CN116667467A - Intelligent control magnetic suspension breeze power generation capacity-increasing compensation device - Google Patents
Intelligent control magnetic suspension breeze power generation capacity-increasing compensation device Download PDFInfo
- Publication number
- CN116667467A CN116667467A CN202310956405.1A CN202310956405A CN116667467A CN 116667467 A CN116667467 A CN 116667467A CN 202310956405 A CN202310956405 A CN 202310956405A CN 116667467 A CN116667467 A CN 116667467A
- Authority
- CN
- China
- Prior art keywords
- wind turbine
- reactive power
- control time
- reactive
- compensation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000010248 power generation Methods 0.000 title claims abstract description 21
- 239000000725 suspension Substances 0.000 title abstract description 5
- 238000000034 method Methods 0.000 claims abstract description 10
- 238000004364 calculation method Methods 0.000 claims abstract description 7
- 238000005457 optimization Methods 0.000 claims abstract description 5
- 239000011159 matrix material Substances 0.000 claims description 39
- 238000005339 levitation Methods 0.000 claims description 14
- 239000013598 vector Substances 0.000 claims description 9
- 238000013528 artificial neural network Methods 0.000 claims description 8
- 230000002068 genetic effect Effects 0.000 claims description 4
- 230000006698 induction Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000004804 winding Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/12—Circuit arrangements for ac mains or ac distribution networks for adjusting voltage in ac networks by changing a characteristic of the network load
- H02J3/16—Circuit arrangements for ac mains or ac distribution networks for adjusting voltage in ac networks by changing a characteristic of the network load by adjustment of reactive power
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/18—Arrangements for adjusting, eliminating or compensating reactive power in networks
- H02J3/1885—Arrangements for adjusting, eliminating or compensating reactive power in networks using rotating means, e.g. synchronous generators
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/24—Arrangements for preventing or reducing oscillations of power in networks
- H02J3/241—The oscillation concerning frequency
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
- H02J3/46—Controlling of the sharing of output between the generators, converters, or transformers
- H02J3/50—Controlling the sharing of the out-of-phase component
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
- H02J2300/20—The dispersed energy generation being of renewable origin
- H02J2300/28—The renewable source being wind energy
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/70—Wind energy
- Y02E10/76—Power conversion electric or electronic aspects
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Power Engineering (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Control Of Eletrric Generators (AREA)
- Wind Motors (AREA)
Abstract
The invention relates to the technical field of wind turbines, and discloses an intelligent control magnetic suspension breeze power generation capacity-increasing compensation device, which comprises the following modules: the data acquisition module is used for acquiring the operation data of the current control time of the wind turbine generator; the calculation module is used for calculating the steady-state reactive limit value of the wind turbine generator; the scheme generation module randomly generates a compensation scheme of the next control time based on constraint conditions, wherein one compensation scheme comprises reactive power required to be output at the next control time of all wind turbines; the scheme optimization module is used for optimizing the compensation scheme of the next control time generated randomly through a multi-objective evolutionary algorithm to obtain a final compensation scheme; according to the method, a multi-target fitness function is established through a multi-target evolutionary algorithm to optimize a compensation scheme of the next control time generated randomly, and the obtained final compensation scheme has the smallest influence on the stability of the power grid and the highest response speed.
Description
Technical Field
The invention relates to the field of wind turbines, in particular to an intelligent control magnetic suspension breeze power generation capacity-increasing compensation device.
Background
A doubly-fed induction machine (Doubly Fed Induction Generator, abbreviated as DFIG) converts wind energy to electrical energy and outputs it to a grid for power. The DFIG can provide reactive power support by adjusting its rotor current in addition to being able to provide active power.
Since the reactive capacity of the DFIG is limited by the capacity of the rotor converter, but the reactive demand of the wind farm is very large, the support of the DFIG to provide reactive power into the grid is limited, and the safety of the wind farm cannot be ensured.
The reactive power compensation equipment and the doubly-fed induction motor of the wind turbine generator are adopted to jointly compensate reactive power to the power grid at present, the reactive power compensation equipment is adopted to compensate reactive power preferentially, reactive power is compensated by the wind turbine generator, and the next quick follow-up is facilitated.
Based on the reactive compensation distribution mode, the limitation of stator and rotor winding currents on reactive output and the limitation of small disturbance stability of the system on reactive output are taken into consideration, so that the actual value of the maximum reactive power which can be actually sent out by the double-fed unit is the same as the preset reactive power set value sent out by the wind turbine unit, and when the power grid system is disturbed, the reactive power which is sent out by the double-fed unit to the power grid according to the set value with the allowance is the same as the value which is actually required by the wind turbine unit with the allowance.
However, the reactive power distribution method still has some problems, and when the reactive power distribution method is used for distribution, the difference between the distributed reactive power of each wind turbine generator and the standard value of the power grid when the power grid is stable is randomly and dynamically changed, so that the distribution method cannot ensure that the power grid stability is highest when the power grid is distributed, the response speed of the power grid reaches the steady state is slower, and the distribution scheme is not optimal.
Disclosure of Invention
The invention provides an intelligent control magnetic levitation breeze power generation capacity-increasing compensation device, which solves the technical problems of poor stability and slow response speed of a distribution mode of compensating reactive power to a power grid by a double-fed unit in the related art.
The invention provides an intelligent control magnetic suspension breeze power generation capacity-increasing compensation device, which comprises the following modules:
the data acquisition module is used for acquiring the operation data of the current control time of the wind turbine generator;
the calculation module is used for calculating the steady-state reactive power limit value of the wind turbine generator；
The scheme generation module randomly generates a compensation scheme of the next control time based on constraint conditions, wherein one compensation scheme comprises reactive power required to be output at the next control time of all wind turbines;
the scheme optimization module is used for optimizing the compensation scheme of the next control time generated randomly through a multi-objective evolutionary algorithm to obtain a final compensation scheme;
wherein,,wherein->For the voltage of the stator of the wind turbine, +.>The frequency of the grid system is the grid-connected point; />Is the stator inductance.
The constraint conditions in the scheme generation module include:；/>the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>Representing reactive power which is required to be output by the s-th wind turbine generator in the next control time, and +.>Representing steady state reactive limit,/->And the total reactive power compensation power required to be provided by all the wind turbines is represented, and N represents the total number of the wind turbines.
The scheme optimizing module comprises the following execution steps:
step 10Initializing a population, and coding by a compensation scheme of the next control time generated randomly to obtain an individual; jth individualExpressed as: />Wherein->、/>And->The reactive power required to be output by the 1 st wind turbine generator, the 2 nd wind turbine generator and the N wind turbine generator in the compensation scheme of the j next control time generated randomly is respectively represented;
102, updating the population through genetic operators;
and 103, selecting an individual with the largest fitness value from the final population to decode when the iteration step 102 reaches the termination condition, and obtaining the final compensation scheme.
The termination conditions of step 102 are: the number of iterations is equal to Z; the default value of Z is 20.
The fitness function of the multi-objective evolutionary algorithm is:
wherein->Indicating fitness value of the jth individual, < ->Andrespectively representing a first weight coefficient and a second weight coefficient,/for>，/>，，/>Representing steady state reactive limit,/->Representing a first neural network.
The first neural network comprises an input layer, a first hidden layer, a second hidden layer and a fully connected layer, wherein the input layer generates an input feature matrix based on the operation data and the jth individual; the row vector of the ith row of the input feature matrix is expressed asWherein->Representing the reactive power which needs to be output at the next control time of the (th) wind turbine in the (th) individual, <>Reactive power output by the u-th wind turbine generator set at the current control time is represented by +.>Representing the rotor active power of the u-th wind turbine and +.>Stator active power of the u-th wind turbine representing the current control time, and>the air quantity of the u-th wind turbine generator set at the current control time is represented by +.>Represents the current control time of the (u) th windWind pressure of the motor unit->Power system frequency indicative of current control time, +.>And indicating the slip of the u-th wind turbine generator in the current control time.
The calculation formula of the first hidden layer of the first neural network is as follows:
wherein->Represents a first intermediate feature matrix, Q represents a first matrix, K represents a second matrix, V represents a third matrix,/a third matrix>Dimension representing row vector of input feature matrix, +.>，，/>Wherein->、/>、/>Respectively representing a first weight matrix, a second weight matrix and a third weight matrix,/->Representing an input feature matrix;
the second hidden layer comprises an RNN unit, the RNN unit sequentially inputs N row vectors of the first intermediate feature matrix in N time steps, the output of the N time steps is input to the full-connection layer, and the full-connection layer outputs a classification label representing response time;
the classification space of the full connection layer comprises 100 classification labels, and the value range of response time is calculatedThe mean value is discretized into 100 point values, and the 100 point values respectively correspond to 100 classification labels of the classification space of the full connection layer.
The intelligent control magnetic levitation breeze power generation capacity-increasing compensation device also comprises an AVC substation and reactive compensation equipment, wherein the AVC substation is connected to the reactive compensation equipment and is used for acquiring target reactive power of a grid-connected point and sending a reactive adjustment instruction to the reactive compensation equipment according to the target reactive power; and after the reactive power of the grid-connected point is detected to reach the full amount of the reactive power output by the reactive compensation equipment to the grid-connected point, controlling all the wind turbines to increase the reactive power to the grid-connected point so as to compensate the reactive compensation power required by the grid-connected point.
The intelligent control magnetic levitation breeze power generation capacity-increasing compensation device further comprises an AVC master station, wherein the AVC master station is connected to the AVC substation, the AVC substation receives reactive power instructions issued by the AVC master station, and target reactive power of a grid-connected point is obtained from the reactive power instructions.
The intelligent control magnetic levitation breeze power generation capacity-increasing compensation device comprises a voltage command issued by an AVC master station, and an AVC substation calculates target reactive power of a grid-connected point according to target grid-connected point voltage carried in the voltage command.
The invention has the beneficial effects that:
according to the invention, a multi-target fitness function is established through a multi-target evolutionary algorithm to optimize a compensation scheme of the next control time generated randomly, and the obtained final compensation scheme can be used for adjusting the first weight coefficient and the second weight coefficient according to the trends of stability and response speed, so that the influence of the final compensation scheme on the stability of the power grid is minimum and the response speed is the fastest.
Drawings
Fig. 1 is a schematic block diagram of the present invention.
FIG. 2 is a schematic flow chart of the steps of the optimizing module of the scheme of the invention.
In the figure: 11. a data acquisition module; 12. a computing module; 13. a scheme generation module; 14. and a scheme optimizing module.
Detailed Description
The subject matter described herein will now be discussed with reference to example embodiments. It is to be understood that these embodiments are merely discussed so that those skilled in the art may better understand and implement the subject matter described herein and that changes may be made in the function and arrangement of the elements discussed without departing from the scope of the disclosure herein. Various examples may omit, replace, or add various procedures or components as desired. In addition, features described with respect to some examples may be combined in other examples as well.
As shown in fig. 1 and 2, an intelligent control magnetic levitation breeze power generation capacity-increasing compensation device comprises:
the data acquisition module is used for acquiring operation data of the current control time of the wind turbine generator;
the difference between adjacent control times is 1-3s.
The calculation module calculates steady-state reactive power limit value of the wind turbine generator；
In one embodiment of the present invention,wherein->For the voltage of the stator of the wind turbine, +.>The frequency of the grid system is the grid-connected point; />Is a stator inductance;
in one embodiment of the present invention,wherein->Representing the maximum power of the network side converter design, < >>And s represents the slip of the generator of the wind turbine generator.
The scheme generation module randomly generates a compensation scheme of the next control time based on constraint conditions, wherein one compensation scheme comprises reactive power required to be output at the next control time of all wind turbines;
the constraint conditions include:
1.；
2.；
3.；
wherein the method comprises the steps ofRepresenting reactive power which is required to be output by the s-th wind turbine generator in the next control time, and +.>Representing steady state reactive limit,/->The total reactive power compensation power required to be provided by all the wind turbines is represented, and N represents the total number of the wind turbines;
the scheme optimization module is used for optimizing the compensation scheme of the next control time generated randomly through a multi-objective evolutionary algorithm to obtain a final compensation scheme;
the method specifically comprises the following steps:
step 101, initializing a population, and coding by a compensation scheme of the next control time generated randomly to obtain an individual; jth individualExpressed as: />Wherein->、/>And->The reactive power required to be output by the 1 st wind turbine generator, the 2 nd wind turbine generator and the N wind turbine generator in the compensation scheme of the j next control time generated randomly is respectively represented;
102, updating the population through genetic operators;
and 103, selecting an individual with the largest fitness value from the final population to decode when the iteration step 102 reaches the termination condition, and obtaining the final compensation scheme.
In one embodiment of the invention, the termination conditions are: the number of iterative steps 102 is equal to Z, which has a default value of 20.
In one embodiment of the invention, if more than two individuals with the largest fitness value are selected from the final population, the individuals are first sorted from large to small and then selected one by one. The multiple final compensation schemes decoded at this time cannot be performed simultaneously and can be selected by the manager.
The multi-objective fitness function of the genetic algorithm is:
wherein->Indicating fitness value of the jth individual, < ->And->Respectively representing a first weight coefficient and a second weight coefficient,/for>，/>，，/>Representing steady state reactive limit,/->Representing a first neural network;
the objective of individual optimization is the maximization of the multi-objective fitness function;
the first weight coefficient and the second weight coefficient may be adjusted by a tendency toward stability and response speed, for example, if the tendency toward stability is greater, the first weight coefficient is increased and the second weight coefficient is decreased.
The first neural network comprises an input layer, a first hidden layer, a second hidden layer and a fully connected layer, wherein the input layer generates an input feature matrix based on the operation data and the jth individual; the row vector of the ith row of the input feature matrix is expressed asWherein->Representing the next control time of the ith wind turbine in the jth individualReactive power to be output between (i.e.)>Reactive power output by the u-th wind turbine generator set at the current control time is represented by +.>Representing the rotor active power of the u-th wind turbine and +.>Stator active power of the u-th wind turbine representing the current control time, and>the air quantity of the u-th wind turbine generator set at the current control time is represented by +.>Wind pressure of the u-th wind turbine generator set at the current control time, < +.>Power system frequency indicative of current control time, +.>Representing the slip of the u-th wind turbine generator in the current control time;
the calculation formula of the first hidden layer is as follows:
wherein->Represents a first intermediate feature matrix, Q represents a first matrix, K represents a second matrix, V represents a third matrix,/a third matrix>Dimension representing row vector of input feature matrix, +.>，，/>Wherein->、/>、/>Respectively representing a first weight matrix, a second weight matrix and a third weight matrix,/->Representing an input feature matrix;
the second hidden layer comprises an RNN unit, the RNN unit sequentially inputs N row vectors of the first intermediate feature matrix in N time steps, the output of the N time steps is input to the full-connection layer, and the full-connection layer outputs a classification label representing response time;
the classification space of the full connection layer comprises 100 classification labels, and the value range of response time is calculatedThe mean value is discretized into 100 point values, and the 100 point values respectively correspond to 100 classification labels of the classification space of the full connection layer.
The response time is defined as follows: the starting point of the response time is a time point when a signal for adjusting the reactive power output by the wind turbine generator system is sent to the wind turbine generator system;
and detecting the voltage of the grid-connected point after starting to adjust, and stopping detection when the difference value between the voltage of the grid-connected point and the standard voltage is smaller than a set voltage fluctuation value in a time period, wherein the total time of the time period is greater than T seconds, and the starting time point of the time period is the end point of the response time.
That is, the grid-connected point voltage meets the stable condition in the time period.
In one example, the standard voltage is defined as 1.0p.u., the voltage fluctuation value (absolute value, neglecting positive and negative) is set to 0.2p.u., T is set to 0.5s, the grid-tie point voltage is maintained in the range of 1.0p.u. to 1.2p.u. for a period of time detected after 0.3s from the start of the response time, the start time point of the period of time is the end of the response time, that is, 0.3s after the start of the response time is the end of the response time, and the response time is 0.3s.
The intelligent control magnetic levitation breeze power generation capacity-increasing compensation device also comprises an AVC substation and reactive compensation equipment, wherein the AVC substation is connected to the reactive compensation equipment and the wind farm and is used for acquiring target reactive power of a grid-connected pointAccording to the target reactive power->Transmitting a reactive power adjustment instruction to reactive power compensation equipment; and reactive power +.in the event of a grid connection point detection>Reactive power output by reactive compensation equipment to grid-connected point is achieved>After full period of (a), controlling all wind turbines in the wind power plant to increase reactive power to grid-connected points +.>To compensate reactive compensation power required by the point of connection;
reactive power compensation equipment connected to AVC substation and wind power plant and used for outputting reactive power to grid connection pointReactive power compensation is carried out;
AVC substation obtains target reactive power of grid-connected pointAVC substation according to target reactive power +.>Transmitting a reactive power adjustment instruction to reactive power compensation equipment, wherein the reactive power compensation equipment outputs reactive power to grid connection points>，/>；
In one embodiment of the invention, the AVC substation obtaining the target reactive power of the wind farm may be achieved by:
1. the AVC substation receives a reactive power instruction issued by the AVC master station and acquires target reactive power from the reactive power instruction；
2. The AVC substation receives a voltage command issued by the AVC master station, and calculates target reactive power according to target grid-connected point voltage carried in the voltage command。
The embodiment has been described above with reference to the embodiment, but the embodiment is not limited to the above-described specific implementation, which is only illustrative and not restrictive, and many forms can be made by those of ordinary skill in the art, given the benefit of this disclosure, are within the scope of this embodiment.
Claims (10)
1. The intelligent control magnetic levitation breeze power generation capacity-increasing compensation device is characterized by comprising the following modules:
the data acquisition module is used for acquiring the operation data of the current control time of the wind turbine generator;
the calculation module is used for calculating the steady-state reactive power limit value of the wind turbine generator；
The scheme generation module randomly generates a compensation scheme of the next control time based on constraint conditions, wherein one compensation scheme comprises reactive power required to be output at the next control time of all wind turbines;
the scheme optimization module is used for optimizing the compensation scheme of the next control time generated randomly through a multi-objective evolutionary algorithm to obtain a final compensation scheme;
wherein the method comprises the steps of，/>For the voltage of the stator of the wind turbine, +.>The frequency of the grid system is the grid-connected point; />Is the stator inductance.
2. The intelligent control magnetic levitation breeze power generation capacity-increasing compensation device according to claim 1, wherein the constraint conditions in the scheme generating module comprise:；/>the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>Representing reactive power which is required to be output by the s-th wind turbine generator in the next control time, and +.>Representing steady state reactive limit,/->And the total reactive power compensation power required to be provided by all the wind turbines is represented, and N represents the total number of the wind turbines.
3. The intelligent control magnetic levitation breeze power generation capacity-increasing compensation device according to claim 2, wherein the scheme optimizing module comprises the following steps:
step 101, initializing a population, and coding by a compensation scheme of the next control time generated randomly to obtain an individual; jth individualExpressed as: />Wherein->、/>And->The reactive power required to be output by the 1 st wind turbine generator, the 2 nd wind turbine generator and the N wind turbine generator in the compensation scheme of the j next control time generated randomly is respectively represented;
102, updating the population through genetic operators;
and 103, selecting an individual with the largest fitness value from the final population to decode when the iteration step 102 reaches the termination condition, and obtaining the final compensation scheme.
4. A intelligently controlled magnetically levitated breeze power generation capacity-increasing compensation device according to claim 3, wherein the termination condition of step 102 is: the number of iterations is equal to Z; the default value of Z is 20.
5. The intelligent control magnetic levitation breeze power generation capacity-increasing compensation device according to claim 4, wherein the fitness function of the multi-objective evolutionary algorithm is:
wherein->Indicating fitness value of the jth individual, < ->And->Respectively representing a first weight coefficient and a second weight coefficient,/for>，/>，/>，/>Representing steady state reactive limit,/->Representing a first neural network.
6. The intelligent control magnetically levitated breeze power generation and capacity compensation device according to claim 5, wherein the first neural network comprises an input layer, a first hidden layer, a second hidden layer and a full connection layer, and the input layer generates an input feature matrix based on the operation data and the jth individual; the row vector of the ith row of the input feature matrix is expressed asWherein->Representing the reactive power which needs to be output at the next control time of the (th) wind turbine in the (th) individual, <>Reactive power output by the u-th wind turbine generator set at the current control time is represented by +.>Representing the rotor active power of the u-th wind turbine and +.>Stator active power of the u-th wind turbine representing the current control time, and>the air quantity of the u-th wind turbine generator set at the current control time is represented by +.>Wind pressure of the u-th wind turbine generator set at the current control time, < +.>Power system frequency indicative of current control time, +.>And indicating the slip of the u-th wind turbine generator in the current control time.
7. The intelligent control magnetic levitation breeze power generation capacity-increasing compensation device according to claim 6, wherein the calculation formula of the first hidden layer of the first neural network is as follows:wherein->Represents a first intermediate feature matrix, Q represents a first matrix, K represents a second matrix, V represents a third matrix,/a third matrix>Dimension representing row vector of input feature matrix, +.>，/>，/>Wherein->、/>、/>Respectively representing a first weight matrix, a second weight matrix and a third weight matrix,/->Representing an input feature matrix;
the second hidden layer comprises an RNN unit, the RNN unit sequentially inputs N row vectors of the first intermediate feature matrix in N time steps, the output of the N time steps is input to the full-connection layer, and the full-connection layer outputs a classification label representing response time;
the classification space of the full connection layer comprises 100 classification labels, and the value range of response time is calculatedThe mean value is discretized into 100 point values, and the 100 point values respectively correspond to 100 classification labels of the classification space of the full connection layer.
8. The intelligent control magnetic levitation breeze power generation capacity-increasing compensation device according to claim 7, further comprising an AVC substation and reactive compensation equipment, wherein the AVC substation is connected to the reactive compensation equipment and is used for acquiring target reactive power of a grid-connected point and sending a reactive adjustment instruction to the reactive compensation equipment according to the target reactive power; and after the reactive power of the grid-connected point is detected to reach the full amount of the reactive power output by the reactive compensation equipment to the grid-connected point, controlling all the wind turbines to increase the reactive power to the grid-connected point so as to compensate the reactive compensation power required by the grid-connected point.
9. The intelligent control magnetic levitation breeze power generation capacity-increasing compensation device according to claim 8, further comprising an AVC master station, wherein the AVC master station is connected to an AVC substation, the AVC substation receives reactive power instructions issued by the AVC master station, and the target reactive power of the grid-connected point is obtained from the reactive power instructions.
10. The intelligent control magnetic levitation breeze power generation capacity-increasing compensation device according to claim 9, wherein the reactive power instruction comprises a voltage instruction issued by an AVC master station, and the AVC sub-station calculates the target reactive power of the grid-connected point according to the target grid-connected point voltage carried in the voltage instruction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310956405.1A CN116667467B (en) | 2023-08-01 | 2023-08-01 | Intelligent control magnetic suspension breeze power generation capacity-increasing compensation device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310956405.1A CN116667467B (en) | 2023-08-01 | 2023-08-01 | Intelligent control magnetic suspension breeze power generation capacity-increasing compensation device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116667467A true CN116667467A (en) | 2023-08-29 |
| CN116667467B CN116667467B (en) | 2023-10-13 |
Family
ID=87712244
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310956405.1A Active CN116667467B (en) | 2023-08-01 | 2023-08-01 | Intelligent control magnetic suspension breeze power generation capacity-increasing compensation device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116667467B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103701134A (en) * | 2014-01-09 | 2014-04-02 | 武汉大学 | Grid-connected wind power plant point voltage control method based on MCR (Magnetic Control Reactor) and capacitance mixed compensation |
| CN103956750A (en) * | 2014-04-23 | 2014-07-30 | 国家电网公司 | Reactive power optimization system and method for control over voltage fluctuation in wind power centralized output mode |
| CN106712044A (en) * | 2016-11-10 | 2017-05-24 | 华北电力大学 | Multi-objective optimization method of reactive voltage in wind power plant |
| WO2019141041A1 (en) * | 2018-01-22 | 2019-07-25 | 佛山科学技术学院 | Multi-objective optimization method for wind power plant machine set layout |
| WO2021088442A1 (en) * | 2019-11-05 | 2021-05-14 | 中国电力科学研究院有限公司 | Method and system for coordinately controlling reactive voltage of wind farm |
| CN112928760A (en) * | 2021-02-04 | 2021-06-08 | 中国电建集团青海省电力设计院有限公司 | Wind power plant active reactive compensation control method considering power grid load fluctuation |
| CN114069726A (en) * | 2021-10-13 | 2022-02-18 | 中国电力科学研究院有限公司 | Wind power plant power coordination control method and system considering economy and safety |
| CN114204613A (en) * | 2020-09-02 | 2022-03-18 | 中国电力科学研究院有限公司 | Reactive compensation method and system for offshore wind farm access power system |
| CN114243708A (en) * | 2021-11-25 | 2022-03-25 | 西南交通大学 | Alternating current model-based power transmission network extension planning optimization method |
| CN115081323A (en) * | 2022-06-17 | 2022-09-20 | 华南理工大学 | Method for solving multi-objective constrained optimization problem and storage medium thereof |
| CN116127084A (en) * | 2022-10-21 | 2023-05-16 | 中国农业大学 | Knowledge graph-based micro-grid scheduling strategy intelligent retrieval system and method |
-
2023
- 2023-08-01 CN CN202310956405.1A patent/CN116667467B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103701134A (en) * | 2014-01-09 | 2014-04-02 | 武汉大学 | Grid-connected wind power plant point voltage control method based on MCR (Magnetic Control Reactor) and capacitance mixed compensation |
| CN103956750A (en) * | 2014-04-23 | 2014-07-30 | 国家电网公司 | Reactive power optimization system and method for control over voltage fluctuation in wind power centralized output mode |
| CN106712044A (en) * | 2016-11-10 | 2017-05-24 | 华北电力大学 | Multi-objective optimization method of reactive voltage in wind power plant |
| WO2019141041A1 (en) * | 2018-01-22 | 2019-07-25 | 佛山科学技术学院 | Multi-objective optimization method for wind power plant machine set layout |
| WO2021088442A1 (en) * | 2019-11-05 | 2021-05-14 | 中国电力科学研究院有限公司 | Method and system for coordinately controlling reactive voltage of wind farm |
| CN114204613A (en) * | 2020-09-02 | 2022-03-18 | 中国电力科学研究院有限公司 | Reactive compensation method and system for offshore wind farm access power system |
| CN112928760A (en) * | 2021-02-04 | 2021-06-08 | 中国电建集团青海省电力设计院有限公司 | Wind power plant active reactive compensation control method considering power grid load fluctuation |
| CN114069726A (en) * | 2021-10-13 | 2022-02-18 | 中国电力科学研究院有限公司 | Wind power plant power coordination control method and system considering economy and safety |
| CN114243708A (en) * | 2021-11-25 | 2022-03-25 | 西南交通大学 | Alternating current model-based power transmission network extension planning optimization method |
| CN115081323A (en) * | 2022-06-17 | 2022-09-20 | 华南理工大学 | Method for solving multi-objective constrained optimization problem and storage medium thereof |
| CN116127084A (en) * | 2022-10-21 | 2023-05-16 | 中国农业大学 | Knowledge graph-based micro-grid scheduling strategy intelligent retrieval system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116667467B (en) | 2023-10-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104620458B (en) | Determine the method and power plant controller of each set point in power plant controller | |
| Kot et al. | Comparison of maximum peak power tracking algorithms for a small wind turbine | |
| Kahla et al. | On-Off control based particle swarm optimization for maximum power point tracking of wind turbine equipped by DFIG connected to the grid with energy storage | |
| Syahputra et al. | Control of doubly-fed induction generator in distributed generation units using adaptive neuro-fuzzy approach | |
| CN104603455A (en) | Wind power plant control system, wind power plant including wind power plant control system and method of controlling wind power plant | |
| CN102290809A (en) | Method and system for controlling a power production entity | |
| Hamid et al. | Optimal MPPT and BES control for grid-tied DFIG-based wind energy conversion system | |
| CN109936146A (en) | A kind of wind power plant coordinating and optimizing control method based on improvement sensitivity algorithm | |
| CN113169557A (en) | Power conversion system, management device thereof, and distributed power supply device | |
| KR20130068560A (en) | Grid connected wind power system and sensorless maximum power point tracking control method thereof using neural network | |
| CN110854907A (en) | Collaborative optimization operation method and system for power distribution network wind power plant under communication fault | |
| CN111162556B (en) | Distributed autonomous control decision method for AC/DC power distribution and utilization system | |
| Nair et al. | Parametrically robust identification based sensorless control approach for doubly fed induction generator | |
| CN116667467B (en) | Intelligent control magnetic suspension breeze power generation capacity-increasing compensation device | |
| Baala et al. | DFIG-based wind turbine control using high-gain observer | |
| Hao et al. | Optimal coordinated control of hybrid AC/VSC-HVDC system integrated with DFIG via cooperative beetle antennae search algorithm | |
| CN116488211A (en) | VSG improved parameter self-adaption method for single-phase photovoltaic energy storage | |
| Mendi et al. | A speed sensorless modified perturb and observe mppt scheme for stand-alone pmsg based wind turbine system | |
| Mol et al. | Integration of wind and PV systems using genetic-assisted artificial neural network | |
| CN112260306B (en) | New energy power station equipartition group control power generation control method and device | |
| CN113890022A (en) | Rapid atomic search method for reactive power optimization of wind energy and solar energy power grid | |
| Oussama et al. | Fractional order PID design for MPPT-Pitch angle control of wind turbine using bat algorithm | |
| Nguyen et al. | Improvement of power output of the Wind Turbine by pitch angle control using RBF neural network | |
| Karad et al. | Genetic algorithm and particle swarm optimization tuned fractional order pitch angle control | |
| Mehta et al. | Control strategies for grid-connected hybrid renewable energy systems: Integrating modified direct torque control based doubly fed induction generator and ANFIS based maximum power point tracking for solar PV generation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |