CN114859169A - Intelligent identification method and system for distribution transformer outgoing line load and storage medium - Google Patents
Intelligent identification method and system for distribution transformer outgoing line load and storage medium Download PDFInfo
- Publication number
- CN114859169A CN114859169A CN202210415158.XA CN202210415158A CN114859169A CN 114859169 A CN114859169 A CN 114859169A CN 202210415158 A CN202210415158 A CN 202210415158A CN 114859169 A CN114859169 A CN 114859169A
- Authority
- CN
- China
- Prior art keywords
- load
- current
- voltage
- time sequence
- signals
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/081—Locating faults in cables, transmission lines, or networks according to type of conductors
- G01R31/086—Locating faults in cables, transmission lines, or networks according to type of conductors in power transmission or distribution networks, i.e. with interconnected conductors
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R19/00—Arrangements for measuring currents or voltages or for indicating presence or sign thereof
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R21/00—Arrangements for measuring electric power or power factor
- G01R21/001—Measuring real or reactive component; Measuring apparent energy
- G01R21/002—Measuring real component
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R21/00—Arrangements for measuring electric power or power factor
- G01R21/001—Measuring real or reactive component; Measuring apparent energy
- G01R21/003—Measuring reactive component
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The invention discloses a distribution and transformation outlet load intelligent identification method and system and a storage medium, wherein the method comprises the following steps: acquiring voltage waveforms and current waveforms of a bus at a distribution and transformation line side, and respectively sampling the voltage waveforms and the current waveforms according to a preset sampling frequency to obtain a plurality of voltage signals and a plurality of current signals; preprocessing the voltage signals and the current signals to obtain a voltage signal time sequence and a current signal time sequence; detecting load switching events according to the voltage signal time sequence and the current signal time sequence to obtain the starting time and the ending time of load state conversion; acquiring a voltage signal time sequence and a current signal time sequence of a time period between the starting time and the ending time, and extracting corresponding load characteristics; and inputting the load characteristics into a pre-trained recognition model for load intelligent recognition, and outputting a recognition result. The invention realizes accurate identification of the user load by using a non-invasive load monitoring technology and guides the user to reasonably use electricity.
Description
Technical Field
The invention relates to the technical field of impact load research, in particular to a distribution transformer outlet load intelligent identification method and system and a storage medium.
Background
In the aspect of electric energy metering, an electric energy department usually obtains the total electricity consumption of a user in the current month by reading an electric energy meter in a traditional mode of 'one user for one meter'. The method has the disadvantages that a user cannot know the power utilization condition of a certain electric appliance within a certain period of time, and the method is not beneficial to the user to take relevant measures to save power, adjust power utilization and the like. Therefore, load identification and power decomposition technology is indispensable for deeply analyzing the internal load components and the power utilization condition of the user.
Load recognition is currently generally classified into two categories, invasive and non-invasive. The traditional intrusive load monitoring needs to install a sensor at each load point needing to be monitored in advance to acquire electricity utilization data, and the monitoring mode needs a large amount of hardware equipment and needs a large amount of cost in purchasing, installing and maintaining. And intrusive load monitoring requires circuit reconstruction of parts of buildings or houses, so that the user acceptance degree is low and the enthusiasm is low. Besides, it has the problems of low reliability, slightly poor data integrity, etc. The non-invasive load monitoring only needs to install monitoring equipment at a distribution and transformation outlet, the types and the electricity utilization conditions of the internal loads of the users are obtained through analysis by collecting electrical parameters such as the voltage and the current of a main terminal, the state monitoring of each type of load in the system is realized through an algorithm, and the non-invasive load monitoring system has the characteristics of low cost, easiness in implementation, high reliability, good data integrity and the like. However, many non-invasive load identification devices need to capture load information changes at a high sampling rate, and the devices are expensive and high in energy consumption. In addition, the complexity of various monitoring algorithms based on pattern recognition is too high, real-time operation on low-cost embedded equipment is difficult, the algorithm recognition accuracy is not high, and the like, and the method is also a research difficulty of the current non-invasive load monitoring.
Disclosure of Invention
The invention aims to provide a distribution transformer outgoing line load intelligent identification method, a distribution transformer outgoing line load intelligent identification system and a storage medium, which utilize a non-intrusive load monitoring technology to realize accurate identification of user loads and guide users to reasonably use electricity.
In order to achieve the purpose, the invention provides an intelligent identification method for distribution transformer outgoing line loads, which comprises the following steps:
acquiring voltage waveforms and current waveforms of a bus at a distribution and transformation line side, and respectively sampling the voltage waveforms and the current waveforms according to a preset sampling frequency to obtain a plurality of voltage signals and a plurality of current signals;
preprocessing the voltage signals and the current signals to obtain a voltage signal time sequence and a current signal time sequence;
detecting load switching events according to the voltage signal time sequence and the current signal time sequence to obtain the starting time and the ending time of load state conversion;
acquiring a voltage signal time sequence and a current signal time sequence of a time period between the starting time and the ending time, and extracting corresponding load characteristics;
and inputting the load characteristics into a pre-trained recognition model for load intelligent recognition, and outputting a recognition result.
Preferably, the sampling frequency is 3200Hz, and the number of acquisition points per cycle is 64.
Preferably, the preprocessing the plurality of voltage signals and the plurality of current signals to obtain a voltage signal time series and a current signal time series includes:
respectively carrying out abnormal data processing and normalization processing on a plurality of voltage signals and a plurality of current signals obtained by sampling, wherein the plurality of voltage signals after processing are ordered according to time to form a voltage signal time sequence, and the plurality of current signals after processing are ordered according to time to form a current signal time sequence;
wherein the exception data processing is: comparing and analyzing the voltage signal or the current signal at any moment with the adjacent voltage signal or current signal, and if the difference value of the amplitudes of the two signals is greater than a preset threshold value, performing correction processing;
wherein the normalization process is: the amplitude correspondences of the plurality of voltage signals and the plurality of current signals are converted to between 0 and 1 so that the respective signals become normalized.
Preferably, the detecting the load switching event according to the voltage signal time sequence and the current signal time sequence to obtain the start time and the end time of the load state transition includes:
acquiring a time sequence of a load power signal according to the voltage signal time sequence and the current signal time sequence;
detecting a change point according to the time sequence of the load power signal, wherein the change point is a point of sudden change of the load power signal on the time sequence; determining a start time when the first change point is detected; when the second change point is detected, an end time is determined.
Preferably, the detecting of the change point according to the time sequence of the load power signal is performed according to the following decision function when H is k (g k ) When the value of (1) is 1, the occurrence of the change point is determined;
wherein:
g k =max(0,(g k-1 +s k )),g 0 =0
s k =x k -μ 0 -β
g k is a statistical function; h k (g k ) Is a decision function; s k Is a log likelihood ratio function; x is the number of k Power at the kth point of the time series; mu.s 0 Is the average value of the time series before the change point occurs; beta isA noise level, the value of which is preset; h is a preset threshold value.
Preferably, the load characteristics include fundamental to 10 th harmonic current magnitude, fundamental power factor angle, fundamental active power, and fundamental reactive power.
Preferably, the fundamental wave to 10 th harmonic current amplitude, the fundamental wave power factor angle, the fundamental wave active power and the fundamental wave reactive power are calculated by a fast fourier transform algorithm, specifically as follows:
where L is the length of the discrete sequence subjected to the discrete Fourier transform, U c (k)、I c (k) In order to be a discrete fourier transform coefficient,represents the discrete Fourier transform coefficient at the k-th frequency point corresponding to a frequency ofu (N), i (N) represent the time sequence of the voltage signal and the time sequence of the current signal, N represents the serial number of the sampling point, j is an imaginary unit, N is a preset value,amplitude of voltage and current, respectively, of the mth harmonicThe value, i.e. the complex representation of the amplitude of the voltage and current at a frequency m times the fundamental frequency, f 0 Representing the fundamental frequency, at 50Hz, f s Is the sampling frequency; p is the active power of fundamental wave, Q is the reactive power of fundamental wave,is the fundamental power factor angle.
Preferably, the inputting the load characteristics into a pre-trained recognition model for load intelligent recognition and outputting a recognition result includes:
and inputting the load characteristics into a multi-classification support vector machine classifier for classification, thereby distinguishing the power utilization state and identifying the load type.
The invention also provides an intelligent identification system for the distribution transformer outgoing line load, which comprises the following components:
the data sampling module is used for acquiring voltage waveforms and current waveforms of a bus at the distribution and transformation line side, and respectively sampling the voltage waveforms and the current waveforms according to a preset sampling frequency to obtain a plurality of voltage signals and a plurality of current signals;
the preprocessing module is used for preprocessing the voltage signals and the current signals to obtain a voltage signal time sequence and a current signal time sequence;
the transient process detection module is used for detecting load switching events according to the voltage signal time sequence and the current signal time sequence to obtain the starting time and the ending time of load state conversion;
the load characteristic modeling module is used for acquiring a voltage signal time sequence and a current signal time sequence of a time period between the starting time and the ending time and extracting corresponding load characteristics;
and the load identification module is used for inputting the load characteristics into a pre-trained identification model for load intelligent identification and outputting an identification result.
In order to achieve the above object, the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the steps of the intelligent identification method for distribution transformer outlet load.
Compared with the prior art, the invention has at least the following advantages:
the method adopts a non-invasive load monitoring technology to carry out data acquisition, data preprocessing, transient process detection, load characteristic modeling and load identification, utilizes the effective load characteristics of the load switching event extracted by the transient process detection to establish a load characteristic model, and finally adopts a multi-classification support vector machine classifier to carry out classification, so that the method has the advantages of high identification accuracy, stable result, stronger robustness, low implementation complexity, low cost and good practical value.
Additional features and advantages of the invention will be set forth in the description which follows.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of an intelligent identification method for distribution and transformation outlet loads in an embodiment of the present invention.
Fig. 2 is a schematic structural diagram of an intelligent identification system for load of distribution and transformation lines in an embodiment of the invention.
Detailed Description
Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. In addition, in the following detailed description, numerous specific details are set forth in order to provide a better understanding of the present invention. It will be understood by those skilled in the art that the present invention may be practiced without some of these specific details. In some instances, well known means have not been described in detail so as not to obscure the present invention.
Referring to fig. 1-2, an embodiment of the present invention provides an intelligent identification method for distribution and transformation line loads, including the following steps:
step S1, obtaining voltage waveform and current waveform of a bus at the distribution and transformation line side, and respectively sampling the voltage waveform and the current waveform according to a preset sampling frequency to obtain a plurality of voltage signals and a plurality of current signals;
specifically, the data acquisition module acquires power data on a bus, wherein the power data comprise voltage and current waveforms, and converts strong voltage and large current into analog weak current signals by using a voltage and current transformer.
Step S2, preprocessing the voltage signals and the current signals to obtain a voltage signal time sequence and a current signal time sequence;
step S3, detecting load switching events according to the voltage signal time sequence and the current signal time sequence, and obtaining the starting time and the ending time of load state conversion;
step S4, acquiring a voltage signal time sequence and a current signal time sequence of a time period between the starting time and the ending time, and extracting corresponding load characteristics;
and step S5, inputting the load characteristics into a pre-trained recognition model for load intelligent recognition, and outputting a recognition result.
Preferably, the sampling frequency of the data acquisition module is 3200Hz, and the number of acquisition points of each cycle is 64 points.
Preferably, the step S2 includes:
respectively carrying out abnormal data processing and normalization processing on a plurality of voltage signals and a plurality of current signals obtained by sampling, wherein the plurality of voltage signals after processing are ordered according to time to form a voltage signal time sequence, and the plurality of current signals after processing are ordered according to time to form a current signal time sequence;
wherein the exception data processing is: comparing and analyzing the voltage signal or the current signal at any moment with the adjacent voltage signal or current signal, and if the difference value of the amplitudes of the two signals is greater than a preset threshold value, performing correction processing;
wherein the normalization process is: correspondingly converting the amplitudes of the voltage signals and the current signals into the range between 0 and 1 so that the signals become standardized, wherein the specific formula is as follows:
where x is the amplitude of the original voltage or current signal, x min And x max Are the maximum and minimum values of the amplitude in the voltage or current signal to be processed,is the amplitude of the normalized voltage or current signal.
Preferably, the step S3 includes:
acquiring a time sequence of a load power signal according to the voltage signal time sequence and the current signal time sequence; wherein the power is equal to the voltage multiplied by the current at the corresponding moment;
detecting a change point according to the time sequence of the load power signal, wherein the change point is a point of sudden change of the load power signal on the time sequence; determining a start time when the first change point is detected; when the second change point is detected, an end time is determined.
Preferably, the detecting of the change point according to the time sequence of the load power signal is performed according to the following decision function when H is k (g k ) When the value of (1) is 1, the occurrence of the change point is determined;
wherein:
g k =max(0,(g k-1 +s k )),g 0 =0
s k =x k -μ 0 -β
g k is a statistical function; h k (g k ) Is a decision function; s k Is a log likelihood ratio function; x is the number of k Power at the kth point of the time series; mu.s 0 Is the average value of the time series before the change point occurs; β is a noise level, the value of which is preset; h is a preset threshold value.
In particular, when the decision function is greater than a threshold value, i.e. H k (g k ) When the system is equal to 1, the state of the change point of the system is changed, if the change occurs for the first time, the system enters a transient state from an original steady state, and H is carried out after the transient state is entered k (g k ) Becomes 0, the transient process continues to detect the change point, when H k (g k ) When the system is changed to 1 again, namely the change point appears again, the system exits from the transient state and enters the steady state, and an impact load event is formed between the two change points, and the event indicates that the impact load running state is changed. And extracting a relevant load characteristic sample based on the impact load event detection result for attribute identification.
Preferably, the load characteristics include fundamental to 10 th harmonic current magnitude, fundamental power factor angle, fundamental active power, and fundamental reactive power.
Preferably, the fundamental wave to 10 th harmonic current amplitude, the fundamental wave power factor angle, the fundamental wave active power and the fundamental wave reactive power are calculated by a fast fourier transform algorithm, specifically as follows:
where L is the length of the discrete sequence subjected to the discrete Fourier transform, U c (k)、I c (k) In order to be a discrete fourier transform coefficient,represents the discrete Fourier transform coefficient at the k-th frequency point corresponding to a frequency ofu (N), i (N) represent the time sequence of the voltage signal and the time sequence of the current signal, N represents the serial number of the sampling point, j is an imaginary unit, N is a preset value,the amplitudes of the voltage and current, respectively, of the mth harmonic, i.e. the complex representation of the amplitudes of the voltage and current with a frequency m times the fundamental frequency, f 0 Representing the fundamental frequency, is 50Hz, f s Is the sampling frequency; p is the active power of fundamental wave, Q is the reactive power of fundamental wave,is the fundamental power factor angle.
Preferably, the step S5 includes:
and inputting the load characteristics into a multi-classification support vector machine classifier for classification, thereby distinguishing the power utilization state and identifying the load type.
In the multi-classification support vector machine classifier, the embodiment introduces a relaxation variable xi i ≧ 0, i ≧ 1,2, …, l, and a penalty C is selected in the objective function>0 to xi i A restriction is made. Thus the original classification problem translates into the following:
s.t.y i [ω·φ(x i )+b]≥1-ξ i ,i=1,2,…,l
ξ i ≥0,i=1,2,…,l
wherein, the parameters omega and b are respectively the normal vector and intercept of the hyperplane H, and l is the number of the labels.
Introducing a Lagrange function and converting the Lagrange function into a Lagrange dual problem of an original problem so as to obtain the following quadratic programming problem:
0<α i <C,i=1,2,…,l
wherein alpha is i Is Lagrange multiplier, K (x) i ·x j ) Is a Gaussian radial basis kernel function, i.e.
Is provided withIs a solution of the above formula, thenThe final optimized classification function is thus:
it should be noted that the above classifier is only an example, and the present invention is not limited to the classifier model, and may also be implemented by using other machine learning algorithms.
Referring to fig. 2, another embodiment of the present invention further provides an intelligent identification system for distribution and transformation line load, where the system includes:
the data sampling module is used for acquiring voltage waveforms and current waveforms of a bus at the distribution and transformation line side, and respectively sampling the voltage waveforms and the current waveforms according to a preset sampling frequency to obtain a plurality of voltage signals and a plurality of current signals;
the preprocessing module is used for preprocessing the voltage signals and the current signals to obtain a voltage signal time sequence and a current signal time sequence;
the transient process detection module is used for detecting load switching events according to the voltage signal time sequence and the current signal time sequence to obtain the starting time and the ending time of load state conversion;
the load characteristic modeling module is used for acquiring a voltage signal time sequence and a current signal time sequence of a time period between the starting time and the ending time and extracting corresponding load characteristics;
and the load identification module is used for inputting the load characteristics into a pre-trained identification model for load intelligent identification and outputting an identification result.
The above-described system embodiments are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
It should be noted that the system described in the foregoing embodiment corresponds to the method described in the foregoing embodiment, and therefore, a part of the system described in the foregoing embodiment that is not described in detail can be obtained by referring to the content of the method described in the foregoing embodiment, that is, the specific step content described in the method of the foregoing embodiment can be understood as the function that can be realized by the system of the present embodiment, and is not described herein again.
Moreover, if the distribution and distribution line load intelligent identification system in the above embodiment is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a computer readable storage medium.
Another embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the intelligent identification method for distribution and distribution line load described in the above embodiments.
Specifically, the computer-readable storage medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like.
Having described embodiments of the present invention, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (10)
1. An intelligent identification method for distribution transformer outlet loads is characterized by comprising the following steps:
acquiring voltage waveforms and current waveforms of a bus at a distribution and transformation line side, and respectively sampling the voltage waveforms and the current waveforms according to a preset sampling frequency to obtain a plurality of voltage signals and a plurality of current signals;
preprocessing the voltage signals and the current signals to obtain a voltage signal time sequence and a current signal time sequence;
detecting load switching events according to the voltage signal time sequence and the current signal time sequence to obtain the starting time and the ending time of load state conversion;
acquiring a voltage signal time sequence and a current signal time sequence of a time period between the starting time and the ending time, and extracting corresponding load characteristics;
and inputting the load characteristics into a pre-trained recognition model for load intelligent recognition, and outputting a recognition result.
2. The method of claim 1, wherein the sampling frequency is 3200Hz with 64 acquisition points per cycle.
3. The method of claim 1, wherein pre-processing the plurality of voltage signals and the plurality of current signals to obtain a voltage signal time series and a current signal time series comprises:
respectively carrying out abnormal data processing and normalization processing on a plurality of voltage signals and a plurality of current signals obtained by sampling, wherein the plurality of voltage signals after processing are ordered according to time to form a voltage signal time sequence, and the plurality of current signals after processing are ordered according to time to form a current signal time sequence;
wherein the exception data processing is: comparing and analyzing the voltage signal or the current signal at any moment with the adjacent voltage signal or current signal, and if the difference value of the amplitudes of the two signals is greater than a preset threshold value, performing correction processing;
wherein the normalization process is: the amplitude correspondences of the plurality of voltage signals and the plurality of current signals are converted to between 0 and 1 so that the respective signals become normalized.
4. The method of claim 1, wherein the detecting the load switching event according to the voltage signal time series and the current signal time series to obtain the start time and the end time of the load state transition comprises:
acquiring a time sequence of a load power signal according to the voltage signal time sequence and the current signal time sequence;
detecting a change point according to the time sequence of the load power signal, wherein the change point is a point of sudden change of the load power signal on the time sequence; determining a start time when the first change point is detected; when the second change point is detected, an end time is determined.
5. The method of claim 4, wherein the detecting the change point is based on a time series of the load power signal, and wherein the detecting the change point is based on a decision function when H is k (g k ) When the value of (1) is 1, the occurrence of the change point is determined;
wherein:
g k =max(0,(g k-1 +s k )),g 0 =0
s k =x k -μ 0 -β
g k is a statistical function; h k (g k ) Is a decision function; s k Is a log likelihood ratio function; x is the number of k Power at the kth point of the time series; mu.s 0 Is the average value of the time series before the change point occurs; β is a noise level, the value of which is preset; h is a preset threshold value.
6. The method of claim 1, wherein the load characteristics include fundamental to 10 harmonic current magnitude, fundamental power factor angle, fundamental active power, and fundamental reactive power.
7. The method of claim 6, wherein the fundamental to 10 th harmonic current amplitudes, fundamental power factor angles, fundamental active power and fundamental reactive power are calculated using a fast Fourier transform algorithm as follows:
where L is the length of the discrete sequence subjected to the discrete Fourier transform, U c (k)、I c (k) In order to be a discrete fourier transform coefficient,represents the discrete Fourier transform coefficient at the k-th frequency point corresponding to a frequency ofu (N), i (N) represent the time sequence of the voltage signal and the time sequence of the current signal, N represents the serial number of the sampling point, j is an imaginary unit, N is a preset value,the amplitudes of the voltage and current, respectively, of the mth harmonic, i.e. the complex representation of the amplitudes of the voltage and current with a frequency m times the fundamental frequency, f 0 Representing the fundamental frequency, is 50Hz, f s Is the sampling frequency; p is the active power of fundamental wave, Q is the reactive power of fundamental wave,is the fundamental power factor angle.
8. The method of claim 1, wherein the inputting the load characteristics into a pre-trained recognition model for load intelligent recognition and outputting a recognition result comprises:
and inputting the load characteristics into a multi-classification support vector machine classifier for classification, thereby distinguishing the power utilization state and identifying the load type.
9. An intelligent identification system for distribution transformer outgoing line loads is characterized by comprising:
the data sampling module is used for acquiring voltage waveforms and current waveforms of a bus at the distribution and transformation line side, and respectively sampling the voltage waveforms and the current waveforms according to a preset sampling frequency to obtain a plurality of voltage signals and a plurality of current signals;
the preprocessing module is used for preprocessing the voltage signals and the current signals to obtain a voltage signal time sequence and a current signal time sequence;
the transient process detection module is used for detecting load switching events according to the voltage signal time sequence and the current signal time sequence to obtain the starting time and the ending time of load state conversion;
the load characteristic modeling module is used for acquiring a voltage signal time sequence and a current signal time sequence of a time period between the starting time and the ending time and extracting corresponding load characteristics;
and the load identification module is used for inputting the load characteristics into a pre-trained identification model for load intelligent identification and outputting an identification result.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the distribution line load intelligent identification method according to any one of claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210415158.XA CN114859169A (en) | 2022-04-20 | 2022-04-20 | Intelligent identification method and system for distribution transformer outgoing line load and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210415158.XA CN114859169A (en) | 2022-04-20 | 2022-04-20 | Intelligent identification method and system for distribution transformer outgoing line load and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114859169A true CN114859169A (en) | 2022-08-05 |
Family
ID=82632367
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210415158.XA Pending CN114859169A (en) | 2022-04-20 | 2022-04-20 | Intelligent identification method and system for distribution transformer outgoing line load and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114859169A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116051910A (en) * | 2023-03-10 | 2023-05-02 | 深圳曼顿科技有限公司 | Non-invasive load identification method, device, terminal equipment and storage medium |
CN116861318A (en) * | 2023-09-05 | 2023-10-10 | 国网浙江省电力有限公司余姚市供电公司 | User electricity load classification method, device, equipment and storage medium |
-
2022
- 2022-04-20 CN CN202210415158.XA patent/CN114859169A/en active Pending
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116051910A (en) * | 2023-03-10 | 2023-05-02 | 深圳曼顿科技有限公司 | Non-invasive load identification method, device, terminal equipment and storage medium |
CN116861318A (en) * | 2023-09-05 | 2023-10-10 | 国网浙江省电力有限公司余姚市供电公司 | User electricity load classification method, device, equipment and storage medium |
CN116861318B (en) * | 2023-09-05 | 2023-11-21 | 国网浙江省电力有限公司余姚市供电公司 | User electricity load classification method, device, equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110018369B (en) | Intelligent household appliance identification and monitoring method based on non-invasive load decomposition | |
CN114859169A (en) | Intelligent identification method and system for distribution transformer outgoing line load and storage medium | |
Yang et al. | Bad data detection algorithm for PMU based on spectral clustering | |
CN110287762B (en) | Non-invasive load identification method and device based on data mining technology | |
CN110648088B (en) | Electric energy quality disturbance source judgment method based on bird swarm algorithm and SVM | |
CN106483370A (en) | Non-intrusion type household loads real-time identification method based on multi-feature fusion and device | |
CN111027408A (en) | Load identification method based on support vector machine and V-I curve characteristics | |
CN111766462B (en) | Non-invasive load identification method based on V-I track | |
CN113496440B (en) | User abnormal electricity consumption detection method and system | |
CN113361831B (en) | Non-invasive load identification electric quantity decomposition method and system based on priority distribution | |
CN111308185A (en) | Non-invasive load identification method | |
CN113887912A (en) | Non-invasive load identification method for deeply learning downward embedded equipment | |
CN115128345A (en) | Power grid safety early warning method and system based on harmonic monitoring | |
Matz et al. | Automated power quality monitoring system for on-line detection and classification of disturbances | |
CN113076354A (en) | User electricity consumption data analysis method and device based on non-invasive load monitoring | |
CN113010985A (en) | Non-invasive load identification method based on parallel AANN | |
CN110244150B (en) | Non-invasive electrical appliance identification method based on root mean square and standard deviation | |
CN116681186A (en) | Power quality analysis method and device based on intelligent terminal | |
CN115343579B (en) | Power grid fault analysis method and device and electronic equipment | |
Li et al. | A training-free non-intrusive load monitoring approach for high-frequency measurements based on graph signal processing | |
CN115825602A (en) | Load identification method and system for comprehensive multivariate information similarity analysis | |
CN112949563B (en) | Non-invasive load identification method based on variable point detection and improved KNN algorithm | |
CN116298509A (en) | Online identification method for harmonic resonance of power system | |
CN115983347A (en) | Non-invasive load decomposition method, device and storage medium | |
CN114676783A (en) | Load identification method based on single classification and fuzzy width learning |
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 |