CN117439197A - Wind turbine generator frequency supporting method, device, equipment and storage medium - Google Patents
Wind turbine generator frequency supporting method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN117439197A CN117439197A CN202311300691.2A CN202311300691A CN117439197A CN 117439197 A CN117439197 A CN 117439197A CN 202311300691 A CN202311300691 A CN 202311300691A CN 117439197 A CN117439197 A CN 117439197A
- Authority
- CN
- China
- Prior art keywords
- wind turbine
- standby power
- node
- turbine generator
- wind
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000003860 storage Methods 0.000 title claims abstract description 15
- 238000010586 diagram Methods 0.000 claims abstract description 62
- 238000003062 neural network model Methods 0.000 claims abstract description 23
- 239000013598 vector Substances 0.000 claims description 80
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000013507 mapping Methods 0.000 claims description 7
- 238000004146 energy storage Methods 0.000 claims description 5
- 230000006870 function Effects 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 230000004044 response Effects 0.000 description 6
- 238000007665 sagging Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 230000004907 flux Effects 0.000 description 3
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- 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
- H02J3/48—Controlling the sharing of the in-phase component
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- 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
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- 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)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Power Engineering (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Biophysics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Primary Health Care (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Control Of Eletrric Generators (AREA)
Abstract
The invention provides a wind turbine generator frequency supporting method, a device, equipment and a storage medium, wherein the method comprises the steps of obtaining a circuit diagram of a wind turbine generator and collecting operation data of the wind turbine generator in real time, generating a wind turbine generator node diagram according to the circuit diagram, calculating through the wind turbine generator node diagram, the operation data and a preset first neural network model to obtain maximum standby power values corresponding to all wind turbine generators in the wind turbine generator, gradually increasing the values of the standby power output by the corresponding wind turbine generators from zero by adopting the maximum standby power values until grid-connected point operation parameters in the operation data become unstable, then obtaining the standby power values of the wind turbine generator when the grid-connected point operation parameters become unstable, wherein the standby power values are the maximum available standby power values of the wind turbine generator without influencing the stability of a main power grid, and further ensuring the stability of the main power grid by enabling the standby power values output by the wind turbine generator to be always smaller than the maximum available standby power values.
Description
Technical Field
The invention relates to the technical field of wind power systems, in particular to a wind turbine generator frequency supporting method, a wind turbine generator frequency supporting device, wind turbine generator frequency supporting equipment and a storage medium.
Background
The new energy is widely applied due to the characteristics of rich resources, renewable performance and the like, and is a common energy in the new energy of wind power, but wind power generation has volatility, so that the frequency supporting capacity such as the inertia coefficient, the sagging coefficient and the like of the power system is continuously reduced, and the frequency safety of the power system is seriously affected.
Currently, in order to maintain stability of a power system, it is generally adopted to store standby power as increased power, for example, a wind driven generator can simulate inertia or droop response of a synchronous machine by temporarily increasing the power so as to realize frequency support; the frequency supporting capacity can be represented by an inertia coefficient and a sagging coefficient of the power system, the larger the values of the inertia coefficient and the sagging coefficient are, the stronger the capacity of the wind power generator for providing frequency supporting is, the temporary power increase is standby power, the standby power is generally obtained by dividing the generated power in the prior art, the corresponding inertia response and sagging response are obtained by calculating the standby power, and the corresponding wind power generator frequency supporting capacity is obtained according to the inertia response and the sagging response.
However, in the prior art, the influence on the reactive power of the wind turbine generator set when the standby power is used is not considered in the calculation and judgment of the standby power, the standby power possibly causes reactive unbalance of the micro grid when being used up, and further, the voltage of the grid-connected point generates overrun fluctuation, the adjustment burden of the main grid is increased, the stability of the main grid is influenced, and the adverse influence on the main grid is increased along with the increase of the number of wind turbine generator sets and the generation scale.
Disclosure of Invention
In view of the foregoing, it is necessary to provide a method, a device, an apparatus and a storage medium for supporting frequency of a wind turbine generator, which are used for solving the technical problems that reactive power unbalance of a micro-grid is caused when standby power is used up, thereby increasing adjustment burden of a main grid and affecting stability of the main grid.
In order to solve the above problems, the present invention provides a method for supporting a frequency of a wind turbine, including:
acquiring a circuit diagram of a wind power plant and acquiring operation data of the wind power plant in real time;
generating a wind power plant node diagram according to the circuit diagram;
calculating according to the wind power plant node diagram, the operation data and a preset first neural network model to obtain maximum standby power values corresponding to all wind power units in the wind power plant;
gradually increasing the value of the standby power output by the corresponding wind turbine generator set from zero based on the maximum standby power value until the grid-connected point operation parameters in the operation data become unstable;
and acquiring a standby power value of the wind turbine generator when the grid-connected point operation parameter becomes unstable, and taking the standby power value as the maximum available standby power value of the wind turbine generator.
Optionally, the first neural network model includes a K-layer hidden layer and a fully connected layer; the calculating according to the wind power plant node diagram, the operation data and a preset first neural network model to obtain the maximum standby power value corresponding to each wind power unit in the wind power plant comprises the following steps:
generating a plurality of first node vectors according to the operation data and the wind power plant node diagram;
inputting the wind power plant node map and the plurality of first node vectors into the corresponding hidden layer to obtain second node vectors corresponding to the wind power units;
and inputting the second node vector into the full connection layer to obtain the maximum standby power value of the wind turbine corresponding to the second node vector.
Optionally, the first neural network model further includes a splicing layer, and the splicing layer is disposed between the hidden layer and the fully-connected layer; the step of inputting the wind power plant node map and the plurality of first node vectors into the corresponding hidden layer to obtain second node vectors corresponding to the wind power units, and then further comprises the steps of:
inputting the second node vector corresponding to each wind turbine generator into the splicing layer to obtain a splicing vector;
and inputting the splicing vector into the full connection layer to obtain the maximum standby power value of the wind power plant.
Optionally, the first neural network model further includes at least one parallel linear mapping layer for mapping the plurality of first node vectors to the same dimension.
Optionally, the first node vector includes a wind turbine unit feature vector, a converter unit feature vector, an energy storage unit feature vector, an inverter unit feature vector, and a grid-connected point feature vector.
Optionally, a calculation formula of the u layer of the hidden layer of the K layer is:
wherein,representing intermediate features of the ith node of the ith layer, D (i) Represents a set of nodes directly connected to node i, < >>Representing intermediate features of the jth node of the (u-1) th layer, W (u) A weight parameter representing a u-th layer, and sigma represents a sigmoid activation function; when u=1, _a->θ j Representing node characteristics of the j-th node.
Optionally, the grid-connected electric operation parameters comprise a lifting fluctuation quantity value and a lifting amplitude value; gradually increasing the value of the standby power output by the corresponding wind turbine generator set from zero based on the maximum standby power value until the grid-connected point operation parameter in the operation data becomes unstable, wherein the step of stopping increasing comprises the following steps:
setting one percent of the maximum standby power value as a step size;
gradually increasing the value of the standby power output by the wind turbine generator corresponding to the maximum standby power value from zero by the step length, and judging the lifting fluctuation value and the lifting amplitude value corresponding to the wind turbine generator within a preset time after each increase;
and stopping increasing the standby power when at least one of the lifting fluctuation value and the lifting amplitude value is larger than a corresponding preset value.
Furthermore, the invention also provides a frequency supporting device of the wind turbine, which comprises:
the data acquisition module is used for acquiring a circuit diagram of the wind power plant and acquiring operation data of the wind power plant in real time;
the node diagram generation module is used for generating a wind power plant node diagram according to the circuit diagram;
the power calculation module is used for calculating according to the wind power plant node diagram, the operation data and a preset first neural network model to obtain the maximum standby power value corresponding to each wind power unit in the wind power plant;
the power test module is used for gradually increasing the value of the standby power output by the corresponding wind turbine generator set from zero based on the maximum standby power value until the grid-connected point operation parameters in the operation data become unstable;
and the available power acquisition module is used for acquiring the standby power value of the wind turbine generator when the grid-connected point operation parameter becomes unstable, and taking the standby power value as the maximum available standby power value of the wind turbine generator.
Further, the invention also provides electronic equipment, which comprises a memory and a processor, wherein the memory is used for storing programs;
the processor is coupled to the memory for executing the program stored in the memory to implement the steps in the wind turbine frequency support method of any one of the above.
Further, the present invention also provides a non-transitory computer readable storage medium, on which a computer program is stored, which when executed by a processor, implements a wind turbine frequency support method as described in any of the above.
The beneficial effects of the invention are as follows: according to the wind turbine generator frequency supporting method, the circuit diagram of the wind power plant is obtained, the operation data of the wind power plant are collected in real time, the wind power plant node diagram is generated according to the circuit diagram, calculation is carried out based on the wind power plant node diagram, the operation data and a preset first neural network model, the maximum standby power value corresponding to each wind turbine generator in the wind power plant is obtained, the value of the standby power output by the corresponding wind turbine generator is gradually increased from zero by adopting the maximum standby power value until the grid-connected point operation parameters in the operation data become unstable, then the standby power value of the wind turbine generator when the grid-connected point operation parameters become unstable is obtained, and the standby power value is the maximum available standby power value of the wind turbine generator, which does not affect the stability of a main power grid, and the standby power value output by the wind turbine generator is always smaller than the maximum available standby power value, so that the stability of the main power grid is ensured.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of an embodiment of a method for supporting a wind turbine frequency according to the present invention;
FIG. 2 is a flowchart illustrating an embodiment of step S103 of the wind turbine frequency support method according to the present invention;
FIG. 3 is a flowchart illustrating an embodiment of step S104 of the wind turbine frequency support method according to the present invention;
FIG. 4 is a schematic structural diagram of an embodiment of a wind turbine generator frequency support device according to the present invention;
fig. 5 is a schematic structural diagram of an embodiment of an electronic device according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be understood that the schematic drawings are not drawn to scale. A flowchart, as used in this disclosure, illustrates operations implemented according to some embodiments of the present invention. It should be appreciated that the operations of the flow diagrams may be implemented out of order and that steps without logical context may be performed in reverse order or concurrently. Moreover, one or more other operations may be added to or removed from the flow diagrams by those skilled in the art under the direction of the present disclosure.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the invention. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
The embodiment of the invention provides a method, a device, equipment and a storage medium for supporting the frequency of a wind turbine, which are respectively described below.
Fig. 1 is a schematic flow chart of an embodiment of a method for supporting a frequency of a wind turbine according to the present invention, as shown in fig. 1, including:
s101, acquiring a circuit diagram of a wind power plant and acquiring operation data of the wind power plant in real time;
s102, generating a wind power plant node diagram according to the circuit diagram;
s103, calculating according to the node diagram, the operation data and a preset first neural network model of the wind power plant to obtain the maximum standby power value corresponding to each wind turbine generator in the wind power plant;
s104, gradually increasing the value of the standby power output by the corresponding wind turbine generator set from zero based on the maximum standby power value until the grid-connected point operation parameters in the operation data become unstable;
s105, acquiring a standby power value of the wind turbine generator when the operation parameters of the grid-connected point become unstable, and taking the standby power value as the maximum available standby power value of the wind turbine generator.
In the embodiment of the invention, the wind power plant is a wind power plant, and the operation data of the wind power plant comprises wind power parameters, wind turbine generator set operation parameters, converter operation parameters, energy storage operation parameters, inverter operation parameters and grid-connected point operation parameters; the nodes on the node diagram of the wind power plant correspond to functional units of the wind power plant, wherein the functional units of the wind power plant comprise a wind turbine generator, a converter, an energy accumulator, an inverter and grid-connected points, and an edge exists between the two nodes to indicate that a direct connection relationship of lines exists between the functional units corresponding to the two nodes, for example: and one converter is directly and electrically connected with one wind turbine generator, and the corresponding node of the converter is connected with the corresponding node of the wind turbine generator by an edge.
It can be understood that in the embodiment of the invention, the maximum available standby power value is the exportable maximum standby power value of the wind turbine without affecting the stability of the main power grid, and after the maximum available standby power corresponding to each wind turbine is obtained, the standby power value output by each wind turbine is limited below the corresponding maximum available standby power value, so that the standby power is ensured not to be used up, the main power grid is not affected by reactive power, and the stability of the main power grid is further ensured.
Compared with the prior art, the wind turbine generator frequency supporting method provided by the invention has the advantages that the circuit diagram of the wind turbine generator is obtained, the operation data of the wind turbine generator are collected in real time, the wind turbine generator node diagram is generated according to the circuit diagram, the calculation is performed based on the wind turbine generator node diagram, the operation data and the preset first neural network model, the maximum standby power value corresponding to each wind turbine generator in the wind turbine generator is obtained, the value of the standby power output by the corresponding wind turbine generator is gradually increased from zero by adopting the maximum standby power value until the grid-connected point operation parameters in the operation data become unstable, then the standby power value of the wind turbine generator when the grid-connected point operation parameters become unstable is obtained, and the standby power value is the maximum available standby power value of the wind turbine generator without affecting the stability of the main power grid.
Referring to fig. 2, fig. 2 is a schematic flow chart of an embodiment of a step S103 of a wind turbine generator frequency supporting method according to the present invention. In some embodiments of the present invention, the first neural network model includes a K-layer hidden layer and a fully connected layer, and step S103 includes:
s201, generating a plurality of first node vectors according to operation data and a wind power plant node diagram;
s202, inputting a wind power plant node map and a plurality of first node vectors into corresponding hidden layers to obtain second node vectors corresponding to each wind power unit;
and S203, inputting the second node vector into the full-connection layer to obtain the maximum standby power value of the wind turbine corresponding to the second node vector.
It should be noted that, in the embodiment of the present invention, a wind power plant includes a plurality of wind power units, a plurality of converters, a plurality of energy storages, a plurality of inverters and a plurality of grid-connected points, and a first node vector corresponding to the wind power unit can be generated through operation parameters of the wind power units and a wind power plant node diagram corresponding to the wind power units; generating a first node vector corresponding to the converter through operation parameters of the converter and a wind power plant node diagram corresponding to the converter; generating a first node vector corresponding to the energy accumulator through the operation parameters of the energy accumulator and the corresponding wind power plant node diagram; generating a first node vector corresponding to the inverter through the operation parameters of the inverter and the corresponding wind power plant node diagram; generating a first node vector corresponding to the grid-connected point through the operation parameters of the grid-connected point and the corresponding wind power plant node diagram; each first node vector is input with a corresponding hidden layer, namely the first node vector can be updated to obtain a corresponding second node vector, namely the number of the first node vectors is K, and the first node vectors correspond to the hidden layers; after the first node vector of the wind turbine is input, the corresponding hidden layer outputs a second node vector of the wind turbine, and the second node vector is calculated through the full connection layer, so that the maximum standby power value of the wind turbine can be obtained, wherein the maximum standby power value is the maximum standby power which can be provided by the wind turbine, but if the wind turbine outputs the maximum standby power, the main power grid is unstable, and therefore the maximum available standby power value needs to be calculated according to the maximum standby power value.
In some embodiments of the present invention, the first neural network model further includes a stitching layer disposed between the hidden layer and the fully-connected layer; after step S202, further includes:
inputting the second node vectors corresponding to the wind turbines into a splicing layer to obtain splicing vectors;
and inputting the splicing vector into the full-connection layer to obtain the maximum standby power value of the wind power plant.
It can be understood that in the embodiment of the present invention, the splicing layer may splice all the second node vectors output by the hidden layer to obtain a spliced vector, and the full connection layer of the first neural network operates on the spliced vector to obtain the maximum standby power value that can be provided by the whole wind power plant.
In some embodiments of the invention, the first neural network model further comprises at least one parallel linear mapping layer for mapping the plurality of first node vectors to the same dimension.
It will be appreciated that a plurality of first node vectors may be mapped to a unified dimension by the parallel line mapping layer for computation.
In some embodiments of the present invention, the first node vector includes a wind turbine unit feature vector, a converter unit feature vector, an energy storage unit feature vector, an inverter unit feature vector, and a grid tie feature vector.
It should be noted that, in the embodiment of the present invention, the feature vector of the wind turbine unit is a first node vector of a node corresponding to the wind turbine unit, where the vector may be expressed as:
wherein,representing the rotor active power of the ith wind turbine and +.>Representing the stator active power of the ith wind turbine and +.>Representing reactive power, < > of the ith wind turbine>Representing the air quantity of the ith wind turbine generator system, < >>Representing the wind pressure of the ith wind turbine generator system, < >>Represents the generator stator reactance of the i-th wind turbine, a->Representing stator-rotor mutual resistance of the ith wind turbine generator system,/->Representing the slip of the ith wind turbine generator system, < >>Representing the rotor resistance of the ith wind turbine and +.>Representing stator self-inductance of the ith wind turbine generator system,/-for the ith wind turbine generator system>Representing the component of the rotor current of the ith wind turbine in the d-axis,>representing the q-axis component of the rotor current of the i-th wind turbine, and (a) and (b)>Representing the component of the rotor self-induction flux linkage of the ith wind turbine in the d-axis,/-axis>Representing the component of the rotor self-induction flux linkage of the ith wind turbine in the q-axis,/->Stator self-induction flux linkage of the ith wind turbine unit>The rated current of a rotor-side converter of the ith wind turbine generator is represented, and g represents the gravitational acceleration; the characteristic vector of the current transformer is a first node vector of the corresponding node of the current transformer, and can be expressed asWherein (1)>Rated voltage of converter corresponding to ith wind turbine generator system, < >>Level number of converter corresponding to ith wind turbine generator system,/">Rated power of converter corresponding to ith wind turbine generator system, (-), for example>Rated apparent power of converter corresponding to ith wind turbine generator system, < >>Grid-side converter rated power, denoted as the converter corresponding to the ith wind turbine, for +.>Rated power of the motor-side converter, which is denoted as the converter corresponding to the ith wind turbine, and +.>The capacity of the converter corresponding to the ith wind turbine generator is expressed; the characteristic vector of the energy accumulator is a first node vector of the corresponding node of the energy accumulator, and can be expressed asWherein (1)>Representing the capacity of the accumulator corresponding to the ith wind turbine generator system,/->Representing the charging efficiency of the energy store corresponding to the ith wind turbine generator system,/->Representing the discharge efficiency of the energy store corresponding to the ith wind turbine generator system,/->Representing the self-discharge rate of the energy accumulator corresponding to the ith wind turbine generator system, ">Representing the cycle life of the energy store corresponding to the ith wind turbine and +.>Representing the response time of the energy accumulator corresponding to the ith wind turbine generator system,/->Representing the voltage of the energy accumulator corresponding to the ith wind turbine generator system,/->Representing the temperature characteristic of an energy accumulator corresponding to the ith wind turbine generator; the inverter characteristic vector is a first node vector of the corresponding node of the inverter, and can be expressed asWherein (1)>Represents the rated power of the inverter corresponding to the ith wind turbine generator system,Representing the efficiency of the inverter corresponding to the ith wind turbine generator system,/->Representing the power factor of the inverter corresponding to the ith wind turbine generator system,/->Representing the total harmonic distortion of the inverter corresponding to the ith wind turbine generator system, ">Representing the failure rate of the inverter corresponding to the ith wind turbine generator; the feature vector of the grid-connected point is a first node vector of the node corresponding to the grid-connected point, and can be expressed asWherein (1)>Representing voltage level of the point of connection +.>Representing maximum transmission power of a point of attachment, +.>Representing the voltage stability of the point of connection +.>Representing failure rate of the point of connection->Representing the time of failure recovery of the point of the union +.>Representing the power system frequency.
In some embodiments of the present invention, the calculation formula of the u-th layer of the K-th hidden layer is:
wherein,representing intermediate features of the ith node of the ith layer, D (i) Represents a set of nodes directly connected to node i, < >>Representing intermediate features of the jth node of the (u-1) th layer, W (u) A weight parameter representing a u-th layer, and sigma represents a sigmoid activation function; when u=1, _a->θ j Representing node characteristics of the j-th node.
It should be noted that, in the embodiment of the present invention, the input of the first layer of the hidden layer is the first node vector, θ j The node characteristic of the j-th node in the first node vector is represented, the node characteristic output by the last layer of the hidden layer is the second node vector, and the node characteristic can be input into a full-connection layer or a splicing layer.
It can be appreciated that in the embodiment of the present invention, the training data of the first neural network model may be obtained through wind power plant modeling, wind power plant modeling is performed through wind power plant operation data, and then a simulation experiment is performed, so as to obtain the training data.
Referring to fig. 3, fig. 3 is a schematic flow chart of an embodiment of step S104 of the wind turbine generator frequency supporting method provided by the present invention; in some embodiments of the present invention, the grid-connected electric operation parameter includes a lifting fluctuation quantity value and a lifting amplitude value, and step S104 includes:
s301, setting one percent of the maximum standby power value as a step size;
s302, gradually increasing the value of the standby power output by the wind turbine corresponding to the maximum standby power value from zero in step length, and judging the lifting fluctuation value and the lifting amplitude value corresponding to the wind turbine within preset time after each increase;
and S303, stopping increasing the standby power when at least one of the lifting fluctuation value and the lifting amplitude value is larger than the corresponding preset value.
In the embodiment of the invention, 1% of the maximum standby power corresponding to the wind turbine is used as an incremental step, namely, the power value of each increment of the wind turbine is 1% of the maximum standby power value, after each increment, the wind turbine is enabled to output with the standby power after the increment, and the standby power output time is preset time, whether the grid-connected point operation parameters of the wind turbine are stable or not is judged in the preset time, and wind power plant operation data are recorded, if so, the standby power is continuously incremented until the grid-connected point operation parameters become unstable in the preset time, so that the unstable standby power output value of the grid-connected point operation parameters becomes the threshold value of the wind turbine capable of outputting the standby power, and once the standby power value output by the wind turbine is larger than the threshold value, the main power grid becomes unstable, so that the standby power output value of the wind turbine can be limited below the threshold value, and the stability of the main power grid is ensured.
It can be understood that in the embodiment of the invention, whether the operation parameter of the grid-connected point is stable or not can be judged by the fluctuation value and the amplitude value of the voltage of the grid-connected point, if the fluctuation value and the amplitude value of the voltage of the grid-connected point in the preset time are smaller than the preset value (namely, the fluctuation and the amplitude of the voltage are in the allowable range), the operation parameter of the grid-connected point is stable, and then the standby power output by the wind turbine generator set does not influence the stability of the main power grid; if the value of at least one of the lifting fluctuation value and the lifting amplitude value of the grid-connected point voltage in the preset time is larger than the preset value (namely, at least one of the lifting fluctuation value and the lifting amplitude value exceeds the allowable range), the grid-connected point operation parameters are unstable, and the fact that the standby power output by the wind turbine generator set affects the stability of the main power grid is indicated; the preset time is counted when the wind turbine generator outputs standby power to the grid-connected point, the time length can be selected according to actual requirements, and if the reliability of data is to be ensured, the time length is set to be larger.
According to the method, the maximum available standby power of the wind turbine is calculated, so that the standby power output by the wind turbine is always smaller than the maximum available standby power, the influence of reactive power of the wind turbine is reduced, the voltage fluctuation of a grid connection point is reduced, the adjustment burden of a main power grid is reduced, and the stability of the main power grid is improved.
Referring to fig. 4, fig. 4 is a schematic structural diagram of an embodiment of a wind turbine generator frequency supporting device provided by the present invention.
The embodiment also provides a wind turbine generator frequency support device, which comprises:
the data acquisition module 401 is used for acquiring a circuit diagram of the wind power plant and acquiring operation data of the wind power plant in real time;
the node diagram generation module 402 is used for generating a wind power plant node diagram according to the circuit diagram;
the power calculation module 403 is configured to calculate according to the node map of the wind power plant, the operation data, and a preset first neural network model, and obtain a maximum standby power value corresponding to each wind turbine in the wind power plant;
the power test module 404 is configured to gradually increase the value of the standby power output by the corresponding wind turbine generator from zero based on the maximum standby power value until the grid-connected point operation parameter in the operation data becomes unstable;
the available power obtaining module 405 is configured to obtain a standby power value of the wind turbine when the grid-connected point operation parameter becomes unstable, and use the standby power value as a maximum available standby power value of the wind turbine.
The solution described in the foregoing embodiment of a wind turbine generator frequency supporting method may be implemented by using the wind turbine generator frequency supporting device provided in the foregoing embodiment, and the specific principles of the foregoing units may refer to the embodiment of a wind turbine generator frequency supporting method, which is not described herein again.
Referring to fig. 5, the present invention also provides an electronic device 500, where the electronic device 500 includes a processor 501, a memory 502, and a display 503. Fig. 5 shows only some of the components of the electronic device 500, but it should be understood that not all of the illustrated components are required to be implemented and that more or fewer components may be implemented instead.
The processor 501 may in some embodiments be a central processing unit (Central Processing Unit, CPU), microprocessor or other data processing chip for executing program code or processing data stored in the memory 502, such as the wind turbine frequency support method of the present invention.
In some embodiments, processor 501 may be a single server or a group of servers. The server farm may be centralized or distributed. In some embodiments, the processor 501 may be local or remote. In some embodiments, the processor 501 may be implemented on a cloud platform. In an embodiment, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an inter-internal, multiple clouds, or the like, or any combination thereof.
The memory 502 may be an internal storage unit of the electronic device 500 in some embodiments, such as a hard disk or memory of the electronic device 500. The memory 502 may also be an external storage device of the electronic device 500 in other embodiments, such as a plug-in hard disk, smart Media Card (SMC), secure Digital (SD) Card, flash Card (Flash Card) or the like, which are provided on the electronic device 500.
Further, the memory 502 may also include both internal storage units and external storage devices of the electronic device 500. The memory 502 is used for storing application software and various types of data for installing the electronic device 500.
The display 503 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like in some embodiments. The display 503 is for displaying information at the electronic device 500 and for displaying a visual user interface. The components 501-503 of the electronic device 500 communicate with each other via a system bus.
In one embodiment, when the processor 501 executes the wind turbine frequency support program in the memory 502, the following steps may be implemented:
acquiring a circuit diagram of a wind power plant and acquiring operation data of the wind power plant in real time;
generating a wind power plant node diagram according to the circuit diagram;
calculating according to the node diagram of the wind power plant, the operation data and a preset first neural network model to obtain the maximum standby power value corresponding to each wind turbine in the wind power plant;
gradually increasing the value of the standby power output by the corresponding wind turbine generator from zero based on the maximum standby power value until the grid-connected point operation parameters in the operation data become unstable;
and acquiring the standby power value of the wind turbine generator when the operation parameters of the grid-connected point become unstable, and taking the standby power value as the maximum available standby power value of the wind turbine generator.
It will be appreciated that the processor 501, when executing the program in the memory 502, may perform other functions in addition to the above functions, see in particular the description of the corresponding method embodiments above.
Further, the type of the electronic device 500 is not particularly limited, and the electronic device 500 may be a portable electronic device such as a mobile phone, a tablet computer, a personal digital assistant (personal digital assistant, PDA), a wearable device, a laptop (laptop), etc. Exemplary embodiments of portable electronic devices include, but are not limited to, portable electronic devices that carry IOS, android, microsoft or other operating systems. The portable electronic device described above may also be other portable electronic devices, such as a laptop computer (laptop) or the like having a touch-sensitive surface, e.g. a touch panel. It should also be appreciated that in other embodiments of the invention, electronic device 500 may not be a portable electronic device, but rather a desktop computer having a touch-sensitive surface (e.g., a touch panel).
In yet another aspect, the present invention further provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, is implemented to perform the method for supporting a wind turbine generator frequency provided by the above methods, the method comprising:
acquiring a circuit diagram of a wind power plant and acquiring operation data of the wind power plant in real time;
generating a wind power plant node diagram according to the circuit diagram;
calculating according to the node diagram of the wind power plant, the operation data and a preset first neural network model to obtain the maximum standby power value corresponding to each wind turbine in the wind power plant;
gradually increasing the value of the standby power output by the corresponding wind turbine generator from zero based on the maximum standby power value until the grid-connected point operation parameters in the operation data become unstable;
and acquiring the standby power value of the wind turbine generator when the operation parameters of the grid-connected point become unstable, and taking the standby power value as the maximum available standby power value of the wind turbine generator.
Those skilled in the art will appreciate that all or part of the flow of the methods of the embodiments described above may be accomplished by way of a computer program that instructs associated hardware, and that the program may be stored in a computer readable storage medium. The computer readable storage medium is a magnetic disk, an optical disk, a read-only memory or a random access memory.
The present invention is not limited to the above-mentioned embodiments, and any changes or substitutions that can be easily understood by those skilled in the art within the technical scope of the present invention are intended to be included in the scope of the present invention.
Claims (10)
1. The frequency supporting method of the wind turbine generator is characterized by comprising the following steps of:
acquiring a circuit diagram of a wind power plant and acquiring operation data of the wind power plant in real time;
generating a wind power plant node diagram according to the circuit diagram;
calculating according to the wind power plant node diagram, the operation data and a preset first neural network model to obtain maximum standby power values corresponding to all wind power units in the wind power plant;
gradually increasing the value of the standby power output by the corresponding wind turbine generator set from zero based on the maximum standby power value until the grid-connected point operation parameters in the operation data become unstable;
and acquiring a standby power value of the wind turbine generator when the grid-connected point operation parameter becomes unstable, and taking the standby power value as the maximum available standby power value of the wind turbine generator.
2. The wind turbine frequency support method of claim 1, wherein the first neural network model comprises a K-layer hidden layer and a fully connected layer; the calculating according to the wind power plant node diagram, the operation data and a preset first neural network model to obtain the maximum standby power value corresponding to each wind power unit in the wind power plant comprises the following steps:
generating a plurality of first node vectors according to the operation data and the wind power plant node diagram;
inputting the wind power plant node map and the plurality of first node vectors into the corresponding hidden layer to obtain second node vectors corresponding to the wind power units;
and inputting the second node vector into the full connection layer to obtain the maximum standby power value of the wind turbine corresponding to the second node vector.
3. The wind turbine frequency support method of claim 2, wherein the first neural network model further comprises a splice layer disposed between the hidden layer and the fully connected layer; the step of inputting the wind power plant node map and the plurality of first node vectors into the corresponding hidden layer to obtain second node vectors corresponding to the wind power units, and then further comprises the steps of:
inputting the second node vector corresponding to each wind turbine generator into the splicing layer to obtain a splicing vector;
and inputting the splicing vector into the full connection layer to obtain the maximum standby power value of the wind power plant.
4. A wind turbine frequency support method according to claim 3, wherein the first neural network model further comprises at least one parallel linear mapping layer for mapping the plurality of first node vectors to the same dimension.
5. The wind turbine frequency support method of claim 2, wherein the first node vector comprises a wind turbine unit feature vector, a converter unit feature vector, an energy storage unit feature vector, an inverter unit feature vector, and a grid tie feature vector.
6. The wind turbine generator system frequency supporting method according to claim 2, wherein a calculation formula of a u-th layer of the hidden layer of the K-th layer is:
wherein,representing intermediate features of the ith node of the ith layer, D (i) Represents a set of nodes directly connected to node i, < >>Representing intermediate features of the jth node of the (u-1) th layer, W (u) A weight parameter representing a u-th layer, and sigma represents a sigmoid activation function; when u=1, _a->θ j Representing node characteristics of the j-th node.
7. The wind turbine frequency support method of claim 1, wherein the grid-connected electrical operating parameters include a lifting fluctuation number value and a lifting amplitude value; gradually increasing the value of the standby power output by the corresponding wind turbine generator set from zero based on the maximum standby power value until the grid-connected point operation parameter in the operation data becomes unstable, wherein the step of stopping increasing comprises the following steps:
setting one percent of the maximum standby power value as a step size;
gradually increasing the value of the standby power output by the wind turbine generator corresponding to the maximum standby power value from zero by the step length, and judging the lifting fluctuation value and the lifting amplitude value corresponding to the wind turbine generator within a preset time after each increase;
and stopping increasing the standby power when at least one of the lifting fluctuation value and the lifting amplitude value is larger than a corresponding preset value.
8. The utility model provides a wind turbine generator system frequency strutting arrangement which characterized in that includes:
the data acquisition module is used for acquiring a circuit diagram of the wind power plant and acquiring operation data of the wind power plant in real time;
the node diagram generation module is used for generating a wind power plant node diagram according to the circuit diagram;
the power calculation module is used for calculating according to the wind power plant node diagram, the operation data and a preset first neural network model to obtain the maximum standby power value corresponding to each wind power unit in the wind power plant;
the power test module is used for gradually increasing the value of the standby power output by the corresponding wind turbine generator set from zero based on the maximum standby power value until the grid-connected point operation parameters in the operation data become unstable;
and the available power acquisition module is used for acquiring the standby power value of the wind turbine generator when the grid-connected point operation parameter becomes unstable, and taking the standby power value as the maximum available standby power value of the wind turbine generator.
9. An electronic device comprising a memory and a processor, wherein the memory is configured to store a program;
the processor is coupled to the memory for executing the program stored in the memory for implementing the steps in the wind turbine frequency support method according to any of the preceding claims 1-7.
10. A non-transitory computer readable storage medium having stored thereon a computer program, which when executed by a processor implements a wind turbine frequency support method according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311300691.2A CN117439197A (en) | 2023-10-09 | 2023-10-09 | Wind turbine generator frequency supporting method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311300691.2A CN117439197A (en) | 2023-10-09 | 2023-10-09 | Wind turbine generator frequency supporting method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117439197A true CN117439197A (en) | 2024-01-23 |
Family
ID=89556128
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311300691.2A Pending CN117439197A (en) | 2023-10-09 | 2023-10-09 | Wind turbine generator frequency supporting method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117439197A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119010367A (en) * | 2024-10-24 | 2024-11-22 | 诚达鑫科技(大连)有限公司 | Cloud platform-based power grid remote control method and system |
-
2023
- 2023-10-09 CN CN202311300691.2A patent/CN117439197A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119010367A (en) * | 2024-10-24 | 2024-11-22 | 诚达鑫科技(大连)有限公司 | Cloud platform-based power grid remote control method and system |
| CN119010367B (en) * | 2024-10-24 | 2025-02-25 | 诚达鑫科技(大连)有限公司 | A cloud platform-based remote control method and system for power grid |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112803505B (en) | Distributed voltage source converter cooperative control method and alternating current-direct current parallel-serial micro-grid | |
| CN106549417A (en) | A kind of virtual synchronous generator control method and device of photovoltaic energy storage system | |
| Akbari et al. | Voltage control of a hybrid ac/dc microgrid in grid-connected operation mode | |
| CN112132363A (en) | Energy storage site selection and volume fixing method for enhancing system operation robustness | |
| CN115579937A (en) | Electromagnetic transient modeling simulation method and device suitable for offshore wind farm | |
| CN117439197A (en) | Wind turbine generator frequency supporting method, device, equipment and storage medium | |
| CN106602610B (en) | A kind of method for building up of wind power plant Equivalent Model | |
| Yenealem | Optimum Allocation of Microgrid and D‐STATCOM in Radial Distribution System for Voltage Profile Enhancement Using Particle Swarm Optimization | |
| Song et al. | Average value model of grid side converter in PMSG for system‐level studies | |
| CN112671042B (en) | Virtual impedance access method and device based on short-circuit ratio and electronic equipment | |
| Liu et al. | Capacitor voltage synchronising control‐based VSG scheme for inertial and primary frequency responses of Type‐4 WTGs | |
| CN111769571B (en) | Frequency modulation method and system based on photovoltaic virtual synchronous generator | |
| Altimania | Modeling of doubly-fed induction generators connected to distribution system based on eMEGASim® real-time digital simulator | |
| CN110867850A (en) | Method for calculating rotating speed of generator and parameters of wind turbine generator and wind turbine generator model | |
| Guo et al. | Energy management by using point of common coupling frequency as an agent for islanded microgrids | |
| CN116232031B (en) | Overvoltage suppression method and device for sub-module of flexible direct current converter | |
| Chen et al. | An aerodynamics-based novel optimal power extraction strategy for offshore wind farms with central VSCs | |
| CN118432160A (en) | Coordination control method and system for offshore wind turbine and flexible direct current system | |
| Kumar et al. | A simplified approach for load flow analysis of radial distribution network with embedded generation | |
| CN115441513A (en) | Phase modulator determining method and device suitable for new energy station | |
| Sreenu et al. | Pairing voltage-source converters with PI tuning controller based on PSO for grid-connected wind-solar cogeneration | |
| CN110854913B (en) | Simulation method of doubly-fed induction wind power generation system | |
| McArdle | Dynamic modelling of wind turbine generators and the impact on small lightly interconnected grids | |
| Benaama et al. | Real time modeling and control of a wind farm connected to a multi-bus network under faulty conditions | |
| Shi et al. | Operation and coordination control of a DC micro‐grid incorporating all‐DC wind farm |
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 |