CN108647275A - The recognition methods of isolated island detecting state and device, storage medium, processor - Google Patents
The recognition methods of isolated island detecting state and device, storage medium, processor Download PDFInfo
- Publication number
- CN108647275A CN108647275A CN201810404742.9A CN201810404742A CN108647275A CN 108647275 A CN108647275 A CN 108647275A CN 201810404742 A CN201810404742 A CN 201810404742A CN 108647275 A CN108647275 A CN 108647275A
- Authority
- CN
- China
- Prior art keywords
- sample
- training
- wavelet coefficient
- wavelet
- point
- 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
Classifications
-
- 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
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a kind of recognition methods of isolated island detecting state and device, storage medium, processors.Wherein, this method includes:The corresponding wavelet coefficient of voltage signal of point of common coupling is obtained according to Wavelet Transformation Algorithm, wherein the point of common coupling refers to the grid-connected tie point with public electric wire net of wind-powered electricity generation;Sample training library is determined according to obtained wavelet coefficient;The sample in the sample training library is calculated using neighbouring sorting algorithm, isolated island detecting state is identified according to result of calculation.The present invention solves isolated island detection algorithm, and there are larger check frequencies, and detection efficiency is relatively low and big technical problem is influenced on power quality.
Description
Technical field
The present invention relates to field of power transmission, recognition methods and device in particular to a kind of isolated island detecting state,
Storage medium, processor.
Background technology
Island effect refers to when distribution major network is since maintenance, electric fault or other reasons lead to cut-off in circuit breaker trip
When electric, continue to power to the load by distributed energy resource system, to form isolated power supply system.Wherein, it is based on inverter side
Isolated island detection algorithm by whether injecting disturbing signal and can be divided mainly into active detection and passive type and detect two classes.
Active detection algorithm to system by injecting microvariations signal, such as voltage magnitude, frequency, due to being incorporated into the power networks
When bulk power grid balanced action, disturbance substantially will not impact power grid, and when generating isolated island, pass through detection voltage, frequency
The situation of change of rate and phase is to realize identification.Passive type detection method passes through point of common coupling before and after detecting system isolated island
Electric quantity signal feature, including voltage magnitude, frequency, phase, voltage/current harmonic content etc. change to determine whether occurring lonely
Island.
Existing active detection algorithm control is more complex, and reduces the quality of inverter output electric energy;Passive type is examined
For method of determining and calculating there are larger check frequency, detection efficiency is relatively low, and this two classes algorithm all cannot be used for electric energy meter.
For in the related technology, for isolated island detection algorithm there are larger check frequency, detection efficiency is relatively low and to electric energy matter
Amount influences the problem of big technology, and currently no effective solution has been proposed.
Invention content
An embodiment of the present invention provides a kind of recognition methods of isolated island detecting state and device, storage medium, processor, with
Isolated island detection algorithm is at least solved there are larger check frequency, detection efficiency is relatively low and influences big technology to power quality and asks
Topic.
One embodiment according to the ... of the embodiment of the present invention provides intelligent electric energy meter isolated island detection recognition method, including:Root
The corresponding wavelet coefficient of voltage signal of point of common coupling is obtained according to Wavelet Transformation Algorithm, wherein point of common coupling refers to wind-powered electricity generation
The grid-connected tie point with public electric wire net;Sample training library is determined according to obtained wavelet coefficient;Using neighbouring sorting algorithm
The sample in sample training library is trained, isolated island detecting state is identified according to training result.
Further, the corresponding wavelet coefficient of voltage signal of point of common coupling is obtained according to Wavelet Transformation Algorithm, including:
The negative sequence voltage of the voltage of point of common coupling is extracted according to symmetrical component method;Select wavelet basis to negative sequence voltage components
It carries out wavelet decomposition and obtains wavelet coefficient.
Further, sample training library is determined according to obtained wavelet coefficient, including:Standard variance is carried out to wavelet coefficient
With energy deviation mean value calculation, sample training library is obtained.
Further, sample training library is determined according to obtained wavelet coefficient, including:Training sample set and test specimens are set
This collection is calculated for test sample and each sample into row distance, is adjusted the distance and is carried out descending sort, selects K sample as survey
K neighbour of sample sheet, wherein the training sample concentration includes the training sample, and the test sample collection includes described
Training sample, wherein K is positive integer.
Another aspect according to the ... of the embodiment of the present invention additionally provides a kind of identification device of isolated island detecting state, including:It obtains
Unit is taken, the corresponding wavelet coefficient of the voltage signal for obtaining point of common coupling according to Wavelet Transformation Algorithm;Determination unit is used
Sample training library is determined in the wavelet coefficient that basis obtains;Detection unit, for being instructed to sample using neighbouring sorting algorithm
The sample for practicing library is trained, and isolated island detecting state is identified according to training result.
Further, acquiring unit further includes:Acquisition module is additionally operable to extract point of common coupling according to symmetrical component method
Voltage negative sequence voltage;It is additionally operable to selection wavelet basis and wavelet coefficient is obtained to negative sequence voltage components progress wavelet decomposition, wherein
The negative sequence voltage components are obtained from the negative sequence voltage.
Further, it is determined that unit, further includes:Determining module is additionally operable to determine that sample is instructed according to obtained wavelet coefficient
Practice library, including:For carrying out standard variance and energy deviation mean value calculation to wavelet coefficient, sample training library is obtained.
Further, it is determined that unit, further includes processing module:It is additionally operable to carry out for test sample and each training sample
Distance calculates, and carries out descending sort to the distance, selects K neighbour of the K sample as test sample, wherein the instruction
It includes the training sample to practice sample set, and the test sample collection includes the training sample, wherein K is positive integer.
According to still another embodiment of the invention, a kind of storage medium is additionally provided, storage medium includes the program of storage,
Wherein, the method for executing any of the above-described when program is run.
According to still another embodiment of the invention, a kind of processor is additionally provided, processor is for running program, wherein
The method that any of the above-described is executed when program is run.
In embodiments of the present invention, the corresponding wavelet systems of voltage signal of point of common coupling are obtained according to Wavelet Transformation Algorithm
Number, wherein point of common coupling refers to the grid-connected tie point with public electric wire net of wind-powered electricity generation;It is true according to the obtained wavelet coefficient
Determine sample training library;The sample in the sample training library is trained using neighbouring sorting algorithm, is identified according to training result
Isolated island detecting state, and then solve in the related technology, for isolated island detection algorithm there are larger check frequency, detection efficiency is relatively low
And big technical problem is influenced on power quality, and then reach under the premise of not influencing power quality, using based on wavelet transformation
Novel detection algorithm can quickly and effectively realize that isolated island detects, accuracy of detection is high, the small effect of check frequency.
Description of the drawings
Attached drawing described herein is used to provide further understanding of the present invention, and is constituted part of this application, this hair
Bright illustrative embodiments and their description are not constituted improper limitations of the present invention for explaining the present invention.In the accompanying drawings:
Fig. 1 is a kind of flow chart of the recognition methods of optional isolated island detecting state according to the ... of the embodiment of the present invention;
Fig. 2 is a kind of identification device schematic diagram (one) of optional isolated island detecting state according to the ... of the embodiment of the present invention;
Fig. 3 is a kind of identification device schematic diagram (two) of optional isolated island detecting state according to the ... of the embodiment of the present invention;
Fig. 4 is a kind of identification device schematic diagram (three) of optional isolated island detecting state according to the ... of the embodiment of the present invention;
Fig. 5 is a kind of identification device schematic diagram (four) of optional isolated island detecting state according to the ... of the embodiment of the present invention;
Specific implementation mode
In order to enable those skilled in the art to better understand the solution of the present invention, below in conjunction in the embodiment of the present invention
Attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only
The embodiment of a part of the invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill people
The every other embodiment that member is obtained without making creative work should all belong to the model that the present invention protects
It encloses.
It should be noted that term " first " in description and claims of this specification and above-mentioned attached drawing, "
Two " etc. be for distinguishing similar object, without being used to describe specific sequence or precedence.It should be appreciated that using in this way
Data can be interchanged in the appropriate case, so as to the embodiment of the present invention described herein can in addition to illustrating herein or
Sequence other than those of description is implemented.In addition, term " comprising " and " having " and their any deformation, it is intended that cover
It includes to be not necessarily limited to for example, containing the process of series of steps or unit, method, system, product or equipment to cover non-exclusive
Those of clearly list step or unit, but may include not listing clearly or for these processes, method, product
Or the other steps or unit that equipment is intrinsic.
According to embodiments of the present invention, a kind of recognition methods embodiment of isolated island detecting state is provided, it should be noted that
Step shown in the flowchart of the accompanying drawings can execute in the computer system of such as a group of computer-executable instructions, and
It, in some cases, can be to execute institute different from sequence herein and although logical order is shown in flow charts
The step of showing or describing.
Fig. 1 is a kind of flow chart of the recognition methods of optional isolated island detecting state according to the ... of the embodiment of the present invention, such as Fig. 1
Shown, this method comprises the following steps:
Step S102 obtains the corresponding wavelet coefficient of voltage signal of point of common coupling according to Wavelet Transformation Algorithm, wherein
The point of common coupling refers to the grid-connected tie point with public electric wire net of wind-powered electricity generation;
Step S104 determines sample training library according to the obtained wavelet coefficient;
Step S106 is trained the sample in the sample training library using neighbouring sorting algorithm, according to training result
Identify isolated island detecting state.
According to above-mentioned steps of the present invention, the corresponding small echo of voltage signal of point of common coupling is obtained according to Wavelet Transformation Algorithm
Coefficient, wherein point of common coupling refers to the grid-connected tie point with public electric wire net of wind-powered electricity generation;According to the obtained wavelet coefficient
Determine sample training library;The sample in the sample training library is trained using neighbouring sorting algorithm, is known according to training result
Other isolated island detecting state, and then solve island detection algorithm there are larger check frequency, detection efficiency is relatively low and to electric energy matter
Amount influences the technical issues of big technology is asked.
Optionally, the corresponding wavelet coefficient of voltage signal of point of common coupling is obtained according to Wavelet Transformation Algorithm, including:Root
The negative sequence voltage of the voltage of the point of common coupling is extracted according to symmetrical component method;Select wavelet basis to the negative sequence voltage components into
Row wavelet decomposition obtains the wavelet coefficient, wherein the negative sequence voltage components are obtained from the negative sequence voltage.
Optionally, sample training library is determined according to the obtained wavelet coefficient, including:To the wavelet coefficient into rower
Quasi- variance and energy deviation mean value calculation obtain the sample training library.
Optionally, sample training library is determined according to the obtained wavelet coefficient, including:Training sample set and test are set
Sample set is calculated for test sample and each training sample into row distance, is carried out descending sort to the distance, is selected K
K neighbour of the sample as test sample, wherein the training sample concentration includes the training sample, the test sample
Collection includes the training sample, wherein K is positive integer.
It is further known that obtaining standard variance and energy deviation average value by repeatedly carrying out feature extraction to characteristic signal
In this, as sample database, with 7:3 ratio setting training sample set and test sample collection.Training sample set act as conduct
The input of grader, extraction algorithm feature train classification models;Test sample collection act as verification grader classifying quality, test
Classification accuracy, sees whether effectively detect island state.
To sum up, the above-mentioned technical proposal that the embodiment of the present invention is provided, using wavelet analysis in extraction electric system transient state
The powerful classification capacity of good characteristic and KNN algorithms when feature extracts small echo from the voltage signal of point of common coupling (PCC)
Coefficient calculates characteristic signal standard variance (SD) and energy content, finally according to sorting algorithm to identify island state.
It, can using the novel detection algorithm based on wavelet transformation under the premise of not influencing power quality by the above method
Quickly and effectively realize isolated island detection, accuracy of detection is high, and check frequency is small, using above-mentioned technical proposal, solves island detection algorithm
There are larger check frequency, detection efficiency is relatively low and influences the technical issues of big technology is asked to power quality, and then provides
The identifying schemes of isolated island detecting state.
Through the above description of the embodiments, those skilled in the art can be understood that according to above-mentioned implementation
The method of example can add the mode of required general hardware platform to realize by software, naturally it is also possible to by hardware, but it is very much
In the case of the former be more preferably embodiment.Based on this understanding, technical scheme of the present invention is substantially in other words to existing
The part that technology contributes can be expressed in the form of software products, which is stored in a storage
In medium (such as ROM/RAM, magnetic disc, CD), including some instructions are used so that a station terminal equipment (can be mobile phone, calculate
Machine, server or network equipment etc.) execute method described in each embodiment of the present invention.
A kind of identification device of isolated island detecting state is additionally provided in the present embodiment, and the device is for realizing above-mentioned implementation
Example and preferred embodiment had carried out repeating no more for explanation.As used below, term " module " may be implemented pre-
Determine the combination of the software and/or hardware of function.Although device described in following embodiment is preferably realized with software,
The realization of the combination of hardware or software and hardware is also that may and be contemplated.
Fig. 2 is a kind of identification device schematic diagram (one) of optional isolated island detecting state according to the ... of the embodiment of the present invention, such as
Shown in Fig. 2, which may include:
Acquiring unit 201, the corresponding wavelet systems of voltage signal for obtaining point of common coupling according to Wavelet Transformation Algorithm
Number, wherein point of common coupling refers to the grid-connected tie point with public electric wire net of wind-powered electricity generation;
Determination unit 203, for determining sample training library according to the obtained wavelet coefficient;
Detection unit 205, for being trained to the sample in the sample training library using neighbouring sorting algorithm, according to instruction
Practice result and identifies isolated island detecting state.
By the comprehensive function of above-mentioned modules, the voltage signal pair of point of common coupling is obtained according to Wavelet Transformation Algorithm
The wavelet coefficient answered, wherein point of common coupling refers to the grid-connected tie point with public electric wire net of wind-powered electricity generation;According to obtaining
Wavelet coefficient determines sample training library;The sample in the sample training library is trained using neighbouring sorting algorithm, according to instruction
Practice result and identify isolated island detecting state, using above-mentioned technical proposal, solves isolated island detection algorithm there are larger check frequency,
Detection efficiency is relatively low and the problem of influencing big technology to power quality, and then provides a kind of identification dress of isolated island detecting state
Set scheme.
It should be noted that the acquiring unit 201 in the embodiment can be used for executing the step in the embodiment of the present application
S102, the determination unit 203 in the embodiment can be used for executing the step S104 in the embodiment of the present application, in the embodiment
Detection unit 205 can be used for executing the step S106 in the embodiment of the present application.Above-mentioned module is realized with corresponding step
Example is identical with application scenarios, but is not limited to the above embodiments disclosure of that.
Fig. 3 is a kind of identification device schematic diagram (two) of optional isolated island detecting state according to the ... of the embodiment of the present invention, such as
Shown in Fig. 3, which further includes in addition to including all units shown in Fig. 2:Acquisition module 207, wherein
Acquisition module 207 is additionally operable to extract the negative sequence voltage of the voltage of the point of common coupling according to symmetrical component method;
It is additionally operable to selection wavelet basis and the wavelet coefficient is obtained to negative sequence voltage components progress wavelet decomposition, wherein described negative
Sequence voltage component is obtained from the negative sequence voltage.
Fig. 4 is a kind of identification device schematic diagram (three) of optional isolated island detecting state according to the ... of the embodiment of the present invention, such as
Shown in Fig. 4, which further includes in addition to including all units shown in Fig. 2:Determining module 209, wherein
Determining module 209 is additionally operable to determine sample training library according to the obtained wavelet coefficient, including:
For carrying out standard variance and energy deviation mean value calculation to the wavelet coefficient, the sample training is obtained
Library.
Fig. 5 is a kind of identification device schematic diagram (four) of optional isolated island detecting state according to the ... of the embodiment of the present invention, such as
Shown in Fig. 5, which further includes in addition to including all units shown in Fig. 2:Processing module 2011, wherein
Processing module 2011 is additionally operable to calculate into row distance for test sample and each training sample, to the distance
Descending sort is carried out, K neighbour of the K sample as test sample is selected, wherein the training sample concentration includes the instruction
Practice sample, the test sample collection includes the training sample, wherein K is positive integer.
The embodiments of the present invention also provide a kind of storage medium, computer program is stored in the storage medium, wherein
The computer program is arranged to execute the step in any of the above-described embodiment of the method when operation.
Optionally, in the present embodiment, above-mentioned storage medium can be set to store by executing based on following steps
Calculation machine program:
S1 obtains the corresponding wavelet coefficient of voltage signal of point of common coupling according to Wavelet Transformation Algorithm, wherein the public affairs
Coupling point refers to the grid-connected tie point with public electric wire net of wind-powered electricity generation altogether;
S2 determines sample training library according to the obtained wavelet coefficient;
S3 is trained the sample in the sample training library using neighbouring sorting algorithm, is identified according to training result lonely
Island detecting state.
Optionally, in the present embodiment, above procedure is for executing following steps:
S4 obtains the corresponding wavelet coefficient of voltage signal of point of common coupling according to Wavelet Transformation Algorithm, including:According to right
The method of weighing extracts the negative sequence voltage of the voltage of the point of common coupling;Wavelet basis is selected to carry out the negative sequence voltage components small
Wave Decomposition obtains the wavelet coefficient, wherein the negative sequence voltage components are obtained from the negative sequence voltage.
Optionally, in the present embodiment, above procedure is for executing following steps:
S5 determines sample training library according to the obtained wavelet coefficient, including:Standard side is carried out to the wavelet coefficient
Difference and energy deviation mean value calculation, obtain the sample training library.
Optionally, in the present embodiment, above procedure is for executing following steps:
S7 determines sample training library according to the obtained wavelet coefficient, including:Training sample set and test sample are set
Collection is calculated for test sample and each training sample into row distance, is carried out descending sort to the distance, is selected K sample
The K neighbour as test sample, wherein the training sample concentration includes the training sample, the test sample collection packet
Include the training sample, wherein K is positive integer.
The embodiments of the present invention also provide a kind of processor, which is arranged to run computer program to execute
Step in any of the above-described embodiment of the method:
S1 obtains the corresponding wavelet coefficient of voltage signal of point of common coupling according to Wavelet Transformation Algorithm, wherein the public affairs
Coupling point refers to the grid-connected tie point with public electric wire net of wind-powered electricity generation altogether;
S2 determines sample training library according to the obtained wavelet coefficient;
S3 is trained the sample in the sample training library using neighbouring sorting algorithm, is identified according to training result lonely
Island detecting state.
Optionally, in the present embodiment, above procedure is for executing following steps:
S4 obtains the corresponding wavelet coefficient of voltage signal of point of common coupling according to Wavelet Transformation Algorithm, including:According to right
The method of weighing extracts the negative sequence voltage of the voltage of the point of common coupling;Wavelet basis is selected to carry out the negative sequence voltage components small
Wave Decomposition obtains the wavelet coefficient, wherein the negative sequence voltage components are obtained from the negative sequence voltage.
Optionally, in the present embodiment, above procedure is for executing following steps:
S5 determines sample training library according to the obtained wavelet coefficient, including:Standard side is carried out to the wavelet coefficient
Difference and energy deviation mean value calculation, obtain the sample training library.
Optionally, in the present embodiment, above procedure is for executing following steps:
S7 determines sample training library according to the obtained wavelet coefficient, including:Training sample set and test sample are set
Collection is calculated for test sample and each training sample into row distance, is carried out descending sort to the distance, is selected K sample
The K neighbour as test sample, wherein the training sample concentration includes the training sample, the test sample collection packet
Include the training sample, wherein K is positive integer.
The recognition methods of above-mentioned isolated island detecting state is illustrated below in conjunction with preferred embodiment, but is not used in restriction originally
The protection domain of inventive embodiments.
Preferred embodiment
The identifying schemes of isolated island detecting state in the preferred embodiment mainly include the following steps:Utilize wavelet analysis
The powerful classification capacity of good characteristic and KNN algorithms when extracting electric system transient state characteristic, from point of common coupling (PCC)
Voltage signal extract wavelet coefficient, calculate characteristic signal standard variance (SD) and energy content, finally according to sorting algorithm with
Identify island state.
The invention is characterized in that:1) novel detection method is used to identify isolated island, blind area is small, precision is high, speed is fast;2) pass through
Signal characteristic value is extracted, Classification and Identification is carried out to database using machine learning algorithm.
Specific implementation step:
1, point of common coupling voltage is acquired first, and the voltage of acquisition symmetrical component method is extracted into negative sequence voltage;
2, selection suitable wavelet base carries out wavelet decomposition to the negative sequence voltage components of acquisition and obtains corresponding wavelet coefficient;
3, wavelet-coefficient standard deviation and energy deviation average value under the conditions of statistics different loads, sample training is formed with this
Library;
4, training sample set and test sample collection are built;
5, the Euclidean distance of test sample and each sample is calculated, formula is as follows;
6, k neighbour's sample is selected, is arranged calculated apart from descending, the relatively small k sample of chosen distance is made
For k neighbour of test sample;
7, classify to the test sample inquired according to the classification of k neighbour and using maximum probability;
8, classification results are returned.
The key point of the preferred embodiment:
1, point of common coupling voltage signal is extracted, its wavelet coefficient is obtained using Wavelet Transformation Algorithm;
2, characteristic value signal standard variance and energy content are calculated, sample database is obtained;
3, grader is obtained by training sample, realizes quickly and effectively detection isolated island.
The advantages of the preferred embodiment:
1, the limitation for overcoming traditional detection method, quick and precisely identifies island state;
2, check frequency is small, and will not be impacted to power quality;
3, it can be implanted into intelligent electric energy meter meter, it is especially suitable for the grid-connected new energy grid connection system of small distributed;
4, the anti-isolated island cost of investment of small distributed energy is saved.
The embodiments of the present invention are for illustration only, can not represent the quality of embodiment.
In the above embodiment of the present invention, all emphasizes particularly on different fields to the description of each embodiment, do not have in some embodiment
The part of detailed description may refer to the associated description of other embodiment.
In several embodiments provided herein, it should be understood that disclosed technology contents can pass through others
Mode is realized.Wherein, the apparatus embodiments described above are merely exemplary, for example, the unit division, Ke Yiwei
A kind of division of logic function, formula that in actual implementation, there may be another division manner, such as multiple units or component can combine or
Person is desirably integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual
Between coupling, direct-coupling or communication connection can be INDIRECT COUPLING or communication link by some interfaces, unit or module
It connects, can be electrical or other forms.
The unit illustrated as separating component may or may not be physically separated, and be shown as unit
Component may or may not be physical unit, you can be located at a place, or may be distributed over multiple units
On.Some or all of unit therein can be selected according to the actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, it can also
It is that each unit physically exists alone, it can also be during two or more units be integrated in one unit.Above-mentioned integrated list
The form that hardware had both may be used in member is realized, can also be realized in the form of SFU software functional unit.
If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can be stored in a computer read/write memory medium.Based on this understanding, technical scheme of the present invention is substantially
The all or part of the part that contributes to existing technology or the technical solution can be in the form of software products in other words
It embodies, which is stored in a storage medium, including some instructions are used so that a computer
Equipment (can be personal computer, server or network equipment etc.) execute each embodiment the method for the present invention whole or
Part steps.And storage medium above-mentioned includes:USB flash disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
Reservoir (RAM, Random Access Memory), mobile hard disk, magnetic disc or CD etc. are various can to store program code
Medium.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also answered
It is considered as protection scope of the present invention.
Claims (10)
1. a kind of recognition methods of isolated island detecting state, which is characterized in that including:
The corresponding wavelet coefficient of voltage signal of point of common coupling is obtained according to Wavelet Transformation Algorithm, wherein the public coupling
Point refers to the grid-connected tie point with public electric wire net of wind-powered electricity generation;
Sample training library is determined according to the obtained wavelet coefficient;
The sample in the sample training library is trained using neighbouring sorting algorithm, identifies that isolated island detects shape according to training result
State.
2. according to the method described in claim 1, it is characterized in that, obtaining the voltage of point of common coupling according to Wavelet Transformation Algorithm
The corresponding wavelet coefficient of signal, including:
The negative sequence voltage of the voltage of the point of common coupling is extracted according to symmetrical component method;
Selection wavelet basis carries out wavelet decomposition to negative sequence voltage components and obtains the wavelet coefficient, wherein the negative sequence voltage components
It is obtained from the negative sequence voltage.
3. according to the method described in claim 1, it is characterized in that, determining sample training according to the obtained wavelet coefficient
Library, including:
Standard variance and energy deviation mean value calculation are carried out to the wavelet coefficient, obtain the sample training library.
4. according to the method described in claim 1, it is characterized in that, determining sample training according to the obtained wavelet coefficient
Library, including:
Training sample set and test sample collection are set, calculated into row distance for test sample and each training sample, to described
Distance carries out descending sort, selects K neighbour of the K sample as test sample, wherein the training sample concentration includes institute
Training sample is stated, the test sample collection includes the training sample, wherein K is positive integer.
5. a kind of identification device of isolated island detecting state, which is characterized in that including:
Acquiring unit, the corresponding wavelet coefficient of voltage signal for obtaining point of common coupling according to Wavelet Transformation Algorithm, wherein
The point of common coupling refers to the grid-connected tie point with public electric wire net of wind-powered electricity generation;
Determination unit, for determining sample training library according to the obtained wavelet coefficient;
Detection unit, for being trained to the sample in the sample training library using neighbouring sorting algorithm, according to training result
Identify isolated island detecting state.
6. device according to claim 5, which is characterized in that the acquiring unit further includes acquisition module:
The acquisition module is additionally operable to extract the negative sequence voltage of the voltage of the point of common coupling according to symmetrical component method;
It is additionally operable to selection wavelet basis and the wavelet coefficient is obtained to negative sequence voltage components progress wavelet decomposition, wherein the negative phase-sequence is electric
Pressure component is obtained from the negative sequence voltage.
7. device according to claim 5, which is characterized in that the determination unit further includes determining module:
The determining module is additionally operable to determine sample training library according to the obtained wavelet coefficient, including:
For carrying out standard variance and energy deviation mean value calculation to the wavelet coefficient, the sample training library is obtained.
8. device according to claim 5, which is characterized in that the determination unit further includes processing module:
The processing module is additionally operable to calculate into row distance for test sample and each training sample, is carried out to the distance
Descending sort selects K neighbour of the K sample as test sample, wherein the training sample concentration includes the trained sample
This, the test sample collection includes the training sample, wherein K is positive integer.
9. a kind of storage medium, which is characterized in that the storage medium includes the program of storage, wherein when described program is run
Perform claim requires the method described in any one of 1 to 4.
10. a kind of processor, which is characterized in that the processor is for running program, wherein right of execution when described program is run
Profit requires the method described in any one of 1 to 4.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810404742.9A CN108647275A (en) | 2018-04-28 | 2018-04-28 | The recognition methods of isolated island detecting state and device, storage medium, processor |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810404742.9A CN108647275A (en) | 2018-04-28 | 2018-04-28 | The recognition methods of isolated island detecting state and device, storage medium, processor |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108647275A true CN108647275A (en) | 2018-10-12 |
Family
ID=63748260
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810404742.9A Pending CN108647275A (en) | 2018-04-28 | 2018-04-28 | The recognition methods of isolated island detecting state and device, storage medium, processor |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108647275A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110224382A (en) * | 2019-06-28 | 2019-09-10 | 国网河北省电力有限公司石家庄供电分公司 | Micro-capacitance sensor relay protecting method and device |
CN114297186A (en) * | 2021-12-30 | 2022-04-08 | 广西电网有限责任公司 | Power consumption data preprocessing method and system based on deviation coefficient |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102253283A (en) * | 2011-06-20 | 2011-11-23 | 山东电力集团公司临沂供电公司 | Island detection method based on wavelet packet energy spectrum |
CN102611140A (en) * | 2012-03-23 | 2012-07-25 | 合肥工业大学 | Grid-connected inverter island detection method based on wavelet transform and neural network |
CN102721885A (en) * | 2012-06-27 | 2012-10-10 | 黑龙江省电力科学研究院 | Island effect detecting method based on wavelet analysis |
US20140225592A1 (en) * | 2011-09-21 | 2014-08-14 | Technische Universitaet Clausthal | Method and device for detecting isolated operation of power generation installations |
CN104502795A (en) * | 2014-11-26 | 2015-04-08 | 国家电网公司 | Intelligent fault diagnosis method suitable for microgrid |
US20160124031A1 (en) * | 2014-11-04 | 2016-05-05 | Walid G. Morsi Ibrahim | Smart multi-purpose monitoring system using wavelet design and machine learning for smart grid applications |
CN105759177A (en) * | 2016-04-26 | 2016-07-13 | 浙江大学城市学院 | Classified-multi-mode-fusion-based distributed grid island detection method |
CN105974272A (en) * | 2016-07-26 | 2016-09-28 | 上海电气分布式能源科技有限公司 | Passive island detection method |
-
2018
- 2018-04-28 CN CN201810404742.9A patent/CN108647275A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102253283A (en) * | 2011-06-20 | 2011-11-23 | 山东电力集团公司临沂供电公司 | Island detection method based on wavelet packet energy spectrum |
US20140225592A1 (en) * | 2011-09-21 | 2014-08-14 | Technische Universitaet Clausthal | Method and device for detecting isolated operation of power generation installations |
CN102611140A (en) * | 2012-03-23 | 2012-07-25 | 合肥工业大学 | Grid-connected inverter island detection method based on wavelet transform and neural network |
CN102721885A (en) * | 2012-06-27 | 2012-10-10 | 黑龙江省电力科学研究院 | Island effect detecting method based on wavelet analysis |
US20160124031A1 (en) * | 2014-11-04 | 2016-05-05 | Walid G. Morsi Ibrahim | Smart multi-purpose monitoring system using wavelet design and machine learning for smart grid applications |
CN104502795A (en) * | 2014-11-26 | 2015-04-08 | 国家电网公司 | Intelligent fault diagnosis method suitable for microgrid |
CN105759177A (en) * | 2016-04-26 | 2016-07-13 | 浙江大学城市学院 | Classified-multi-mode-fusion-based distributed grid island detection method |
CN105974272A (en) * | 2016-07-26 | 2016-09-28 | 上海电气分布式能源科技有限公司 | Passive island detection method |
Non-Patent Citations (3)
Title |
---|
HIEU THANH DO 等: "Wavelet packet-based passive islanding detection method for grid connected photovoltaic inverters", 《2016 IEEE 8TH INTERNATIONAL POWER ELECTRONICS AND MOTION CONTROL CONFERENCE(IPEMC-ECCE ASIA)》 * |
谢东 等: "基于小波变换与神经网络的孤岛检测技术", 《中国电机工程学报》 * |
郗忠梅 等: "基于小波变换和神经网络的光伏发电孤岛效应检测方法", 《山东农业大学学报(自然科学版)》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110224382A (en) * | 2019-06-28 | 2019-09-10 | 国网河北省电力有限公司石家庄供电分公司 | Micro-capacitance sensor relay protecting method and device |
CN110224382B (en) * | 2019-06-28 | 2021-08-17 | 国网河北省电力有限公司石家庄供电分公司 | Micro-grid relay protection method and device |
CN114297186A (en) * | 2021-12-30 | 2022-04-08 | 广西电网有限责任公司 | Power consumption data preprocessing method and system based on deviation coefficient |
CN114297186B (en) * | 2021-12-30 | 2024-04-26 | 广西电网有限责任公司 | Power consumption data preprocessing method and system based on deviation coefficient |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105512799B (en) | Power system transient stability evaluation method based on mass online historical data | |
CN102074955B (en) | Method based on knowledge discovery technology for stability assessment and control of electric system | |
CN105759177B (en) | A kind of distributed power grid island detection method based on classification multi-model fusion | |
CN107273920A (en) | A kind of non-intrusion type household electrical appliance recognition methods based on random forest | |
CN109116203A (en) | Power equipment partial discharges fault diagnostic method based on convolutional neural networks | |
KR20190070838A (en) | Battery classification method and system | |
CN111160241B (en) | Power distribution network fault classification method, system and medium based on deep learning | |
CN104052612B (en) | A kind of Fault Identification of telecommunication service and the method and system of positioning | |
CN107835496A (en) | A kind of recognition methods of refuse messages, device and server | |
CN105184316A (en) | Support vector machine power grid business classification method based on feature weight learning | |
CN101251896B (en) | Object detecting system and method based on multiple classifiers | |
CN106443380B (en) | A kind of distribution cable local discharge signal recognition methods and device | |
CN110188090A (en) | A kind of distribution topological data method for evaluating quality and device based on data mining | |
CN107833311A (en) | A kind of fault detection method and platform of shared bicycle | |
CN108647275A (en) | The recognition methods of isolated island detecting state and device, storage medium, processor | |
CN106707118B (en) | Partial Discharge Pattern Recognition Method and device | |
CN108898182A (en) | A kind of MMC method for diagnosing faults based on core pivot element analysis and support vector machines | |
CN108845177A (en) | A kind of lightning stroke monitoring for power distribution network and recognition methods, device and equipment | |
CN110824297A (en) | Single-phase earth fault discrimination method and device based on SVM (support vector machine) | |
CN111062569A (en) | Low-current fault discrimination method based on BP neural network | |
CN114169249A (en) | Artificial intelligence identification method for high-resistance grounding fault of power distribution network | |
CN108009582A (en) | The method that a kind of electronic equipment standard working index is set | |
Narasimhulu et al. | Detection and classification of high impedance fault in power distribution system using hybrid technique | |
CN107219494A (en) | A kind of electric energy meter testing results system | |
CN108802565B (en) | Medium-voltage power distribution network disconnection ungrounded fault detection method based on machine 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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181012 |