * | 2016-05-25 | 2016-09-28 | 华北电力大学（保定） | Non-invasive air conditioner load monitoring method |
| CN106908671A (en) * | 2017-01-13 | 2017-06-30 | 中国海洋大学 | A kind of non-intrusion type household loads intelligent detecting method and system |
| CN108054749A (en) * | 2017-11-27 | 2018-05-18 | 华北电力大学 | A kind of non-intrusive electrical load decomposition method and device |
| WO2018099418A1 (en) * | 2016-11-30 | 2018-06-07 | The Chinese University Of Hong Kong | Analysis of cell-free dna in urine and other samples |
| CN109145949A (en) * | 2018-07-19 | 2019-01-04 | 山东师范大学 | Non-intrusive electrical load monitoring and decomposition method and system based on integrated study |
| WO2019025938A1 (en) * | 2017-08-04 | 2019-02-07 | 3M Innovative Properties Company | Confined space configuration and operations management system |
| CN109752613A (en) * | 2018-12-31 | 2019-05-14 | 天津求实智源科技有限公司 | Default electricity use detection system and method based on non-intrusion type load monitoring |
| CN109767054A (en) * | 2018-11-22 | 2019-05-17 | 福建网能科技开发有限责任公司 | Efficiency cloud appraisal procedure and edge efficiency gateway based on deep neural network algorithm |
| CN110376457A (en) * | 2019-06-28 | 2019-10-25 | 同济大学 | Non-intrusion type load monitoring method and device based on semi-supervised learning algorithm |
| CN110443302A (en) * | 2019-08-02 | 2019-11-12 | 天津相和电气科技有限公司 | Load discrimination method and its application based on Fusion Features and deep learning |
-
2019
- 2019-12-27 CN CN201911375093.5A patent/CN111242161B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050037515A1 (en) * | 2001-04-23 | 2005-02-17 | Nicholson Jeremy Kirk | Methods for analysis of spectral data and their applications osteoporosis |
| US20120212213A1 (en) * | 2011-02-18 | 2012-08-23 | Honeywell International Inc. | Non-invasive energy consumption monitoring |
| US20140207398A1 (en) * | 2013-01-23 | 2014-07-24 | Samsung Electronics Co., Ltd | Transient Normalization for Appliance Classification, Disaggregation, and Power Estimation in Non-Intrusive Load Monitoring |
| CN105972761A (en) * | 2016-05-25 | 2016-09-28 | 华北电力大学（保定） | Non-invasive air conditioner load monitoring method |
| WO2018099418A1 (en) * | 2016-11-30 | 2018-06-07 | The Chinese University Of Hong Kong | Analysis of cell-free dna in urine and other samples |
| CN106908671A (en) * | 2017-01-13 | 2017-06-30 | 中国海洋大学 | A kind of non-intrusion type household loads intelligent detecting method and system |
| WO2019025938A1 (en) * | 2017-08-04 | 2019-02-07 | 3M Innovative Properties Company | Confined space configuration and operations management system |
| CN108054749A (en) * | 2017-11-27 | 2018-05-18 | 华北电力大学 | A kind of non-intrusive electrical load decomposition method and device |
| CN109145949A (en) * | 2018-07-19 | 2019-01-04 | 山东师范大学 | Non-intrusive electrical load monitoring and decomposition method and system based on integrated study |
| CN109767054A (en) * | 2018-11-22 | 2019-05-17 | 福建网能科技开发有限责任公司 | Efficiency cloud appraisal procedure and edge efficiency gateway based on deep neural network algorithm |
| CN109752613A (en) * | 2018-12-31 | 2019-05-14 | 天津求实智源科技有限公司 | Default electricity use detection system and method based on non-intrusion type load monitoring |
| CN110376457A (en) * | 2019-06-28 | 2019-10-25 | 同济大学 | Non-intrusion type load monitoring method and device based on semi-supervised learning algorithm |
| CN110443302A (en) * | 2019-08-02 | 2019-11-12 | 天津相和电气科技有限公司 | Load discrimination method and its application based on Fusion Features and deep learning |
Non-Patent Citations (3)
| Title |
|---|
| 宋旭帆;周明;涂京;李庚银;: "基于k-NN结合核Fisher判别的非侵入式负荷监测方法" * |
| 康丽萍;孙显;许光銮;: "加权KNN的图文数据融合分类" * |
| 程祥;李林芝;吴浩;丁一;宋永华;孙维真;: "非侵入式负荷监测与分解研究综述" * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112446416A (en) * | 2020-10-09 | 2021-03-05 | 国网山东省电力公司日照供电公司 | Non-invasive load monitoring and identifying method and system |
| CN112381264A (en) * | 2020-10-20 | 2021-02-19 | 昆明理工大学 | Electricity load identification method based on improved graph convolution neural network |
| CN113033775A (en) * | 2021-03-10 | 2021-06-25 | 南方电网数字电网研究院有限公司 | Non-invasive load identification network architecture based on supervised learning |
| CN113033775B (en) * | 2021-03-10 | 2023-08-18 | 南方电网数字电网研究院有限公司 | Non-invasive load identification network architecture based on supervised learning |
| CN112989131A (en) * | 2021-03-29 | 2021-06-18 | 广州水沐青华科技有限公司 | Graph representation learning electric appliance equipment power fingerprint decomposition method, storage medium and system |
| CN114977176A (en) * | 2022-07-19 | 2022-08-30 | 深圳江行联加智能科技有限公司 | Power load decomposition method, device, equipment and storage medium |
| CN114977176B (en) * | 2022-07-19 | 2022-11-18 | 深圳江行联加智能科技有限公司 | Power load decomposition method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111242161B (en) | 2023-08-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111242161B (en) | Non-invasive non-resident user load identification method based on intelligent learning | |
| Liu et al. | Energy disaggregation of appliances consumptions using ham approach | |
| CN110991786B (en) | 10kV static load model parameter identification method based on similar daily load curve | |
| CN109145949A (en) | Non-intrusive electrical load monitoring and decomposition method and system based on integrated study | |
| CN112699913A (en) | Transformer area household variable relation abnormity diagnosis method and device | |
| CN112149873B (en) | Low-voltage station line loss reasonable interval prediction method based on deep learning | |
| CN111209976B (en) | Non-invasive load monitoring method and system | |
| CN109598451A (en) | A kind of non-intrusion type load discrimination method based on PCA Yu LSTM neural network | |
| CN106485089B (en) | The interval parameter acquisition methods of harmonic wave user's typical condition | |
| CN111368904B (en) | Electrical equipment identification method based on electric power fingerprint | |
| CN110119545B (en) | Non-invasive power load identification method based on stack type self-encoder | |
| CN105740635B (en) | A kind of cloud ideal solution evaluation method of transformer electromagnetic design scheme | |
| CN110321934A (en) | A kind of method and system detecting user power utilization abnormal data | |
| CN106154180A (en) | Energy-storage battery charge/discharge anomaly detection method and detecting system | |
| CN109359665A (en) | A kind of family's electric load recognition methods and device based on support vector machines | |
| CN113780684A (en) | Intelligent building user energy consumption behavior prediction method based on LSTM neural network | |
| CN113887912A (en) | Non-invasive load identification method for deeply learning downward embedded equipment | |
| CN114236234A (en) | Electrical appliance characteristic identification method based on fundamental wave and harmonic wave mixed criterion | |
| Feng et al. | Identification of disturbance sources based on random forest model | |
| CN117332288A (en) | Building energy saving technology evaluation system and method | |
| CN104360948A (en) | IEC 61850 configuration file engineering consistency test method based on fuzzy algorithm | |
| CN110889465B (en) | Power demand side equipment identification method and system based on self-adaptive resonant network | |
| Shijian et al. | Energy efficiency evaluation system based on ladder-based comprehensive assessment method | |
| Nuran et al. | Non-Intrusive Load Monitoring Method for Appliance Identification Using Random Forest Algorithm | |
| CN109378834A (en) | Large scale electric network voltage stability margin assessment system based on information maximal correlation |
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 |