CN116776181A - Terminal side load identification method, medium and system based on improved fuzzy clustering - Google Patents
Terminal side load identification method, medium and system based on improved fuzzy clustering Download PDFInfo
- Publication number
- CN116776181A CN116776181A CN202310644357.2A CN202310644357A CN116776181A CN 116776181 A CN116776181 A CN 116776181A CN 202310644357 A CN202310644357 A CN 202310644357A CN 116776181 A CN116776181 A CN 116776181A
- Authority
- CN
- China
- Prior art keywords
- load
- terminal side
- algorithm
- improved
- 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 30
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 42
- 238000012545 processing Methods 0.000 claims abstract description 11
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 10
- 238000005070 sampling Methods 0.000 claims description 23
- 239000011159 matrix material Substances 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 2
- 238000009499 grossing Methods 0.000 claims description 2
- 238000001228 spectrum Methods 0.000 claims description 2
- 230000009466 transformation Effects 0.000 claims description 2
- 238000012850 discrimination method Methods 0.000 claims 1
- 238000011160 research Methods 0.000 abstract description 5
- 230000035945 sensitivity Effects 0.000 abstract description 3
- 238000010606 normalization Methods 0.000 description 5
- 238000011161 development Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 238000004378 air conditioning Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000010561 standard procedure Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2337—Non-hierarchical techniques using fuzzy logic, i.e. fuzzy clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
- G06F2218/04—Denoising
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Automation & Control Theory (AREA)
- Probability & Statistics with Applications (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a terminal side load identification method, medium and system based on improved fuzzy clustering, comprising the following steps: decomposing and reconstructing the obtained load signal at the terminal side by adopting a variation mode decomposition algorithm to obtain an intrinsic mode component of the load signal; and carrying out load identification on the intrinsic mode components of the load signal by adopting an improved probability fuzzy C-means clustering algorithm to obtain the load type corresponding to the load signal. The invention adopts the VMD algorithm to inhibit the noise and interference of the load, effectively separates the characteristic frequencies of similar loads, shows good robustness when processing bad data including noise interference and the like, adopts the improved PFCM algorithm to overcome the sensitivity to distortion data, reduces the operand, improves the clustering effectiveness, improves the accuracy of load identification, and has certain guiding significance for load identification research.
Description
Technical Field
The invention relates to the technical field of load identification, in particular to a terminal side load identification method, medium and system based on improved fuzzy clustering.
Background
The load data of the power system is an important scientific basis for explaining the electricity consumption condition and the development trend of each type in social activities, and is also an important basis for researching and analyzing the relationship between the economic development trend and the production trend of each department of the power system. With the wide development of the electric power market in recent years, the load identification of an electric power system has become the basic research content of the work of electric power planning, customized electricity price, system trend, load modeling and the like as the universal application of the work of the power supply side and the power demand side. Therefore, the analysis and research on the load identification technology can further improve the overall management level of the power system, is convenient for researching the long-term trend of the load of the power consumer, and has important significance for scientific management and operation work of the power supply side.
The clustering algorithm is one of key technologies in the fields of image recognition, data mining and the like, and has extremely wide application value. With the advent of the big data age, a large amount of inconsistent data, mixed type data, partial value missing data and the like are generated, while traditional clustering algorithms such as a fuzzy C-means clustering algorithm and a K-means algorithm are sensitive to an initial clustering center and distortion data, and clustering consistency is easy to generate under the big data age, so that the phenomenon of unclear judgment of classification results is caused by the clustering results.
Disclosure of Invention
The embodiment of the invention provides a terminal side load identification method, medium and system based on improved fuzzy clustering, which are used for solving the problem that the load identification classification result in the prior art is unclear.
In a first aspect, a terminal side load identification method based on improved fuzzy clustering is provided, including:
decomposing and reconstructing the obtained load signal at the terminal side by adopting a variation mode decomposition algorithm to obtain an intrinsic mode component of the load signal;
and carrying out load identification on the intrinsic mode components of the load signal by adopting an improved probability fuzzy C-means clustering algorithm to obtain the load type corresponding to the load signal.
In a second aspect, there is provided a computer readable storage medium having computer program instructions stored thereon; the computer program instructions, when executed by a processor, implement a terminal side load identification method based on improved fuzzy clustering as described in the embodiment of the first aspect.
In a third aspect, a terminal side load identification system based on improved fuzzy clustering is provided, including: a computer readable storage medium as in the second aspect embodiment described above.
In this way, the embodiment of the invention adopts the VMD algorithm to inhibit the noise and interference of the load, effectively separates the characteristic frequencies of similar loads, shows good robustness when processing bad data including noise interference and the like, adopts the improved PFCM algorithm to overcome the sensitivity to distortion data, reduces the operand, improves the clustering effectiveness, improves the accuracy of load identification, and has a certain guiding significance for load identification research.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments of the present invention will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a terminal side load identification method based on improved fuzzy clustering according to an embodiment of the present invention;
FIG. 2 is a flow chart of a variation modal decomposition algorithm;
FIG. 3 is a flowchart of an improved probability fuzzy C-means clustering algorithm;
FIG. 4 is a schematic block diagram of a computer-readable storage medium of an embodiment of the present invention;
fig. 5 is a block diagram of a terminal side load recognition system based on improved fuzzy clustering according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The embodiment of the invention discloses a terminal side load identification method based on improved fuzzy clustering. As shown in fig. 1, the method of the embodiment of the invention includes the following steps:
step S101: and decomposing and reconstructing the obtained load signal at the terminal side by adopting a variation mode decomposition algorithm to obtain an intrinsic mode component of the load signal.
The terminal side may be a home appliance side, and the terminal is various home appliances, for example, an air conditioner, a television, and the like.
Specifically, as shown in fig. 2, this step includes the following procedure:
1. it is assumed that the load signal is decomposed into several orders of eigenmode components.
2. And for each order of intrinsic mode component, obtaining an analysis signal of each order of intrinsic mode component through Hilbert transformation.
The resolved signal of the k-order eigenmode component is represented by:
wherein ,uk Representing the kth order eigenmode component, i.e. { u 1 ,u 2 ,...,u k δ (t) represents a pulse function, and t represents a sampling time.
3. Introducing an index operator into the analysis signal, adjusting the corresponding center frequency, and estimating the frequency bandwidth of each order of intrinsic mode component through a Gaussian smoothing index after the frequency spectrum of each order of intrinsic mode component is modulated onto the corresponding base frequency band to obtain a constraint variation function.
Specifically, an exponential operator is introduced into the analytic signal, as shown in the following formula:
wherein ,ωk Representing the center frequency corresponding to the kth order eigenmode component, i.e. { omega 1 ,ω 2 ,...,ω k }。
The constraint variation function includes:
wherein ,the symbol of the bias is represented, and f represents the load signal.
4. The constrained variational function is converted into an unconstrained variational function by introducing Lagrange functions.
Specifically, the unconstrained variational function is represented by the following formula:
wherein λ represents Lagrang operator, which may increase constraint stringency; alpha represents a penalty factor that may increase the accuracy of the signal reconstruction.
5. And solving the unconstrained variational function by a multiplication operator alternating direction method, and continuously and iteratively updating the intrinsic mode component and the corresponding center frequency until the iteration stop condition is met.
To solve the above-mentioned variation problem, the method of alternately using multiplication operators to alternately search forLambda (lambda) n+1 Thereby solving the saddle point of the Lagrange function, namely the constraint variation optimal solution shown in the formula.
Wherein the kth order modal IMF component u k Center frequency omega k And the iterative update formulas of Lagrange operator lambda are respectively expressed as follows:
wherein ,indicating the current residual quantity->Results after wiener filtering, < >>Representing the corresponding center frequency of the eigenmode component, < ->Representing the fourier transform result of the eigenmode component with the real part of the inverse fourier transform passing through the time domain form of the eigenmode component { u } k (t) } represents ∈> and />Respectively representing the nth and the n+1th Fourier transform results of Lagrang operator, wherein τ represents noise margin, and good denoising effect can be obtained by taking 0 under the condition of strong background noise, and +.>Representing the fourier transform result of the load signal, ω represents the center frequency corresponding to the first order eigenmode component.
When the constraint variation problem is solved, the center frequency and the frequency bandwidth of the k-order eigenmode components are gradually and adaptively updated, the characteristic frequencies of similar loads are effectively separated, the load data at the terminal side is reconstructed, and the problem of modal aliasing of signals is effectively solved.
Step S102: and carrying out load identification on the intrinsic mode components of the load signal by adopting an improved probability fuzzy C-means clustering algorithm to obtain the load type corresponding to the load signal.
Specifically, the method comprises the following steps:
1. and (3) introducing the covariance matrix into a PCM algorithm, combining the PCM algorithm with an FCM algorithm, and establishing an objective function of the improved probability fuzzy C-means clustering algorithm.
Introducing a covariance matrix for describing the compactness of a data matrix into a PCM (Possimiltic C-Means clustering) algorithm can improve the clustering effectiveness, so that the PCM algorithm is improved, and the improved PCM algorithm can be expressed as:
wherein c represents the number of clusters, n represents the number of samples, the samples are eigen mode components, m represents fuzzy weights, d ij Representing sample X j Into clustersHeart V i Euclidean distance, t ij Representing a sample representative value, sigma 2 Representing covariance matrix, i is more than or equal to 1 and less than or equal to c, j is more than or equal to 1 and less than or equal to n.
Specifically, the covariance matrix is:
wherein ,representing the average value of the sample vector,/">
In order to overcome the defects that the improved PCM algorithm has consistency and FCM (Fuzzy C-means) algorithm is sensitive to distortion data and reduce the operation cost, the improved PCM algorithm and the FCM algorithm are combined to obtain an objective function J of an improved probability Fuzzy C-means clustering algorithm (PFCM) m,p (U, T, V) specifically as follows:
wherein ,uij And (3) representing the membership degree of the jth sample er belonging to the ith class of cluster, wherein a, b and p represent preset parameters.
Specifically, the fuzzy membership matrix is:
wherein γ represents the number of iterations, d kj Representing sample X j To the clustering center V k Is a euclidean distance of (c).
Specifically, the sample typical values are:
specifically, the class center matrix is:
2. and inputting the intrinsic mode components of the load signal into the objective function for iterative calculation until the objective function converges to the minimum, and obtaining the load type corresponding to the load signal.
As shown in fig. 3, setting relevant parameters includes: optimal clustering number, clustering center, fuzzy weighting number and maximum iteration number. Input X j Calculating covariance matrix, fuzzy membership matrix, sample typical value and class center matrix of the sample, and continuously iterating until J is obtained by calculation m,p (U, T, V) converges to a minimum value as a load type corresponding to the load signal. The load types include: fixed load, variable load, and unexpected load.
Preferably, before step S101, the embodiment of the present invention performs preprocessing on the collected raw data, so as to reduce adverse effects caused by distorted data, and the specific process is as follows:
1. and acquiring load data of each terminal at the terminal side in the scene at each sampling time in the target time period to obtain a first data sequence.
It should be understood that the sequences are all chronological. It should also be understood that the load data of one sampling time includes load data of different terminals collected in the application scenario. The load data may be fundamental wave active power, reactive power, fundamental wave current amplitude, 3, 5, 7 harmonic current amplitude, etc. when the electric equipment is in steady state operation. In addition, if the collected load data is missing or repeated, the collected load data can be identified and restored by a conventional method.
For example, the air conditioning current, television current, computer current, etc. are collected at sample time t1, and one type of load data collected at each sample time may be represented in the form of a column vector.
2. And deleting distorted load data in the first data sequence to obtain a second data sequence.
Specifically, before this step, the distortion data is found by the following method, and the specific process includes:
(1) The mean, residual error and standard deviation of the load data for each sample time in the first data sequence are calculated.
Specifically, the average value ofThe calculation formula is as follows:
wherein ,Xjs Represents the load data, and J represents the number of load data at the sampling time.
Specifically, residual error T js The calculation formula is as follows:
specifically, the standard deviation δ is calculated as follows:
(2) And judging whether the Laida criterion is met or not according to the average value, the residual error and the standard deviation of the load data of each sampling time.
(3) If the Laida criterion is satisfied, the load data distortion of the sampling time is determined.
Specifically, the Laida criterion is: first, assuming that load data of a sampling time only contains random errors, when the residual error of the load data of the sampling time is calculated to be more than three times of standard deviation, the load data of the sampling time is considered to be coarse errors rather than random errors, and the load data of the sampling time is taken as distortion data to be removed.
3. And carrying out standardization processing on the load data of each sampling time in the second data sequence to obtain a third data sequence.
As described above, the load data for one sampling time contains data for a plurality of different terminals, and therefore, these data are normalized by this step. Specifically, the embodiment of the invention adopts a normalization standard method (Z-Score), and the specific calculation formula is as follows:
wherein ,Xi Representing load data before normalization processing, y i Represents the load data after normalization processing, μ represents the mean value of the load data before normalization processing, σ represents the standard deviation of the load data before normalization processing.
4. And extracting the load data of the same terminal in the third data sequence to obtain a load signal.
For example, load data of the air conditioner is extracted, and the load signals are obtained still according to time sequence.
Through the processing, the original data is screened and standardized in advance, so that the subsequent detection of steady-state events and classification are facilitated, and the method is more efficient and accurate.
Furthermore, as shown in fig. 4, an embodiment of the present invention further provides a computer-readable storage medium having computer program instructions stored thereon; the computer program instructions, when executed by a processor, implement the terminal side load identification method based on improved fuzzy clustering as described in the above embodiments.
In addition, the embodiment of the invention also provides a terminal side load identification system based on improved fuzzy clustering, which comprises the following steps: the computer-readable storage medium as in the above embodiments.
Specifically, as shown in fig. 5, the system includes: the device comprises a load acquisition module, a load preprocessing module, a load decomposition module and a load identification module.
The load acquisition module is used for acquiring load data of each terminal at the terminal side included in the scene at each sampling time in the target time period to obtain a first data sequence.
The load preprocessing module is used for calculating the mean value, the residual error and the standard deviation of the load data of each sampling time in the first data sequence; judging whether the Laida criterion is met or not according to the average value, the residual error and the standard deviation of the load data of each sampling time; if the Laida criterion is met, determining that the load data of the sampling time is distorted, and deleting the distorted load data in the first data sequence to obtain a second data sequence; carrying out standardization processing on the load data of each sampling time in the second data sequence to obtain a third data sequence; and extracting the load data of the same terminal in the third data sequence to obtain a load signal.
The load decomposition module is used for decomposing and reconstructing the obtained load signal at the terminal side by adopting a variation modal decomposition algorithm to obtain an intrinsic modal component of the load signal.
The load identification module is used for carrying out load identification on the intrinsic mode components of the load signal by adopting an improved probability fuzzy C-means clustering algorithm to obtain the load type corresponding to the load signal.
In summary, the embodiment of the invention adopts the VMD algorithm to inhibit the noise and interference of the load, effectively separates the characteristic frequencies of similar loads, shows good robustness when processing bad data including noise interference and the like, adopts the improved PFCM algorithm to overcome the sensitivity to distortion data, reduces the operand, improves the clustering effectiveness, improves the accuracy of load identification, and has certain guiding significance for load identification research.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (10)
1. The terminal side load identification method based on the improved fuzzy clustering is characterized by comprising the following steps of:
decomposing and reconstructing the obtained load signal at the terminal side by adopting a variation mode decomposition algorithm to obtain an intrinsic mode component of the load signal;
and carrying out load identification on the intrinsic mode components of the load signal by adopting an improved probability fuzzy C-means clustering algorithm to obtain the load type corresponding to the load signal.
2. The method for identifying the load on the terminal side based on the improved fuzzy clustering according to claim 1, wherein the step of decomposing and reconstructing the acquired load signal on the terminal side by adopting a variation mode decomposition algorithm comprises the following steps:
assuming that the load signal is decomposed into several orders of eigenmode components;
for the intrinsic mode components of each order, obtaining an analysis signal of the intrinsic mode components of each order through Hilbert transformation;
introducing an index operator into the analysis signal, adjusting the corresponding center frequency, and estimating the frequency bandwidth of the intrinsic mode component of each order through a Gaussian smoothing index after the frequency spectrum of the intrinsic mode component of each order is modulated onto the corresponding base frequency band to obtain a constraint variation function;
converting the constrained variational function into an unconstrained variational function by introducing a Lagrange function;
solving the unconstrained variational function through a multiplication operator alternating direction method, and continuously and iteratively updating the intrinsic mode component and the corresponding center frequency until the iteration stop condition is met.
3. The terminal-side load recognition method based on improved fuzzy clustering of claim 2, wherein the constraint variation function comprises:
wherein ,represents a bias derivative symbol, f represents a load signal, u k Representing the kth order eigenmode component, ω k Representing the center frequency corresponding to the kth order eigenmode component, delta (t) representing the pulse function, t representing the sampling time;
the unconstrained variational function L ({ u) k },{ω k }, { λ }) includes:
wherein lambda represents Lagrang operator, alpha represents penalty factor;
the iterative updating algorithm of the eigenvector component, the center frequency and the Lagrange operator comprises the following steps:
wherein ,indicating the current residual quantity->Results after wiener filtering, < >>Represents the center frequency corresponding to the current eigenmode component, < >>Fourier transform results representing eigenmode components, +.> and />Respectively representing the nth and n+1th Fourier transform results of Lagrang operator, τ represents noise margin,>representing the fourier transform result of the load signal, ω represents the center frequency corresponding to the first order eigenmode component.
4. The method for identifying the terminal side load based on the improved fuzzy clustering according to claim 1, wherein the step of identifying the load by adopting the improved probability fuzzy C-means clustering algorithm comprises the following steps:
introducing a covariance matrix into a PCM algorithm, combining the covariance matrix with an FCM algorithm, and establishing an objective function of the improved probability fuzzy C-means clustering algorithm;
and inputting the intrinsic mode component of the load signal into the objective function for iterative calculation until the objective function converges to the minimum, and obtaining the load type corresponding to the load signal.
5. The terminal side load identification method based on improved fuzzy clustering of claim 4, wherein the objective function J of the improved probability fuzzy C-means clustering algorithm m,p (U, T, V) includes:
wherein c represents the number of clusters, n represents the number of samples, the samples are eigen mode components, m represents fuzzy weights, d ij Representing sample X j To the clustering center V i Euclidean distance, t ij Representative of sample representative value, u ij Representing membership degree, sigma of jth sample er belonging to ith class cluster 2 The covariance matrix is represented, and a, b and p represent preset parameters, i is more than or equal to 1 and less than or equal to c, and j is more than or equal to 1 and less than or equal to n.
6. The terminal side load identification method based on improved fuzzy clustering of claim 5, wherein the fuzzy membership matrix is:
typical values for the samples are:
the class center matrix is:
the covariance matrix is:
wherein ,gamma represents the number of iterations.
7. The method for identifying a load on a terminal side based on improved fuzzy clustering according to claim 1, wherein before the step of obtaining an eigen-modal component of the load signal by decomposing the obtained load signal on the terminal side using a variational modal decomposition algorithm, the method further comprises:
collecting load data of each terminal at a terminal side in a scene at each sampling time in a target time period to obtain a first data sequence;
deleting distorted load data in the first data sequence to obtain a second data sequence;
carrying out standardization processing on the load data of each sampling time in the second data sequence to obtain a third data sequence;
and extracting the load data of the same terminal in the third data sequence to obtain the load signal.
8. The improved fuzzy clustering based terminal-side load discrimination method of claim 1, wherein prior to the step of deleting distorted load data in the first data sequence, the method further comprises:
calculating a mean, a residual error, and a standard deviation of the load data for each sampling time in the first data sequence;
judging whether the Laida criterion is met or not according to the average value, the residual error and the standard deviation of the load data of each sampling time;
if the Laida criterion is met, determining the load data distortion for the sampling time.
9. A computer-readable storage medium, characterized by: the computer readable storage medium has stored thereon computer program instructions; the computer program instructions, when executed by a processor, implement the improved fuzzy clustering based terminal side load identification method of any one of claims 1 to 8.
10. A terminal side load identification system based on improved fuzzy clustering is characterized by comprising: the computer readable storage medium of claim 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310644357.2A CN116776181A (en) | 2023-06-01 | 2023-06-01 | Terminal side load identification method, medium and system based on improved fuzzy clustering |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310644357.2A CN116776181A (en) | 2023-06-01 | 2023-06-01 | Terminal side load identification method, medium and system based on improved fuzzy clustering |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116776181A true CN116776181A (en) | 2023-09-19 |
Family
ID=88007256
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310644357.2A Pending CN116776181A (en) | 2023-06-01 | 2023-06-01 | Terminal side load identification method, medium and system based on improved fuzzy clustering |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116776181A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117194924A (en) * | 2023-09-26 | 2023-12-08 | 北京市计量检测科学研究院 | Method, system, equipment and medium for identifying indoor charging behavior of electric bicycle |
-
2023
- 2023-06-01 CN CN202310644357.2A patent/CN116776181A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117194924A (en) * | 2023-09-26 | 2023-12-08 | 北京市计量检测科学研究院 | Method, system, equipment and medium for identifying indoor charging behavior of electric bicycle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10176246B2 (en) | Fast grouping of time series | |
| CN110830450A (en) | Abnormal flow monitoring method, device and equipment based on statistics and storage medium | |
| CN115412455B (en) | Method and device for detecting abnormality of multiple performance indexes of server based on time sequence | |
| CN109934301B (en) | Power load cluster analysis method, device and equipment | |
| CN111080105A (en) | Transformer area user-to-user relationship identification method and system based on voltage time sequence data | |
| CN116776181A (en) | Terminal side load identification method, medium and system based on improved fuzzy clustering | |
| US8481912B2 (en) | Robust spectral analyzer for one-dimensional and multi-dimensional data analysis | |
| CN111783696A (en) | Edge calculation method for low-voltage branch topology real-time analysis based on PV relation | |
| CN111915449B (en) | Power load data dimension reduction reconstruction processing method based on VMD and OMP | |
| CN110796159A (en) | Power data classification method and system based on k-means algorithm | |
| CN115081795A (en) | Enterprise energy consumption abnormity cause analysis method and system under multidimensional scene | |
| CN112417371A (en) | Method for monitoring running state of intelligent electric energy meter in distribution network area | |
| Kumar et al. | Data-driven electrical load disaggregation using graph signal processing | |
| CN117634905A (en) | Power grid business data feature extraction method | |
| CN117290788A (en) | Power distribution network fault identification method and system based on improved wavelet transformation algorithm | |
| CN111506636A (en) | System and method for analyzing residential electricity consumption behavior based on autoregressive and neighbor algorithm | |
| CN115797044B (en) | Credit wind control early warning method and system based on cluster analysis | |
| CN111339986A (en) | Frequency law mining method and system for equipment based on time domain/frequency domain analysis | |
| CN112734072A (en) | Power load prediction method, system, terminal device and medium | |
| Kaddour et al. | Event Detection for Non-intrusive Load Monitoring using Tukey s Fences | |
| CN113343877B (en) | Electrical appliance fingerprint feature extraction method based on different Prony methods | |
| CN113723835B (en) | Water consumption evaluation method and terminal equipment for thermal power plant | |
| CN113724098B (en) | Method and system for detecting electricity stealing users based on clustering and neural network | |
| CN117648636A (en) | VMD-SAST-based power quality disturbance detection and identification method and system | |
| CN117951610B (en) | Communication signal identification and classification method based on characteristic data analysis |
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 |